Systems, analyzers, controllers, and associated methods to enhance fluid production of refining operations

Abstract

Embodiments of systems and methods for enhancing control of refining and product blending pool operations are disclosed. A method includes receiving, by a machine learning model, a customer specification specifying at least one property for a blended formulation and accessing a business data including an inventory of products in a blending pool, including a quantity of each product and a listing of known properties of each product. The method further includes generating, by a machine learning model, a plurality of blended formulations based on the inventory of products and predicting properties for one or more of the generated blended formulations. The method also includes retaining the generated blended formulations whose predicted properties meet or are better than the customer specification and publishing a list of the retained generated blended formulations.

Description

SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID PRODUCTION OF REFINING OPERATIONSCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to, and the benefit of U.S. Provisional Application No. 63 / 786,014, filed April 9, 2025, titled SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID PRODUCTION OF REFINING OPERATIONS, U.S. Provisional Application No. 63 / 778,798, filed March 27, 2025, titled SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID PRODUCTION OF REFINING OPERATIONS, U.S. Patent Application No. 18 / 948,759, filed November 15, 2024, titled “SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID SEPARATION FOR DISTILLATION OPERATIONS,” U.S. Provisional Application No. 63 / 660,196, filed June 14, 2024, titled “SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID PRODUCTION OF REFINING OPERATIONS,” U.S. Provisional Application No. 63 / 658,825, filed June 11, 2024, titled “SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID PRODUCTION OF REFINING OPERATIONS,” and U.S. Provisional Application No. 63 / 655,589, filed June 3, 2024, titled “SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE FLUID PRODUCTION OF REFINING OPERATIONS,” the disclosures of which are incorporated herein by reference in their entireties.FIELD OF DISCLOSURE

[0002] The disclosure herein relates to systems, analyzers, controllers, and associated methods to enhance fluid production for refining operations and, more particularly, to systems, analyzers, controllers, and associated methods to enhance fluid production of refining operations and sub-operations using machine learning models during the refining operations and sub-operations.BACKGROUND

[0003] Many and varied operations are executed continuously and simultaneously at a refinery. Each operation affects each subsequent operation or sub-operation. For example,if the product from a first operation is produced based on maximizing a first factor, for example, the research octane number of gasoline, the production of that particular product affects further downstream operations. Additionally, further upstream operations may not be suited for production of that particular product or may, at least, cause other operations to produce that particular product in an inefficient manner. Additionally, a variety of starting feedstock are utilized at a refinery. Even further, different batches or portions of one feedstock may vary over time, for example, different portions of a feedstock may include different properties and / or compositions over time. Optimization (in other words, efficient and accurate production of targeted products) of such operations and feedstock poses a significant challenge when attempting to meet a target product, particularly over a period time, as equipment and materials used in the operation change over time. Such problems pose further difficulties since updating one operation affects every other operation at the refinery.

[0004] Controllers and monitoring devices may be utilized at a refinery to attempt to optimize (in other words, efficiently and accurately produce targeted products) those operations. However, those controllers and monitoring devices utilize algorithms that require expert personnel and that take extended amounts of time to execute. For example, first-principle models require expert personnel to ensure that the first-principle model is accurately calculating some formula, in other words, expert personnel are required to maintain the first-principle model. Further still, the equipment utilized at one refinery may experience a different service or maintenance cycle than equipment at another refinery. Such factors further complicate any attempt at uniform optimization at a plurality of refineries.SUMMARY

[0005] Thus, in view of the foregoing, Applicant has recognized these problems and others in the art, and has recognized a need for systems, analyzers, controllers, and associated methods for enhancing fluid production for refinery operations. Particularly, the present disclosure relates to systems, analyzers, controllers, and associated methods to enhance fluid production of refining operations and sub-operations using machine learning models during the refining operations and sub-operations. Such fluids may include hydrocarbons and / or renewable hydrocarbons and fluid production may include, for example, production of transportation fuel, among other products.

[0006] The disclosure herein provides embodiments of systems, analyzers, controllers, and associated methods for enhancing fluid production of ongoing and / or continuous refining operations, as well as refining sub-operations. Such systems, analyzers, controllers, and associated methods may include obtaining data corresponding to a refinery operation from one or more sources, such as sensors, analyzers, refining equipment, devices and / or other sources. The data, along with, in some embodiments, a target product, may then be applied to a machine learning model to produce an output indicative of or including parameters that indicate settings for the devices and / or refining equipment to be set to, to accurately achieve or produce the targeted product.

[0007] Accordingly, an embodiment of the disclosure is directed to a system for enhancing fluid production for refining operations. The system may include a plurality of refining equipment each configured with refining equipment parameter settings to perform a refining sub-operation of a refinery operation on a flow of feedstock thereto. The system may include a plurality of sensors to measure a sensor parameter associated with the plurality of refining equipment and each one of the plurality of sensors positioned at one of (a) proximate one of the plurality of refining equipment or (b) within one of the plurality of refining equipment. The system may include a plurality of refining operation control devices, each one of the plurality of refining operation control devices positioned proximate one of the plurality of the refining equipment and being either downstream or upstream thereof and having parameters to control an aspect and / or property of feedstock flowing to one of the plurality of refining equipment or a product flowing from one of the plurality of refining equipment. The system may include one or more sample collection assemblies to collect samples of the feedstock and products associated with each of the plurality of refining equipment. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a plurality of operation controllers, each one of the plurality of operation controllers in signal communication with one of a plurality of subsets of the plurality of refining equipment, one of a plurality of subsets of the plurality of sensors, one of a plurality of subsets of the plurality of refining operation control devices, and the one or more sample analysis assemblies. Each of the plurality of operation controllers may include (i) a plurality of predictive control circuitries each storing one or more selected models, the plurality of predictive control circuitries configured to: determine an output based on application of data from the one of the plurality of subsets of the plurality of refining equipment, the one of the plurality of subsets of the plurality of sensors, the one of the plurality of subsets ofthe plurality of refining operation control devices, and target products and corresponding properties to the corresponding one or more selected models; (ii) a local enhancement circuity storing a machine learning model and configured to: in response to reception of the output from one or more of the plurality of predictive control circuitries, determine one or more target setpoints based on application of the output and the data from the one of the plurality of subsets of the plurality of refining equipment, the one of the plurality of subsets of the plurality of sensors, the one of the plurality of subsets of the plurality of refining operation control devices to the corresponding one or more selected models; and (iii) a plurality of equipment and device controllers, each of the equipment and device controllers in signal communication with the local enhancement circuitry and configured to: in response to a determination of one or more target setpoints, adjust the one of the plurality of subsets of the plurality of refining equipment and the one of the plurality of subsets of the plurality of refining operation control devices to the one or more target setpoints.

[0008] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a fluid catalytic cracking (FCC) operation. The system may include a FCC unit configured to crack a feedstock via a combination of temperature, pressure, and catalyst. The system may include a regenerator in fluid communication with the FCC unit, to receive coked catalyst from the FCC unit, regenerate the coked catalyst, and to provide regenerated catalyst to the FCC unit. The system may include a plurality of sensors to measure a parameter associated with the FCC unit and the regenerator and each positioned at one of (a) proximate one of the FCC unit or the regenerator or (b) within one of the FCC unit and the regenerator. The system may include a plurality of refining operation control devices each positioned proximate and downstream or upstream of one of the FCC unit and the regenerator and to control an aspect and / or property of fluid or catalyst flowing to or from one of the FCC unit and the regenerator. The system may include one or more sample collection assemblies to collect samples of the fluid or catalyst associated with each of the FCC unit and the regenerator. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a FCC controller in signal communication with the FCC unit, the regenerator, the plurality of sensors, the plurality of refining operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The FCC controller may be configured to determine an output including predicted properties of the feedstock and parameter settings of the plurality of refining operation control devices, the FCC unit, and the regenerator based on application of one or more of(i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refining operation control devices, the FCC unit, and the regenerator based on the output to enhance production of cracked fluid.

[0009] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a distillation operation. The system may include a distillation column to receive a feedstock and separate the feedstock into a plurality of fluids. The system may include a plurality of sensors to measure a parameter associated with the distillation column and each positioned at one of (a) proximate the distillation column or (b) within the distillation column. The system may include a plurality of refining operation control devices each positioned proximate and downstream or upstream of the distillation column and to control an aspect and / or property of fluid flowing to or from the distillation column. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the distillation column. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a distillation controller in signal communication with the distillation column, the plurality of sensors, the plurality of refining operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The distillation controller may be configured to determine an output including predicted properties of the feedstock and parameter settings of the plurality of refining operation control devices and the distillation column based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refining operation control devices and distillation column based on the output to enhance production of the plurality of fluids.

[0010] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a hydrotreatment. The system may include a hydrotreater to receive a feedstock and refine the feedstock into a refined feedstock. The system may include a plurality of sensors to measure a parameter associated with the hydrotreater and each positioned at one of (a) proximate the hydrotreater or (b) within the hydrotreater. Thesystem may include a plurality of refining operation control devices each positioned proximate and downstream or upstream of the hydrotreater and to control an aspect and / or property of fluid flowing to or from the hydrotreater. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the hydrotreater. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a hydrotreater controller in signal communication with the hydrotreater, the plurality of sensors, the plurality of flow control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The hydrotreater controller may be configured to determine an output including predicted properties of the feedstock and parameter settings of the plurality of refining operation control devices and the hydrotreater based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refining operation control devices and hydrotreater based on the output to enhance production of the refined feedstock.

[0011] Another embodiment of the disclosure is directed to a system for enhancing reformate production in a reformer operation. The system may include a reformer to receive a feedstock and convert the feedstock into reformate and by-product hydrogen. The system may include a plurality of sensors to measure a parameter associated with the reformer and each positioned at one of (a) proximate the reformer or (b) within the reformer. The system may include a plurality of refining operation control devices each positioned proximate and downstream or upstream of the reformer and to control an aspect and / or property of fluid flowing to or from the reformer. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the reformer. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a reformer controller in signal communication with the reformer, the plurality of sensors, the plurality of refining operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The reformer controller may be configured to determine an output including predicted properties of the feedstock and parameter settings of the plurality of refining operation control devices and the reformer based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysisfrom the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refining operation control devices and reformer based on the output to enhance production of the reformate, hydrogen, sand other gasses.

[0012] Another embodiment of the disclosure is directed to a system for enhancing alkylate production for an alkylation operation. The system may include an alkylation unit to receive a feedstock and produce an alkylate. The system may include a plurality of sensors to measure a parameter associated with the alkylation unit and each positioned at one of (a) proximate the alkylation unit or (b) within the alkylation unit. The system may include a plurality of refining operation control devices each positioned proximate and downstream or upstream of the alkylation unit and to control an aspect and / or property of fluid flowing to or from the alkylation unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the alkylation unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include an alkylation controller in signal communication with the alkylation unit, the plurality of sensors, the plurality of refining operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The alkylation controller may be configured to determine an output including predicted properties of the feedstock and parameter settings of the plurality of refining operation control devices and the alkylation unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refining operation control devices and alkylation unit based on the output to enhance production of the alkylate.

[0013] Another embodiment of the disclosure is directed to a system for enhancing isomerate production for an isomerization operation. The system may include an isomerization unit to receive a feedstock and produce an isomerate. The system may include a plurality of sensors to measure a parameter associated with the isomerization unit and each positioned at one of (a) proximate the isomerization unit or (b) within the isomerization unit. The system may include a plurality of refining operation control devices each positioned proximate and downstream or upstream of the isomerization unit and tocontrol an aspect and / or property of fluid flowing to or from the isomerization unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the isomerization unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include an isomerization controller in signal communication with the isomerization unit, the plurality of sensors, the plurality of refining operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The isomerization controller may be configured to determine an output including predicted properties of the feedstock and parameter settings of the plurality of refining operation control devices and the isomerization unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refining operation control devices and isomerization unit based on the output to enhance production of the isomerate.

[0014] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a coker operation in a coker unit. The system may include a plurality of coke drums to receive heavy distillate or other fluids and each of the plurality of coke drums configured with refining equipment parameter settings to convert the heavy distillate or other fluids. The system may include a plurality of sensors to measure a parameter associated with the coker unit and each positioned at one of (a) proximate the coker unit or (b) within the coker unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the coker unit and to control aspects of fluid flowing to or from the coker unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the coker unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a coker controller in signal communication with the coker unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The coker controller may be configured to (1) determine an output including predicted properties of the heavy distillate or other fluids and parameter settings of the plurality of refinery operation control devices and the unit based on application of one or more of (i) data measured by the plurality ofsensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of the amount of heavy distillate or other fluids or type of heavy distillate or other fluids and parameters associated with the plurality of refinery operation control devices and coker unit based on the output to enhance production of fluid from the coker unit.

[0015] Another embodiment of the disclosure is directed to a system for enhancing aromatics recovery for an aromatics recovery operation. The system may include an aromatics recovery unit to receive a feedstock and capture aromatics within the feedstock. The system may include a plurality of sensors to measure a parameter associated with the aromatics recovery unit and each positioned at one of (a) proximate the aromatics recovery unit or (b) within the aromatics recovery unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the aromatics recovery unit and to control aspects of fluid flowing to or from the aromatics recovery unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the aromatics recovery unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include an aromatics recovery controller in signal communication with the aromatics recovery unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The aromatics recovery controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the aromatics recovery unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices and aromatics recovery unit based on the output to enhance capture of aromatics.

[0016] Another embodiment of the disclosure is directed to a system for enhancing sulfur recovery for a sulfur recovery operation. The system may include a sulfur recovery unit to receive a feedstock and capture sulfur within the feedstock. The system may include a plurality of sensors to measure a parameter associated with the sulfur recovery unit and each positioned at one of (a) proximate the sulfur recovery unit or (b) within the sulfurrecovery unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the sulfur recovery unit and to control aspects of fluid flowing to or from the sulfur recovery unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the sulfur recovery unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a sulfur recovery controller in signal communication with the sulfur recovery unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the sulfur recovery controller configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the sulfur recovery unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; (2) adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices and sulfur recovery unit based on the output to enhance capture of sulfur.

[0017] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a solvent deasphalting (SDA) operation. The system may include a SDA unit to receive a feedstock and produce a fluid. The system may include a plurality of sensors to measure a parameter associated with the SDA unit and each positioned at one of (a) proximate the SDA unit or (b) within the SDA unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the SDA unit and to control aspects of fluid flowing to or from the SDA unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the SDA unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a SDA controller in signal communication with the SDA unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The SDA controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the SDA unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysisassemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices and SDA unit based on the output to enhance the production of fluid from the SDA unit.

[0018] Another embodiment of the disclosure is directed to a system for enhancing fluid production for an enhanced supercritical solvent deasphalting operation wherein a portion of the operation (the deasphalted oil stripper) is performed at supercritical conditions of the solvent (e.g., a supercritical solvent deasphalting operation). The system may include a supercritical solvent deasphalting unit to receive a feedstock and produce a fluid. The system may include a plurality of sensors to measure a parameter associated with the supercritical solvent deasphalting unit and each positioned at one of (a) proximate the supercritical solvent deasphalting unit or (b) within the supercritical solvent deasphalting unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the supercritical solvent deasphalting unit and to control aspects of fluid flowing to or from the supercritical solvent deasphalting unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the supercritical solvent deasphalting unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a supercritical solvent deasphalting unit controller in signal communication with the supercritical solvent deasphalting unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the supercritical solvent deasphalting controller configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the supercritical solvent deasphalting unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices and supercritical solvent deasphalting unit based on the output to enhance the production of fluid from the supercritical solvent deasphalting unit.

[0019] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a blending operation. The system may include a blending unit to receive aplurality of feedstock and produce a blended fluid. The system may include a plurality of sensors to measure a parameter associated with the blending unit and each positioned at one of (a) proximate the supercritical solvent deasphalting unit or (b) within the blending unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the blending unit and to control aspects of fluid flowing to or from the blending unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the blending unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a blending controller in signal communication with the blending unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The blending controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the blending unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices and blending unit based on the output to enhance the production of fluid from the blending unit.

[0020] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a propylene splitter operation. The system may include a propylene splitter unit to receive a feedstock and produce a fluid. The system may include a plurality of sensors to measure a parameter associated with the propylene splitter unit and each positioned at one of (a) proximate the propylene splitter unit or (b) within the propylene splitter unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the propylene splitter unit and to control aspects of fluid flowing to or from the propylene splitter unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the propylene splitter unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include propylene splitter controller in signal communication with the propylene splitter unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machinelearning model. The propylene splitter controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the propylene splitter unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2)adjust one or more of the amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices and propylene splitter unit based on the output to enhance the production of fluid from the propylene splitter unit.

[0021] Another embodiment of the disclosure is directed to a system for enhancing utilization of steam for a refinery operation. The system may include one or more heat sources to produce steam. The system may include a plurality of refinery equipment to utilize the steam for the refinery operation. The system may include a plurality of sensors to measure a parameter associated with the one or more heat sources and the plurality of refinery equipment and each positioned at one of (a) proximate one of the one or more heat sources and the plurality of refinery equipment or (b) within one of the one or more heat sources and the plurality of refinery equipment. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the one or more heat sources and the plurality of refinery equipment and to control aspects of fluid flowing to or from the one of the one or more heat sources and the plurality of refinery equipment. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a steam controller in signal communication with the one or more heat sources, the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The steam controller may be configured to (l)determine an output including predicted parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and (2) adjust an amount of steam produced by the one or more heat sources and an amount of steam provided to each of the plurality of refinery equipment.

[0022] Another embodiment of the disclosure is directed to a system for enhancing utilization of hydrogen for a refinery operation. The system may include one or more hydrogen sources. The system may include a plurality of refinery equipment to utilize the hydrogen for the refinery operation. The system may include a plurality of sensors to measure a parameter associated with the one or more hydrogen sources and the plurality of refinery equipment and each positioned at one of (a) proximate one of the one or more hydrogen sources and the plurality of refinery equipment or (b) within one of the one or more hydrogen sources and the plurality of refinery equipment. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the one or more hydrogen sources and the plurality of refinery equipment and to control aspects of fluid flowing to or from the one of the one or more hydrogen sources and the plurality of refinery equipment; one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a hydrogen controller in signal communication with the one or more hydrogen sources, the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The hydrogen controller may be configured to (1) determine an output including predicted parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; (2) adjust an amount of hydrogen produced by the one or more hydrogen sources and an amount of hydrogen provided to each of the plurality of refinery equipment.

[0023] Another embodiment of the disclosure is directed to a system for enhancing utilization and blends of feed for a refinery operation. The system may include one or more feed sources. The system may include a plurality of refinery equipment to utilize the feed for the refinery operation. The system may include a plurality of sensors to measure a parameter associated with the one or more feed sources and the plurality of refinery equipment and each positioned at one of (a) proximate one of the one or more feed sources and the plurality of refinery equipment or (b) within one of the one or more feed sources and the plurality of refinery equipment. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of oneof the one or more feed sources and the plurality of refinery equipment and to control aspects of fluid flowing to or from the one of the one or more feed sources and the plurality of refinery equipment. The system may include one or more sample collection assemblies to collect samples of the feed and the fluid associated with the plurality of refinery equipment. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a feed controller in signal communication with the one or more feed sources, the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The feed controller configured to (1) determine an output including predicted properties of a selected feed parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of an amount or blend of feed provided to each of the plurality of refinery equipment.

[0024] Another embodiment of the disclosure is directed to a system for enhancing blends for a gasoline pool for a refinery operation. The system may include a plurality of refinery equipment to produce gasoline via the refinery operation. The system may include a plurality of sensors to measure a parameter associated with the plurality of refinery equipment and each positioned at one of (a) proximate one of the plurality of refinery equipment or (b) within one of the plurality of refinery equipment. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the plurality of refinery equipment and to control aspects of fluid flowing to the plurality of refinery equipment. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment and the gasoline produced via the plurality of refinery equipment. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a gasoline pool controller in signal communication with the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The gasoline pool controller configured to (1) determine an output including predicted properties of gasoline for a selected gasoline pool and parameter settings of the plurality of refinery operation controldevices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and (2) adjust one or more of an amount or blend of gasoline to achieve properties associated with the selected gasoline pool.

[0025] Another embodiment of the disclosure is directed to a system for enhancing blends for a diesel pool for a refinery operation. The system may include a plurality of refinery equipment to produce diesel via the refinery operation. The system may include a plurality of sensors to measure a parameter associated with the plurality of refinery equipment and each positioned at one of (a) proximate one of the plurality of refinery equipment or (b) within one of the plurality of refinery equipment. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the plurality of refinery equipment and to control aspects of fluid flowing to the plurality of refinery equipment. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment and the diesel produced via the plurality of refinery equipment. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a diesel pool controller in signal communication with the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The diesel pool controller may be configured to (1) determine an output including predicted properties of diesel for a selected diesel pool and parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model; and (2) adjust one or more of an amount or blend of diesel to achieve properties associated with the selected diesel pool.

[0026] Another embodiment of the disclosure is directed to a system for enhancing fuel gas or C3 and heavier hydrocarbon production for an absorber operation. The system may include an absorber unit to receive a feed and produce a fuel gas or C3 and heavier hydrocarbon. The system may include a plurality of sensors to measure a parameter associated with the absorber unit and each positioned at one of (a) proximate the absorber unit or (b) within the absorber unit. The system may include a plurality of refinery operationcontrol devices each positioned proximate and downstream or upstream of the absorber unit and to control aspects of fluid flowing to or from the absorber unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the absorber unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include an absorber controller in signal communication with the absorber unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The absorber controller configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the absorber unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and (2) adjust one or more of the amount of feed or type of feed and parameters associated with the plurality of refinery operation control devices and absorber unit based on the output to enhance production of the fuel gas or C3 and heavier hydrocarbon.

[0027] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a hydrocracker operation. The system may include A hydrocracker unit to receive a feed and produce one or more fluids. The system may include a plurality of sensors to measure a parameter associated with the hydrocracker unit and each positioned at one of (a) proximate the hydrocracker unit or (b) within the hydrocracker unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the hydrocracker unit and to control aspects of fluid flowing to or from the hydrocracker unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the hydrocracker unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a hydrocracker controller in signal communication with the hydrocracker unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The hydrocracker controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the hydrocracker unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysisassemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and (2) adjust one or more of the amount of feed or type of feed and parameters associated with the plurality of refinery operation control devices and hydrocracker unit based on the output to enhance fluid production.

[0028] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a gasoline desulfurization operation. The system may include a gasoline desulfurization unit to receive a feed and produce one or more fluids. The system may include a plurality of sensors to measure a parameter associated with the gasoline desulfurization unit and each positioned at one of (a) proximate the gasoline desulfurization unit or (b) within the gasoline desulfurization unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the gasoline desulfurization unit and to control aspects of fluid flowing to or from the gasoline desulfurization unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the gasoline desulfurization unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a gasoline desulfurization controller in signal communication with the gasoline desulfurization unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the gasoline desulfurization controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the gasoline desulfurization unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and (2) adjust one or more of the amount of feed or type of feed and parameters associated with the plurality of refinery operation control devices and gasoline desulfurization unit based on the output to enhance fluid production.

[0029] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a hydrodeoxygenation (HDO) operation. The system may include a HDO unit to receive a feed and produce one or more fluids. The system may include a plurality of sensors to measure a parameter associated with the HDO unit and each positioned at one of (a) proximate the HDO unit or (b) within the HDO unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstreamor upstream of the HDO unit and to control aspects of fluid flowing to or from the HDO unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the HDO unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a HDO controller in signal communication with the HDO unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model. The HDO controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the HDO unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and (2) adjust one or more of the amount of feed or type of feed and parameters associated with the plurality of refinery operation control devices and HDO unit based on the output to enhance fluid production.

[0030] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a resid destruction operation. The system may include a resid destruction unit to receive a feed and produce one or more fluids. The system may include a plurality of sensors to measure a parameter associated with the resid destruction unit and each positioned at one of (a) proximate the resid destruction unit or (b) within the resid destruction unit. The system may include a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the resid destruction unit and to control aspects of fluid flowing to or from the resid destruction unit. The system may include one or more sample collection assemblies to collect samples of the fluid associated with the resid destruction unit. The system may include one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples. The system may include a resid destruction controller in signal communication with the resid destruction unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the resid destruction controller may be configured to (1) determine an output including predicted properties of the feedstock and parameter settings of the plurality of refinery operation control devices and the resid destruction unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and correspondingtarget properties to the trained machine learning model, and (2) adjust one or more of the amount of feed or type of feed and parameters associated with the plurality of refinery operation control devices and resid destruction unit based on the output to enhance fluid production.

[0031] Another embodiment of the disclosure is directed to a controller to enhance fluid production of a refining operation. The controller may include a first plurality of inputs each in signal communication with one of a plurality of sensors to measure a set of first parameters associated with aspects of a refining operation and on or more refining suboperations. The controller may include a second plurality of inputs each in signal communication with one or more analyzers to analyze and provide properties of samples of fluids input to and output from each of a plurality of refining equipment. The controller may include a first plurality of inputs / outputs each in signal communication with one of the plurality of refining equipment, the controller configured to receive a set of second parameters associated with each of the plurality of refining equipment and to transmit instructions and selected parameters to cause each of the plurality of refining equipment to operate at the selected parameters. The controller may include a second plurality of inputs / outputs each in signal communication with one of a plurality of sub-controllers each configured to control one of the plurality of refining sub-operations. The controller may be configured to apply one or more of the set of first parameters, the set of second parameters, or the properties to a trained machine learning model, and determine an adjusted one or more inputs, intermediaries, or operating parameters based on application of data received from the plurality of sensors, the one or more analyzers, the plurality of refining equipment, and the plurality of sub-controllers; and adjust, via the sub-controllers, a type and amount of refining equipment fluid inputs and refining equipment parameters based on the adjusted one or more inputs, intermediaries, or operating parameters.

[0032] Another embodiment of the disclosure is directed to a method for enhancing fluid production of a refining operation. The method may include obtaining data substantially continuously for a plurality of ongoing and continuous refining operations in real-time or near real-time from one or more of (a) a plurality of sensors or (b) a plurality analyzers. The method may include determining one or more parameters for each of one or more devices or one or more refining equipment based at least in part on application of corresponding data to a corresponding machine learning model of a plurality of machine learning models at a first selected time interval. The method may include adjusting each of the one or more devices or one or more refining equipment based at least in part on the oneor more parameters. The method may include determining an updated value for each of the one or more parameters based at least in part on application to a supervisory machine learning model at a second selected time interval of one or more of (a) an output from each of the plurality of machine learning models, (b) current data, (c) an actual product output and product properties of the refining operations, (d) a predicted amount and properties of product output from the refining operations, or (e) target product properties. The method may include adjusting each of the one or more devices or one or more refining equipment based at least in part on a difference between the updated value for each of the one or more parameters and current parameters for the one or more devices or one or more refining equipment.

[0033] Another embodiment of the disclosure is directed to a method for enhancing control of a fluid catalytic cracking operation. The method may include supplying a hydrocarbon feedstock to one or more processing units associated with a petroleum refining operation, the hydrocarbon feedstock having one or more hydrocarbon feedstock properties and the one or more processing units including one or more fractionation units. The method may include analyzing a hydrocarbon feedstock sample via one or more analyzers to provide hydrocarbon feedstock sample properties. The method may include predicting one or more hydrocarbon feedstock sample properties associated with the hydrocarbon feedstock sample based on (a) the hydrocarbon feedstock sample properties and (b) a first output from application of the hydrocarbon feedstock sample properties to a first trained machine learning model. The method may include operating the one or more processing units to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of intermediate materials or unit product materials. The method may include analyzing the unit material sample via the one or more analyzers to provide unit material sample properties. The method may include predicting one or more unit material sample properties associated with the unit material sample based on (c) the unit material sample properties and (d) a second output from application of the unit material sample properties to a second trained machine learning model. The method may include controlling, during the petroleum refining operation, based on the one or more hydrocarbon feedstock sample properties and the one or more unit material sample properties, one or more of: (a) one or more hydrocarbon feedstock properties associated with the hydrocarbon feedstock supplied to the one or more first processing units; (b) one or more intermediate properties associated with the intermediate materials produced by the one or more first processing units; (c) oneor more unit product materials properties associated with the unit product materials; or (d) operation of the one or more first processing units, so that the controlling, during the petroleum refining operation, causes the petroleum refining operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the petroleum refining operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0034] Another embodiment of the disclosure is directed to a distillation unit control assembly to enhance control of a refining operation associated with a hydrocarbon refinery. The distillation unit control assembly may include a first analyzer positioned to: (i) receive a hydrocarbon feedstock sample of a hydrocarbon feedstock supplied to one or more first processing units associated with the petroleum refining operation, the one or more first processing units comprising one or more fractionation units; and (ii) analyze the hydrocarbon feedstock sample to provide hydrocarbon feedstock sample properties. The distillation unit control assembly may include a second analyzer positioned to: (i) receive a unit material sample of one more unit materials produced by the one or more first processing units, the one or more unit materials comprising one or more of intermediate materials or unit product materials, and (ii) analyze the unit material sample to provide unit material sample properties. The distillation unit control assembly may include an operations controller in communication with the first analyzer and the second analyzer, the operations controller configured to: (i) predict one or more hydrocarbon feedstock sample properties associated with the hydrocarbon feedstock sample based on the hydrocarbon feedstock sample properties and application of the hydrocarbon feedstock sample properties to a first trained machine learning model; (ii) predict one or more unit material sample properties associated with the unit material sample based on the unit material sample properties and application of the unit material sample properties to a second trained machine learning model; and (iii) control, during the refining operation, based at least in part on the one or more hydrocarbon feedstock sample properties and the one or more unit material sample properties, one or more of: (aa) one or more hydrocarbon feedstock parameters associated with the hydrocarbon feedstock supplied to the one or more firstprocessing units; (bb) the one or more hydrocarbon feedstock properties associated with the hydrocarbon feedstock supplied to the one or more first processing units; (cc) one or more intermediate properties associated with the intermediate materials produced by the one or more first processing units; (dd) one or more unit materials properties associated with the one or more unit materials; (ee) operation of the one or more first processing units; or (ff) operation of one or more second processing units positioned downstream relative to the one or more first processing units, so that controlling during the refining operation causes the refining operation to produce one or more of: (aa) one or more intermediate materials each having one or more properties within a selected range of one or more target properties of the one or more intermediate materials; (bb) one or more unit materials each having one or more properties within a selected range of one or more target properties of the one or more unit materials; or (cc) one or more downstream materials each having one or more properties within a selected range of one or more target properties of the one or more downstream materials, thereby to cause the refining operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0035] Another embodiment of the disclosure is directed to a method for enhancing control of a reforming operation associated with a petroleum refining operation. The method may include supplying naphtha to a reformer associated with the petroleum refining operation, the naphtha having one or more naphtha properties. The method may include analyzing a naphtha sample via a first analyzer to provide naphtha sample properties. The method may include predicting one or more naphtha sample properties associated with the naphtha sample based on (A) the naphtha sample properties and (B) a first output from application of the naphtha sample properties to a first trained machine learning model. The method may include operating the reformer to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of reformate, hydrogen, or reformer gas. The method may include analyzing the unit material sample via a second analyzer to provide unit material sample properties. The method may include predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model. The method may include controlling, during the reforming operation, based on the naphtha sample properties and the one or more unit material sample properties, one or more of: (a) one or more naphthaproperties associated with the naphtha supplied to the reformer; (b) one or more unit product materials properties associated with the unit product materials; (c) operation of the reformer; or (d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the reforming operation, causes the reforming operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the reforming operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0036] Another embodiment of the disclosure is directed to a method for enhancing control of an alkylation operation associated with a petroleum refining operation. The method may include supplying a feedstock to an alkylation unit associated with the petroleum refining operation, the feedstock having one or more feedstock properties. The method may include analyzing a feedstock sample via a first analyzer to provide feedstock sample properties. The method may include predicting one or more feedstock sample properties associated with the feedstock sample based on (A) the feedstock sample properties and (B) a first output from application of the feedstock sample properties to a first trained machine learning model. The method may include supplying one or more other input materials or intermediates to the alkylation unit associated with the petroleum refining operation, the one or more other input materials or intermediates having one or more other input materials properties or intermediates properties, respectively. The method may include analyzing one or more other input materials sample via a second analyzer to provide other input materials sample properties. The method may include predicting one or more other input materials sample properties associated with the other input materials sample based on (C) the other input materials sample properties and (D) a second output from application of the other input materials sample properties to a second trained machine learning model. The method may include operating the alkylation unit to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of alkylate or iso-butane. The method may include analyzing the unit material sample via a third analyzer to provide unit material sample properties. The method may include predicting one or more unit material sample propertiesassociated with the unit material sample based on (E) the unit material sample properties and (F) a second output from application of the unit material sample properties to a second trained machine learning model. The method may include controlling, during the alkylation operation, based on the feedstock sample properties and the one or more unit material sample properties, one or more of: (a) one or more feedstock properties associated with the feedstock properties supplied to the alkylation unit; (b) one or more other input materials properties or intermediates properties associated with the other input materials properties or intermediates properties supplied to the alkylation unit; (c) one or more unit product materials properties associated with the unit product materials; (d) operation of the alkylation unit; or (e) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the alkylation operation, causes the alkylation operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the petroleum refining operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0037] Another embodiment of the disclosure is directed to a method for enhancing control of an isomerization operation associated with a petroleum refining operation. The method may include supplying naphtha to an isomerization unit associated with the petroleum refining operation, the naphtha having one or more naphtha properties. The method may include analyzing a naphtha sample via a first analyzer to provide naphtha sample properties. The method may include predicting one or more naphtha sample properties associated with the naphtha sample based on (A) the naphtha sample properties and (B) a first output from application of the naphtha sample properties to a first trained machine learning model. The method may include operating the isomerization unit to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of gasoline, C3 and lighter alkanes, or hydrogen sulfide. The method may include analyzing the unit material sample via a second analyzer to provide unit material sample properties. The method may include predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second outputfrom application of the unit material sample properties to a second trained machine learning model. The method may include controlling, during the isomerization operation, based on the naphtha sample properties and the one or more unit material sample properties, one or more of: (a) one or more naphtha properties associated with the naphtha supplied to the isomerization unit; (b) one or more unit product materials properties associated with the unit product materials; (c) operation of the isomerization unit; or (d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the isomerization operation, causes the isomerization operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the isomerization operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0038] Another embodiment of the disclosure is directed to a method for enhancing control of a hydrotreatment operation associated with a petroleum refining operation. The method may include supplying feedstock to a hydrotreater associated with the petroleum refining operation, the feedstock having one or more feedstock properties. The method may include analyzing a feedstock sample via a first analyzer to provide feedstock sample properties. The method may include predicting one or more feedstock sample properties associated with the feedstock sample based on (A) the feedstock sample properties and (B) a first output from application of the feedstock sample properties to a first trained machine learning model. The method may include operating the hydrotreater to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of gas, gasoline, diesel, or i- butanes. The method may include analyzing the unit material sample via a second analyzer to provide unit material sample properties. The method may include predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model. The method may include controlling, during the hydrotreatment operation, based on the feedstock sample properties and the one or more unit material sample properties, one or more of: (a) one ormore feedstock properties associated with the feedstock supplied to the hydrotreater; (b) one or more unit product materials properties associated with the unit product materials; (c) operation of the hydrotreater; or (d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the hydrotreatment operation, causes the hydrotreatment operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the hydrotreatment operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0039] Still other aspects and advantages of these embodiments and other embodiments, are discussed in detail herein. Moreover, it is to be understood that both the foregoing information and the following detailed description provide merely illustrative examples of various aspects and embodiments, and are intended to provide an overview or framework for understanding the nature and character of the claimed aspects and embodiments. Accordingly, these and other objects, along with advantages and features of the present disclosure herein disclosed, will become apparent through reference to the following description and the accompanying drawings. Furthermore, it is to be understood that the features of the various embodiments described herein are not mutually exclusive and may exist in various combinations and permutations.BRIEF DESCRIPTION OF THE DRAWINGS

[0040] These and other features, aspects, and advantages of the disclosure will become better understood with regard to the following descriptions, claims, and accompanying drawings. It is to be noted, however, that the drawings illustrate only several embodiments of the disclosure and, therefore, are not to be considered limiting of the scope of the disclosure.

[0041] FIG. 1A and FIG. IB are simplified diagrams of a refining control system to enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0042] FIG. 2 is a simplified diagram that illustrates an apparatus for enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0043] FIG. 3 is another simplified diagrams of a refining control system to enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0044] FIG. 4 is a simplified diagram that illustrates training of a machine learning model for enhanced fluid production at refinery, according to an embodiment of the disclosure.

[0045] FIG. 5 is a schematic diagram of a FCC control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0046] FIG. 6 is a schematic diagram of an enhanced hydrotreater control system and a distillation control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0047] FIG. 7A is a schematic diagram of an enhanced catalytic reformer control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0048] FIG. 7B is a schematic diagram of an enhanced steam methane reformer control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0049] FIG. 8 is a schematic diagram of an enhanced alkylation control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0050] FIG. 9 is a schematic diagram of an enhanced isomerization control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0051] FIG. 10 is a schematic diagram of an enhanced coker control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0052] FIG. 11 is a schematic diagram of an enhanced aromatics recovery control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0053] FIG. 12 is a schematic diagram of an enhanced sulfur recovery control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0054] FIG. 13 is a schematic diagram of a Solvent Deasphalting Unit (SDA) control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0055] FIG. 14 is a schematic diagram of an enhanced supercritical extraction solvent deasphalting unit control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0056] FIG. 15 is a schematic diagram of an IMO fuel blending control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0057] FIG. 16 is a schematic diagram of a propylene splitter control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0058] FIG. 17 is a schematic diagram of a steam control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0059] FIG. 18 is a schematic diagram of hydrogen control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0060] FIG. 19 is a schematic diagram of a feed control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0061] FIG. 20 is a schematic diagram of a gasoline pool control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0062] FIG. 21 is a schematic diagram of a diesel pool control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0063] FIG. 22 is a schematic diagram of an absorber control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0064] FIG. 23 is a schematic diagram of a hydrocracker control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0065] FIG. 24 is a schematic diagram of a gasoline desulfurization control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0066] FIG. 25 is a schematic diagram of a hydrodeoxygenation control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0067] FIG. 26 is a schematic diagram of a resid destruction control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0068] FIG. 27A and FIG. 27B are simplified diagrams of control systems to enhance to enhance fluid production at refinery, according to an embodiment of the disclosure.

[0069] FIG. 28 is a flow chart illustrating enhanced fluid production at a refinery, according to an embodiment of the disclosure.

[0070] FIG. 29 is a schematic diagram of processes within a refinery.

[0071] FIG. 29A is a schematic diagram of the different products of the refinery and other sources that may be added to each of the blending pools.

[0072] FIG. 30 is a schematic diagram the different products of the refinery and other sources that may be added to a biofuel blending pool.

[0073] FIG. 31 is a schematic diagram of a methane steam reformer process that may be used in a refinery to provide hydrogen gas.

[0074] FIG. 32 is a schematic diagram of a machine learning model that may be used with the various processes within a refinery.

[0075] FIG. 32A is a schematic diagram of a heavy naphtha splitter that may be connected to the machine learning model of FIG. 32.

[0076] FIG. 33 is a flow diagram of a method, according to an embodiment of the disclosure.

[0077] FIG. 34 is a flow diagram of another method, according to an embodiment of the disclosure.

[0078] FIG. 35 is a flow diagram of yet another method, according to an embodiment of the disclosure.

[0079] FIG. 36 is a flow diagram of a method, according to an embodiment of the disclosure.

[0080] FIG. 37 is a flow diagram of another method, according to an embodiment of the disclosure.

[0081] FIG. 38 is a flow diagram of a method, according to an embodiment of the disclosure.

[0082] FIG. 39 is a flow diagram of a method, according to an embodiment of the disclosure.

[0083] FIG. 40 is a flow diagram of another method, according to an embodiment of the disclosure.

[0084] FIG. 41 is a flow diagram of yet another method, according to an embodiment of the

[0085] FIG. 42 is a flow diagram of a method, according to an embodiment of the disclosure.

[0086] FIG. 43 is a flow diagram of another method, according to an embodiment of the disclosure.

[0087] FIG. 44 is a flow diagram of yet another method, according to an embodiment of the disclosure.

[0088] FIG. 45 is a flow diagram of a method, according to an embodiment of the disclosure.

[0089] FIG. 46 is a flow diagram of another method, according to an embodiment of the disclosure.DETAILED DESCRIPTION

[0090] As used herein “profit” is the potential financial gain from a potential sale of products from a refinery operation less the costs of feedstocks and operational costs of the refinery operation. The potential value of a sale may be based on current market prices for similar products or current prices paid by contracted customers. Costs of feedstocks may include market prices for similar feedstocks as well as the operational costs of upstream processes preparing the feedstocks for use in the refinery operation. Operational costs may include equipment depreciation, employee wages and benefits, and consumables used to process the feedstocks, such as hydrogen, water, catalysts, steam, natural gas, cooling, electricity, and other utilities. For example, a machine learning model may generate adjustments to one or more operational parameters of a refinery process based on the potential profit from the products it produces. A potential profit may be determined from a generated algorithm or generated simulations based on current market pricing and potential ranges of production rates and the corresponding variable production costs. To continue the example, product A may sell for $2 a barrel and may be produced at a rate ranging from 50 barrels a day to 100 barrels a day. Product B may sell for $4 a barrel and be produced at a rate ranging from 10 barrels a day to 20 barrels a day. However, the more product B produced results in less product A being produced, increased utility costs, and accelerated deactivation of the catalysts of the refinery process. All of these variables and more may be managed by the machine learning model to increase the profitability of the refinery process.

[0091] So that the manner in which the features and advantages of the embodiments of the systems and methods disclosed herein, as well as others that will become apparent, may be understood in more detail, a more particular description of embodiments of systems and methods briefly summarized above may be had by reference to the following detailed description of embodiments thereof, in which one or more are further illustrated in the appended drawings, which form a part of this specification. It is to be noted, however, that the drawings illustrate only various embodiments of the systems and methods disclosed herein and are therefore not to be considered limiting of the scope of the systems and methods disclosed herein as it may include other effective embodiments as well.

[0092] The disclosure herein provides embodiments of systems, analyzers, controllers, and associated methods for enhancing fluid production of ongoing and / or continuous refining operations, as well as refining sub-operations. Such systems, analyzers, controllers, andassociated methods may include obtaining data corresponding to a refinery operation from one or more sources, such as sensors, analyzers, refining equipment, refining operation control devices, other devices, and / or other sources. The data, along with, in some embodiments, a target product, may then be applied to a machine learning model to produce an output indicative of or including parameters that indicate settings for the refining operation control devices and / or refining equipment to be set to, to accurately achieve or produce the targeted product. Such an application of data to a trained machine learning model may occur at one or more different layers in the control system of the refinery. Further, a plurality of controllers positioned throughout the refinery may each include a plurality of trained machine learning models that are trained to enhance fluid production of one or more refinery operations or sub-operations.

[0093] In embodiments, the refining operations and / or sub-operations may include the processing, converting, refining, enhancing and / or otherwise altering a fluid via the refining operation or sub-operation. The fluid may be a liquid, vapor, and / or gas and may include a hydrocarbon and final product may include a transportation fuel. “Hydrocarbons” or “hydrocarbon fluids” as used herein, may refer to petroleum fluids, renewable fluids, and other hydrocarbon based fluids. “Petroleum fluids” as used herein, may refer to fluid products containing crude oil, petroleum products, natural gas, renewable liquids and / or gasses, and / or distillates or refinery intermediates. For example, crude oil contains a combination of hydrocarbons having different boiling points that exists as a viscous liquid in underground geological formations and at the surface. Petroleum products, for example, may be produced by processing crude oil and other liquids at petroleum refineries, by extracting liquid hydrocarbons at natural gas processing plants, and by producing finished petroleum products at industrial facilities. For example, a petroleum product may include a transportation fuel, among other products. Refinery intermediates, for example, may refer to any refinery hydrocarbon that is not crude oil or a finished petroleum product (such as gasoline), including all refinery output from distillation (for example, distillates or distillation fractions) or from other conversion units. In some non-limiting embodiments of systems and methods, petroleum fluids may include heavy blend crude oil used at a pipeline origination station, natural gas, and / or other types of crude oil, as will be understood by one skilled in the art. Heavy blend crude oil is typically characterized as having an American Petroleum Institute (API) gravity of about 30 degrees or below. In other embodiments, the petroleum fluids may include lighter blend crude oils, for example, having an API gravity of greater than 30 degrees. “Renewable fluids” as used herein, mayrefer to fluid products containing plant and / or animal derived feedstock. Further, the renewable fluids may be hydrocarbon based. For example, a renewable fluid may be a pyrolysis oil, oleaginous feedstock, biomass derived feedstock, natural gas or other liquids or gasses, as will be understood by those skilled in the art. The API gravity of renewable liquids may vary depending on the type of renewable liquid.

[0094] In an embodiment, the systems and methods may include a computing device, apparatus and / or controller (referred to hereafter as a controller) to obtain various data points and / or parameters to train a machine learning model. Such data may include a historical data set and / or a currently generated data set including an outcome. In another embodiment, the data set may include a simulated and / or filled-in data set. For example, a refinery may be modeled based on a first-principle model and synthetic or pseudo-data may be generated for a selected time interval (for example, 1 month, 2 months, 6 months, 1 year, or even longer). For such a data set, random perturbations and / or anomalies are used to simulate a data set. In another embodiment, the data may include a partial data set. In such an embodiment, the partial data set, may be filled in via a first principle model and / or a machine learning model. Each data set may include a series of parameters, properties, spectra, and / or other data points associated with a refining operation or process or suboperation or sub-process. Each data set may also include target parameters, target properties, and / or an outcome and / or target product. Further, in an embodiment where a supervised machine learning model is utilized, each outcome may be classified as a positive or negative outcome or marked in a manner to indicate desirability of the outcome. In other embodiments, the function generated by a set of data may indicate a desired outcome, based on a maximum or minimum point in that function, thus enabling a machine learning model to determine desired parameters based on that maximum or minimum, or based on some other factor in other embodiments. In yet another embodiment, a trained machine learning model may learn or be trained based on trends included in the data (in other words, the trained machine learning model may comprise a deep learning model). In another embodiment, any of the trained machine learning models described herein may predict and / or optimize target parameters and / or fluids used within a refinery, refinery operation, or refinery sub-operation.

[0095] Once these data sets have been received by the controller, the controller may pre- process the data. For example, the controller may normalize the data (in other words, remove data points that appear to be outliers), remove data corresponding to abnormal events (for example, data generated during start-up, shut-down, turn-arounds, and / orupsets), remove undesired data, remove invalid measurements, and / or segregate the data set into sequences of contiguous data based on selected time intervals (for example, time intervals of 30 minutes, 1 hour, 2 hours, and / or 3 hours, or more or less than the time intervals listed).

[0096] Once the data has been pre-processed, the controller may begin training a model based on a portion of the data set. For example, the controller may utilize an 80 / 20 training and testing process. Other percentages may be utilized in training, testing, and / or validation. As the model is fed data, the model may compare data received to the outcome (in other words, whether the outcome was desired based on some factor, such as an indicated positive / negative flag or classification, based on some maximum or minimum of a function generated based on the data, or based on a trend within the data). Once the training portion of data has been utilized, the controller may test and / or validate the model using the remining portion of the data set. If such testing or validation does not achieve a selected error rate or reach some other error and / or accuracy based threshold, then the controller may re-train or refine the model using a different and / or randomized portion of the data set and a remaining portion of the data set for testing. Once a model has reached (e.g., achieved) that threshold, then the controller may output the trained machine learning model for further use.

[0097] Further, a trained machine learning model may be further refined using new data, as such data is generated. Such a refinement may occur while the trained machine learning model is in use. In another embodiment, the trained machine learning model may be refined in an offline environment. In another embodiment, two instances of a trained machine learning model may exist, one stored as an offline copy, while the other is utilized during refining operations. In such an embodiment, the offline copy may be refined and, if testing and / or error rating meets a selected threshold, in addition to other factors, then a controller may replace the version currently utilized to the refined version.

[0098] It will be understood that such systems and methods described herein may utilize a number of trained machine learning models or classifiers (also referred to as trained models or classifiers). For example, a model may be trained for each specific operation or process, as well as each particular piece of equipment, at a refinery, such as fluid catalytic cracking (FCC) operations or processes, hydrocracking operations or processes, reforming operations or processes, alkylation operations or processes, isomerization operations or processes, hydrotreating operations or processes, distillation operations or processes, blending operations or processes, hydrodeoxygenation operations or processes, steammanagement, hydrogen coordination or management, absorption, propylene splitting operations or processes, aromatic recovery, sulfur recovery, coker unit operations, feed optimization, IMO blending, hydrodeoxygenation, hydrocracker operations, other blending operations, an enhanced supercritical solvent deasphalting operation, solvent deasphalting (SDA) operation, operations or processes for formation of specific fuels, and / or the refining operation or process overall (which may, in an embodiment, utilize outputs from models associated with each sub-operation or sub-process). The use of terms operation and process refers to the steps taken to produce a particular product from a selected feedstock (and, in some embodiments, other inputs). As such, when referring to a particular refining operation or process, the terms “operation” and “process” may be used interchangeably. Further, such models may be trained specifically for equipment at a particular plant or refinery. For example, a FCC unit at a first plant may exhibit different characteristics than that of a FCC unit at a second plant. Thus, a model trained for one may not work for the other and training a model for either FCC unit may include utilization of historical data corresponding to that FCC unit. Various aspects of one model may be utilized to train other models for other similar equipment though.

[0099] Once a model is available, the controller, one or more sub-operation controllers or sub-controllers, and / or one or more operation controllers including a local enhancement or optimization module or circuitry, predictive controls, and / or equipment and device controls may begin optimizing, enhancing, and / or adjusting an operation and / or parameters associated with that operation, in real-time or near real-time and / or continuously or substantially continuously, at a refinery. In such embodiments, the controller may obtain data from a plurality of sensors, a plurality of refining operation control devices (such as flow control devices, temperature control devices, pressure control devices, and / or other device configured to control an aspect of a refining operation), equipment at the refinery (in other words, refining equipment), and / or one or more sample analyzers and / or, in some embodiments, one or more sub-operation controllers or sub-controllers. In another embodiment, one or more operation controllers may obtain such data, as well as target products and / or other factors or parameters from a refinery controller or platform.

[0100] As noted, one input to any of the models described herein may include spectra or properties of feedstock, intermediaries, products or outputs, and / or other fluids or materials utilized in a refinery, determined via one or more of a spectrographic analyzer or a chromatographic analyzer. The controller or controllers may work in conjunction with such an analyzer to further enhance fluid production (for example, transportation fuel,hydrocarbon based fluid products, and / or other fluids produced during a refining operation) of the refining operation or sub-operation. As such, spectrographic analyzers may be calibrated or standardized and results may be obtained in a faster than typical timeframe, thus enabling prompt acquisition of fluid properties. For example, for any operation described herein, the controller may obtain spectrographic or chromatographic analysis of any feedstock utilized, any intermediaries produced, and / or any products produced by first initiating sample collection. Once a sample has been obtained, the controller and / or an analyzer may initiate analysis of the sample.

[0101] Once the controller or controllers has / have obtained data related to each operation and / or analysis of one or more fluids associated with the operation, then the controller may apply such data and analysis to a corresponding machine learning model. The output of the model may indicate adjustment of one or more devices or refining operation control devices and / or refining equipment and / or adjustment of a feedstock or intermediary used in the operation or sub-operation. In some embodiments, the output may include targets and / or properties for a feedstock and / or blend of feedstock. In another embodiment, the output may be in the form of a vector, each component of the vector corresponding to a value associated with a parameter of equipment or a device or refining operation control device. In an embodiment, a refining operation control device may comprise or include a temperature control device (such as a furnace, heat exchanger, condenser, boiler, induction coil, fans, a cooling device, and / or other device capable of adjusting the temperature of a fluid and / or the temperature within refining equipment), a flow control device (such as a pump, valve, control valve, and / or other device capable of adjusting the flow rate of a fluid), a pressure control device (such as a compressor, a pump, a let-down station or valve, and / or another device configured to adjust the pressure of a fluid), and / or other devices configured to adjust some aspect of a fluid and / or aspect of refining equipment.

[0102] Once the controller has the output of the model, the controller may adjust the relevant aspects of the refining operation. For example, the controller may adjust components of a blend utilized in a feedstock, settings for various refining operation control devices (such as temperature, pressure, flow rate, and / or another aspect associated with a fluid and / or device), use of hydrogen, recovery of selected fluids or materials, and / or use of other fluids or materials (for example, a catalyst), among other adjustments.

[0103] In another embodiment, the controller may optimize an operation based on the current demand for selected products. For example, for a particular targeted product, selected amounts of feed and / or intermediaries may be utilized, increasing the demand forthat feed and / or intermediaries. In other embodiments, demand may be a factor utilized in training a model. For example, a selected product may experience increased demand at varying times or a particular feedstock, used to produce a particular product, may be in high demand. Data indicating such demand may be utilized in the described trained learning models.

[0104] In yet another embodiment, the controller may compare the output of the model to the current properties for a selected operation. Based on that difference of such a comparison, the controller may adjust various aspects of that operation.

[0105] By utilizing the trained machine learning models, the systems and methods described herein may determine specific adjustments to a plurality of operations and parameters specific to equipment at a refinery to accurately and more frequently (as compared to typical adjustment times) reach (e.g., achieve) a target product. Further, such adjustments may increase efficiency of the refinery equipment and / or reduce energy utilized by the refinery equipment, thus reducing cost of the refinery operation. The target product may be based on a number of factors, such as demand and / or price or cost for the product, cost of the product and / or feedstock, and / or based on a target product provided by a refinery controller or platform. Such adjustments may be determined in real-time or near real-time using data from continuous and / or ongoing refinery operations.

[0106] Thus, rather than attempting to adjust operations at a significant delay, a refinery’s operations may be adjusted in-real time or at time intervals shorter than in typical optimization operations (such typical optimization operations including operations by operating personnel to efficiently and accurately produce a target product). Further, such adjustments may be determined faster than typical adjustments to operations, leading to relevant and timely adjustments. Further, such analysis and adjustment utilizes complex non-linear equations which typically take longer to analyze, however with the use of machine learning, such analysis occurs significantly faster and with comparable accuracy.

[0107] FIG. 1 A and FIG. IB simplified diagrams of a refining control system to enhance fluid production at a refinery, according to an embodiment of the disclosure. As illustrated in FIG. 1A, a refinery 100 may include various refining control operation devices and refining equipment. While selected equipment are illustrated in FIG. 1A, it will be understood by those skilled in the art that additional and / or different equipment may be included in or at a refinery 100, particularly based on the type of feedstock processed at the refinery. For example, the refinery 100 may include a desalter, blending tanks, storage tanks, and / or wastewater treatment units, among other equipment. Further, each unit orequipment at the refinery 100 may be optimized using the machine learning models s disclosed herein, using data specific to the equipment from the refinery 100. In other words, the equipment may be operated such that the corresponding refinery operations produce an accurate and / or on-specification target product.

[0108] As illustrated in FIG. 1A, a refinery 100 may include a refinery controller 101 and / or a plurality of operation controllers 102. As will be illustrated in subsequent drawings, additional components may be included, such as a refining enhancer, other circuitry, various other controllers, and / or other computing devices. In an embodiment, the refinery controller 101 and / or the plurality of operation controllers 102 may include, for example, a trained machine learning model, as well as other instructions to adjust various devices and / or operations or processes within the refinery 100. The refinery controller 101 and / or the plurality of operation controllers 102 may connect to or be in signal communication with (a) one or more sensors, meters, transducers, and / or other measurement devices positioned throughout the refinery 100 and / or (b) to the equipment (for example, connected to some control aspect or device associated with the equipment) positioned at the refinery 100. The refinery controller 101 may be configured to receive data via such a connection. Further, the refinery controller 101 may receive such data in real-time or near real-time. In an embodiment, the refinery controller 101 may determine a target product and / or other parameters for a selected period of time. The refinery controller 101 may provide such data to each of the operation controllers 102. In other embodiments, the refinery controller 101 may utilize outputs from each of the operation controllers 102 to determine parameters for a target product. In other embodiments, the refinery controller 101 may apply those outputs, as well as other data, to a machine learning model.

[0109] In another embodiment, each of the operation controllers 102 may include a local enhancement circuitry 184, predictive controls circuitry 194, 191, and / or 195, and / or equipment and device controls 199. In embodiments, the circuitry may be a module or instructions. In embodiments, the operation controller 102 may include one or more varying or different predictive controls. For example, as illustrated, one or more of the predictive controls circuitry 191 may include a trained machine learning model 193. The trained machine learning model 193 may be trained for a specific operation and / or piece of equipment and, in some embodiments, may be trained to recognize an adjustment, maximization, and / or optimization for specified factors of the specific operation and / or piece of equipment. As such, the operation controller 102 may include a plurality of predictive control circuitry 191. The operation controls may also include predictive controlcircuitry 194, which includes a trained machine learning model 196 and / or a first-principle model (and / or, in some embodiments, another type of model). The trained machine learning model 196 may be trained to fill missing data for the first-principle model 198. The operation controller may also include predictive control circuitry 195, which may include a first-principle model 197. The first-principle model 197 may be a model using a known, physics based equation or formulation.

[0110] In an embodiment, the operation controller 102 may include a local enhancement circuitry 184. The local enhancement circuitry 184 may include a trained machine learning model 190 and target setpoint instructions 192. The trained machine learning model 190 may utilize data associated with a specific refining operation and / or the output from each predictive controls circuitry to produce an output. The target setpoint instructions may utilize the output of the trained machine learning model 190 to determine a set of parameters that equipment and / or devices associated with a specific refining operation should be set to, to reach (e.g., achieve) a target product. The operation controller may also include the equipment and device controls 199. The equipment and device controls 199 may cause equipment and / or devices to adjust to the target setpoints.[OHl] As illustrated in Fig. IB, the operation controllers 102 may further be connected to or in signal communication with a sample collection assembly 186 and / or a sample analysis assembly or sample analyzer 188. The sample analyzers 188 may include spectrographic analyzers, standardized spectrographic analyzers, and / or chromatographic analyzers. The type of spectrographic analyzers utilized may include one or more of near-infrared spectroscopic analyzer, a mid-infrared spectroscopic analyzer, a combination of a nearinfrared spectroscopic analyzer and a mid-infrared spectroscopic analyzer, a Raman spectroscopic analyzer, or a nuclear magnetic resonance spectroscopic analyzer. The sample analyzer 188 may analyze received samples and provide corresponding spectra indicating properties or other analysis indicating components and / or properties of the sample. The operation controllers 102 may also be connected to one or more sub-controllers or sub-operation controllers that are positioned or configured to manage selected aspects or operations of the refinery 100.

[0112] The refinery controller 101 and / or operation controllers 102 may include a processor and a memory or non-transitory machine-readable storage medium storing instructions executable by the processor (as illustrated in subsequent drawings). In some examples, the refinery controller 101 and / or the operation controller 102 may be a computing device. The term “computing device” is used herein to refer to any one or all ofprogrammable logic controllers (PLCs), distributed control systems (DCSs), a proportional integral derivative (PID) controller, a DCS-PID controller, programmable automation controllers (PACs), industrial computers, servers, virtual computing device or environment, desktop computers, personal data assistants (PDAs), laptop computers, tablet computers, smart books, palm-top computers, personal computers, smartphones, virtual computing devices, cloud based computing devices, and similar electronic devices equipped with at least a processor and any other physical components necessarily to perform the various operations described herein. Devices such as smartphones, laptop computers, and tablet computers are generally collectively referred to as mobile devices.

[0113] The term “server” or “server device” is used to refer to any computing device capable of functioning as a server, such as a master exchange server, web server, mail server, document server, or any other type of server. A server may be a dedicated computing device or a server module (e.g., an application) hosted by a computing device that causes the computing device to operate as a server. A server module (e.g., server application) may be a full function server module, or a light or secondary server module (e.g., light or secondary server application) that is configured to provide synchronization services among the dynamic databases on computing devices. A light server or secondary server may be a slimmed-down version of server type functionality that can be implemented on a computing device, such as a smart phone, thereby enabling it to function as an Internet server (e.g., an enterprise e-mail server) only to the extent necessary to provide the functionality described herein.

[0114] As used herein, a “non-transitory machine-readable storage medium” or “memory” may be any electronic, magnetic, optical, or other physical storage apparatus to contain or store information such as executable instructions, data, and the like. For example, any machine-readable storage medium described herein may be any of random access memory (RAM), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disc, and the like, or a combination thereof. The memory may store or include instructions executable by the processor.

[0115] As used herein, a “processor” or “processing circuitry” may include, for example one processor or multiple processors included in a single device or distributed across multiple computing devices. The processor (such as, processing circuitry 202 shown in FIG. 2 and / or a processor included in, for example, refinery controller 101 and / or the operation controllers 102 (not illustrated)) may be at least one of a central processing unit (CPU), a semiconductor-based microprocessor, a graphics processing unit (GPU), a field-programmable gate array (FPGA) to retrieve and execute instructions, a real time processor (RTP), other electronic circuitry suitable for the retrieval and execution instructions stored on a machine-readable storage medium, or a combination thereof.

[0116] Turning to the equipment positioned at the refinery 100, the refinery 100 may include a reactor 104 and, in some embodiments, a regenerator 120. The reactor 104 may be a catalytic reactor and / or a fluid catalytic cracking unit or reactor. The reactor 104 may include one or more sensors or meters positioned within the reactor 104 (such as sensor or meter 108) and / or proximate the reactor (such as sensors or meters 112, 114, 110, and 144). These sensor or meters may measure some aspect of fluid or material where the sensor or meter is positioned. Further, the reactor 104 may receive feedstock and / or an amount of water / steam at one or more locations of the reactor 104. The reactor 104 may be positioned or configured to convert heavy gas oil, residua, and / or other gas oil blends to an effluent or cracked fluid including smaller molecules, the effluent, in some embodiments, being further separated downstream into different products via distillation or fractionation. The reactor 104 may be operated at or it may be beneficial to operate the reactor 104 at a selected temperature range and / or pressure range to reduce over-cracking, which may cause a loss in valuable products, as well as to reduce over-all energy usage. Further, the amount of catalyst within and / or being fed to (for example, from the regenerator 120 and / or as fresh catalyst) the reactor 104 may impact the value of product produced by the reactor 104. Further, as a catalyst is regenerated within the regenerator 120, degradation may occur and / or coke deposited on the catalyst may not be completely burned off, particularly after multiple uses, thus further impacting product from the reactor 104. The feedstock fed to the reactor 104 may also affect parameters, such as temperature and residence time, among other parameters. Thus, several factors and / or parameters may impact the product produced by a reactor 104, those factors and / or parameters including temperature, pressure, type of catalyst, quality of catalyst, amount of catalyst, flow rate of feed or feed stock and / or catalyst, amount and temperature of steam injected, and / or properties of feed or feedstock, in addition to the product desired or targeted. The refinery controller 101 and / or operation controllers 102 may gather data related to such factors over time and apply that data, along with, in some embodiments, spectra provided from the sample analyzer 188, to trained machine learning models to produce parameters that enable production of a target product via a minimal amount of energy and / or lowest cost. Such application of data to a model may occur within various modules or circuits of one or more of the operation controllers 102 and / or, in addition to other data generated within the refinery 100, within the refinerycontroller 101. For example, one trained machine learning model within the predictive controls module 191 may be trained to maximize or be utilized for maximizing operating temperature in relation feedstock and a threshold temperature that may cause overcracking. In another example, another trained machine learning model may be trained to adjust or be utilized for adjusting heater temperature and / or temperature within the reactor in relation to feedstock and process parameters, composition, and / or other aspects to maximize yield or economically optimize yield from the reactor 104. In another embodiment, the trained machine learning model may be trained to adjust or be utilized for adjusting one or more refinery operation control devices to produce a selected yield of a product that also maximizes profit. Such an application of data to such a model may generate a vector that includes parameters or parameter settings corresponding to devices and / or equipment associated with the reactor 104 and, in some embodiments, the regenerator 120. That vector may be utilized by the local enhancement model to further determine, based on the outputs from other models as well as gathered data, parameters or parameter settings that enhance production of effluent from the reactor 104, such parameters or parameter settings being applied to actual equipment and / or devices via the equipment and device controller. Other models may be trained to determine parameters based on other relationships associated with the reactor 104 and / or other equipment.

[0117] In an embodiment, a trained machine learning model may be utilized by predictive controls (which may also be referred to as a prediction model) to optimize targets and / or properties and / or the predictive controls may be utilized by a an online optimization algorithm (which may also be referred to as the local enhancement module) to generate or determine targets.

[0118] The refinery 100 may include a regenerator 120. While a reactor 104 with a side- by-side configuration is illustrated in FIG. 1 A (as well as FIG. 5), it will be understood that other configurations may be utilized, such as a stacked configuration. In an embodiment, in addition to reactor data and corresponding fluid properties, refinery controller 101 and / or operation controllers 102 may obtain data and fluid properties corresponding to the regenerator 120. For example, the refinery controller 101 and / or operation controllers 102 may obtain data from sensors or meters 112, 116, 124, 126, 128, 132, 134, 138, 140, and 144, flow control devices associated with the reactor 104 and / or the regenerator 120 (such as valves 118, 130, 136, and 142), as well as properties or spectra associated with spent catalyst, regenerated catalyst, a feed or feedstock (for example, to aid in catalyst regeneration), and / or air (which may include pure oxygen or some combination of oxygenand other elements). Data may be obtained from other devices, such as flow control devices (such as, valves and / or pumps, among other devices configured to control flow of a fluid) and / or temperature control devices (such as boilers, heat exchangers, heating coils, condensers, and / or other heating or cooling devices). In an embodiment, the regenerator 120 may be positioned or configured to bum coke off of spent catalyst, the coke being deposited onto the catalyst in the reactor 104. The regenerator 120 may then provide the regenerated catalyst back to the reactor 104. In embodiments, the refinery controller 101 and / or operation controllers 102 may apply the data from the regenerator 120 to produce parameters or parameter settings to adjust corresponding equipment or devices to. The trained machine learning models may be trained or be utilized to determine parameters to maximize the amount of coke burned from catalyst, to increase temperature within the reactor 104 (for example, via heat from regenerated catalyst), and / or to minimize the amount of resources utilized by the regenerator 120.

[0119] Other equipment may be positioned throughout the refinery 100 and the refinery controller 101 and / or operation controllers 102 may connect to such equipment. The refinery controller 101 and / or operation controllers 102 may obtain or gather data related to that equipment during the refining operation. For example, the refinery controller 101 and / or operation controllers 102 may obtain data from and / or related to a fractionation column 148 or distillation column. Further, the refinery 100 may include and the refinery controller 101 and / or operation controllers 102 and / or one or more of the sub-controllers 190 may obtain data from a hydrotreater (such as hydrotreater 166 and hydrotreater 174) and / or an alkylation unit 158. The refinery controller 101 and / or operation controllers 102 may obtain data from the valve 146, sensors or meters 150, 154, 160, 164, 168, 172, 178, and 180, as well as the properties associated with the products from the fractionation column 148 (for example, LPG, gasoline, diesel, slurry, and / or other products), the hydrotreater 166 (for example, gasoline or high-octane gasoline), the hydrotreater 174 (for example, diesel, low-sulfur diesel, and / or higher purity diesel), and / or the alkylation unit 158 (for example, alkylate).

[0120] In an embodiment, the refinery controller 101 and / or operation controllers 102 may obtain data in real time and / or continuously or substantially continuously. In another embodiment, the refinery controller 101 and / or operation controllers 102 may obtain data periodically. In another embodiment, the refinery controller 101 and / or operation controllers 102 may apply data to a trained machine learning model at a selected time interval. Such an interval may be based on the time for samples from various positionswithin the refinery 100 to be collected and then analyzed. In yet another embodiment, each of the operation controllers 102 may obtain data related to a selected section of the refinery 100. Each of the operation controllers 102 may also obtain properties and / or spectra from the sample analyzer 188. After the operation controllers 102 obtain the properties and / or spectra and data, then the operation controllers 102 may apply the properties and / or spectra and data to a corresponding predictive controls module to produce parameters to produce a target product. The local enhancement module of the operation controller may then apply, to a trained machine learning model of the local enhancement module, the output of each of the predictive controls module, the data obtained throughout the refinery 100, and / or the properties and / or each spectra associated with a collected sample. Such an application may produce an enhanced or optimized set of parameters, which may then be applied to equipment or devices via the equipment and devices controls.

[0121] In yet another embodiment, the refinery controller 101 may first obtain data and the properties and / or spectra and then apply the data and the properties and / or spectra to a trained machine learning model. The refinery controller 101 may transmit the output of the trained machine learning model to each operation controller 102. In another embodiment, the refinery controller 101 may provide target products and corresponding parameters to each of the operation controllers 102, based on user input, previously utilized parameters, current cost of a target product and / or feedstock, and / or other factors. In another embodiment, the refinery controller 102 may facilitate communication between each of the operation controllers 102, facilitate data acquisition for the operation controllers 102, and / or facilitate parameter prediction and / or adjustment among the plurality of operation controllers 102. For example, if one operation controller adjusts a process to meet a selected target, that adjustment may affect upstream and / or downstream processes. The refinery controller 101 may facilitate communication and / or perform additional predictions to ensure that such parameter adjustments enable the upstream and / or downstream processes to continue to produce target products.

[0122] FIG. 2 is a simplified diagram that illustrates an apparatus for enhance fluid production at a refinery, according to an embodiment of the disclosure. Such an apparatus 200 may be comprised of a processing circuitry 202, a memory 204, a communications circuitry 206, a modeling circuitry 208, a fluid adjustment circuitry 210, and an equipment and device adjustment circuitry 212, each of which will be described in greater detail below. While the various components are illustrated in FIG. 2 as being connected with processing circuitry 202, it will be understood that the apparatus 200 may further comprisea bus (not expressly shown in FIG. 2) for passing information amongst any combination of the various components of the apparatus 200. The apparatus 200 may be configured to execute various operations described herein, such as those described above in connection with FIGS. 1 A-1B and below in connection with FIGS. 3-16.

[0123] The processing circuitry 202 (and / or co-processor or any other processor assisting or otherwise associated with the processor) may be in communication with the memory 204 via a bus for passing information amongst components of the apparatus. The processing circuitry 202 may be embodied in a number of unusual ways and may, for example, include one or more processing devices configured to perform independently. Furthermore, the processor may include one or more processors configured in tandem via a bus to enable independent execution of software instructions, pipelining, and / or multithreading.

[0124] The processing circuitry 202 may be configured to execute software instructions stored in the memory 204 or otherwise accessible to the processing circuitry 202 (e.g., software instructions stored on a separate storage device). In some cases, the processing circuitry 202 may be configured to execute hard-coded functionality. As such, whether configured by hardware or software methods, or by a combination of hardware with software, the processing circuitry 202 represents an entity (for example, physically embodied in circuitry) capable of performing operations according to various embodiments of the present disclosure while configured accordingly. Alternatively, as another example, when the processing circuitry 202 is embodied as an executor of software instructions, the software instructions may specifically configure the processing circuitry 202 to perform the algorithms and / or operations described herein when the software instructions are executed.

[0125] Memory 204 is non-transitory and may include, for example, one or more volatile and / or non-volatile memories. In other words, for example, the memory 204 may be an electronic storage device (for example, a computer readable storage medium). The memory 204 may be configured to store information, data, content, applications, software instructions, or the like, for enabling the apparatus 200 to carry out various functions in accordance with example embodiments contemplated herein.

[0126] The communications circuitry 206 may be any means such as a device or circuitry embodied in either hardware or a combination of hardware and software that is configured to receive and / or transmit data from / to a network and / or any other device, circuitry, or module in communication with the apparatus 200. In this regard, the communications circuitry 206 may include, for example, a network interface for enabling communications with a wired or wireless communication network. For example, the communicationscircuitry 206 may include one or more network interface cards, antennas, buses, switches, routers, modems, and supporting hardware and / or software, or any other device suitable for enabling communications via a network. Furthermore, the communications circuitry 206 may include the processing circuitry for causing transmission of such signals to a network or for handling receipt of signals received from a network. The communications circuitry 206, in an embodiment, may enable reception of parameters from various components, devices, and / or sensors (for example, flow control devices, analyzers, sensors, equipment, and / or other components), as well as communication of instructions and / or signals indicative of adjustment to those components and / or devices.

[0127] The apparatus 200 may include a modeling circuitry 208 configured to obtain parameters from one or more components, equipment, devices, sensors, and / or analyzers and / or apply those parameters to a trained machine learning model to obtain parameters that enable equipment to produce a target product. In other embodiments, the modeling circuitry 208 may apply, in addition to the parameters described herein, the output of other similar circuitry (in other words, an additional plurality of modeling circuitry that each correspond to one of a plurality of sub-operations). Obtaining the parameters from the one or more components, equipment, devices, sensors, and / or analyzers may occur periodically, at selected times, continuously, or substantially continuously. In an example, the modeling circuitry 208 may obtain parameters for sub-operations first, generating an output for each sub-operation. Upon generation of an output for each sub-operation, the modeling circuitry 208 may obtain each output and a current data set. The modeling circuitry 208 may poll the components, devices, sensors, and / or analyzers to obtain such parameters or, in an embodiment, receive the parameters without polling. The modeling circuitry 208 may obtain the parameters via the communications circuitry 206. Application of the parameters to the trained machine learning model may determine, generate, or cause generation of an output. The output may be indicative of an adjustment to equipment, fluids, devices, and / or operations to meet or accurately meet a target product and / or to operate the equipment at higher than typical efficiency, for example, utilizing less power or resources such as in a heater or boiler or utilizing a heat exchanger to reduce power usage.

[0128] In another embodiment, the modeling circuitry 208 may train the trained machine learning model prior to use. In such embodiments, the modeling circuitry 208 may obtain historical data, preprocess the historical data, and then train and test the machine learning model. In yet another embodiment, after a refining operation (in other words, after a selected product has been generated via the refining operation), the modeling circuitry 208may re-train or refine the trained machine learning model, based on the results of the refining operation (in other words, the accuracy of the parameters in reaching (e.g., achieving) the target product’s properties).

[0129] In another, the modeling circuitry 208 may train and / or include a plurality of machine learning models. Each of the plurality of machine learning models may correspond to a selected refinery operation and / or sub-operation.

[0130] The modeling circuitry 208 may utilize processing circuitry 202, memory 204, or any other hardware component included in the apparatus 200 to perform these operations, as described above in connection with FIGS. 1A-1B and below in connection with FIGS. 3-10. The output of the modeling circuitry 208 may be transmitted to other circuitry of the apparatus 200 (such as the fluid adjustment circuitry 210 and / or equipment and device adjustment circuitry 212).

[0131] In addition, the apparatus 200 further comprises the fluid adjustment circuitry 210 that may cause adjustment of feedstock and / or other fluids utilized in a refining operation. In an embodiment the output from the modeling circuitry 208 may be a matrix, a series of parameters, and / or some indicator. In an embodiment, the fluid adjustment circuitry 210 may utilize that output to adjust a blend of feedstock and / or the fluid used in other inputs (for example, an amount of hydrogen, butane, other alkanes, and / or other fluids). The fluid adjustment circuitry 210 may utilize processing circuitry 202, memory 204, or any other hardware component included in the apparatus 200 to perform these operations, as described above in connection with FIGS. 1A-1B and below in connection with FIGS. 3- 26. The fluid adjustment circuitry 210 may further utilize communications circuitry 206 to transmit signals to adjust the type and / or amount of feedstock to utilize.

[0132] In addition, the apparatus 200 further comprises the equipment and device adjustment circuitry 212 that may cause adjustment of equipment and / or devices utilized in a refining operation. In an embodiment, the equipment and device adjustment circuitry 212 may utilize that output to adjust temperature, pressure, flow rate, and / or other parameters corresponding to the equipment and / or devices positioned within the refinery (e.g., by setting valve positions, pump speeds, etc.). The equipment and device adjustment circuitry 212 may utilize processing circuitry 202, memory 204, or any other hardware component included in the apparatus 200 to perform these operations, as described above in connection with FIGS. 1A and IB and below in connection with FIGS. 3-10. The equipment and device adjustment circuitry 212 may further utilize communications circuitry 206 to transmit signals to adjust equipment and / or devices utilized.

[0133] Although components 202-212 are described in part using functional language, it will be understood that the particular implementations necessarily include the use of particular hardware. It should also be understood that certain of these components 202-212 may include similar or common hardware. For example, the modeling circuitry 208, the fluid adjustment circuitry 210, and the equipment and device adjustment circuitry 212 may, in some embodiments, each at times utilize the processing circuitry 202, memory 204, or communications circuitry 206, such that duplicate hardware is not required to facilitate operation of these physical elements of the apparatus 200 (although dedicated hardware elements may be used for any of these components in some embodiments, such as those in which enhanced parallelism may be desired). Use of the terms “circuitry,” with respect to elements of the apparatus therefore shall be interpreted as necessarily including the particular hardware configured to perform the functions associated with the particular element being described. Of course, while the terms “circuitry” should be understood broadly to include hardware, in some embodiments, the terms “circuitry” may in addition refer to software instructions that configure the hardware components of the apparatus 200 to perform the various functions described herein.

[0134] Although the modeling circuitry 208, the fluid adjustment circuitry 210, and the equipment and device adjustment circuitry 212 may utilize processing circuitry 202, memory 204, or communications circuitry 206 as described above, it will be understood that any of these elements of apparatus 200 may include one or more dedicated processors, specially configured field programmable gate arrays (FPGA), or application specific interface circuits (ASIC) to perform its corresponding functions, and may accordingly utilize processing circuitry 202 executing software stored in a memory or memory 204, communications circuitry 206 for enabling any functions not performed by special-purpose hardware elements. In all embodiments, however, it will be understood that the modeling circuitry 208, the fluid adjustment circuitry 210, and the equipment and device adjustment circuitry 212 are implemented via particular machinery designed for performing the functions described herein in connection with such elements of apparatus 200.

[0135] In some embodiments, various components of the apparatus 200 may be hosted remotely (e.g., by one or more cloud servers) and thus need not physically reside on the corresponding apparatus 200. Thus, some or all of the functionality described herein may be provided by third party circuitry. For example, a given apparatus 200 may access one or more third party circuitries via any sort of networked connection that facilitates transmission of data and electronic information between the apparatus 200 and the thirdparty circuitries. In turn, that apparatus 200 may be in remote communication with one or more of the other components describe above as comprising the apparatus 200.

[0136] As will be appreciated based on this disclosure, example embodiments contemplated herein may be implemented by an apparatus 200 (or by a refinery controller). Furthermore, some example embodiments (such as the embodiments described for FIGS. 1A-1B and 3-10) may be a computer program product comprising software instructions stored on at least one non-transitory computer-readable storage medium (such as memory 204). Any suitable non-transitory computer-readable storage medium may be utilized in such embodiments, some examples of which are non-transitory hard disks, CD-ROMs, flash memory, optical storage devices, and magnetic storage devices. It should be appreciated, with respect to certain devices embodied by apparatus 200 as described in FIG. 2, that loading the software instructions onto a computing device or apparatus produces a special-purpose machine comprising the means for implementing various functions described herein.

[0137] FIG. 3 a simplified diagram that illustrates example refining controllers and an example refining enhancer to enhance control of a refining process at a refinery, according to an embodiment of the disclosure. As illustrated in FIG. 3, a refinery may include one or more operation controllers 302. The operation controllers 302 may connect to, for example, a number of feeds and / or processing units (refinery equipment configured to process a feedstock or other input). As illustrated, the operation controllers 302 may connect to and receive data from feed A 303 A, feed B 303B, and up to feed 303N, sensors or other devices associated with each feed (such as sensor 304A, 304B, and up to 304N), and various flow control devices (such as valve 306A, valve 306B, and up to valve 306N). In such embodiments, each of feed A 303 A, feed B 303B, and up to feed 303N may flow to a first processing unit 308. A processing unit, for example, in this case, the first processing unit 308, may include one or more refining devices or equipment positioned at a refinery (for example, a FCC unit, a distillation column, and other equipment as described herein). The first processing unit 308 may convert, process, and / or transform a feed into a unit material (such as unit material A 310A, unit material B 310B, and up to unit material N 310N). Additional processing units may be positioned throughout the refinery. As illustrated though, the unit materials may flow to a “Nth” processing unit 314. Sensors (such as sensor 312A, 312B, and up to 312N) and valves (such as valve 313 A, valve 313B, and up to valve 313N) may be positioned between the feed and “Nth” processing unit 314. The final processing device (in other words, the “Nth” processing unit 314) may produce one or moreend materials (such as end materials A 316A, end materials 316B, and up to end materials 316N). Sensors (such as sensor 318A, 318B, and up to 318N) and valves (such as valve 320A, valve 320B, and up to valve 320N) may be positioned between the end materials and the material destination 322.

[0138] In an embodiment, as each feed is fed to the next processing unit, the operation controller 302 may determine various characteristics and / or properties of the feed. For example, the operation controller 302 may determine temperature, pressure, and / or flow rate, in addition to the content of the feed and the spectra or properties determined via spectrographic analysis of the feed. For example, as illustrated, the operation controller 302 may determine or obtain feed information 324 (including, at least feed content (e.g., composition) 326 and / or feed properties 328, among other data), unit material information 330 (including, at least unit material content (e.g., composition) 332 and / or unit material properties 334, among other data), and / or end material information 336 (including, at least end material content (e.g., composition) 338 and / or end material properties 340, among other data). Thus, the operation controller 302 may obtain data related to each feed / material in real-time or near real-time, during a refinery operation, and / or directly or indirectly (for example, spectra may be obtained via a sample or spectrographic analyzer).

[0139] Once all the data has been obtained, the operation controller 302 may apply, to the machine learning model 360 of a local enhancer 358, the data including processing unit constraints 350, a target product 352 (including a target content (e.g., composition) 354 and target properties 356), and / or material differences 344 (including content differences 346 and properties difference 348) as determined via a comparator 342 (the comparator positioned or configured to compare composition (e.g., content) and properties of different materials). The machine learning model 360 may produce material targets 362 which may be utilized to produce target feed ratios 364 and target operation unit parameters 366. In another embodiment, these values may be fed to the comparator and then, after obtaining differences related to another material, reapplied to the machine learning model 360. The machine learning model 360 may then produce adjusted targets 370 (including adjusted target feed ratios 372 and adjusted target operation unit parameters 374).

[0140] In another embodiment, the output of the machine learning model (for example, a vector comprising a plurality of components, each component being a parameter setting for a selected or specific device or equipment) may be compared to current parameter settings for the selected or specific devices or equipment in the comparator 342. In such embodiments, if the comparator 342 determines that there is a difference between an outputof the machine learning model, then the parameter settings of the equipment or devices at the refinery may be adjusted.

[0141] In embodiments, the controller 302 may drive the materials to the target by adjusting the valves and / or feed (for example, the blend of different feeds or materials used in the subsequent operation) at one or more points in the overall refining operation.

[0142] The machine learning model 360 may include neural networks, supervised learning models, semi -supervised learning models, unsupervised learning models, or some combination thereof, as will be readily understood by one having ordinary skill in the art. In another embodiment, different types of machine learning algorithms may be utilized for different refinery operations. In further embodiments, some refining operations may use, rather than or in addition to a neural network, decision trees, support vector machines, hidden Markov models, Bayesian networks, linear regression, k-means, and / or tabular reinforcement learning. Specific neural networks that may be utilized include a recurrent neural network, such as a long short-term memory network. Such neural networks may utilize a fixed horizon of historical data to predict future behavior. Additionally, such neural networks may utilize standard active functions, for example a rectified linear unit or a hyperbolic tangent. As noted, in embodiments, different models may be utilized for different operations. The determination for which model to use for each operation may be determined based on error rates associated with a selected model, the R2value, SHAP plots and / or values, gain directions and / or magnitude, and / or gain distributions, among other factors.

[0143] In an embodiment, the operation controller 302, local enhancer 358, and / or comparator 342 may be included in a single controller, a plurality of controllers, one or more computing devices, and / or as one or more modules or as instructions. In other embodiments, a plurality of controllers or computing devices may each include a specific model corresponding to one of the processing units. In another embodiment, the operation controller 302 may include or may be a supervisory controller that considers the predictions of other processing unit specific controllers when generating adjusted targets via the supervisory controller’s machine learning model.

[0144] As noted, data may be obtained in real time. In some embodiments, the application of data to a machine learning model may be delayed by the time taken to obtain spectra or properties for a feed or material. Thus, in an embodiment where the operation controller 302 is a supervisory controller, the supervisory controller may generate adjusted targets after each sub-controller generates a target for a specific processing unit. Thus, the overalladjustment targets may be determined at a second time interval, greater than the first time interval, while each sub-adjustment target may be determined at a first time interval.

[0145] In another embodiment, a refinery may include a plurality of operation controllers. Each operation controller 302 may include a plurality of trained machine learning models. Each trained machine learning model may be trained to recognize a specific or selected trend in a set of data. Thus, each operation may be adjusted based on the outputs of a plurality of models, ensuring the operation as a whole produces an accurate target product. Further, each operation controller may interact with each other operation controllers. For example, adjusted parameters from all operation controllers may be provided to each operation controller. Thus, as one operation is adjusted, a downstream and / or upstream operation may be further adjusted based on the adjustment of the one operation.

[0146] FIG. 4 is a simplified diagram that illustrates the training of a machine learning model for enhanced fluid production at refinery, according to an embodiment of the disclosure. Each model described herein may be trained prior to use. Such training may be performed prior to use with a set of historical data specific to a refinery. In a further embodiment, a plurality of machine learning models may be trained, each based on data specific to an operation and selected equipment at the refinery.

[0147] As noted, the machine learning models described herein may be trained using data. As illustrated in FIG. 4, the data may include historical, equipment specific data 402. In other embodiments, the training data may include data related to the entire operation of a refinery, as well as outputs from equipment specific models. In another embodiment, a machine learning model may be re-trained and / or refined via current and marked up equipment specific data 404. The historical equipment specific data 402 and current and marked up equipment specific data 404 may include feed composition (e.g., content), feed properties, material composition (e.g., content), material properties, a target product (e.g., target product composition) or products, target composition (e.g., content), target properties, temperatures in equipment, pressure in equipment, flow rates associated with feed and / or materials, and / or equipment parameters. In embodiments, the historical equipment specific data 402 may include or may be utilized to generate a non-linear concave function. In such embodiments, the desired outcome may be determined based on the maximum of such a function. In another embodiment, the desired outcome may be included or added to the data set. In yet another embodiment, training may include the machine learning model learning particular patterns that indicate what the desired outcome may be based on trends within the data. In another embodiment, physics-based data maybe provided along with the historical data set to ensure that outputs from a trained machine learning model remain consistent and / or emulate real process / actual possibilities. In yet another embodiment, a plurality of machine learning models may be trained for the same operation. Each of the plurality of machine learning models may utilize different portions of historical data and / or other inputs to cause the model to maximize a specific property or parameter. Another model may be trained to utilize the outputs of each of those plurality of models, in addition to data.

[0148] Once the historical data, and any other current data, is available, that data may be pre-processed 406. In such embodiments, the data may be normalized. In other words, outlying data points that are anomalies may be removed from the data set. Further, data corresponding to abnormal events may be removed, such as data generating during startup, shut-down, turn-arounds, maintenance, and / or upsets. Further, undesired data and invalid measurements may be removed. Finally, data may be segregated or separated into sequences based on time. The sequences may comprise data obtained over a consecutive time period, such as time intervals of 30 minutes, 1 hour, 2 hours, and / or 3 hours, or more or less than the time intervals listed. In another embodiment, other factors may be utilized to segregate or separate the data, such as feed used and / or target product being produced.

[0149] Once the data set has been pre-processed, a model may be trained 408. In embodiments, a portion of the data set (for example, 70%, 80%, or 90%) may be fed to the machine learning model. The machine learning model may utilize the inputs versus the known desired outcome (such as target product content and properties) and / or known undesired outcome to “learn” what parameters can be utilized to reach the known desired outcome and what parameters lead to the known undesired outcome. Once the data has been used to train the machine learning model, then the remaining portion of the data set may be utilized to test 410 the trained machine learning model. If the trained machine learning model does not meet or achieve a selected error rate, then the trained machine learning model may be re-trained or refined with a different randomized portion of the data set, and the re-training repeated as necessary, until the selected error rate is met or achieved. In another embodiment, other training schema may be utilized. In another embodiment, readiness of the trained machine learning model may be determined based on how close the trained machine learning model comes to an expected outcome, based on the test data set.

[0150] Once the trained machine learning model 412 meets a selected error rate, then the trained machine learning model may be released for further use. In another embodiment, aseparate step may include selection of a type of machine learning model prior to training of the machine learning model. In other embodiments, various types of models may be trained, then tested. The most accurate models, determined by an error rate for each model, may be utilized.

[0151] FIG. 5 is a schematic diagram of a FCC control system 500 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. As noted, specific sections or portions of a refinery may include a sub-controller to enhance that particular operation. As illustrated in FIG. 5, a FCC operation may be enhanced via a FCC controller 502 and corresponding machine learning models (for example, FCC specific machine learning models utilized in the local enhancement module 504 and / or the predictive controls module 506). The FCC controller 502 may connect to sources of and control various parts of the FCC reactor 532, including, in some embodiments, a regenerator 552. For example, the FCC controller 502 may control amounts and / or type of feed 514, FCC catalyst 510, fluffing steam 522, stripping steam 526, pre-stripping steam 536, and / or spent catalyst 542 flowing into or from the FCC reactor 532 through conduits 512, 520, 524, 530, 546, 562. Further, the FCC controller 502 may connect to sources of and control spent catalyst 542 (for example, via slide valve 548), regenerated catalyst 556 (for example, via slide valve 564), and / or air 560 flowing into the regenerator 552. Further, the FCC controller 502 may obtain data related to each input material or feed, as well as the temperature and / or pressure within the FCC reactor 532 and / or regenerator 552.

[0152] Prior to generating adjusted parameters for operation of the FCC reactor 532, the FCC controller 502 may initiate collection of samples of one or more of the materials or feeds flowing into and out of the FCC reactor 532 and / or regenerator 552, via the sample collection and analysis assembly 508. Once the sample collection and analysis assembly 508 obtains one or more samples, the sample collection and analysis assembly 508 may analyze those samples to produce properties and / or a spectra indicative of various properties, as well as data from sensors disposed throughout the FCC operation. Once the properties and / or spectra are analyzed, the sample collection and analysis assembly 508 may transmit the data, including the sample and sensor data and analysis, to the FCC controller 502. The data may include feedstock data indicative of one or more of the properties or composition of the feedstocks of the FCC, operational data indicative of one or more of the temperatures, pressures, feed rates of feedstocks, catalysts, steam, and other materials throughout the FCC, and other operating parameters of the FCC, and product data indicative of one or more of the properties or composition of the products of the FCC. Uponreception of the data, the FCC controller 502 may apply the data, along with target product composition and / or properties, to one or more machine learning models within the predictive controls module 506 (or, in other embodiments, a plurality of predictive controls modules may be included in the FCC controller 502 and each may include a machine learning model. Alternatively, a single machine learning model may incorporate the functionality of the predictive control modules and the local enhancement module. In other embodiments, the output may indicate that a new or fresh catalyst should be utilized.

[0153] The output of each of the machine learning models in the predictive controls module 506 may then be utilized by the local enhancement module 504 to determine (for example, as a vector) new parameters and / or feed blend or composition to supply to the FCC reactor 532. The FCC controller 502 may then adjust the parameters of and / or feeds and / or materials for the FCC reactor 532 and / or regenerator 552.

[0154] The FCC reactor 532 may exhibit non-linear operation in relation to temperature, as well as in relation to other factors. If the temperature is below or above a threshold range, then the output from the FCC reactor 532 may not include the highest possible product yield. Thus, at least one machine learning model for a FCC operation may, when trained, determine a desired outcome based on the maximum of the non-linear objective function relating to temperature and the output or yield (for example, an increase in amount of one or more products of a plurality of products) of the FCC reactor 532. In another embodiment such a non-linear objective function may maximize profit (for example, based on an increase in yield of a particular product or one or more products of a plurality of products). In another embodiment, a non-linear objective function relating to temperature and product composition may be used by a machine learning model to generate target operational parameters to achieve a target point of the non-linear objective function. The resulting model may be utilized to drive, in part, the FCC reactor 532 operation to that maximum non-linear function or non-linear profit function. Such a function is also dependent on the properties of the feed, which, as noted, change over time, among other factors. For example, another machine learning model may, when trained, determine a desired outcome based on the maximum or minimum of another non-linear function relating to temperature of other areas, pressure within the FCC reactor 532, temperature within the regenerator 552, amount of catalyst, type of catalyst, age or deactivation state of catalyst, and / or flow rates to and / or from the FCC reactor 532. Another machine learning model may, when trained, determine a predicted feedstock blend for a FCC operation based on value to unit constraints. Another machine learning model may, when trained, determine adjustments to hydrotreater severityto vary aromatic saturation against FCC constraints (in other words, the amount of feed from an upstream hydrotreater to a FCC reactor 532 may be adjusted based on, for example, the content and / or composition of the feed, among other factors). Another machine learning model may, when trained, determine adjustments to a hydrocracker conversion to feed unconverted gas oil to the FCC that provides optimal FCC yield against FCC constraints and, in some embodiments, in terms of profit. The FCC constraints may include minimum regeneration temperature, wet gas compressor capacity, FCC fractionation limits, surge drum capacity, charge pump capacity, heater capacity, reactor capacity, regenerator capacity, main air blower capacity, and gas concentration section limits. In yet another embodiment, another machine learning model may, when trained, determine adjustments to hydrotreater severity to maximize aromatic saturation to hydrotreater constraints.

[0155] In another embodiment, the FCC controller 502 may first cause sampling of various fluids (e.g., liquids, vapors, and / or gases) used and / or produced in the FCC operation. For example, as FCC operation occurs (for example, as a continuous and / or ongoing operation) various fluids and / or materials may be utilized and / or produced therein. Prior to application of data to any of the machine learning models described herein, the FCC controller 502 may initiate capture of one or more of those fluids via the sample collection and analysis assembly 508. Once samples are analyzed, the FCC controller 502 may predict properties of the corresponding feedstocks and operational parameters that may achieve an accurate output of a target product. In other words, the FCC controller 502 may determine the composition of feedstocks and the blends that may be used to achieve a target product property and / or composition. The feedstocks may then be adjusted, blended, and / or supplemented to achieve a target feedstock composition determined by one or more of the machine learning models of the FCC controller 502. Stated another way, the FCC controller 502 may control the properties, composition, and / or feed ratios associated with a feedstock or hydrocarbon feedstock and / or an intermediate fluid or intermediate product.

[0156] In an embodiment related to FIG. 1, the machine learning model may be trained or configured to determine an amount of giveaway of light cycle oil (LCO) in the slurry 182 against an exchanger fouling rate in a slurry circuit from the bottoms of the FCC main fractionator 148. The light cycle oil (LCO) is shown as becoming diesel 176 after hydrotreating in the hydrotreater 174. The slurry contains contaminants released in the FCC process, as well as polynuclear aromatics that were not cracked during the FCC process. The slurry 182 is generally a thick fluid and may not flow well through the conduits from the FCC main fractionator. The addition of light cycle oil (LCO) assists in improving theflow properties of the slurry 182 preventing clogs and fouling downstream. The machine learning model may be trained or configured to determine a slurry cut point to prevent, reduce, or significantly reduce fouling in downstream slurry exchanger sections by permitting some light cycle oil (LCO) to be added to the bottoms and the slurry 182.

[0157] FIG. 6 is a schematic diagram of an enhanced hydrotreater control system and a distillation control system 600 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. As illustrated in FIG. 6, a distillation / fractionation portion of the refinery may include a distillation controller 602 and / or a hydrotreater controller 608. The distillation controller 602 may obtain data related to a fractionation / distillation column 616. For example, the distillation controller 602 may obtain temperature and / or pressure within the fractionation / distillation column 616. Further, the distillation controller 602 may initiate collection of samples of various fluids associated with the fractionation / distillation column 616 via the sample collection and analysis assembly 614. For example, the sample collection and analysis assembly 614 may obtain samples of off-gas 624, LPG 628, naphtha / gasoline 634, diesel 640, and / or slurry 620, among other fluids associated with the fractionation / distillation column 616. Sensor packages 618, 622, 626, 630, 636 may be disposed to measure the temperature, pressure, flow rate, and composition of the products from the fractionation / distillation column 616 including off-gas 624, LPG 628, gasoline 634, diesel 640, and slurry 620.

[0158] Once the sample collection and analysis assembly 614 obtains the samples, the sample collection and analysis assembly 614 may analyze the samples to produce properties or spectra indicative of the properties of each collected sample. The sample collection and analysis assembly 614 may provide the properties and / or spectra to the distillation controller 602. The distillation controller 602 may then apply the data, properties, and / or spectra to the to one or more training machine learning models associated with one or more of a local enhancement module 604 and / or predictive controls module 606. Based on the output of the trained machine learning models, which may indicate parameter and / or feed adjustment of the fractionation / distillation column 616, the distillation controller 602 may adjust the parameters and / or the feed via the local enhancement module 604 and, in some embodiments, an equipment and device control module. The equipment and device control module may comprise a PLC or DCS. In some embodiments, the equipment and device control module may comprise a DCS-PID module, controller, or circuitry.

[0159] In an embodiment, the distillation machine learning model 604 may be trained to maximize lift within the distillation column. Such a model may utilize temperature and / or feed flow rate to maximize such a parameter (in other words, to maximize lift or pressure). Further, such a model may predict parameters based on, in part, the concave objective function for profit to determine a feed and / or temperature input that drive the distillation column to include a maximum lift in a pressure limited column. The parameters for such an application of data to a trained machine learning model may include providing more energy and / or material to the column or increasing material or energy to increase pressure if all pressure control handles are exhausted. For example, the output from one of the trained machine learning models may indicate an increase in temperature and / or feed to maximize the output of a selected one or more products from the fractionation / distillation column 616. Such a maximization of the output may optimize profit for the fractionation / distillation column 616.

[0160] The fractionation / distillation column 616 may include a vacuum column. Such issues described above may also occur for a vacuum column when the vacuum tower may no longer be cooled (for example, due to cooling water limitations) or when a vacuum ejector system is limited and may no longer decrease pressure. The concave objective function in this case can be used to determine what feed and temperature in the column with uncontrolled pressure give the most profitable light vacuum gas oil (LVGO), middle vacuum gas oil (MVGO), heavy gas oil (HVGO) lift from resid.

[0161] In another example, the fractionation / distillation column 616 may comprise a vacuum column and / or crude unit. In such examples, one trained machine learning model may be trained or configured to utilize a resid viscosity, asphalt m-value, and / or other asphalt property as an input and / or, in other embodiments, sample analysis of the outputs and inputs of the vacuum column. Further, the trained machine learning model may utilize as an input, current valve settings, heater outlet temperature (for example a vacuum heater outlet temperature), and / or vacuum operating parameters. The output of such a model may include updated settings or set points for the valve settings, heater outlet temperature (for example a vacuum heater outlet temperature), and / or vacuum operating parameters. Such a trained machine learning model may minimize the amount of gas oil in the resid, when the resid is being utilized to make asphalt. The distillation controller 602 may utilize such an output to set equipment to parameters or settings output from the trained machine learning model.

[0162] The issues described above may also occur for an atmospheric vacuum column, where the feed and temperature in the column with uncontrolled pressure may be determined with a neural network model and controller to give higher lift of naphtha, distillate, and atmospheric gas oil from a crude column feed. For an atmospheric vacuum column, several constraints may be considered, such as product quality, hydraulic constraints, operating limits, and column differential pressure limits. Alternatively, problems associated with operation of the atmospheric vacuum column may be formulated to manipulate other variables such as pump-around return flow, pump-around return temperatures, and stripping steam that optimize the lift in the column when the column pressure is not being controlled.

[0163] In an embodiment, properties of feedstock utilized in a distillation operation may and / or other operations described herein may include boiling point, viscosity, composition, API gravity, paraffin concentration (amount of paraffins), aromatic concentration (amount of aromatics), naphthenic concentration (amount of naphthenes), each of paraffin, aromatic, and naphthenic concentration, distillation points, Coker gas oil content, carbon residue content, nitrogen content, sulfur content, saturates content, thiophene content, single-ring aromatics content, dual-ring aromatics content, triple-ring aromatics content, or quad-ring aromatics content. In another embodiment, fluids, target products, material, and / or unit materials produced by a fractionation / distillation column 616 may include one or more of an amount of butane-free gasoline, an amount of total butane, an amount of dry gas, an amount of coke, an amount of gasoline, octane rating, an amount of light fuel oil, an amount of heavy fuel oil, an amount of hydrogen sulfide, an amount of sulfur in light fuel oil, or an aniline point of light fuel oil. In another embodiment, properties of the fluids, target products, material, and / or unit materials produced by the fractionation / distillation column 616 may include one or more of pentane content, raw crude water content, desalted crude water content, heavy atmospheric gas oil (HAGO) content, light atmospheric gas oil (LAGO) flash, or kerosene flash point. In yet another embodiment, the distillation controller 602 may control the pentane content, the raw crude water content, the desalted crude water content, the heavy atmospheric gas oil (HAGO) content, the light atmospheric gas oil (LAGO) flash, or the kerosene flash point, one or more of: crude blend, make-up water, desalter severity, HAGO wash rate, stripping, LAGO draw rate, stripping steam, or kerosene draw of the one or more of the first processing units.

[0164] In yet another embodiment, the properties of the fluids, target products, material, and / or unit materials produced by the fractionation / distillation and absorber column 616may include one or more of ethane content, propane content, propene content, isobutane content, or n-butane content. In such embodiments, the distillation controller 602 may control one or more of the ethane content, the propane content, the propene content, the isobutane content, or the n-butane content, one or more of: absorber pressure, lean oil flow rate, lean oil temperature, high-pressure separator temperature, reactor conversion, or stripper reboiler duty.

[0165] In yet another embodiment, the properties of the fluids, target products, material, and / or unit materials produced by the fractionation / distillation column 616 may include one or more of high-pressure separator water content or stripper bottoms water content. In such embodiments, the distillation controller 602 may control a temperature of a high- pressure separator.

[0166] In another embodiment, the fractionation / distillation column 616 may comprise a vacuum tower (in other words, a distillation tower operating under reduced pressure). In such embodiments, one of the trained machine learning models may infer or predict a micro-carbon residue (MCR) or HVGO MCR based on various parameters and / or feeds (such as, for example, wash rate, c-factor, bed distribution, lift drive-up entrainment, and / or feed properties, among others), enabling a controller (for example, the distillation controller 602) to determine adjustments to a vacuum distillation operation based on the inferred or predicted MCR. In another embodiment, rather than or in addition to utilizing HVGO MCR, the trained machine learning models may infer or predict nickel and / or vanadium (and / or other metals) content in HVGO. In yet another embodiment, rather than or in addition to utilizing HVGO MCR, the trained machine learning models may infer or predict a distillation cut point, a gas oil lift from resid, and / or HVGO wash bed lifecycle for HVGO production and / or to prevent premature shutdown.

[0167] In another embodiment, the trained machine learning model may also optimize deisopentanizer fractionation, such an optimization increasing octane on, in some embodiments, an isomerization unit. Such a trained machine learning model may be utilized to optimize DIP feed limit based on various factors, such factors being applied to the trained machine learning model. Further, such factors may include amount of steam utilized, temperature from a reboiler, a reflux rate, feed properties, and / or output properties.

[0168] In another embodiment, the distillation controller 602 (and / or, in embodiments, the local enhancement module 604 and / or predictive controls module 606) may include a trained machine learning model trained and / or configured to determine a salt point temperature for the fractionation / distillation column 616 (or, in some embodiments, a crudeatmospheric distillation column). In such embodiments, the distillation controller 602 may input fractionation / distillation column 616 setpoints, valve setpoints, overhead temperature, and / or overhead reflux, among other factors, to the model. The trained machine learning model may output updates to the setpoints for the fractionation / distillation column 616 and / or valves, as well as temperature and / or overhead reflux setpoints. Such a trained machine learning model may prevent salt deposition in overhead piping and / or other downstream mechanical equipment. These salt depositions may lead to a loss of containment, premature damage of equipment, and / or premature equipment or plant shutdown.

[0169] Further, FIG. 6 illustrates a hydrotreater controller 608. The hydrotreater controller 608 may obtain data related to each hydrotreater 632 and 638. Data obtained from each hydrotreater may be analyzed separately, as each hydrotreater performs a different function (for example, increase gasoline octane or remove sulfur and / or impurities from diesel). In yet another embodiment, the hydrotreater controller 608 may include a machine learning model specific for and trained for each specific hydrotreater, due to the changes each piece of equipment may experience over time.

[0170] The hydrotreater controller 608 may obtain data related to each hydrotreater and / or initiate capture of samples associated with each hydrotreater. The sample collection and analysis assembly 614 may then analyze the samples to produce properties or spectra indicative of properties of the fluids associated with the hydrotreater. Once the hydrotreater controller 608 obtains data, properties, and / or spectra related to a hydrotreater, the hydrotreater controller 608 may apply the data, properties, and / or spectra to a machine learning model within one or more of the local enhancement module 610 or the predictive controls module 612. The output of the hydrotreater machine learning model may indicate adjustments to parameters and / or feed associated with the hydrotreater. Using such an output, the local enhancement module 610 may adjust the parameters and / or feed associated with the hydrotreater, for example via a PID controller, DCS controller, PLC controller, or a DCS-PID controller.

[0171] In some embodiments, the local enhancement module 610 may include programming and an algorithm configured to facilitate optimization of the hydrotreaters 632, 638 to achieve the target parameters based on the inputs, the target parameters, unit constraints, and the outputs of the hydrotreaters 632, 638 from one or more machine learning models (e.g., of the predictive controls modules 612), and inputs. The algorithm may be modeled by a machine learning model and configured to facilitate optimization ofthe hydrotreaters 632, 638 based on a machine learning model. In some embodiments, the local enhancement module 610 includes an optimizer comprising an algorithm configured to achieve target parameters based on the optimization (e.g. maximization) of an objective function based on the outputs from the first machine learning models (e.g., of the predictive controls modules 612), the target parameters, unit constraints, and inputs.

[0172] In an embodiment, the machine learning model utilized in the hydrotreater controller 608 may be trained to maximize sulfur removal at a lowest possible temperature. In an example, as a targeted product’s sulfur level or amount becomes lower, the hydrotreater temperature setting increase becomes even higher to achieve the same amount of sulfur removal. Thus, the output of the machine learning model of the hydrotreater controller 608 may indicate adjustment of hydrotreater severity to achieve maximum aromatic saturation of hydrotreater feed against hydrotreater operation constraints. Such an output may comprise a vector or other list of values indicative of equipment and / or device parameter settings.

[0173] In an embodiment, one of the hydrotreaters may be a naphtha hydrotreater. The naphtha hydrotreater may be utilized, in conjunction with a distillate hydrotreater, to treat wild naphtha. The treated wild naphtha may be utilized by one or more different refinery equipment, such as, but not limited to, a hydrocracker, a crude unit, and / or a gasoline desulfurization unit. In such embodiments, one trained machine learning model may be trained or configured to maximize the amount of treated naphtha produced in relation to the amount of naphtha used in the refinery equipment. The trained machine learning model may adjust the kerosene or flash target in a crude column to increase or adjust distillate transported to the naphtha or distillate hydrotreater. Further, the trained machine learning model may also determine an amount of heavy coker naphtha to transport to distillate hydrotreaters to thereby produce a minimum amount of wild naphtha via the naphtha hydrotreater.

[0174] FIG. 7A is a schematic diagram of an enhanced catalytic reformer control system 700 to enhance fluid production (for example, such as C3 and heavier hydrocarbon production) at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to a reformer may include a catalytic reformer controller 702. Similar to previously described controllers, the catalytic reformer controller 702 may obtain data associated with the equipment of the reformer unit, such as reactors 712, 716, and 720, furnaces 710, 714, 718, a separator 722, and stabilizer 724. The catalytic reformer controller 702 may also initiate capture of samples of fluids associated with thereformer. The sample collection and analysis assembly 708 may then analyze the samples and produce properties and / or a spectra for each sample. The catalytic reformer controller 702 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 704 and / or predictive controls module 706 to produce an output indicative of adjustment to parameters and / or feed. The catalytic reformer controller 702 may then utilize the output to adjust various parameters and / or feed associated with the reformer via the local enhancement module 704, and, for example, further via a PID controller, DCS controller, PLC controller, or a DCS-PID controller.

[0175] In an example, the catalytic reformer controller 702 may optimize the reformer process based on a number of factors. One factor may include octane-barrels versus reactor temperature. The octane-barrels (in other words, the change in octane above a base value multiplied by the number of product barrels) vs reactor severity (reactor operating temperature) is a concave function with octane-barrels passing through a maximum “optimal” point. Thus, in an embodiment, the model may be trained to maximize or be utilized for maximizing that point on the curve.

[0176] In an embodiment, one of the machine learning models may determine an amount of sweet naphtha to transport to the reformer in relation to an amount of sweet naphtha sent for blending. Such a model may be based on a total amount of sweet naphtha produced (for example, produced by a naphtha hydrotreater and / or hydrocracker) and an amount of sweet naphtha for a blending process in relation to an output of the reformer.

[0177] FIG. 7B is a schematic diagram of an enhanced steam methane reformer control system 750 to enhance fluid production (for example, such as hydrogen production) at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to a reformer may include a steam methane reformer controller 726. Similar to previously described controllers, the steam methane reformer controller 726 may obtain data associated with the equipment of the steam methane reformer unit, such as convection tubes 732, 736, a pre-reactor 734, a furnace 738, an effluent boiler 740, and a methane pre-heater 742. The steam methane reformer controller 726 may also initiate capture of samples of fluids associated with the steam methane reformer. The sample collection and analysis assembly 708 may then analyze the samples and produce properties and / or a spectra for each sample. The steam methane reformer controller 726 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 728 and / or predictive controls module 730 to produce an output indicative of adjustment to parameters and / or feed. The steam methane reformer controller726 may then utilize the output to adjust various parameters and / or feed associated with the reformer via the local enhancement module 728, and, for example, further via a PID controller, DCS controller, PLC controller, or a DCS-PID controller. In an example, the steam methane reformer controller 726 may optimize the reformer process based on a number of factors, for example, the hydrogen output may be maximized.

[0178] FIG. 8 is a schematic diagram of an enhanced alkylation control system 800 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to alkylation may include an alkylation controller 802. Similar to previously described controllers, the alkylation controller 802 may obtain data associated with the equipment of the alkylation unit. The alkylation controller 802 may also initiate capture of samples of fluids associated with the alkylation unit, including the alkylation reactor 810, the acid settler 812, the caustic scrubber 814, or the deisobutanizer 816. The sample collection and analysis assembly 808 may then analyze the samples and produce properties and / or a spectra for each sample. The alkylation controller 802 may apply the data, properties, and / or spectra to one or more machine learning model of the local enhancement module 804 and / or the predictive controls module 806 to produce an output indicative of adjustment to parameters and / or feed. The alkylation controller 802 may then utilize the output to adjust various parameters and / or feed associated with the alkylation unit via the local enhancement module 804.

[0179] In embodiments, the octane-barrels (in other words, the change in octane above a base value multiplied by the number of product barrels) versus iso-butane to olefin feed ratio is a concave function with octane-barrels passing through a maximum “optimal” point. The alkylate octane will decrease as the iso-butane to olefin ratio is decreased. An optimal maximum point in terms of octane-barrels in the alkylate will be reached (e.g., achieved) as olefin feed is increased (and, in embodiments, the iso-butane to olefin ratio is decreased) from a minimum feed to a maximum feed. Thus, in an embodiment, the model may be trained to maximize or be utilized for maximizing that point on the curve.

[0180] One trained machine learning model may be based on the non-linear relationship of olefin feed to acid strength and another may be based on the non-linear relationship of fresh acid to acid strength. The alkylation controller 802 may, based on the trained machine learning model of acid purity, control key parameters in the acid regenerator or acid rerun column and minimize acid consumption. In embodiments, controlling acid strength in the alkylation unit prevents polymerization which, if occurring, may result in a unit shutdown and lost economic opportunity. The alkylation controller 802 may, based on the trainedmachine learning model, also be used to achieve a higher alkylate octane in a product. The relationship between acid strength and alkylate octane is nonlinear. Thus, the controller will be able to determine the acid strength that maximizes alkylate octane and control at that acid strength. Running at a lower acid strength operates the unit closer to acid runaway where polymerization could occur. Thus, the alkylation controller 802 may, based on the trained machine learning models therein, enable operation of an alkylation unit at a lower acid strength that minimizes acid consumption, while preventing polymerization and unit shutdown.

[0181] FIG. 9 is a schematic diagram of an enhanced isomerization control system 900 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to isomerization may include an isomerization controller 902. Similar to previously described controllers, the isomerization controller 902 may obtain data associated with the equipment of the isomerization unit. The isomerization controller 902 may also initiate capture of samples of fluids associated with the isomerization unit from the deisobutanizer 912, the debutanizer 916, the stripper 920, the isomerization reactor 922, the feed heater 924, the stabilizer 926, or the heat exchangers 914, 918. The sample collection and analysis assembly 908 may then analyze the samples and produce properties and / or a spectra for each sample. The isomerization controller 902 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 904 and / or predictive controls module 906 to produce an output indicative of adjustment to parameters and / or feed. The isomerization controller 902 may then utilize the output to adjust various parameters and / or feed associated with the isomerization unit via the local enhancement module 906.

[0182] For an isomerization process, the product distribution will shift in each of the reactors depending on the reactor operating temperature due to the chemical reaction equilibrium that is satisfied for the reversible reaction. The product distribution determined by reactor operating temperature will determine the overall octane-barrels. The optimal reactor temperature(s) can be determined to produce a product with maximum octane- barrels. Thus, at least one machine learning model of an isomerization process may maximize a point in octane-barrels (in other words, the change in octane above a base value multiplied by the number of product barrels) versus reactor temperature, which is a concave function with octane-barrels passing through a maximum “optimal” point. Thus, in an embodiment, the model may be trained to maximize or be utilized for maximizing that point on the curve.

[0183] FIG. 10 is a schematic diagram of an enhanced coker control system 1000 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to a coker unit may include a coker controller 1002, along with various equipment and devices, such as one or more coke drums 1016, 1018, a boiler or heater 1012, valves 1014, 1020 and / or the fractionation or distillation column 1010. Similar to previously described controllers, the coker controller 1002 may obtain data associated with that equipment and devices. The coker controller 1002 may also initiate capture of samples of fluids associated with the coker unit. The sample collection and analysis assembly 1008 may then analyze the samples and produce properties and / or a spectra for each sample. The coker controller 1002 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1004 and / or predictive controls module 1006 to produce an output indicative of adjustment to parameters and / or feed. At least one of the machine learning models may be trained based on the relation between product yield versus heater outlet temperature. Such a model may determine parameters that maximizes yield at the lowest potential heater temperature. In another embodiment, such a model may optimize heater outlet temperature to give the product yield that maximizes profit. The coker controller 1002 may then utilize the output to adjust various parameters and / or feed associated with the coker unit via the local enhancement module 1006.

[0184] A machine learning model may manage the coker unit by adjusting a coker heater outlet temperature against process constraints throughout the course of a coke drum cycle to produce a product yield from the coker. The machine learning model may balance the cost of spalling the heater with the improved (e.g., increased) product yield from increased heater outlet temperature throughout the operation of the coke drum cycle. The machine learning model may also control a charge of feedstocks for the coke drum cycle based on feed quality. The machine learning model may analyze the sensor and sample data of the feedstock to predict the coker heater outlet temperature and the charge of feedstocks for the coke drum cycle. Alternatively, the machine learning model may forecast feed quality based on sensor and sample data of the products of the coker.

[0185] FIG. 11 is a schematic diagram of an enhanced aromatics recovery control system 1100 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to an aromatics recovery unit may include an aromatics recovery controller 1102, a heat exchanger 1110, an extractive distillation column 1112, and a solvent recovery column 1114. Similar to previouslydescribed controllers, the aromatics recovery controller 1102 may obtain data associated with the equipment of the aromatics recovery unit. The aromatics recovery controller 1102 may also initiate capture of samples of fluids associated with the aromatics recovery unit. The sample collection and analysis assembly 1108 may then analyze the samples and produce properties and / or a spectra for each sample. The aromatics recovery controller 1102 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1104 and / or predictive controls module 1106 to produce an output indicative of adjustment to parameters and / or feed. The aromatics recovery controller 1102 may then utilize the output to adjust various parameters and / or feed associated with the aromatics recovery unit via the local enhancement module 1106.

[0186] Solvent loading, in an aromatics recovery unit, may determine how much aromatics can be absorbed in the solvent. Solvent loading may also be affected by solvent quality, feed quality, and tray fouling. Sulfolane solvent may include an affinity for smaller molecules over larger molecules (for example, C5>C6>C7>C8>C9). Further, in some embodiments, a feed composition analyzer may not be available. As such, the trained machine learning model of the aromatics recovery controller 1102 may predict solvent quality and feed composition. The aromatics controller may determine the maximum feed target for the aromatics recovery unit that can meet product quality constraints.

[0187] FIG. 12 is a schematic diagram of an enhanced sulfur recovery control system 1200 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to a sulfur recovery unit 1201 may include a sulfur controller 1202, a furnace 1210, one or more condensers 1212, 1218, 1224, and 1230, one or more heat exchangers 1214, 1220, and 1226, a one or more reactors 1216, 1222, and 1228, and a sulfur pit 1232 or other sulfur storage area or tank. Similar to previously described controllers, the sulfur controller 1202 may obtain data associated with the equipment of the sulfur recovery unit 1201. The sulfur controller 1202 may also initiate capture of samples of fluids associated with the sulfur recovery unit 1201. The sample collection and analysis assembly 1208 may then analyze the samples and produce properties and / or a spectra for each sample. The sulfur controller 1202 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1204 and / or predictive controls module 1206 to produce an output indicative of adjustment to parameters and / or feed. The sulfur controller 1202 may then utilize the output to adjust various parameters and / or feed associated with the sulfur recovery unit 1201 via the local enhancement module 1206.

[0188] An external combustion chamber (ECC) or furnace 1210 in the sulfur recovery unit 1201 converts EES to elemental sulfur through a Claus or modified Claus process. Equipment within the sulfur recovery unit 1201 may receive amine acid gas and ammonia acid gas as feeds which contain EES. The sulfur controller 1202 may, based on trained machine learning models stored therein, may manipulate air flow, oxygen flow, amine acid gas flow, and amine acid gas to maximize EES conversion by targeting an excess SO2 value. The sulfur controller 1202 may also target an ideal reaction temperature and consider constraints for ECC pressure, as well as other safety limits

[0189] Further, the sulfur controller 1202 may, based on trained machine learning models stored therein, coordinate amine acid gas and ammonia gas feeds to a plurality of sulfur recover units with ECC. The sulfur controller 1202 may distribute feeds among the sulfur recover units to target overall maximum overall amine acid gas and ammonia gas conversion in the sulfur recovery units. Thus, the SO2 target may be met for all reactors while safety constraints remain satisfied.

[0190] An additional controller (such as a refinery controller or supervisory controller) may further modify process units upstream to the sulfur recovery unit(s) to adjust operation parameters (such as feed, feed composition, or reactor temperature) in the manner that minimizes economic loss if the sulfur recovery unit(s) are constrained and operating at their capacity. Thus, enabling an automated sulfur shedding plan for a refinery.

[0191] In some applications, a machine learning model may access or receive feedstock data indicative of a composition of a hydrogen sulfide feed to be processed by a sulfur recovery unit and combustion feed data indicative of a composition of a sulfur dioxide product of a reaction furnace 1210 of the sulfur recovery unit 1201. The machine learning model may also access or receive data reaction furnace operational data indicative of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, and a pressure of the reaction furnace and reactor operational data indicative of a feed rate of hydrogen sulfide feed into one or more reactors of the sulfur recovery unit, a feed rate of sulfur dioxide feed into one or more reactors, a temperature of one or more reactors, and a pressure of one or more reactors. Further, the machine learning model may access or receive product data indicative of a composition of a product of one or more reactors of the sulfur recovery unit and tail gas data indicative of a composition of tail gas from the sulfur recovery unit. The machine learning model may be trained with historical data including feed rates of hydrogen sulfide feed into the reaction furnace, temperatures of the reaction furnace, pressures of the reaction furnace, feed rates of hydrogen sulfidefeed into the reactor, feed rates of sulfur dioxide feed into the reactor, temperatures of the reactor, and pressures of the reactor.

[0192] With some or all of this data, the machine learning model may generate an adjustment to one or more of a feed rate of hydrogen sulfide feed into the reaction furnace 1210, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor to increase the efficiency of the sulfur recovery unit 1201 or to reduce the an imbalance between hydrogen sulfide and sulfur dioxide in one or more reactors 1216, 1222, 1228.

[0193] The machine learning model may publish the adjustment to a user for review and approval or for informational purposes only. The machine learning model may receive approval from the user to implement the adjustment or the user may implement the adjustment. The user may also input instructions modifying the adjustment or rejecting the adjustment. In some applications, the machine learning model may have authority to implement some adjustments without user approval and may automatically implement the adjustment to the one or more of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor based on one or more of the tail gas data or the product data.

[0194] The machine learning model may generate a predicted feed rate of one or more sulfur dioxide feed or hydrogen sulfide into a later reactor based on one or more of the tail gas data, the product data, or the second reactor product data to balance the reaction of sulfur dioxide feed with hydrogen sulfide in the second reactor. The machine learning model may wait to receive approval from a user to feed sulfur dioxide or hydrogen sulfide into the later reactor or may implement the changes to efficiently balance the reactions within the reactors of the sulfur recovery unit.

[0195] FIG. 13 is a schematic diagram of a Solvent Deasphalting Unit (SDA) control system 1300 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to the SDA may include a SDA controller 1302, a furnace orboiler 1316, one or more heat exchangers 1310, 1314, 1324, 1330, 1340, 1342, and 1346, a deasphalting tower 1312, an asphalt flash drum 1318, an asphalt stripper 1320, a deasphalted oil stripper 1326, a jet condenser 1332, a compressor 1334, a vaporizer 1336, a solvent vaporizer 1338, and a propane work drum1344. Similar to previously described controllers, the SDA controller 1302 may obtain data associated with the equipment of the SDA unit. The SDA controller 1302 may also initiate capture of samples of fluids associated with the SDA unit. The sample collection and analysis assembly 1308 may then analyze the samples and produce properties and / or a spectra for each sample. The SDA controller 1302 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1304 and / or predictive controls module 1306 to produce an output indicative of adjustment to parameters and / or feed. The SDA controller 1302 may then utilize the output to adjust various parameters and / or feed associated with the SDA unit via the local enhancement module 1306. The SDA controller 1302 may maximize gas oil from resid by setting parameters and inferring resid compositions from upstream equipment (for example, from an upstream controller, a refinery controller, and / or a supervisory controller). The SDA controller 1302 may also coordinate resid from other equipment, such as from a crude tower, a vacuum tower, and / or from a third party. The SDA controller 1302 may adjust DAO lift targets and / or DAO properties for further downstream operations.

[0196] FIG. 14 is a schematic diagram of an enhanced supercritical extraction solvent deasphalting unit control system 1400 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to a supercritical extraction solvent deasphalting unit may include a supercritical extraction solvent deasphalting unit controller, simply referred to as SDA controller 1402, a mixer 1410 or blender, one or more separators 1412, 1416, 1420, and / or one or more strippers 1414, 1418, 1422. Similar to previously described controllers, the SDA controller 1402 may obtain data associated with the equipment of the supercritical extraction solvent deasphalting unit. The SDA controller 1402 may also initiate capture of samples of fluids associated with the supercritical solvent deasphalting unit. The sample collection and analysis assembly 1408 may then analyze the samples and produce properties and / or a spectra for each sample. The SDA controller 1402 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1404 and / or predictive controls module 1406 to produce an output indicative of adjustment to parameters and / or feed. The SDA controller 1402 may then utilize the output to adjust various parameters and / or feed associated with the SDA unit via the local enhancement module 1406. The SDA controller 1402 may maximize gas oil from resid by setting parameters and inferring resid compositions from upstream equipment (for example, from an upstream controller, a refinery controller, and / or a supervisory controller). The SDAcontroller 1402 may also coordinate resid from other equipment, such as from a crude tower, a vacuum tower, and / or from a third party. The SDA controller 1402 may adjust DAO lift targets and / or DAO properties for further downstream operations.

[0197] FIG. 15 is a schematic diagram of an IMO fuel blending control system 1500 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to an IMO unit may include an IMO controller 1502, a blend tank 1508, a FCC unit 1512, slurry tanks 1514, 1518, and 1522, a crude tower 1528, ATM resid tanks 1530, 1534, 1538, a vacuum tower 1544, VGO tanks 1546, 1550, 1554, VTB tanks 1560, 1564, 1568, pumps 1510, 1526, 1542, 1558, and valves 1516, 1520, 1524, 1532, 1536, 1540, 1548, 1552, 1556, 1562, 1566, 1570. Similar to previously described controllers, the IMO controller 1502 may obtain data associated with the equipment of the sulfur recovery unit. The IMO controller 1502 may also initiate capture of samples of fluids associated with the IMO unit. The sample collection and analysis assembly (not illustrated) may then analyze the samples and produce properties and / or a spectra for each sample. The IMO controller 1502 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1504 and / or predictive controls module 1506 to produce an output indicative of adjustment to parameters and / or feed. The IMO controller 1502 may then utilize the output to adjust various parameters and / or feed associated with the IMO unit via the local enhancement module 1504. In embodiments, the IMO controller 1502 may, via the trained machine leaning model, minimize the amount of sulfur in a final fuel or, in other words, may produce a low-sulfur or ultra-low sulfur diesel fuel.

[0198] FIG. 16 is a schematic diagram of an enhanced propylene splitter control system 1600 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to propylene distillation may include a splitter controller 1602. Similar to previously described controllers, the splitter controller 1602 may obtain data associated with the equipment of the propylene splitter 1601, such as from a feed treater 1612, a splitter 1614, a reboiler 1618, a cooler 1624, a cooler 1630, a knockout drum 1632, and a compressor 1634. The feed treater 1612 may include a compressor to pressurize the feed 1610, a feed heater to heat the feed 1610, a cooling unit to cool the feed 1610, and / or a process to remove contaminants, such as amine treating or an absorber to selectively obtain hydrocarbons for the feed 1610.

[0199] Once prepared for processing, the feed 1610 is fed into splitter 1614 that splits the feed 1610 comprising a mix of propane 1626 and propylene 1638. The feed 1610 may bea refinery grade propylene, which comprises 60% to 70% propylene and about 30% to 40% propane. Lighter propylene rises in the splitter 1614 while heavier propane descends in the splitter 1614. A bottoms stream 1616 from the splitter 1614 may be fed into one or more reboilers 1618 and then fed back into the splitter 1614 to heat the feed 1610 within the splitter 1614. Another bottoms stream 1620 comprising a high percentage of propane is withdrawn from the splitter 1614 for sale as propane 1626.

[0200] An overhead stream 1628 from the splitter 1614 has a high purity of propylene. The overhead stream 1628 may be sent to a knockout drum 1632 to separate liquid from the vapor of the overhead stream 1628 and then to a compressor 1634 or heat pump. The compressor 1634 compresses the overhead stream 1628 and sends the overhead stream 1628 to the cooler 1630 and / or the reboiler 1618. The portion of the overhead stream 1628 sent to the reboiler is kept separate from the bottoms stream 1616 and may be heated to achieve a target temperature. The portion of the overhead stream 1628 passed through the reboiler 1618 may then be passed through a cooler 1624 before drawn off as propylene 1638 for sale as a finished product. The splitter 1614 may be operated to achieve a target purity of polymer grade propylene of 99.5% or more of propylene in the propylene 1638. Alternatively, a target purity may be chemical grade propylene of about 93% to 96% of propylene in the propylene 1638.

[0201] A portion of the overhead stream 1628 after being passed through the cooler 1624 may be merged with another portion of the overhead stream that was cooled in the cooler 1630 as reflux 1636. Reflux 1636 is injected near the top of the splitter 1614. The reflux 1636 cools the upward moving vapor and causes propane in the upward moving stream to cool and move downward within the splitter 1614 to the splitter bottoms. The splitter 1614 may also have cooling provided by a cooling tower (not shown) or other process to assist in maintaining desirable temperatures distributed throughout the splitter 1614.

[0202] The splitter controller 1602 may also initiate capture of samples of fluids associated with the propylene splitter unit. The sample collection and analysis assembly 1608 may then analyze the samples and produce properties and / or a spectra for each sample. Additionally, the sample collection and analysis assembly 1608 may obtain data from one or more sensor packages 1640, 1642, 1644, 1646, 1648, 1650, 1652, 1654, 1656 disposed to measure, analyze, and / or sample the properties or composition of fluids throughout the propylene splitter 1601 and the operational parameters of the equipment and processes of the propylene splitter 1601. The sensor packages 1640, 1642, 1644, 1646, 1648, 1650, 1652, 1654, 1656 may include one or more temperature sensors, pressure sensors, flow ratesensors, and composition sensors, such as spectrometers, gas chromatographs, oxygen analyzers, sulfur analyzers, or propylene analyzers, as well as sampling units. The samples may be analyzed in a lab or by an analyzer and returned to the propylene splitter operation. The data from sensor packages 1640, 1642, 1644, 1646, 1648, 1650, 1652, 1654, 1656 may be provided to the sample collection and analysis assembly 1608, which in turn may provide the data to the splitter controller 1602 or separate a machine learning model.

[0203] The splitter controller 1602 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1604 and / or predictive controls module 1606 to produce an output indicative of adjustment to parameters and / or feed. The splitter controller 1602 may then utilize the output to adjust various parameters and / or feed associated with the propylene splitter unit via the local enhancement module 1604.

[0204] For a propylene distillation operation, the splitter controller 1602 may optimize the propylene splitter to achieve the highest purity product, thus maximizing the final product's value. Such a value may be based on the market value of the final purity of the propylene product. A challenge in controlling the propylene splitter is the different operating parameters that may be adjusted including reflux temperature, feed rate of the reflux, bottoms withdrawal rate, reboiler temperature, reboil feed rate, cooler temperature, cooler feed rates, and pressures within the system. At least one machine learning model of a propylene splitter operation may maximize a feed rate versus product purity constrained by an operational constraint such as tower flood point or reboiler / condenser constraints to achieve that product purity. Thus, in an embodiment, the model may be trained to maximize or be utilized for maximizing that point on a curve.

[0205] A machine learning model may be used to optimize overhead, tray, and bottoms temperatures within the splitter 1614. In addition, the machine learning model may control or recommend settings for feed rate of the feed 1610, a bottoms withdrawal rate, or an overhead propylene product withdrawal rate. The machine learning model may be trained on historical data of the feed data, operational data, and product data of the splitter 1614 to improve operation by generating adjustments to the operational parameters of the propylene splitter or a feed rate of the feed into the propylene splitter based on one or more of the feed data, operational data, or product data. The effect of each adjustment may be predicted by the machine learning model, published to a user, reviewed by the user, and the user may instruct implementation of the adjustment or modify the adjustment. The effects may include changes in utility consumption, changes in operational parameters of the splitterlike pressure, reflux flow, compressor operation, operating within a margin of a constraint, exceeding a constraint, or changes in product purity in the propane and the propylene product streams. The user may approve each adjustment to be implemented at the different systems of the propylene splitter including the feed treater 1612, the splitter 1614, the reboiler 1618, the cooler 1624, the cooler 1630, knockout drum 1632, or compressor 1634. Alternatively, the machine learning model may implement each adjustment.

[0206] In some applications, a change in product purity or a measured operating parameter may be detected. The machine learning model may also generate a prediction of a cause of the change in the operating parameters of the propylene splitter based on one or more of the feed data, operational data, or product data. For example, the feed rate of feed may be reduced in response to product data indicating a reduction in purity of the product. The detected change may be a change in weather proximate the splitter and the machine learning model generates an adjustment based on the change in ambient temperature, snow, or rainstorms on the splitter 1614 to more efficiently operate the splitter 1614.

[0207] The machine learning model may access and receive business data indicative of average or current market pricing for a plurality of purities of propylene as well as market pricing for propane. The machine learning model may generate a target purity or flow for the overhead stream of propylene and the bottom stream of propane based on the business data. The target purity may be used by the machine learning model to generate an adjustment to the operational parameters or feed rate of the feed of the propylene splitter to produce a product achieving the target purity. In some applications, the machine learning model may determine that the product exceeds the target purity and then generate a second adjustment to reduce product purity toward the target purity. In some applications, the product data may indicate propylene content in a bottoms stream from the propylene splitter. The adjustment may be made to achieve a decrease in propylene in the bottoms stream from the propylene splitter.

[0208] The business data may also be used to generate a predicted maximum market value of the product based on a production rate of the product and the target purity and use the prediction to modify the operating parameters of the propylene splitter 1601. In some applications, the machine learning model may be programmed and / or trained to increase a potential profit from operation of the propylene splitter based upon the business data. The machine learning model may also be trained to maximize a feed rate of the feed while producing product that achieves the target purity The machine learning model may also be to increase the feed rate of feed until the target purity is achieved.

[0209] While discussed above as a propylene splitter 1601, the splitter control system 1600 may be used with a naphtha splitter. One trained machine learning model may be trained or configured to optimize operation of the naphtha splitter (such an optimization including adjustments to change the amount and / or purity of C7 and / or C6 produced and the impact of the C7 and / or C6 on downstream refinery equipment).

[0210] In another embodiment, the splitter control system 1600 may be used with a combined C4 splitter and C4 Isomerization in an alkylation unit. In such embodiments, one trained machine learning model may be trained or configured to determine adjusted setpoints of components, devices, or refinery equipment in the splitter to minimize nC4 in an overhead IC4 stream, that IC4 in bottoms C4 is minimized, and that the overhead IC4 streamflow meets demand associated with an alkylation unit.

[0211] FIG. 17 is a schematic diagram of a steam control system 1700 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. Many sections or portions of the refinery may utilize steam. For example, steam may be used in a FCC unit for stripping, while, in another unit, steam may be utilized as a heat source. As such, the sections or portions of a refinery that utilize steam may include a steam controller 1702. Similar to previously described controllers, the steam controller 1702 may obtain data associated with the equipment of the refinery, such as from one or more steam drums 1708, one or more boilers 1710, one or more waste heat sources 1712, one or more heat exchangers 1714, one or more condensers 1716, and one or more refinery equipment 1718 (in particular, refinery equipment 1718 that utilizes steam to some degree). The steam controller 1702 may apply the data and / or properties to one or more machine learning models of the local enhancement module 1704 and / or predictive controls module 1706 to produce an output indicative of adjustment to parameters. The steam controller 1702 may then utilize the output to adjust various parameters associated with refinery equipment that utilizes steam via the local enhancement module 1706.

[0212] The steam controller 1702 may prioritize steam to units or portions of the refinery that are generating high value products and / or products or intermediaries that are utilized to produce high value products. As such, at least one machine learning model for steam management may maximize steam production for one or more different refinery operations, while providing sufficient steam to other refinery operations that utilize steam.

[0213] FIG. 18 is a schematic diagram of hydrogen control system 1800 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. Similar to steam, several refinery operations may utilize hydrogen for various purposes. Further, arefinery may also produce some amount of hydrogen, either as a main product and / or as a by-product. Thus, hydrogen management may occur at the refinery level, rather than at a sub-level. Similar to previously described controllers, the hydrogen controller 1802 may obtain data associated with the equipment that produces hydrogen and / or utilizes hydrogen, such as from a methane reformer or a steam methane reformer 1808, a catalytic reformer 1809, a hydrolysis unit 1810, an external hydrogen source 1812 (such data including an amount of hydrogen available at a selected times), and / or refinery equipment 1814 that utilizes hydrogen. The hydrogen controller 1802 may also initiate capture of samples of fluids associated with the devices and / or equipment that produce and / or utilize hydrogen. The sample collection and analysis assembly (not illustrated) may then analyze the samples and produce properties and / or a spectra for each sample. The hydrogen controller 1802 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1804 and / or predictive controls module 1806 to produce an output indicative of adjustment to parameters and / or feed. The hydrogen controller 1802 may then utilize the output to adjust various parameters and / or feed associated with the hydrogen production units and / or equipment or devices utilizing hydrogen via the local enhancement module 1806.

[0214] The hydrogen controller 1802 may prioritize hydrogen to units or portions of the refinery that are generating high value products and / or products or intermediaries that are utilized to produce high value products, as well as maximize purity of hydrogen, such as via methane reforming and / or hydrolysis. As such, at least one machine learning model for hydrogen management may maximize hydrogen production or acquisition for one or more different refinery operations, while providing sufficient hydrogen to other refinery operations that utilize hydrogen.

[0215] In some applications, a machine learning model may receive hydrogen production data. Hydrogen production data may include feed date indicative of properties of the feed fed into equipment that produces hydrogen, operational data of equipment that produces hydrogen, and hydrogen product data indicative of one or more properties the hydrogen produced by the equipment that produces hydrogen. Hydrogen product equipment may include steam methane reformers, hydrolysis units, and catalytic reformers. The machine learning model may be trained with historical data including one or more of hydrogen production data, operational data of equipment that produces hydrogen, hydrogen product data, and hydrogen consumption data.

[0216] The machine learning model may also receive hydrogen consumption data including the operational data of equipment that consume hydrogen and distribution data indicative of connections between the equipment that produces hydrogen and the equipment that consumes hydrogen. The machine learning model may use this data to adjustment or prioritize the distribution of hydrogen from the equipment that produces hydrogen to the equipment that consumes hydrogen.

[0217] In some applications, the machine learning model may access and receive business data. The business data may be indicative of market values of the products of equipment that consumes hydrogen and the machine learning model may use this business data to prioritize hydrogen distribution based on the business data. The machine learning model may also generate adjustments to the distribution of hydrogen based on nearness of the equipment that consumes hydrogen to the equipment that produces hydrogen. For example, the machine learning model may generate priorities based on a score or scoring matrix that may include nearness or proximity to hydrogen producing equipment and / or a potential profit of the hydrogen consuming equipment to determine the priority of hydrogen consuming equipment. Further, the score may include what the minimum consumption of hydrogen is. For example, two processes whose minimum is less than what is available may have a higher priority because of the profitability of the combined processes when compared to a process that consumes more hydrogen than the two processes.

[0218] In some applications, the machine learning model may generate adjustments or process settings for hydrogen producing equipment to increase hydrogen gas production, or generate adjustments or process settings for hydrogen consuming equipment to reduce overall hydrogen consumption. In another application, the machine learning model may receive product demand from a gasoline, diesel, jet fuel, asphalt, or other blending pool controller so that the machine learning model may prioritize hydrogen delivery to those processes producing the products requested by the gasoline, diesel, jet fuel, asphalt, or other blending pool controller.

[0219] In another application, the machine learning model may generate adjustments to one or more operational parameters of a steam methane reformer to decrease the consumption of steam and increase potential profit of the production of hydrogen by reducing the use of utilities. Further, the machine learning model may optimize the production of hydrogen. In some applications, the machine learning model may receive or generate a prediction of a state of a catalyst of the steam methane reformer and generate an adjustment to one or more operational temperature or pressure of the steam methanereformer based on the prediction of the state of the catalyst of the steam methane reformer. The machine learning model may also generate an adjustment to one or more operational parameters of the catalytic reformer is constrained by operating parameters of the catalytic reformer used to achieve a target property of reformate produced by the catalytic reformer.

[0220] In some applications, the machine learning model may prioritize methane production from steam methane reformers, hydrolysis units, and catalytic reformers, while reducing use of hydrogen from an external hydrogen source. The machine learning model may use business data to prioritize hydrogen from the external source and the catalytic reformer in the event that hydrogen from these sources is less expensive.

[0221] The machine learning model may generate a prediction of a minimum hydrogen consumption for each of the equipment that consumes hydrogen based on the hydrogen consumption. The prediction of the minimum hydrogen consumption for each of the equipment that consumes hydrogen may be used by the machine learning model to constrain or act as a boundary for adjustments to the distribution of hydrogen within the refinery.

[0222] FIG. 19 is a schematic diagram of a feed control system 1900 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. Each refinery operation utilizes a feed stream or feedstock. Such a feed stream or feedstock may, in some examples, be adjusted, to optimize or enhance fluid production of a corresponding refinery operation. Similar to previously described controllers, the feed controller 1902 may obtain data associated with the equipment that produces a feed or intermediary, blends a feed or intermediary, and / or utilizes a feed and / or intermediary, such as from one or more blend tanks 1908, one or more in-line blend pipes 1910, one or more feedstock sources 1912, one or more intermediary sources 1914, one or more sample collection and analysis assemblies 1916, and / or refinery equipment 1918. The feed controller 1902 may also initiate capture of samples of fluids associated with the devices and / or equipment that produce, blend, and / or utilize feed. The sample collection and analysis assembly (not illustrated) may then analyze the samples and produce properties and / or a spectra for each sample. The feed controller 1902 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1904 and / or predictive controls module 1906 to produce an output indicative of adjustment to parameters and / or feed. The feed controller 1902 may then utilize the output to adjust various parameters and / or blends of a feed or intermediary associated with the refinery equipment 1918 via the local enhancement module 1906. The trained machine learning model utilized for the feedcontroller 1902 may be trained to or utilized to predict feed, blend, and / or intermediary properties and / or components that produce a maximum or greater than typical yield for a particular refinery operation.

[0223] A machine learning model trained with historical data including steam production data and operational data of the plurality of units of the refinery that utilize steam may access or receive operational data of a plurality of units of a refinery that utilize steam and generate a prediction of a minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam based on the operational data. This data may be used by the machine learning model to generate an adjustment to a distribution of steam to each of the plurality of units of the refinery that utilize steam based on the generated prediction of a minimum steam consumption for each of the plurality of units of the refinery that utilize steam. The adjustments may take into consideration the nearness of each of the plurality of units of the refinery that utilize steam to a unit that produces steam and give priority to the nearest units. The machine learning model may publish eh adjustment to a user and the user may approve for implementation, modify, or reject the adjustment. In some applications, the machine learning model may have authority to implement the adjustments or certain types of adjustments, such as small changes to pressure or temperature.

[0224] In some applications, the machine learning model may generate adjustments to more than just the steam producing equipment and generate adjustments to one or more operating parameters of a unit that consumes steam to reduce steam consumption and improve overall efficiency of the steam distribution system within the refinery. To do this, the machine learning model may be trained with the historical data of the steam consuming units. Further, the machine learning model may access or receive product data indicative of a property of a product of one of the products of the plurality of units of the refinery that utilize steam and business data indicative of market values of the products of the plurality of units of the refinery that utilize steam. The machine learning model may use the product data and the business data to generate a value of the product of one of the plurality of units of the refinery that utilize steam based on the business data. This value may be used to prioritize steam distribution to the unit based on the value. An adjustment to the distribution of steam may prioritize a unit of the plurality of units of the refinery that utilize steam having a higher value than a unit of the plurality of units of the refinery that utilize steam having a lower value.

[0225] The machine learning model may also generate a potential profit for each of the plurality of units of the refinery that utilize steam. The potential profit may be used to determine adjustments to the distribution of steam to each of the plurality of units of the refinery that utilize steam. The machine learning model may prioritize the distribution of steam to each of the plurality of units of the refinery that utilize steam by the potential profit of each of the plurality of units of the refinery that utilize steam. When steam production is less than the prediction of the minimum steam consumption for each of the plurality of units of the refinery that utilize steam, the adjustment to the distribution of steam to units that consumer steam based on the potential profit of each of the plurality of units of the refinery that utilize steam.

[0226] The machine learning model may use the efficiency in steam delivery to adjust a priority of the plurality of units of the refinery that utilize steam. Additionally, weather data including ambient temperature and solar radiation on the units of the refinery may be used in generating the adjustment to the distribution of steam. The machine learning model may determine that a change in the weather data may cause a change in the operating parameters of a refinery unit or the steam distribution system and generate an adjustment based on the determined change.

[0227] The machine learning model may receive data indicating a change in the operational data of one or more of the plurality of units of the refinery that utilize steam and update the prediction of minimum steam consumption for each of the plurality of units of the refinery that utilize steam to generate another adjustment to the distribution of steam to each of the plurality of units of the refinery that utilize steam.

[0228] The machine learning model may use operational goals embodied in an objective function to drive the steam control system toward specific objectives. For example, the machine learning model may be programmed to reduce energy consumption while meeting the one or more operational goals of each of the plurality of units of the refinery that utilize steam. Operational goals of the steam consuming units may include a target octane number, target octane-barrels, or a target volume swell of the product of the steam consuming unit. The machine learning model may be programmed to reduce energy consumption while meeting the one or more operational goals of each of the plurality of units of the refinery that utilize steam. Further, the machine learning model may be programmed to maximize a potential profit of each of the plurality of units of the refinery that utilize steam.

[0229] In another application, the machine learning model may generate a margin or a tolerance above the minimum steam consumption for each of the plurality of units of therefinery that utilize steam based on the historical data and a confidence interval based on the historical data that actually delivered steam to each of the plurality of units of the refinery that utilize steam will achieve or exceed the minimum steam consumption. The confidence level may be set by a user or generated by a risk analysis of the unit’s processes. The margin may be used by the machine learning model to generate the adjustments to the distribution of steam to each of the plurality of units of the refinery that utilize steam.

[0230] The machine learning model may also determine heat losses throughout the distribution of steam to each of the plurality of units of the refinery that utilize steam and generate the adjustment to the distribution of steam to each of the plurality of units of the refinery that utilize steam based on the determined heat losses. The heat losses may also be based on weather data.

[0231] In determining the distribution of steam within the refinery, the machine learning model may generate an efficiency value for each unit that produces steam and base each adjustment on the efficiency value for each unit that produces steam. In other words, the machine learning model may prioritize steam production for one or more units that produces steam that have a higher efficiency value. Conversely, the machine learning model generate an efficiency value for steam consuming units and may prioritize steam for one or more units that consumes steam with a higher efficiency value.

[0232] FIG. 20 is a schematic diagram of a gasoline pool control system 2000 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. After processing various feeds via one or more different operations or sub-operations, various products from those operations or sub-operations may be combined to produce a selected gasoline or to form a selected gasoline pool. Such a gasoline pool may include a specification, the specification including one or more of an octane number, a research octane number, a motor octane number, a Reid vapor pressure, an amount of benzene, a density, a color, a flash point, an amount and / or type of lubricant, an amount and / or type of detergents, an amount and / or type of anti-rust agents, amount and / or type of anti-icing agents, and / or amount of sulfur or other contaminants, among other properties. To reach (e.g., achieve) the properties specified, a refinery controller and / or a gasoline pool controller 2002, for example may obtain analysis of and / or other data associated with various products within a refinery and select a percentage, the percentage in relation to the whole final gasoline product, of each product for combination or blending. As such, the refinery controller and / or gasoline pool controller 2002 may obtain data from a variety of sources. For example, the gasoline pool controller 2002 may obtain data from an FCC unit2008, a fractionation / distillation column 2010, an alkylation unit 2012, a gasoline desulfurization unit 2014, an isomerization unit 2015, a reformer 2016 or catalytic reformer, and / or an external gasoline source 2017 (for example, the external gasoline source 2017 may include a source that a refinery purchases and / or obtains gasoline from). Further, the gasoline pool controller 2002 may obtain data from the sample collection and analysis assembly 2018 and / or other refinery equipment 2020. In other embodiments, the gasoline pool controller 2002 may connect to a refinery controller and / or other controllers or sub-operation controllers within the refinery to obtain data related to that operation or sub-operation. Further, the gasoline pool controller 2002 may obtain data and / or properties from the collection and analysis assembly 2018 related to other fluids produced within the refinery. Once such data and / or properties has been collected, the gasoline pool controller may apply the data to one or more trained machine learning models stored in the local enhancement module 2004 and / or the predictive controls module 2006 to produce amounts of each varying fluid and / or properties associated with a fluid that causes production of the fluid to reach (e.g., achieve) selected properties. In an embodiment, the local enhancement module 2004 may apply the output of a plurality of trained machine learning models each stored in one or more of a plurality of predictive controls modules 2006 to a trained machine learning model of the local enhancement module 2004.

[0233] Once a prediction is determined by the gasoline pool controller 2002, the gasoline pool controller 2002 may adjust one or more devices within the refinery to cause those one or more devices to provide fluids for and / or adjust parameters to produce the selected or target gasoline. The selected components of the selected or targeted gasoline may then be blended.

[0234] In an embodiment, the trained machine learning models within the gasoline pool controller 2002 may be trained to or utilized for predicting parameters and / or properties for one or more of the units described in relation to the gasoline pool controller 2002. For example, if a specific property of a target gasoline pool is known or input into the trained machine learning model, along with other related data, then the gasoline pool controller 2002 may determine, based on application of that specific property and / or data to a trained machine learning model, process parameters and / or feed and / or intermediary properties for that particular process. In an embodiment, another controller specific for that operation may utilize the output to drive that operation to produce a fluid that accurately exhibits that specific parameter. In further embodiments, the gasoline pool controller 2002 may determine such parameters and / or properties for a plurality of other operations. In otherembodiments, the gasoline pool controller 2002 may work in conjunction with other controllers to produce selected fluids. Thus, the gasoline pool controller 2002, in embodiments, may coordinate targeted outputs, by adjusting or causing adjustment of one or more refinery operations or sub-operations and / or by blending selected components from the refinery operations or sub-operations, from a plurality of operations to meet a selected gasoline pool specification.

[0235] In another embodiment, the gasoline pool controller 2002 may select a source of gasoline based on an output from the trained machine learning models. The trained machine learning models may output a blend percentage of gasoline from the sources to reach (e.g., achieve) a target octane and / or volatility limit. In such embodiments, the volatility limit may comprise a RVP or vapor liquid ratio. In another embodiment, such a blend percentage of gasoline may comprise a higher percentage of gasoline from the external gasoline source 2017 and smaller percentages of gasoline and / or other fluids from other sources to reach (e.g., achieve) the octane and / or volatility limit.

[0236] FIG. 21 is a schematic diagram of a diesel pool control system 2100 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. After processing various feeds via one or more different operations or sub-operations, various products from those operations or sub-operations may be combined to produce a selected diesel fuel or to form a selected diesel pool. Such a diesel pool may include a specification, the specification including one or more of a cetane number, a density, a color, a flash point, a pour point, an amount and / or type of lubricant, an amount and / or type of detergents, an amount and / or type of anti-rust agents, an amount and / or type of anti-icing agents, and / or an amount of sulfur or other contaminants, among other properties. To reach (e.g., achieve) the properties specified, a refinery controller and / or a diesel pool controller 2102, for example may obtain analysis of and / or other data associated with various products within a refinery and select a percentage, the percentage in relation to the whole final diesel product, of each product for combination or blending. As such, the refinery controller and / or diesel pool controller 2102 may obtain data from a variety of sources. For example, the diesel pool controller 2102 may obtain data from an FCC unit 2108, a fractionation / distillation column 2110, a hydrocracker 2112, a hydrotreater 2114, a hydrodeoxygenation (HDO) unit 2115, and / or a coker unit 2116. Further, the diesel pool controller 2102 may obtain data from the sample collection and analysis assembly 2118 and / or other refinery equipment 2120. In other embodiments, the diesel pool controller 2102 may connect to a refinery controller and / or other controllers or sub-operationcontrollers within the refinery to obtain data related to that operation or sub-operation. Further, the diesel pool controller 2102 may obtain data and / or properties from the collection and analysis assembly 2118 related to other fluids produced within the refinery. Once such data and / or properties has been collected, the diesel pool controller 2102 may apply the data to one or more trained machine learning models stored in the local enhancement module 2104 and / or the predictive controls module 2106 to produce amounts of each varying fluid and / or properties associated with a fluid that causes production of the fluid to reach (e.g., achieve) selected properties. In an embodiment, the local enhancement module 2104 may apply the output of a plurality of trained machine learning models each stored in one or more of a plurality of predictive controls modules 2106 to a trained machine learning model of the local enhancement module 2104.

[0237] Once a prediction is determined by the diesel pool controller 2102, the diesel pool controller 2102 may adjust one or more devices (for example, refinery operation control devices) within the refinery to cause those one or more devices to provide fluids for and / or adjust parameters to produce the selected or target diesel. The selected components of the selected or targeted diesel may then be blended.

[0238] In an embodiment, the trained machine learning models within the diesel pool controller 2102 may be trained to or be utilized for predicting parameters and / or properties for one or more of the units described in relation to the diesel pool controller 2102. For example, if a specific property of a diesel pool controller 2102 is known or input into the trained machine learning model, along with other related data, then the diesel pool controller 2102 may determine, based on application of that specific property and / or data to the trained machine learning model, process parameters and / or feed and / or intermediary properties for that particular process. In an embodiment, another controller specific for that operation may utilize the output to drive that operation to produce a fluid that accurately exhibits that specific parameter. In further embodiments, the diesel pool controller 2102 may determine such parameters and / or properties for a plurality of other operations. In other embodiments, the diesel pool controller 2102 may work in conjunction with other controllers to produce selected fluids. Thus, the diesel pool controller 2102, in embodiments, may coordinate targeted outputs, by adjusting or causing adjustment of one or more refinery operations or sub-operations and / or by blending selected components from the refinery operations or sub-operations, from a plurality of operations to meet a selected diesel pool specification

[0239] FIG. 22 is a schematic diagram of an absorber control system 2200 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to an absorber unit 2201 may include an absorber controller 2202. Similar to previously described controllers, the absorber controller 2202 may obtain data associated with the refinery equipment of the absorber unit 2201, such as from a feed cooler 2212, a cooler 2213, an absorber column 2214, a stripper 2222, one or more heat exchangers (not shown), and / or one or more distillation units 2226. In some applications, the hydrocarbon feedstock is a wet gas from a compressor which comprises heavy hydrocarbons along with fuel gas. In this example, heavy hydrocarbons are recovered from wet gas. There may be range of heavier hydrocarbons to be recovered but the target material may be the lightest of the heavy hydrocarbons of interest. Lean oil 2216 absorbs heavier hydrocarbons as well as the target material from the feedstock 2210.

[0240] The absorber controller 2202 may also initiate capture of samples of fluids associated with the absorber operation. The sample collection and analysis assembly 2208 may then analyze the samples and produce properties and / or a spectra for each sample. The absorber controller 2202 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 2204 and / or predictive controls module 2206 to produce an output indicative of adjustment to parameters and / or feed. The absorber controller 2202 may then utilize the output to adjust various parameters and / or feed associated with the absorber operation via the local enhancement module 2206.

[0241] For an absorber operation, the absorber controller 2202 may optimize the absorber operation, by manipulating lean oil 2216 properties, as well as operating conditions or parameters, to achieve a minimal amount of targeted material in the overhead fuel gas 2220. Thus, in an embodiment, one or more trained machine learning models of the absorber controller 2202 may be trained to increase absorption rates of a targeted material of the feedstock 2210 in lean oil 2216 and / or other operating conditions or parameters associated with the absorber unit 2201.

[0242] The feedstock 2210 may be passed through the feed cooler 2212 to adjust the temperature of the feedstock 2210 in preparation to be fed into the absorber column 2214. Lean oil 2216 or other solvent may be passed through a cooler 2213 to adjust the temperature of the lean oil 2216 in preparation to be fed in near the top of the absorber column 2214. The feedstock 2210 is fed into the bottom of the absorber column 2214 and travels up through the descending lean oil 2216. As the feedstock 2210 travels up through the absorber column 2214 and the descending lean oil 2216, the targeted material isdissolved into the lean oil 2216, which exits the bottoms of the absorber column 2214 as rich oil 2218. The fuel gas 2220 exits overhead from the absorber column 2214.

[0243] The rich oil 2218 is then fed into the stripper 2222 of the absorber unit 2201. Within the stripper 2222, gas (lighter hydrocarbons) and vapor 2223 (heavier hydrocarbons) may separate any remaining gases from the rich oil 2218. The remaining gases may be circulated back to the absorber column 2214 with the targeted material being recaptured in the lean oil 2216 and any untargeted gases being allowed to rise up through the absorber column and exit as fuel gas 2220. The rich oil 2218 exits the stripper 2222 and is sent to one or more distillation units 2226 to separate the rich oil 2218 into two or more products 2228, 2230 with the targeted material being a component of the first product 2228 and the lean oil being a component of the second product 2230.

[0244] In one application, the targeted material 2224 may be propylene. In another application, the targeted material 2224 may be propane and butane from an FCC or hydrocracked gas. In another application, benzene, toluene, and xylene may be the targeted material 2224. The absorber unit 2201 uses solubility of the targeted material to separate the targeted material from the feedstock 2210 into a component of one of the products 2228, 2230. In some applications, the lean oil 2216 may instead be amine, water, or stabilized naphtha that may be used as a solvent to dissolve the targeted material 2224.

[0245] Sensor packages 2232, 2234, 2236, 2238, 2240, 2242 may be disposed to measure, analyze or sample the feedstock 2210, the targeted material 2224, the lean oil 2216, the rich oil 2218, the first product 2228, or the second product 2230 within the absorber unit 2201. Sensor packages 2232, 2234, 2236, 2238, 2240, 2242 may include one or more temperature sensors, pressure sensors, flow rate sensors, and composition sensors, such as spectrometers, gas chromatographs, oxygen analyzers, sulfur analyzers, and octane analyzers, as well as sampling units. The samples may be analyzed in a lab or by an analyzer and returned to the absorber operation. The data from sensor packages 2232, 2234, 2236, 2238, 2240, 2242 may be provided to the sample collection and analysis assembly 2208, which in turn may provide the data to the absorber controller 2202 or separate a machine learning model.

[0246] A machine learning model may be trained on historical data including feedstock data, operational data, and product data of the absorber. The machine learning model may access or receive one or more of (a) operational data of an absorber indicative of operational parameters of the absorber and including sensor data from one or more sensors disposed to measure an operational parameter of the absorber, (b) product data indicative of a propertyor component of a product from a process of the absorber or (c) feedstock data of a hydrocarbon feedstock being fed into the absorber. The machine learning model may use this data to determine a change in the one or more of the operational data, the product data, or the feedstock data and then generate a prediction of an effect of the change on the operation of the absorber. Based on the prediction, the machine learning model may generate an adjustment to an operating parameter of the absorber. In some applications, the prediction may be of lean oil quality or of lean oil loading based on the operating data or increase absorber pressure to an operational constraint. The machine learning model may also predict a risk of exceeding an operational constraint that may result in a flooding condition. The machine learning model may also generate recommendations or adjustments to operational parameters to avoid exceeding the operational constraint, such as an adjustment of temperatures, pressures, or feed rates within the absorber. The machine learning model may generate adjustments to increase lean oil loading efficiency.

[0247] The machine learning model may publish the adjustment to a user for approval for implementation, modification, or rejection. In some applications, the machine learning model may implement small adjustments or larger adjustments to prevent shut down of the absorber. In some applications, the user may input instructions to implement an adjustment to the operating parameter of the absorber. The adjustment may be an adjustment to a feed rate of the hydrocarbon feedstock or an adjustment to achieve an increase in lean oil loading efficiency. The adjustment may be made to move the process closer to achieving vapor liquid equilibrium within an absorber column. To achieve vapor liquid equilibrium, the machine learning model may adjust the temperature or pressure of the absorber column or the stripper of the absorber, the feed rate or temperature of the feedstock, or a feed rate or temperature of the lean oil.

[0248] In some applications, the machine learning model may generate a plurality of simulations of the operation of the absorber based on the change in the operational data with each simulation having a different adjustment to an operational parameter of the absorber. The machine learning model may then select a simulation of the plurality of simulations that achieves a target absorption rate while not exceeding an operational constraint of the absorber. A challenge in operating the absorber unit 2201 are delays in identifying the effects of changes in the system. Once a simulation is selected, the machine learning model may generate an adjustment to the system based on the selected simulation in advance of actual effects being detected.

[0249] The machine learning model may generate a prediction of process constraints for each process of the absorber. The machine learning model may generate or update a prediction of process constraints on a regular periodic basis. For example, the machine learning model may generate an updated prediction of process constraints based on predicted fouling of equipment each 12 hours or on a daily basis. Alternatively, the machine learning model may generate an updated prediction each time a change in the process is detected by the machine learning model. The change may be detected based on a comparison of historical data with current operating parameters. The change may also be determined as a prediction based on historical data. If based on historical data, the prediction may be published to a user as an email, message, or a message displayed on screen. The user may approve the prediction and input instructions to direct the machine learning model to use the predicted process constraints in operating the absorber. An example of a change affecting process constraints may include a prediction of fouling within a process of the absorber. The predicted fouling may indicate a change in upper limits of flow through the fouled equipment.

[0250] To add additional confidence that a constraint will not be exceeded, the machine learning model may generate a margin away from the process constraint based on the historical data and a confidence interval that the process of the absorber will not exceed the process constraint during operation of the absorber. The margin will be added to the predicted process constraint when generating an adjustment to prevent a process constraint from being exceeded. The machine learning model may generate an operating target for a process of the absorber based on the process constraint. As adjustments are generated, each adjustment moves operation of the process to the operating target. In some applications, the machine learning model may generate a prediction of a maximum feed rate of feedstock into the absorber, and then generate a target feed rate of feedstock into the absorber is based on the predicted maximum feed rate of feedstock.

[0251] FIG. 23 is a schematic diagram of a hydrocracker control system 2300 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. As noted, specific sections or portions of a refinery may include a sub-controller to enhance that particular operation. As illustrated in FIG. 5, a hydrocracking operation may be enhanced via a hydrocracker controller 2302 and corresponding machine learning models (for example, hydrocracker specific machine learning models utilized in the local enhancement module 2304 and / or the predictive controls module 2306). The hydrocracker controller 2302 may connect to sources of and control various parts of the equipment, suchas feed heater 2312, reactors 2314, 2316, heat exchangers 2310, 2320, a separator 2318, and / or a stripper 2322. Further, the hydrocracker controller 2302 may obtain data related to each input material or feed, as well as the temperature and / or pressure within the equipment.

[0252] Prior to generating adjusted parameters for operation of the hydrocracker operation, the hydrocracker controller 2302 may initiate collection of samples of one or more of the materials or feeds utilized in the hydrocracking operations, via the sample collection and analysis assembly 2308. Once the sample collection and analysis assembly 2308 obtains one or more samples, the sample collection and analysis assembly 2308 may analyze those samples to produce properties and / or a spectra indicative of various properties. Once the properties and / or spectra are generated, the sample collection and analysis assembly 2308 may transmit the properties and / or spectra to the hydrocracker controller 2302. Upon reception of the properties and / or spectra, the hydrocracker controller 2302 may apply the properties and / or spectra and other data, along with target product concentration and / or properties, to a plurality of machine learning models within the predictive controls module 2306 (or, in other embodiments, a plurality of predictive controls modules may be included in the hydrocracker controller 2302 and each may include a machine learning model). The output of each of the machine learning models in the predictive controls module 2306 may then be utilized by the local enhancement module 2304 to determine (for example, as a vector) new parameters and / or feed blend or concentration to supply to the equipment utilized in the hydrocracking operation. In other embodiments, the output may indicate that a new or fresh catalyst should be utilized. The hydrocracker controller 2302 may then adjust the parameters of and / or feeds and / or materials for the equipment associated with the hydrocracking operation.

[0253] In an embodiment, a machine learning model may, when trained, determine adjustments to a hydrocracker conversion to give FCC feed composition that provides optimal FCC yield against FCC constraints. In yet another embodiment, another machine learning model may, when trained, determine adjustments to hydrotreater severity to maximize aromatic saturation to hydrotreater constraints.

[0254] In another embodiment, the hydrocracker controller 2302 may first cause sampling of various fluids used and / or produced in the hydrocracker operation. For example, as hydrocracking occurs (for example, as a continuous and / or ongoing operation) various fluids and / or materials may be utilized and / or produced therein. Prior to application of data to the any of the machine learning models described herein, the hydrocracker controller2302 may initiate capture of one or more of those fluids via the sample collection and analysis assembly 2308. Once analyzed, the hydrocracker controller 2302 may predict properties of the corresponding fluids that may achieve an accurate output of a target product, as well as various parameters as described herein. In other words, the hydrocracker controller 2302 may determine compositions of a fluid to be utilized. The fluids used may then be adjusted, blended, and / or supplemented to meet those compositions determined by one or more of the machine learning models of the hydrocracker controller 2302. Stated another way, the hydrocracker controller 2302 may control the properties, composition (e.g., content), and / or feed ratios associated with a feedstock or hydrocarbon feedstock and / or an Intermediate fluid or intermediate product.

[0255] FIG. 24 is a schematic diagram of a gasoline desulfurization control system 2400 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. In embodiments, a section of the refinery corresponding to a gasoline desulfurization operation may include a gasoline desulfurization controller 2402. Similar to previously described controllers, the gasoline desulfurization controller 2402 may obtain data associated with the refinery equipment of the absorber operation, such as from a selective hydrogeneration reactor 2410, a splitter 2412, a hydrodesulfurization reactor 2414, a separator 2416, and a second splitter 2418. The gasoline desulfurization controller 2402 may also initiate capture of samples of fluids associated with the gasoline desulfurization operation. The sample collection and analysis assembly 2408 may then analyze the samples and produce properties and / or a spectra for each sample. The gasoline desulfurization controller 2402 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 2404 and / or predictive controls module 2406 to produce an output indicative of adjustment to parameters and / or feed. The gasoline desulfurization controller 2402 may then utilize the output to adjust various parameters and / or feed associated with the gasoline desulfurization operation via the local enhancement module 2404.

[0256] For a gasoline desulfurization operation, the gasoline desulfurization controller 2402 may optimize sulfur removal from gasoline. As a sulfur amount in a targeted product becomes lower, a reactor’s temperature may be increased to achieve the same amount of sulfur removal in the target product. Such behavior occurs due to the remaining sulfur in the product being difficult to treat and remove (in other words, the removing sulfur in a product including larger amounts of sulfur requires less energy than removing sulfur in a product including smaller amounts of sulfur). As such, a linear model may be less effectivefor control when utilized with for a target product sulfur concentration at lower values. Thus, use of a linear model results in less stable control, potential to go off productspecification (in other words, produce an inaccurate target product), and potential to prematurely deactivate catalyst.

[0257] Alternatively, a machine learning model may manage a light naphtha sulfur target and a heavy naphtha sulfur target as part of an overall average sulfur target for the combined streams while also maximizing the overall octane-barrels produced by the combined product of the gasoline desulfurization unit. Further, the machine learning model may manage one or more selective hydrogenation unit reactor variables, including temperature and pressure, and one or more splitter variables to produce the light naphtha product with the highest octane-barrels given a specific light naphtha sulfur target. The machine learning model may manage hydrodesulfurization reactor temperatures and other operating variables to produce a heavy naphtha product with maximum octane-barrels with a specific sulfur target.

[0258] FIG. 25 is a schematic diagram of a hydrodeoxygenation (HDO) control system 2500 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to hydrodeoxygenation may include a HDO controller 2502. A HDO unit may be utilized, in an embodiment, for treatment and / or processing of a renewable feedstock. Typically, renewable feedstock may include oxygen or a greater than typical amount of oxygen. To process such a feedstock, the oxygen is first, or at some point in the process, removed. The HDO unit may process such feedstock to remove that oxygen, enabling conversion of the feedstock to a transportation fuel, such as renewable diesel, renewable naphtha, and / or renewable LPG. Similar to previously described controllers, the HDO controller 2502 may obtain data associated with the equipment of the HDO unit, such as one or more a filter 2510, a surge drum 2512, a pump 2514, a heat exchanger 2516, a furnace 2518, a reactor 2520, a condenser 2522, a separator 2524, and / or a stripper 2526. The HDO controller 2502 may also initiate capture of samples of fluids associated with the propylene splitter unit. The sample collection and analysis assembly 2508 may then analyze the samples and produce properties and / or a spectra for each sample. The HDO controller 2502 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 2504 and / or predictive controls module 2506 to produce an output indicative of adjustment to parameters and / or feed. The HDO controller 2502 may then utilize the output to adjustvarious parameters and / or feed associated with the HDO unit via the local enhancement module 2504.

[0259] For a HDO operation, the HDO controller 2502 may optimize or maximize the renewable fuel production by manipulating a reactor and a heater outlet temperature, quench flows, liquid recycle streams, system pressure, hydrogen to hydrocarbon ration, and / or other operation conditions (such additionally described components also being included, in embodiments, in the HDO unit). The HDO controller may further drive the HDO unit to produce the maximum product yield.

[0260] FIG. 26 is a schematic diagram of a resid destruction control system 2600 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. In embodiments, a section of the refinery corresponding to a resid destruction operation may include a resid destruction controller 2602. Similar to previously described controllers, the resid destruction controller 2602 may obtain data associated with the refinery equipment of the resid destruction operation, such as from a vacuum tower 2610, a crude tower 2612, an external resid source 2614, one or more coker units 2616 A, 2616B, and up to 2616N, a supercritical solvent deasphalting unit (SDA) 2618, an external resid operation facility 2620. The resid destruction controller 2602 may also initiate capture of samples of fluids associated with the resid destruction operation. The sample collection and analysis assembly 2608 may then analyze the samples and produce properties and / or a spectra for each sample. The resid destruction controller 2602 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 2604 and / or predictive controls module 2606 to produce an output indicative of adjustment to parameters and / or feed. The resid destruction controller 2602 may then utilize the output to adjust various parameters and / or feed associated with the resid destruction operation via the local enhancement module 2606.

[0261] For a resid destruction operation, the resid destruction controller 2602 may optimize yield of high value products. For example, the resid destruction controller 2602 may determine amounts of resid flowing to for example, each coker and / or supercritical solvent deasphalting unit and determine what amount at each unit may produce a selected target.

[0262] In an embodiment, each controller illustrated in FIGS. 5-26 may utilize various data points and properties to predict parameters and fluids to reach (e.g., achieve) a target product. Those controllers may each connect to a supervisory controller or refinery controller. In embodiments, the supervisory controller or refinery controller may utilize the output of each machine learning model of each of the controllers. In yet anotherembodiment, each of the controllers may utilize some output from the machine learning model of the supervisory controller or refinery controller. Further, each of the controllers and / or the supervisory controller may adjust a refining operation control device, and thus adjust a process, in real-time, near real-time, and / or continuously.

[0263] FIG. 27 A and FIG. 27B are simplified diagrams of control systems 2700 to enhance to enhance fluid production at refinery, according to an embodiment of the disclosure. As noted, control system 2700 may include an operation controller 2701. Further, the operation controller 2701 may connect to one or more sensors 2716A, 2716B, and up to 2716N, one or more devices 2718 A, 2718B, and up to 2718N (such as flow control devices and / or temperature control devices), one or more equipment 2720A, 2720B, and up to 2720N, one or more analyzers 2722A, 2722B, and up to 2722N, and one or more predictive controls 2714A, 2714B, and up to 2714N. The operation controller 2701 may include memory 2704 and one or more processors 2702. The memory 2704 may store instructions executable by one or more processors 2702. In an example, the memory 2704 may be a non-transitory machine-readable storage medium. As noted, the memory 2704 may store or include instructions executable by the processor 2702.

[0264] As used herein, “signal communication” refers to electric communication such as hardwiring two components together or wireless communication, as understood by those skilled in the art. For example, wireless communication may be Wi-Fi®, Bluetooth®, ZigBee, or other near-field communications. In addition, signal communication may include one or more intermediate controllers or relays disposed between elements in signal communication.

[0265] The memory 2704 may include or store sample and data collection and instructions 2706. Upon execution of such instructions, the operation controller 2701 may obtain samples associated with each equipment 2720A, 2720B, and up to 2720N. Further, the operation controller 2701 may obtain data from the one or more sensors 2716A, 2716B, and up to 2716N and / or one or more flow control devices 2718 A, 2718B, and up to 2718N. Upon collection of the samples, the operation controller 2701 may send the sample to one of the one or more analyzers 2722A, 2722B, and up to 2722N. The one of the one or more analyzers 2722A, 2722B, and up to 2722N may then analyze the sample and generate properties and / or a spectra.

[0266] The operation controller 2701 may connect to and receive data from the one or more predictive controls 2714A, 2714B, and up to 2714N. In an embodiment, the operation controller 2701 may receive the output from each trained machine learning model of eachthe predictive controls 2714A, 2714B, and up to 2714N. In an embodiment, the output may comprise a vector or, in other embodiments, a value indicative of a parameter adjustment.

[0267] The memory 2704 may include or store trained machine learning models 2708. The trained machine learning models 2708 may include at least one trained machine learning model to generate an output indicative of parameter and / or feed adjustment. The operation controller 2701 may apply the data, properties, spectra, and / or the output of each trained machine learning model from one or more predictive controls 2714A, 2714B, and up to 2714N to the trained machine learning models 2708 to generate an output indicative of parameter adjustments and / or feed adjustment.

[0268] The memory 2704 may include or store parameter adjustment instructions 2710. Upon generation of the output, the operation controller 2701 may adjust parameters associated with equipment at the refinery. Further the memory 2704 may include or store feed adjustment instructions 2712 to adjust feed based on the output.

[0269] In FIG. 27B, predictive controls 2714 may connect to subsets of each of the components described in FIG. 27A. For example, the predictive controls 2714 may connect to a subset of the sensors 2736A, 2736B, and up to 2736N, a subset of the devices 2738A, 2738B, and up to 2738N, a subset of the equipment 2740A, 2740B, and up to 2740N, and / or a subset of the analyzers 2742A, 2742B, and up to 2742N. The predictive controls 2714 may include a trained machine learning model 2728 and instructions stored in a memory 2726 and executable by a processor 2724.

[0270] The instructions may include sample and data collection instructions 2730, which when executed cause the predictive controls 2714 to collect various data points and / or properties. Based on application of the data received to the trained machine learning model 2728 and, in some embodiments, an output from the operation controller 2701, the predictive controls 2714 may supply or provide the output to the operation controller 2701.

[0271] FIG. 28 is a flow chart illustrating enhanced fluid production at a refinery, according to an embodiment of the disclosure. Unless otherwise specified, the actions of method 2800 may be completed within operation controller 2701 (FIG. 27A) and / or predictive controls 2714A to 2714N. Specifically, method 2800 may be included in one or more programs, protocols, or instructions loaded into the memory 2704 of operation controller 2701 and executed on the processor or one or more processors of the operation controller 2701. In other embodiments, method 2800 may be implemented in or included in components of FIGS. 1A-28B. The order in which the operations are described is not intended to beconstrued as a limitation, and any number of the described blocks may be combined in any order and / or in parallel to implement the methods.

[0272] At block 2802, the one or more predictive controls may each obtain data from corresponding sources. In such an example, each of predictive controls may poll corresponding sensors, flow control devices, equipment, temperature control devices, and / or other data generating sources related to a corresponding refinery unit to obtain data therefrom. Further, the predictive controls may initiate sample collection for inputs or feedstock, as well as intermediaries and / or products produced by the corresponding source. Such a sample may be analyzed by one or more spectroscopic analyzers, which may subsequently produce properties and / or spectra of the samples.

[0273] At block 2804, once each sub-controller has obtained data, each sub-controller may apply that data, which may also include one or more different properties and / or spectra, to a corresponding machine leaning model stored therein. In another embodiment, the targeted product and / or targeted properties may be applied, in addition to the data described above, to the machine learning model of the predictive controls. The machine learning model may produce vectors, indicators, and / or other values indicative of one or more parameters that may cause the corresponding source to produce a targeted product. Each of the parameters output from the trained machine learning model may correspond to some aspect of the source. For example, the parameters may include temperature, amounts of other fluids used in the operation (for example, hydrogen or alkanes, among others), pressure, flow rate, residence time, feedstock used, and / or intermediaries used.

[0274] At block 2806, each of the predictive controls may determine whether the subparameters are different than currently set parameters. If the parameters are different, then, in some embodiments and at block 2808, each of the predictive controls may adjust one or more of the equipment, devices, or fluids. In such embodiments, the predictive controls may provide the adjustments to an equipment and device controller. In another embodiment, the predictive controls may provide the adjustments to the operation controller 2701 (FIG. 27A) to perform such adjustments. In another embodiment, rather than or in addition to adjusting the equipment or devices, the predictive controls may provide the trained machine learning model output to the operation controller 2701.

[0275] At block 2810, the operation controller 2701 (FIG. 27A) may determine updated parameters and / or fluid compositions (e.g., contents) and / or ratios based on application of the obtained data, as well as the outputs from each of the predictive controls, to a trained machine learning model. The operation controller 2701, in some embodiments, may firstobtain data from the all, substantially all, a portion of the refinery, or from a corresponding operation. Data, as noted above, may include data from sensors, meters, equipment, and / or other devices, as well as properties and / or spectra obtained from samples taken from each unit within the refinery. Further, the operation controller 2701 may obtain the output of each model of each predictive controls. Once the operation controller 2701 obtains all relevant data, the operation controller 2701 may determine the updated parameters based on application of that data to a machine learning model.

[0276] At block 2812, the operation controller 2701 (FIG. 27A) may determine whether the output of the model indicates updates to the parameters or whether the determined parameters are different than the current parameters. For example, the operation controller 2701 may compare the values of the updated parameters to the currently set parameters. If the parameters are different, then at block 2814, the operation controller 2701 may adjust the devices, equipment, or fluid within the refinery to the updated parameters.

[0277] In an embodiment, refinery operations may occur continuously or substantially continuously. As such, method 2800 may be an iterative and continuous process that occurs in real-time or near real-time. As target products change and / or other aspects of the refinery change, parameters may continue to be adjusted via method 2800.

[0278] FIG. 29 is a schematic diagram of a refinery 3500. Crude oil 3502 is initially processed by an atmospheric distillation tower 3504 into its constituent parts. Some of the lightest parts from the atmospheric distillation tower 3504 are a gas 3506 that is sent to gas processing 3508. Gas processing 3508 separates sour gas 3509 from the feeds thereto, which include gas 3506 and other gas 3507 resulting from different processes throughout the refinery. Gas processing 3508 diverts the sour gas 3509 to amine treating 3516. The remainder of the gas 3506 and other gas 3507 that is not sour gas is passed to the mercaptan treater 3510 that separates mercaptans from the fuel gas. The fuel gas may be finished as liquid petroleum gas (“LPG”) 3512. The separated butane 3514 may be kept as a finished product, sent to the gasoline blending pool, or sent to C4 isomerization 3591 to be processed into isobutane 3593 as a finished product or further sent to an alkylation unit 3594.

[0279] Amine treating 3516 separates the hydrogen sulfide gas 3520 from the refinery fuel 3518. The hydrogen sulfide gas 3520 and the hydrogen sulfide gas collected from processes throughout the refinery 3500 is sent to the sulfur plant 3522. The sulfur plant 3522 converts the hydrogen sulfide gas 3520 into sulfur 3530 as a finished product.

[0280] Additionally, sour water 3532 collected from processes throughout the refinery 3500 is sent to the sour water steam stripper 3528. The sour water steam stripper 3528 usessteam 3534 to remove hydrogen sulfide gas 3526 from the sour water 3532. The hydrogen sulfide gas 3526 is also sent to the sulfur plant 3522.

[0281] The atmospheric distillation tower 3504 separates light naphtha 3536 from the crude oil 3502. The light naphtha 3536 is sent to a hydrotreater 3538 that removes sulfur from the light naphtha 3536. The hydrotreated light naphtha is then sent to isomerization 3540 to be processed into isomerate 3542. Isomerate 3542 are isomers of the light naphtha that have higher octane values. The isomerate 3542 may then be sent to the gasoline blending pool 3543.

[0282] The atmospheric distillation tower 3504 separates heavy naphtha 3544 from the crude oil 3502. Optionally, the heavy naphtha 3544 may be sent to a splitter 3545. The splitter 3545 may include one or more splitter columns that separate heavier C7+ naphtha molecules from lighter components of the heavy naphtha 3544. The heavier C7+ naphtha may be sent to the hydrotreater 3554 to be desulfurized and produced as jet fuel 3558. The remaining lighter components of the heavy naphtha may be sent to a hydrotreater 3546 to remove sulfur from the heavy naphtha 3544 prior to being sent to the catalytic reformer 3548 to be converted into reformate 3550.

[0283] Alternatively, the heavy naphtha 3544 may be sent directly to the hydrotreater 3546 to remove sulfur from the heavy naphtha 3544 prior to being sent to the catalytic reformer 3548. From the hydrotreater 3546, the desulfurized heavy naphtha is sent to a catalytic reformer 3548 to be processed into reformate 3550. Reformate 3550 includes high-octane branched and cyclic hydrocarbons, such as benzene, toluene, xylene, and ethylbenzene. The reformate 3550 may then be sent to the gasoline blending pool 3543.

[0284] Another product from the atmospheric distillation tower 3504 is jet fuel 3552. The jet fuel 3552 may include kerosene and other equivalent hydrocarbons. The jet fuel 3552 may be sent from the atmospheric distillation tower 3504 to a hydrotreater 3554 to remove contaminants from the jet fuel 3552, such as sulfur and mercaptans. Once desulfurized, the finished jet fuel 3558 may be sold or sent to the jet fuel blending pool 3559 shown in FIG. 29A to be blended with other products and additives and then made available for sale and distribution. The jet fuel 3552 may also be separated into kerosene (not shown).

[0285] Further, diesel 3560 is another product separated from crude oil 3502 by the atmospheric distillation tower 3504. The diesel 3560 is sent from the atmospheric distillation tower 3504 to a hydrotreater 3562 to remove sulfur. The desulfurized diesel 3564 may then be sold or sent to the diesel blending pool 3565.

[0286] The atmospheric distillation tower 3504 also separates atmospheric gas oil 3566 and atmospheric bottoms 3568 from the crude oil 3502. The atmospheric bottoms 3568 may be sent to vacuum distillation 3570 where the atmospheric bottoms 3568 may be further separated into light vacuum gas oil 3572 (“LVGO”), medium vacuum gas oil 3599 (“MVGO), heavy vacuum gas oil 3584 (“HVGO”), and vacuum residuum 3521. Vacuum distillation 3570 may also be configured to separate the atmospheric bottoms 3568 into more or less components.

[0287] The atmospheric gas oil 3566, the LVGO 3572, the MVGO 3599, and deasphalted oil 3501 from solvent deasphalting 3598 (“SDA”) may be sent to a hydrotreater 3574 to remove sulfur, then fed into a fluid catalytic cracker 3576. The fluid catalytic cracker 3576 processes the atmospheric gas oil 3566 and the light vacuum gas oil 3572 into naphtha 3578, jet fuel 3581, diesel 3582, fuel oil 3583, and butenes and pentenes 3592.

[0288] The butenes and pentenes 3592 from the fluid catalytic cracker 3576, as well as the isobutane 3593 from C4 isomerization 3591, may be sent to an alkylation unit 3594 where the feedstocks are processed into alkylate 3596. The alkylate 3596 may then be sold or sent to the gasoline blending pool 3543. Alkylate 3596 has a high octane rating and low RVP.

[0289] The naphtha 3578 may be sent to a hydrotreater 3580 to further remove sulfur from the naphtha 3578. The desulfurized naphtha may then be sold or sent to the gasoline blending pool 3543. The jet fuel 3581 may also be passed through a hydrotreater 3585 to remove sulfur and other contaminants and then may be sent to the jet fuel blending pool 3559. The diesel 3582 may also be passed through a hydrotreater 3587 to remove sulfur and other contaminants and then sent to the diesel blending pool 3565, and the fuel oil 3583 may be sold or stored for later sale and distribution. Lastly, the fuel oil 3583 may also be passed through a hydrotreater 3585 to remove sulfur and other contaminants and then sent to the fuel oil blending pool 3571 shown in FIG. 29A. In some embodiments, the fuel oil blending pool 3571 may be used to blend formulations of low sulfur fuel oil or ultra-low sulfur fuel oil.

[0290] The MVGO 3599, HVGO 3584, and the deasphalted oil 3501 may be sent to the hydrocracker 3586 to be processed into gasoline 3588, diesel 3590, and jet fuel 3595. The hydrocracker 3586 may also produce smaller hydrocarbons that may be sent to gas processing 3508. The hydrocracker 3586 process integrates desulfurization and other contaminant removal, so further hydrotreating is not necessary for its products. The gasoline 3588 may be sold or sent to the gasoline blending pool 3543 shown in FIG. 29A.The diesel 3590 may be sold or sent to the diesel blending pool 3565 shown in FIG. 29A. The jet fuel 3595 may be sold or sent to the jet fuel blending pool 3559 shown in FIG. 29A.

[0291] The vacuum residuum 3521 may be sent to solvent deasphalting 3598 (“SDA”) or used directly in asphalt 3519. In some applications, the vacuum residuum 3521 may be sent to the asphalt blending pool 3573 shown in FIG. 29A. The SDA 3598 may be used to extract lighter components from the vacuum residuum 3521 using solvents such as propane, butane, pentane, or a combination of these hydrocarbons to extract deasphalted oil 3501 from the vacuum residuum 3521. As discussed above, the deasphalted oil 3501 may be sent to the hydrocracker 3586 or the fluid catalytic cracker 3576 for refining into hydrocarbon products including naphtha, jet fuel, diesel, and fuel oil. Once the lighter components are removed, the remaining components may be referred to as pitch 3579. The pitch 3579 may also be used in the asphalt blending pool 3573.

[0292] The vacuum residuum 3521 and pitch 3579 may also be sent to the coker 3597 to be processed into naphtha 3503 and processed through a gasoline desulfurization unit 3556 (“GDU”). The GDU 3556 may include one or more processes useful to remove contaminants from the naphtha 3503 in addition to gasoline desulfurization, including hydrotreating processes, catalysts, particulate catches, clay treaters, salt driers, and mercaptan treaters, separators, and steam strippers. The naphtha 3503 may then be sent to the gasoline blending pool 3543. The coker 3597 also processes the vacuum residuum 3521 and pitch 3579 into jet fuel 3511, diesel 3513, fuel oil 3515, and petroleum coke 3517. The jet fuel 3511 may be passed through a hydrotreater 3523 and then sent to the jet fuel blending pool 3559. The diesel 3513 may be sent to a hydrotreater 3525 to remove sulfur and then sent to the diesel blending pool 3565. The fuel oil 3515 may also be processed through hydrotreater 3527 and then sent to the fuel oil blending pool 3571 shown in FIG. 29A.

[0293] The hydrotreaters 3538, 3546, 3554, 3562, 3574, 3580, 3585, 3587, 3589, 3523, 3525, and 3527 refer broadly to desulfurization and contaminant removal processes generally, including hydrotreating processes, clay treaters, salt driers, mercaptan treaters, gasoline desulfurization units, separators, steam strippers, filters, and particulate catches.

[0294] Many of the connections, feedstocks, and outputs are not shown, and those of skill in the art recognize that different configurations are possible and processes may be added or replaced by other processes known in the art. For example, atmospheric distillation tower 3504 and vacuum distillation 3570 may each represent multiple units set up in parallel or series, and may separate their feedstocks into more or fewer crude oil components.Additional equipment may be added to each process to further refine and separate the products of each process. For example, products and components of the products may be passed through isomerization, reformation, and alkylation processes not shown in FIG. 29 to process the products and components to meet regulatory requirements and customer specifications.

[0295] FIG. 29A is a schematic diagram of hydrocarbon refinery products 3505 produced by the refinery 3500 and their movement into the blending pools 3524, including a gasoline blending pool 3543, a jet fuel blending pool 3559, a diesel blending pool 3565, a fuel oil blending pool 3571, and an asphalt blending pool 3573. Each blending pool 3524 stores products from various refinery product streams and products from other sources in storage tanks 3575 and may use these products to blend these products into different formulations that meet various regulatory requirements, industry standards, and customer specifications.

[0296] As shown, the butane 3514, the naphtha 3503, naphtha 3578, the isomerate 3542, the reformate 3550, the alkylate 3596, and the gasoline 3588 may all be sent to the gasoline blending pool 3543. Additionally, materials may be obtained from other sources 3529 including other refineries, third parties, or off the open market. Gasoline specifications may include research octane number (RON), motor octane number (MON), volatility or Reid vapor pressure (“RVP”), sulfur concentration, benzene concentration, aromatic concentration, olefin concentration, driveability index, distillation curve, vapor-liquid ratio, stability, and corrosion resistance.

[0297] For example, butane 3531, naphtha 3533, isomerate 3535, reformate 3537, alkylate 3539, and gasoline 3541 may be obtained from other sources 3529 and added to the gasoline blending pool 3543. Butane 3531 may be blended in the gasoline blending pool 3543 for use during seasons of cold weather because butane 3531 increases the Reid Vapor Pressure (“RVP”) helping the gasoline blend vaporize and ignite in cold gasoline engines. Coker naphtha 3503 may be included in a blended gasoline after hydrotreating but may include a higher proportion of olefins. Naphtha 3578 from the fluid catalytic cracker 3576, also known as FCC gasoline, may be a large contributor to the gasoline blending pool 3543 and may also contain olefins and aromatic molecules. The naphtha 3503 and naphtha 3578 may be passed through a catalytic reformer 3548 to improve (e.g., increase) their octane number through their conversion to aromatics and isoparaffins before being sent to the gasoline blending pool 3543.

[0298] Isomerate 3542 increases (e.g., improves) the octane rating of a blended gasoline without increasing aromatic concentration and is useful in meeting regulatory limits onbenzene. Reformate 3550 also improves the octane rating of a blended gasoline by including aromatics and isoparaffins. Alkylate 3596 is a useful blending component of gasoline that increases octane rating through its composition of isoparaffins and branches alkanes. Alkylate 3596 contains few, if any, aromatics. Hydrocracked gasoline 3588, also known as hydrocracked naphtha, is low in sulfur and may be used to reduce sulfur concentration in a blended gasoline.

[0299] Additionally, natural gasoline 3547, oxygenates 3549, such as MTBE, ETBE, or ethanol may be sent to the gasoline blending pool 3543. Natural gasoline 3547 may be derived from natural gas liquids during gas processing. Natural gasoline 3547 typically has a low octane rating and may be used as a low cost component in blended gasolines. Oxygenates 3549 may help increase octane rating in blended gasolines and may help reduce carbon monoxide emissions.

[0300] The different components of the gasoline blending pool 3543 are mixed to create the blended product properties ordered by customers and that comply with regulatory requirements. In many applications, higher-octane components, like reformate and alkylate, balance lower-octane product streams. Further, aromatics, benzene, and olefins are often limited to meet regulatory standards.

[0301] In general, inputs into the gasoline blending pool 3543 may include reformate, isomerate, alkylate, naphtha from different sources, butane, oxygenates, and other additives. Each formulation of blended gasoline from the gasoline blending pool 3543 has properties that may be measured and specified through testing including Reid vapor pressure (“RVP”) at different temperatures, olefin concentration, oxygenate concentration, benzene concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, sulfur concentration, mercaptan sulfur, gum concentration, oxidation stability, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control, and density. Each formulation of blended gasoline from the gasoline blending pool may be selected for production based on the current market price for similar formulations, forecasted demand, predicted profit per batch, regulatory constraints, and current inventory levels in the storage tanks of the gasoline blending pool 3543.

[0302] The jet fuel blending pool 3559 may include the jet fuel 3511, the jet fuel 3558, the jet fuel 3581, the jet fuel 3595, and additives. Additives may include kerosene, light oil, and diesel. The jet fuel blending pool 3559 may also include components from other sources 3529 such as other refineries, third parties, and the open market including jet fuel3551, and kerosene 3553. Each of these components may be blended to meet customer specifications and regulatory requirements including freezing point, flash point, distillation range, density, sulfur concentration, aromatic and olefin concentration, viscosity, energy content, anti-icing capabilities, static dissipation, and corrosion inhibition.

[0303] In general, inputs into the jet fuel blending pool 3559 may include sources of heavy naphtha, kerosene, jet fuels, reformate, and other additives. Each formulation of blended jet fuel from the jet fuel blending pool 3559 has properties that may be measured and specified through testing including aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, viscosity, energy content, anti-icing capabilities, static dissipation, and corrosion inhibition. Each formulation of blended jet fuel from the jet fuel blending pool 3559 may be selected for production based on the current market price for similar formulations, forecasted demand, predicted profit per batch, regulatory constraints, and current inventory levels in the storage tanks of the jet fuel blending pool 3559.

[0304] Diesel fuel may be blended from a variety of refinery products to meet customer and regulatory specifications, including cetane number, sulfur concentration, cold flow properties, and energy content. A higher cetane number indicates improved combustion efficiency. Regulations require sulfur concentration to be below 15 ppm. Diesels used in cold temperature regions and during cold seasons may include lighter hydrocarbons left by adjusting distillation, separation, or splitter cut points to meet the cloud point temperature and pour point temperature specifications of the blended diesel formulation. Heavier blending components, such as diesel 3513 from the coker 3597 and fuel oils 3515 and 3583, may be less expensive than other blend components and increase density of the blended diesel, but may also reduce fuel efficiency.

[0305] The diesel 3513, the diesel 3564, the diesel 3582, the diesel 3590, the fuel oil 3515, and the fuel oil 3583 may all be sent to the diesel blending pool 3565. Diesel 3564 is a straight run diesel that has been hydrotreated to remove sulfur and has a high cetane number and low aromatic concentration. Diesel 3590 from the hydrocracker 3586 has a high cetane number, low sulfur concentration, and low aromatic concentration. Diesel 3582 and fuel oil 3583 from the fluid catalytic may contain high aromatics and thus a lower cetane number. Fuel oil 3583 may be blended in limited quantities to reduce smoke emissions. Diesel 3513 and fuel oil 3515 from the coker 3597 may be high in sulfur and may behydrotreated before being added to the diesel blending pool 3565. Diesel 3513 may have a high aromatic concentration, and thus a lower cetane number. The fuel oil 3583 may also include a high aromatic concentration and blended in limited quantities to reduce smoke emissions. Components of the diesel blending pool 3565 may also be sourced from other sources 3529. For example, diesel 3555 may be sourced from other refineries or third parties.

[0306] In general, inputs into the diesel blending pool 3565 may include sources of gas oil, diesel, and other additives. Additives may include kerosene, jet fuel, and light oil. Each formulation of blended diesel from the diesel blending pool 3565 has properties that may be measured and specified through testing including aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content (e.g., concentration), red dye content (e.g., concentration) (if applicable), Ramsbottom carbon residue, and corrosion inhibition. Each formulation of diesel from the diesel blending pool 3565 may be selected for production based on the current market price for similar formulations, forecasted demand, regulatory constraints, predicted profit per batch, and current inventory levels in the storage tanks of the diesel blending pool 3565. Some formulations of diesel may be created to meet specifications for low sulfur diesel and ultra-low sulfur diesel.

[0307] The fuel oil blending pool 3571 may receive refinery products 3505, such as fuel oil 3515 from the coker 3597, fuel oil 3583 from the fluid catalytic cracker, as well as the diesel 3513, the diesel 3564, the diesel 3582, and the diesel 3590. The diesel 3513, the diesel 3564, the diesel 3582, and the diesel 3590 may be blended with the fuel oil 3515 and the fuel oil 3583 to improve combustibility, lower viscosity, improve cold weather performance, reduce sulfur co concentration and assist with regulatory compliance, reduce sludge formation in fuel tanks and engine components, and enhance combustion stability. However, the diesel 3513, the diesel 3564, the diesel 3582, and the diesel 3590 may be more valuable when blended into a diesel fuel formulation. Additionally, the fuel oil blending pool 3571 may receive components from other sources 3529, including fuel oil 3557 and diesel 3555.

[0308] In general, inputs into the fuel oil blending pool 3571 may include sources of gas oil, diesel, and other additives. Each formulation of blended fuel oil from the fuel oil blending pool 3571 has properties that may be measured and specified through testing including aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, lubricity, NOx emission factor, viscosity, energy content, and corrosion inhibition. Each formulation of fuel oil from the fuel oil blending pool 3571 may be selected for production based on the current market price for similar formulations, forecasted demand, regulatory constraints, predicted profit per batch, and current inventory levels in the storage tanks of the fuel oil blending pool 3571. Some formulations may be created to meet low sulfur fuel oil specifications.

[0309] The asphalt blending pool 3573 (which may also be referred to as an “asphalt binder blending pool”) may be configured to form an asphalt binder by receiving refinery products 3505 including asphalt 3519, heavy vacuum gas oil 3584 (“HVGO”), medium vacuum gas oil 3599 (“MVGO”), and vacuum gas oil that may be obtained from vacuum distillation 3570 as a combination of MVGO 3599, HVGO 3584, atmospheric gas oil 3566, vacuum residuum 3521, deasphalted oil 3501, pitch 3579, as well as components from other sources 3529, including pitch 3561, asphalt 3563, MVGO 3567, and HVGO 3569, as well as other materials, such as polymers, biomaterial, and polyphosphoric acid. For example, asphalt may be blended to include polymers, such as styrene-butadiene-styrene, crumb rubber, devulcanized rubber. The polymer may include polymers such as styrene-butadiene- styrene, crumb rubber, devulcanized rubber, and / or other materials. The constituents of an asphalt formulation include oils, resins, and asphaltenes. In some embodiments, the constituents further include saturates. Oils are the light fraction, having molecular weights in the range of from about 24 g / mol to about 800 g / mol. Resins are the more polar fraction, having molecular weights in the range of from about 800 g / mol to about 2000 g / mol. Asphaltenes are high molecular weight molecules in a range of from about 1800 g / mol to about 8000 g / mol and possess aromatic rings.

[0310] The composition of the blended asphalt binder and the blending feedstocks used to blend the asphalt binder may be determined according to the IP 469 Standard. The IP 469 Standard outlines a methodology for conducting a SARA (saturates, aromatics, resins, and asphaltenes) analysis of the material and may be used to quantity the composition of thedifferent components (saturates, aromatics, resins, and asphaltenes) (also referred to as “fractions”) in the material. The different components are separated based on solubility using chromatography and solvents. The saturates include non-polar hydrocarbons including alkanes and cycloalkanes; the aromatics include compounds with one or more aromatic rings; the resins include polar, non-asphaltene hydrocarbons; and the aromatics include highly polar, high molecular weight hydrocarbons that are insoluble in n-heptane. During a SARA analysis, n-heptane is used to precipitate asphaltenes from the sample, while the remaining soluble material (referred to as “maltenes”) is further fractionated using a chromatography column. In the chromatography column, a silica or alumina column is employed to separate the maltenes into saturates, aromatics, and resins using specific solvents of varying polarity. The saturates are separated from the maltenes by elution using a non-polar solvent, such as n-hexane or heptane; followed by separation of the aromatics by elution using an aromatic-rich solvent, such as toluene or benzene. Finally, the resins are separated by elution using a polar solvent, such as dichloromethane (DCM) or acetone.

[0311] In general, inputs into the asphalt blending pool 3573 may include sources of vacuum residue, atmospheric resid, heavier fractions from crude distillation, pitch, solvent deasphalted asphalt, and other additives, including oils, polymers. Each formulation of blended asphalt from the asphalt blending pool 3573 has properties that may be measured and specified through testing including penetration point deviation, softening point deviation, sulfur concentration, polymer-modified asphalt performance, oxidation stability, h...

Claims

CLAIMSWHAT IS CLAIMED IS:

1. A method for enhancing blends of a hydrocarbon product for a one or more product pools in a refinery operation, the method comprising: monitoring one or more product properties of the hydrocarbon product with one or more sensor packages during a process modifying the hydrocarbon product; receiving product pool data indicative of a demand for a blended formulation including the hydrocarbon product, the blended formulation having a blended property; generating a target property of the hydrocarbon product based on the product pool data; predicting adjustments to one or more operational parameters for the process modifying the hydrocarbon product by a machine learning model based on data from the one or more sensor packages, a historical data of the process, the product pool data, and the target property of the hydrocarbon product; and dynamically adjusting one or more operational parameters of the process modifying the hydrocarbon product to adjust one or more product properties of the hydrocarbon product to achieve the target property.

2. The method of claim 1, wherein the product pool data includes a customer specification for the blended formulation.

3. The method of any of claims 1 to 2, wherein the target property is a target octane- barrels of the hydrocarbon product modified by the process.

4. The method of any of claims 1 to 3, wherein the target property is a target octane number of the hydrocarbon product.

5. The method of any of claims 1 to 4, wherein the blended formulation is for a gasoline blend, wherein the blended property includes one or more of Reid vapor pressure (“RVP”) at different temperatures, olefin concentration, oxygenate concentration, benzene concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, sulfur concentration, mercaptan sulfur, gum concentration, oxidation stability, corrosion, sulfurcompliance risk score, fuel economy impact, driveability index, blend volatility control, and density.

6. The method of any of claims 1 to 5, wherein the blended formulation is for a jet fuel blend, wherein the blended property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, viscosity, energy content, anti- icing capabilities, static dissipation, and corrosion inhibition.

7. The method of any of claims 1 to 6, wherein the blended formulation is for a diesel fuel blend, wherein the blended property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, and corrosion inhibition.

8. The method of any of claims 1 to 7, wherein the blended formulation is for a fuel oil blend, wherein the blended property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, lubricity, NOx emission factor, viscosity, energy content, and corrosion inhibition.

9. The method of any of claims 1 to 8, wherein the blended formulation is for a biofuel blend, wherein the blended property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability,final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, corrosion inhibition, Reid vapor pressure (“RVP”) at different temperatures, olefin oxygenate concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, mercaptan sulfur, gum concentration, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, or blend volatility control.

10. The method of any of claims 1 to 9, wherein the blended formulation is for an asphalt blend, wherein the blended property includes one or more of penetration point deviation, softening point deviation, sulfur concentration, polymer-modified asphalt performance, oxidation stability, high-temperature viscosity, storage stability, elastic recovery, rutting resistance, fatigue crack resistance, thermal cracking resistance, weather durability, density, and load bearing performance.

11. The method of any of claims 1 to 4, wherein the target property is measured or sampled proximate an exit of reactor a separator, a distillation unit, a stripper, or a stabilizer of the process.

12. The method of any of claims 1 to 11, wherein dynamically adjusting one or more operational parameters of the process includes dynamically adjusting an operating temperature of a reactor of the process.

13. The method of claim 12, further comprising predicting, by the machine learning model, a deactivation state of catalysts of the reactor of the process, wherein dynamically adjusting an operating temperature of a reactor of the process is further based on the predicted deactivation state of catalysts of the reactor of the process.

14. The method of of any of claims 1 to 13, further comprising: monitoring one or more product properties of a second hydrocarbon product with one or more second sensor packages during a second process modifying the second hydrocarbon product;generating a second target property of the second hydrocarbon product based on the product pool data; predicting adjustments to one or more operational parameters for the second process modifying the second hydrocarbon product based on second data from the one or more second sensor packages, a historical data of the second process, the product pool data, and the second target property of the second hydrocarbon product; and dynamically adjusting one or more operational parameters of the second process modifying the hydrocarbon product to adjust one or more product properties of the second hydrocarbon product to achieve the second target property of the second hydrocarbon product.

15. The method of claim 14, wherein the hydrocarbon product is blended with the second hydrocarbon product to produce the blended formulation having the blended property.

16. The method of any of claims 14 to 15, wherein the target property of the hydrocarbon product is the same as the second target property of the second hydrocarbon product, but the target property of the hydrocarbon product has a different value than the second target property of the second hydrocarbon product.

17. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 1 to 16.

18. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 1 to 16.

19. A method comprising: accessing, by a machine learning model, an inventory of a plurality of products stored within a blending pool, wherein for each product of the plurality of products, the inventory includes a chemical composition of the product and a quantity of the product available within the blending pool; generating, by the machine learning model, a plurality of potential blended formulations from the products in a blending pool based on the inventory;predicting, by the machine learning model, a plurality of properties for each of the plurality of potential blended formulations; and publishing a list of the plurality of potential blended formulations.

20. The method of claim 19, further comprising ordering the list of the plurality of potential blended formulations according to a product property.

21. The method of claims 19 or 20, wherein the inventory further includes an average rate of production of the product.

22. The method of claims 19, 20, or 21, further comprising: accessing, by the machine learning model, data containing process costs and material costs for each of the plurality of products stored within a blending pool; generating, by the machine learning model, a cost for each of the plurality of potential blended formulations; and adding the cost for each of the plurality of potential blended formulations to the list.

23. The method of claims 19, 20, 21, or 22, further comprising: receiving a one or more specified property levels; and receiving an instruction to republish the list with formulations whose predicted properties meet or are better than the one or more specified property levels.

24. The method of claim 19, wherein the product property describes a range for the product property.

25. The method of claims 23 or 24, wherein the product property includes a confidence level of accuracy of the predicted product property.

26. The method of claims 19, 20, 21, 22, 23, 24, or 25, further comprising: receiving an instruction to produce a quantity of a selected blended formulation from the list of the plurality of potential blended formulations; determining an available quantity of the selected blended formulation that may be blended from the inventory; and sending instructions to blend the quantity of the selected blended formulations.

27. The method of claim 26, wherein determining an available quantity of the selected blended formulation that may be blended from the inventory is based on one or more of the inventory, customer orders, and a forecasted demand for a component of the selected blended formulation .

28. The method of claims 19, 20, 21, 22, 23, 24, 25, 26, or 27, further comprising predicting demand for a component by the machine learning model based on a business data and a current date, wherein the business data includes one or more of a sales data, a regulatory data, a seasonality of product data, and a weather data to generate a forecasted demand for the component.

29. The method of claims 26, 27, or 28, further comprising: determining a deficit between the instruction and the available quantity; and determining a list of components and a quantity of each component needed to produce the deficit of the selected blended formulation.

30. The method of claim 29, further comprising: determining a list of processes used to produce the list of components needed to produce the deficit of the selected blended formulation; and predicting a production rate of the list of components needed to produce the deficit of the selected blended formulation, a cost of production of the list of components, and a quantity of each component needed to produce the deficit of the selected blended formulation.

31. The method of claim 30, further comprising: accessing pricing and availability to purchase each of the components of the list of components needed to produce the deficit of the selected blended formulation from other sources; comparing the production rate of the list of components needed to produce the deficit of the selected blended formulation and the cost of production of the list of components with the pricing and availability to purchase each of the components of the list of components needed to produce the deficit of the selected blended formulation from other sources;generating a recommendation of whether to purchase none, one, or more of and a quantity of the components of the list of components needed to produce the deficit of the selected blended formulation; and publish the recommendation for user feedback.

32. The method of claims 29, 30, or 31, further comprising: predicting a completion date of producing the instructed quantity of the selected blended formulation based on historical information, a current rate of production, and other orders for a same components of the list of components needed to produce the deficit of the selected blended formulation; and publishing the predicted completion date.

33. The method of claim 32, further comprising: predicting a margin of time based on historical information of delays in production and a current status of a targeted process producing the instructed quantity of the selected blended formulation; and publishing an anticipated date of completion based on the predicted completion date plus the predicted margin of time.

34. The method of claims 29, 30, 31, 32, or 33, further comprising: sending instructions to increase production of one or more components of the list of components needed to produce the deficit of the selected blended formulation to a process controller controlling a targeted process producing the instructed quantity of the selected blended formulation.

35. The method of claim 34, wherein sending instructions to increase production includes changing one or more of operating temperature, pressure, and feed rate of a feedstock.

36. The method of claims 34 or 35, wherein sending instructions to increase production includes changing one or more of operating temperature, pressure, and feed rate of a feedstock to increase production of a first product of a process over a second product of the process.

37. The method of claim 36, wherein the first product has an property value different from an property value of a second product of the process.

38. The method of any of claims 19 to 37, further comprising receiving instructions regarding the list of the plurality of potential blended formulations.

39. The method of any of claims 19 to 38, wherein the blended formulation is for a gasoline blend, wherein the plurality of properties include one or more of Reid vapor pressure (“RVP”) at different temperatures, olefin concentration, oxygenate concentration, benzene concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, sulfur concentration, mercaptan sulfur, gum concentration, oxidation stability, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control, and density.

40. The method of any of claims 19 to 39, wherein the blended formulation is for a jet fuel blend, wherein the plurality of properties include one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, viscosity, energy content, anti-icing capabilities, static dissipation, and corrosion inhibition.

41. The method of any of claims 19 to 40, wherein the blended formulation is for a diesel fuel blend, wherein the plurality of properties include one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, and corrosion inhibition.

42. The method of any of claims 19 to 41, wherein the blended formulation is for a fuel oil blend, wherein the plurality of properties include one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, lubricity, NOx emission factor, viscosity, energy content, and corrosion inhibition.

43. The method of any of claims 19 to 42, wherein the blended formulation is for a biofuel blend, wherein the plurality of properties include one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, corrosion inhibition, Reid vapor pressure (“RVP”) at different temperatures, olefin oxygenate concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, mercaptan sulfur, gum concentration, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, or blend volatility control.

44. The method of any of claims 19 to 43, wherein the blended formulation is for an asphalt blend, wherein the plurality of properties include one or more of penetration point deviation, softening point deviation, sulfur concentration, polymer-modified asphalt performance, oxidation stability, high-temperature viscosity, storage stability, elastic recovery, rutting resistance, fatigue crack resistance, thermal cracking resistance, weather durability, density, and load bearing performance.

45. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 19 to 44.

46. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 19 to 44.

47. A method comprising: receiving sensor data from a plurality of sensor packages at a machine learning model, wherein a first sensor package of the plurality of sensor packages is disposed to measure one or more process parameters of a first process, a second sensor package of the plurality of sensor packages is disposed to measure one or more of a composition or a product property of a first product of the first process, a third sensor package disposed to measure one or more process parameters of a second process, and a fourth sensor package of the plurality of sensor packages is disposed to measure one or more of a composition or a product property of a first product of the second process, wherein the machine learning model has been trained with historical data of the first process, the second process, the first product of the first process, and the first product of the second process; predicting, by the machine learning model, a product property for a blended formulation of the first product of the first process with the first product of the second process; predicting, by the machine learning model, an adjustment to an operational parameter of the first process to improve the product property of the blended formulation based on the historical data and the sensor data; and predicting, by the machine learning model, an adjustment to an operational parameter of the second process to improve the product property of the blended formulation based on the historical data and the sensor data.

48. The method of claim 47, further comprising publishing the adjustment to a user.

49. The method of claims 47 and 211, wherein each adjustment is different.

50. The method of any of claims 47 to 49, wherein each process has different levels of equipment wear.

51. The method of any of claims 47 to 50, wherein the first process is different from the second process.

52. The method of any of claims 47 to 51, wherein the first process and the second process are each one of a distillation, hydrotreater, isomerization, reformation, alkalization, fluid catalytic cracking, hydrocracking, coker processes, stripper, stabilizer, scrubber, separation, gasoline desulfurization unit, C4 Isomerization, catalytic dewaxing, and hydrodeoxygenation process.

53. The method of any of claims 47 to 52, wherein the first product of the first process is different from the first product of the second process.

54. The method of any of claims 47 to 53, wherein the first product of the first process results from a product stream that is different from a product stream of the first product of the second process.

55. The method of any of claims 47 to 54, wherein the blended formulation is for a gasoline blend, wherein the product property includes one or more of Reid vapor pressure (“RVP”) at different temperatures, olefin concentration, oxygenate concentration, benzene concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, sulfur concentration, mercaptan sulfur, gum concentration, oxidation stability, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control, and density.

56. The method of any of claims 47 or 55, wherein the blended formulation is for a jet fuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, viscosity, energy content, anti-icing capabilities, static dissipation, and corrosion inhibition.

57. The method of any of claims 47 to 56, wherein the blended formulation is for a diesel fuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density,pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, and corrosion inhibition.

58. The method of any of claims 47 to 57, wherein the blended formulation is for a fuel oil blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, lubricity, NOx emission factor, viscosity, energy content, and corrosion inhibition.

59. The method of any of claims 47 to 58, wherein the blended formulation is for a biofuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, corrosion inhibition, Reid vapor pressure (“RVP”) at different temperatures, olefin oxygenate concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, mercaptan sulfur, gum concentration, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, or blend volatility control.

60. The method of any of claims 47 to 59, wherein the blended formulation is for an asphalt blend, wherein the product property includes one or more of penetration point deviation, softening point deviation, sulfur concentration, polymer-modified asphalt performance, oxidation stability, high-temperature viscosity, storage stability, elasticrecovery, rutting resistance, fatigue crack resistance, thermal cracking resistance, weather durability, density, and load bearing performance.

61. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 47 to 59.

62. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 47 to 59.

63. A method for optimizing a refinery blending pool using a trained machine learning (ML) model, comprising: receiving, by a computing system, near real-time process data from at least two refinery equipment supplying blend components to the blending pool; applying the trained ML model to analyze near real-time blend component characteristics; generating, by the ML model, predictive blending parameters based on correlations between current blending pool characteristics, current blend component properties, past blend component properties, current unit operating conditions, past unit operating conditions, current target product specifications, or past target product specifications; dynamically adjusting one or more blending parameters in response to the predictive blending parameters; and providing one or more of real-time blending recommendations or automated control adjustments to maximize blending pool efficiency while ensuring compliance with regulatory and quality requirements.

64. The method of claim 63, wherein the blend component characteristics include at least one of sulfur concentration, aromatic concentration, boiling range, flash point, freeze point, or density.

65. The method of claims 63 or 64, wherein dynamically adjusting one or more blending parameters in response to the predictive blending parameters is performed with at least one advanced control system.

66. The method of any of claims 63 to 65, wherein the blending parameters include at least one of flow rates, component ratios, temperature, pressure, or additive dosages to optimize product quality and yield.

67. The method of any of claims 63 to 66, further comprising continuously refining the ML model by incorporating feedback from one or more of near real-time process analyzers, laboratory test results, and economic pricing models to improve future blending recommendations.

68. The method of any of claims 63 to 67, wherein providing one or more of near realtime blending recommendations or automated control adjustments is accomplished with a user interface.

69. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 63 to 68.

70. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 63 to 68.

71. A method for improving pooling of refinery products using a machine learning (ML) model, the method comprising: receiving first current upstream refinery product data and second current upstream refinery product data of a refinery product blending pool and receiving current refinery product blending pool data; analyzing, using the ML model, the first current upstream refinery product data, the second current upstream refinery product data, and the current refinery product pool data to identify one or more adjustments to one or more refinery processes, process controllers, or refinery controllers to achieve a set of target product specifications for the refinery product blending pool; and outputting the one or more adjustments to the one or more refinery processes, process controllers, or refinery controllers to achieve the set of target product specifications for the refinery blending pool.

72. The method of claim 71, wherein outputting near real-time recommendations includes outputting near real-time recommendations via a user interface.

73. The method of claims 71 or 72, further comprising automatically modifying one or more setpoints of one or more refining parameters.

74. The method of any of claims 71 to 73, further comprising dynamically adjusting one or more process variables within the refinery product blending pool.

75. The method of any of claims 71 to 74, further wherein dynamically adjusting one or more process variables within the refinery product blending pool includes one or more of a feed rate, a temperature setting, or a chemical additive concentration.

76. The method of any of claims 71 to 75, wherein dynamically adjusting one or more process variables within the refinery product blending pool is in response to a predictive adjustment to one or more refining parameters.

77. The method of any of claims 71 to 76, continuously monitoring and refining the ML model by incorporating feedback from one or more of process performance metrics, laboratory test results, or economic factors to enhance future predictions.

78. The method of any of claims 71 to 77, wherein the blending pools include one or more of gasoline blending pool, a jet fuel blending pool, a diesel blending pool, a fuel oil blending pool, a biofuel blending pool, and an asphalt blending pool.

79. The method of any of claims 71 to 78, further comprising generating, by the ML model, predictive adjustments for refining parameters based on correlations between feedstock properties, process conditions, and target product specifications.

80. The method of any of claims 71 to 79, further comprising continuously monitoring and refining the ML model by incorporating feedback from process performance metrics, laboratory test results, and economic factors to enhance future predictions; and connecting the ML model to one or more refinery databases, sensor data, business data, and lab data.

81. The method of any of claims 71 to 80, further comprising: receiving, by the ML model, data from one or more refinery databases, sensor data, business data, and lab data for analysis and training, wherein the data includes process data, business information, demand planning, historical forecast information, pricing information, product distribution information, regulatory information, inventory levels, and laboratory analysis of samples; analyzing and adjusting, by the ML model, one or more refinery processes, process controllers, and a refinery controller based on the received data; and publishing, by the ML model, recommendations and warnings to a user interface and receiving instructions from the user interface for data exchange, wherein the user interface allows engineers to review the data, recommendations, and warnings, and make requests.

82. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 71 to 81.

83. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 71 to 81.

84. A system for optimizing refinery processes, the system comprising: an artificial intelligence (Al) model; and one or more refinery databases, sensor data, business data, and lab data connected to the Al; wherein the Al is configured to: receive data from the one or more refinery databases, sensor data, business data, and lab data for analysis and training, wherein the data includes process data, business information, demand planning, historical forecast information, pricing information, product distribution information, regulatory information, inventory levels, and laboratory analysis of samples; analyze and optimize one or more refinery processes, process controllers, and a refinery controller based on the received data; andpublish recommendations and warnings to a user interface and receive instructions from the user interface for data exchange, wherein the user interface allows engineers to review the data, recommendations, and warnings, and make requests.

85. The system of claim 84, wherein the one or more refinery databases further include incident information and analysis, historical pricing and purchasing data, and process training information.

86. The system of claims 84 or 85, wherein the sensor data further includes operating pressure and temperature data, and material composition data.

87. The system of any of claims 84 to 86, wherein the business data further includes costs, availability, and location of storage, disposal, and carbon capture options.

88. The system of any of claims 84 to 87, wherein analyzing and optimizing the one or more refinery processes comprises making near real-time adjustments to the refinery processes to improve efficiency and profitability.

89. The system of any of claims 84 to 88, wherein the Al is trained using the data received from the one or more refinery databases, sensor data, business data, and lab data.

90. The system of any of claims 84 to 89, wherein the one or more refinery databases further include incident information and analysis, historical pricing and purchasing data, and process training information.

91. The system of any of claims 84 to 90, wherein the sensor data further includes operating pressure and temperature data, and material composition data.

92. The system of any of claims 84 to 91, wherein the business data further includes costs, availability, and location of storage, disposal, and carbon capture options.

93. The system of any of claims 84 to 92, wherein analyzing and optimizing the one or more refinery processes comprises making near real-time adjustments to the refinery processes to improve efficiency and profitability.

94. The system of any of claims 84 to 93, wherein the Al is trained using the data received from the one or more refinery databases, sensor data, business data, and lab data.

95. The system of any of claims 84 to 94, wherein the Al is configured to access the one or more refinery databases, sensor data, business data, and lab data to obtain the data for analysis and training.

96. The system of any of claims 84 to 95, wherein the recommendations include adjustments to the one or more refinery processes, process controllers, and the refinery controller.

97. The system of any of claims 84 to 96, wherein the warnings include alerts related to the one or more refinery processes, process controllers, and the refinery controller.

98. The system of any of claims 84 to 97, wherein the Al is configured to access the one or more refinery databases, sensor data, business data, and lab data to obtain the data for analysis and training.

99. The system of any of claims 84 to 98, wherein the recommendations include adjustments to the one or more refinery processes, process controllers, and the refinery controller.

100. The system of any of claims 84 to 99, wherein the warnings include alerts related to the one or more refinery processes, process controllers, and the refinery controller.

101. The system of any of claims 84 to 100, wherein the user interface is configured to display the data, recommendations, and warnings received from the Al.

102. A method compri sing : receiving, by a machine learning model, a customer specification specifying at least one property for a blended formulation; accessing a business data including an inventory of products in a blending pool, including a quantity of each product and a listing of known properties of each product;generating, by a machine learning model, a plurality of blended formulations based on the inventory of products; predicting properties for each of the generated blended formulations; retaining the generated blended formulations whose predicted properties meet or are better than the customer specification; and publishing a list of the retained generated blended formulations.

103. The method of claim 102, further comprising ordering the list of the retained generated blended formulations according to a product property.

104. The method of claims 102 or 103, wherein the inventory further includes an average rate of production of the product.

105. The method of claims 102, 103, or 104, further comprising: accessing, by the machine learning model, data containing process costs and material costs for each of the plurality of products stored within a blending pool; generating, by the machine learning model, a cost for each of the retained generated blended formulations; and adding the cost for each retained generated blended formulations to the list.

106. The method of claims 102, 103, 104, or 105, further comprising: receiving a one or more specified property levels; and receiving an instruction to republish the list with formulations whose predicted properties meet or are better than the one or more specified property levels.

107. The method of claim 106, wherein the one or more specified property levels describe a range for the one or more specified property levels.

108. The method of claims 106 or 107, wherein the one or more specified property levels includes a confidence level.

109. The method of claims 102, 103, 104, 105, 106, 107, or 108, further comprising: receiving an instruction to produce a quantity of a selected blended formulation from the list of the retained generated blended formulations;determining an available quantity of the selected blended formulation that may be blended from the inventory; and sending instructions to blend the quantity of the selected blended formulations.

110. The method of claim 109, wherein determining an available quantity of the selected blended formulation that may be blended from the inventory is based on one or more of the inventory, customer orders, and a forecasted demand for a component.

111. The method of claims 102, 103, 104, 105, 106, 107, 108, 109, or 110, further comprising predicting demand for a component by the machine learning model based on a business data and current date, wherein the business data includes one or more of a sales data, a regulatory data, a seasonality of product data, and a weather data to generate a forecasted demand for the component.

112. The method of claims 109, 110, or 111, further comprising: determining a deficit between the instruction and the available quantity; and determining a list of components and a quantity of each component needed to produce the deficit of the selected blended formulation.

113. The method of claim 112, further comprising: determining a list of processes used to produce the list of components needed to produce the deficit of the selected blended formulation; and predicting a production rate of the list of components needed to produce the deficit of the selected blended formulation, a cost of production of the list of components, and a quantity of each component needed to produce the deficit of the selected blended formulation.

114. The method of claims 112 or 113, further comprising: accessing pricing and availability to purchase each component of the list of components needed to produce the deficit of the selected blended formulation from other sources; comparing a production rate of the list of components needed to produce the deficit of the selected blended formulation and a cost of production of the list of components withthe pricing and availability to purchase each of the components of the list of components needed to produce the deficit of the selected blended formulation from other sources; generating a recommendation of whether to purchase none, one, or more of and a quantity of the components of the list of components needed to produce the deficit of the selected blended formulation; and publish the recommendation for user feedback.

115. The method of claims 112, 113, or 114, further comprising: predicting a completion date of producing the instructed quantity of the selected blended formulation based on historical information, a current rate of production, and demand for components of the list of components needed to produce the deficit of the selected blended formulation; and publishing the predicted completion date.

116. The method of claim 115, further comprising: predicting a margin of time based on historical information of delays in production and current status of a process producing the instructed quantity of the selected blended formulation; and publishing an anticipated date of completion based on the predicted completion date plus the predicted margin of time.

117. The method of any of claims 112 to 116, further comprising: sending instructions to improve production of one or more components of the list of components needed to produce the deficit of the selected blended formulation to a process controllers.

118. The method of claim 117, wherein sending instructions to improve production includes changing one or more of operating temperature, pressure, and feed rate of a feedstock.

119. The method of claims 117 or 118, wherein sending instructions to improve production includes changing one or more of operating temperature, pressure, and feed rate of a feedstock to increase production of a first product of a process over a second product of the process.

120. The method of claim 119, wherein the first product has an property value different from an property value of a second product of the process.

121. The method of any of claims 102 to 120, further comprising receiving instructions regarding a list of a plurality of potential blended formulations.

122. The method of any of claims 102 to 120, wherein the blended formulation is for a gasoline blend, wherein the product property includes one or more of Reid vapor pressure (“RVP”) at different temperatures, olefin concentration, oxygenate concentration, benzene concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, sulfur concentration, mercaptan sulfur, gum concentration, oxidation stability, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control, and density.

123. The method of any of claims 102 to 122, wherein the blended formulation is for a jet fuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, viscosity, energy content, anti-icing capabilities, static dissipation, and corrosion inhibition.

124. The method of any of claims 102 to 123, wherein the blended formulation is for a diesel fuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, and corrosion inhibition.

125. The method of any of claims 102 to 124, wherein the blended formulation is for a fuel oil blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, lubricity, NOx emission factor, viscosity, energy content, and corrosion inhibition.

126. The method of any of claims 102 to 125, wherein the blended formulation is for a biofuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, corrosion inhibition, Reid vapor pressure (“RVP”) at different temperatures, olefin oxygenate concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, mercaptan sulfur, gum concentration, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, or blend volatility control.

127. The method of any of claims 102 to 126, wherein the blended formulation is for an asphalt blend, wherein the product property includes one or more of penetration point deviation, softening point deviation, sulfur concentration, polymer-modified asphalt performance, oxidation stability, high-temperature viscosity, storage stability, elastic recovery, rutting resistance, fatigue crack resistance, thermal cracking resistance, weather durability, density, and load bearing performance.

128. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 102 to 127.

129. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 102 to 127.

130. A system configured for optimizing blend properties in a refinery operation to achieve target specifications, the system comprising: a plurality of refinery equipment configured to produce a hydrocarbon product; a plurality of sensors for measuring one or more measured parameters associated with the plurality of refinery equipment; one or more sample collection assemblies for collecting samples of a fluid associated with the plurality of refinery equipment and the hydrocarbon product produced via the plurality of refinery equipment; one or more sample analysis assemblies for analyzing one or more collected samples to provide one or more collected properties of the one or more collected samples; one or more product pool sources; one or more tank monitoring modules for measuring one or more achieved properties of one or more product pools in one or more tanks being filled; one or more upstream property modules for calculating one or more target properties of upstream refinery equipment based on one or more remaining tank volumes; a means for analyzing the one or more measured parameters; and a means for calculating at least one parameter of the fluid based on the one or more measured parameters to enhance the blends for the one or more product pools.

131. The system of claim 130, wherein the one or more product pool sources include one or more of jet, diesel, gasoline, naphtha, or asphalt.

132. The system of any of claims 130 or 131, further comprising a means for determining deviations from target values based on the one or more collected properties of the one or more collected samples and the one or more achieved properties of the one or more product pools.

133. The system of any of claims 130 to 132, further comprising at least one refinery operation control device.

134. The system of claim 133, wherein the at least one refinery operation control device is positioned proximate to and downstream or upstream of one of the plurality of refinery equipment.

135. The system of claims 133 or 134, wherein the at least one refinery operation control device is configured to control aspects of the fluid flowing to the plurality of refinery equipment.

136. The system of claim 135, wherein the aspects of the fluid flowing to the plurality of refinery equipment include at least one of flow rate, pressure, temperature, or composition.

137. The system of any of claims 130 to 136, wherein the plurality of refinery equipment comprises at least one of a distillation unit, a hydrotreating unit, a hydrocracking unit, or a blending unit.

138. The system of any of claims 130 to 137, wherein the plurality of sensors comprises at least one of a temperature sensor, a pressure sensor, a flow sensor, or a composition sensor.

139. The system of any of claims 130 to 138, wherein the one or more sample collection assemblies are configured to collect samples at one or more locations selected from a group consisting of an inlet of the plurality of refinery equipment, an outlet of the plurality of refinery equipment, and an intermediate location within the plurality of refinery equipment.

140. The system of any of claims 130 to 139, wherein the one or more sample analysis assemblies are configured to determine at least one property selected from a group consisting of a density, a viscosity, a sulfur concentration, a cetane number, and a flash point of the one or more collected samples.

141. The system of any of claims 130 to 140, further comprising a data processing unit configured to:aggregate and analyze measured parameters from the plurality of sensors and the one or more collected properties of the one or more collected samples from the one or more sample analysis assemblies; compute optimized targets for the one or more product pools using predictive modeling and historical data trends; dynamically adjust refinery operation control devices based on deviations from predefined quality specifications; provide near real-time feedback to operators for manual intervention when necessary; and ensure compliance with regulatory and performance constraints through automated enforcement mechanisms.

142. The system of claim 141, wherein the data processing unit is further configured to determine optimized targets for the one or more product pools based on at least one of cost- efficiency, performance, or compliance with specifications.

143. The system of claims 141 or 142, wherein the data processing unit is further configured to adjust refinery operation control devices to meet the optimized target.

144. The system of any of claims 141 to 143, wherein the data processing unit is configured to dynamically update optimized targets based on near real-time data.

145. The system of any of claims 141 to 144, wherein the data processing unit is further configured to adjust the one or more target properties for one refinery unit based on rundown results from at least one other refinery unit to achieve an average flash target for the one or more product pools.

146. The system of any of claims 141 to 145, wherein the data processing unit is configured to determine the optimized targets using at least one of a linear programming model, a non-linear programming model, or a machine learning model, each tailored to dynamic refinery conditions.

147. The system of any of claims 130 to 146, wherein the system is configured to enhance the blends for the one or more product pools in near real-time, with a latency ofless than 5 seconds, based on the one or more measured parameters, the one or more collected properties of the one or more collected samples, and the one or more achieved properties of the one or more product pools.

148. The system of any of claims 130 to 147, wherein the system is configured to continuously monitor and adjust the blends for the one or more product pools based on changes in the one or more measured parameters, the one or more collected properties of the one or more collected samples, and the one or more achieved properties of the one or more product pools.

149. The system of any of claims 130 to 148, wherein the system is configured to optimize the blends for the one or more product pools to meet a predefined set of specifications, dynamically updated by one or more of the system or manually input by an operator.

150. The system of claim 149, wherein the predefined set of specifications comprises at least one of a cetane number, a sulfur concentration, a density, a viscosity, or a flash point of the one or more product pools.

151. The system of any of claims 130 to 150, wherein the one or more product pools comprises at least one of a diesel blending pool, a jet fuel blending pool, a gasoline blending pool, an asphalt blending pool, and a naphtha blending pool.

152. The system of any of claims 130 to 151, further comprising Al-assisted blending mechanisms configured to recommend pathways for achieving product specifications, including adjusting one or more of fractionator cut points or blending streams.

153. The system of any of claims 130 to 152, wherein an achieved flash point for the one or more product pools in the one or more tanks being filled is monitored periodically or continuously to adjust upstream processing parameters in near real-time.

154. The system of any of claims 130 to 153, wherein the system is configured to adjust an upstream processing parameters of a first refinery unit based on one or more of flashpoint measurements or rundown results from a second refinery unit to achieve a desired overall pool target.

155. The system of any of claims 130 to 154, wherein the system is configured to calculate and enforce constraints for jet fuel optimization, including maintaining a predefined jet pool flash point limit.

156. The system of any of claims 130 to 155, wherein blending jet fuel into diesel is achieved by one or more of adjusting a cut point on a fractionator or by mixing a separate stream.

157. The system of any of claims 130 to 156, further comprising a disturbance variable monitor configured to identify external factors impacting system performance.

158. The system of claim 157, further comprising a feedback mechanism that is configured to adjust one or more of refinery operation control devices, upon identifying external factors impacting system performance.

159. The system of any of claims 130 to 158, wherein the system is configured to achieve a pool flash point target by dynamically redistributing feed rates among multiple refinery units based on near real-time performance data.

160. The system of any of claims 130 to 159, wherein the system is further configured to optimize jet pool flash point coordination across multiple columns by analyzing performance metrics specific to individual column capacities.

161. The system of any of claims 130 to 160, wherein the system predicts flash point blending behavior of two or more fluid sources using non-linear modeling to refine mixture predictions for enhanced optimization.

162. The system of any of claims 130 to 161, wherein economic optimization includes balancing diesel and jet production based on near real-time market conditions for maximum profitability.

163. The system of any of claims 130 to 162, wherein disturbance variables provide predictive control insights by identifying external changes impacting system operations and proactively adjusting control settings.

164. The system of any of claims 130 to 163, wherein each of the plurality of sensors is positioned at one of (a) proximate to one of the plurality of refinery equipment or (b) within one of the plurality of refinery equipment.

165. The system of any of claims 130 to 164, wherein the refinery equipment includes at least one of one or more columns, one or more fractionators, or one or more distillation towers.

166. The system of any of claims 130 to 165, wherein the fluid samples are collected from the refinery equipment.

167. The system of any of claims 130 to 166, wherein the fluid samples are collected using one or more sample collection assemblies.

168. A method for enhancing blends of a hydrocarbon product for a one or more product pools in a refinery operation, the method comprising: measuring parameters with one or more sensor packages; collecting and / or analyzing fluid samples to determine measured properties; monitoring one or more achieved properties; generating one or more property targets for one or more upstream refinery units; and dynamically adjusting one or more functions of the one or more refinery units.

169. The method of claim 168, wherein the method enables near real-time optimization of product quality and operational efficiency.

170. The method of any of claims 168 or 169, wherein the one or more functions include a feed rate or blending ratio.

171. The method of any of claims 168, 169, or 170, wherein the measured properties include at least one of density, viscosity, sulfur concentration, cetane number, or flash point at one or more locations of refinery equipment.

172. The method of any of claims 168 to 171, wherein the one or more achieved properties include flash points of a one or more product pools in a one or more tanks being filled.

173. The method of any of claims 168 to 172, wherein calculating the one or more property targets for the upstream refinery units includes calculating flash point targets.

174. The method of any of claims 168 to 173, wherein the one or more achieved properties are monitored in one or more storage tanks.

175. The method of claim 174, wherein a flash point targets are calculated based on remaining volume in one or more storage tanks.

176. The method of any of claims 168 to 175, wherein the one or more property targets include at least one of flow rate, pressure, temperature, or composition.

177. The method of any of claims 168 to 176, wherein dynamically adjusting the one or more functions of the one or more refinery units includes redistributing one or more feed rates among two or more of the refinery units.

178. The method of any of claims 168 to 177, further comprising adjusting the one or more property targets for the one or more upstream refinery units by analyzing near real-time sensor data, calculating deviations from predefined specifications, and determining corrective actions to align with operational goals.

179. The method of claim 178, wherein adjusting the one or more property targets is based on rundown results from another refinery unit to meet an average pool target.

180. The method of any of claims 168 to 179, further comprising enforcing one or more constraints on one or more functions of the one or more refinery units, wherein the constraints include predefined operational limits such as maximum flow rates, temperaturethresholds, or specific compositional tolerances, and are enforced through automated control systems integrated with near real-time monitoring data.

181. The method of claim 180, wherein the one or more constraints include maintaining predefined flash point limits.

182. The method of any of claims 168 to 181, wherein dynamically adjusting the one or more functions of the one or more refinery units includes adjusting one or more blending pathways.

183. The method of any of claims 168 to 182, wherein adjusting one or more blending pathways includes adjusting one or more of fractionator cut points or blending streams.

184. The method of any of claims 168 to 183, further comprising coordinating flash point adjustments across multiple columns to achieve a target jet pool flash point while compensating for varying column performance.

185. The method of any of claims 168 to 184, wherein economic considerations guide dynamic adjustments, factoring in market values of jet and diesel fuels for optimal profitability.

186. The method of any of claims 168 to 185, further comprising using non-linear blending models to predict flash point behavior of mixtures with improved accuracy.

187. The method of any of claims 168 to 186, further comprising leveraging disturbance variables to proactively adjust system parameters based on anticipated changes.

188. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 168 to 187.

189. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 168 to 187.

190. A method compri sing : receiving at a machine learning model a first sensor data from a plurality of sensor packages, wherein each sensor package is disposed to measure one or more process parameters of one of a plurality of duplicated processes or a product property of a product of one of the plurality of duplicated processes; accessing historical data of each of the plurality of duplicated processes and the products of the plurality of duplicated processes; predicting an adjustment to an operational parameter of one of a plurality of duplicated processes to improve one or more of the product property of the product of one of the plurality of duplicated processes, a production rate of the product of one of a plurality of duplicated processes, or a process cost based on one or more of the historical data, the first sensor data, or demand for the product of the products of the plurality of duplicated processes; and publishing the predicted adjustment.

191. The method of claim 190, wherein predicting an adjustment includes predicting an adjustment to each process of the plurality of duplicated processes to achieve an aggregated target property value of aggregated products from the plurality of duplicated processes.

192. The method of claims 190 and 201, wherein each adjustment is different.

193. The method of any of claims 190 to 192, wherein each process has different levels of equipment wear.

194. The method of any of claims 190 to 193, further comprising: receiving an instruction to implement the adjustment; and implementing the adjustment to the operational parameter of one of a plurality of duplicated processes.

195. The method of any of claims 190 to 194, further comprising: receiving at the machine learning model a second sensor data after the adjustment has been implemented from the plurality of sensor packages; determining what changes resulted from the adjustment; andretraining the machine learning model with the first sensor data and the second sensor data.

196. The method of any of claims 190 to 195, further comprising accessing weather data, wherein predicting an adjustment is further based on weather data.

197. The method of any of claims 190 to 196, wherein the adjustment is made to a process control algorithm of the one of a plurality of duplicated processes.

198. The method of any of claims 190 to 197, wherein publishing the predicted adjustment includes sending the predicted adjustment to a user.

199. The method of any of claims 190 to 198, wherein the demand for a blended formulation including the product of the products of the plurality of duplicated processes, wherein the blended formulation is for a gasoline blend, wherein the product property includes one or more of Reid vapor pressure (“RVP”) at different temperatures, olefin concentration, concentration content, benzene concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, sulfur concentration, mercaptan sulfur, gum concentration, oxidation stability, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control, and density.

200. The method of any of claims 190 or 199, wherein the demand for a blended formulation including the product of the products of the plurality of duplicated processes, wherein the blended formulation is for a jet fuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel bum quality, oxidative stability, viscosity, energy content, anti-icing capabilities, static dissipation, and corrosion inhibition.

201. The method of any of claims 190 to 200, wherein the demand for a blended formulation including the product of the products of the plurality of duplicated processes,wherein the blended formulation is for a diesel fuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, and corrosion inhibition.

202. The method of any of claims 190 to 201, wherein the demand for a blended formulation including the product of the products of the plurality of duplicated processes, wherein the blended formulation is for a fuel oil blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, lubricity, NOx emission factor, viscosity, energy content, and corrosion inhibition.

203. The method of any of claims 190 to 202, wherein the demand for a blended formulation including the product of the products of the plurality of duplicated processes, wherein the blended formulation is for a biofuel blend, wherein the product property includes one or more of aromatic concentration, olefin concentration, benzene concentration, sulfur concentration, density, pour point, cloud point, cetane number, cetane stability, water concentration, haze, flash point, flash point stability, flash point variability, freeze point, freeze point stability, freeze point variability, final smoke point, smoke point stability, particulate emissions, fuel burn quality, oxidative stability, diesel lubricity, NOx emission factor, viscosity, energy content, conductivity, ash content, red dye content (if applicable), Ramsbottom carbon residue, corrosion inhibition, Reid vapor pressure (“RVP”) at different temperatures, olefin oxygenate concentration, deposit formation potential, knock resistance index, long-term storage stability, aromatics concentration, vapor liquid ratio, vapor lock index, mercaptan sulfur, gum concentration, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control.

204. The method of any of claims 190 to 203, wherein the demand for a blended formulation including the product of the products of the plurality of duplicated processes, wherein the blended formulation is for an asphalt blend, wherein the product property includes one or more of penetration point deviation, softening point deviation, sulfur concentration, polymer-modified asphalt performance, oxidation stability, high- temperature viscosity, storage stability, elastic recovery, rutting resistance, fatigue crack resistance, thermal cracking resistance, weather durability, density, and load bearing performance.

205. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 190 to 204.

206. A computing system including a processor and a memory including instructions and a machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 190 to 204.

207. A system for using a machine learning model, comprising: a historical database of historical information; a training database including the historical information and process data, the training database used for one or more of initial or updated training of the machine learning model; and the machine learning model trained using the training database to analyze and improve specific processes, process controllers, and process interactions; wherein the information includes one or more of process data, incident information, information analysis, business information, demand planning, historical forecast information, historical pricing data, historical purchasing data, or process training information.

208. The system of claim 207, wherein the machine learning model receives refinery information, wherein the refinery information includes feedstock data indicative of a feedstock, wherein the feedstock data includes one or more of operating pressure data or operating temperature data of an upstream process that processed the feedstock.

209. The system of claims 207 or 208, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more processes or subprocesses.

210. The system of any of claims 208 to 209, wherein the feedstock data includes material composition data, wherein the material composition data describes material moving through one or more processes.

211. The system of claim 210, wherein the material composition data includes quantities or percentages of one or more of contaminants, reactants, sulfur, nitrogen, water, perchloroethylene, benzene, aromatics, olefins, butane, light naphtha, heavy naphtha, kerosene, jet fuel, diesel, fuel oil, and other specific types of hydrocarbons input, output, or moving through a process.

212. The system of any of claims 208 to 211, wherein the feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

213. The system of claim 212, wherein the feedstock process data is from a feedstock process controller.

214. The system of any of claims 212 to 213, wherein the feedstock process data is from a feedstock process.

215. The system of claim 214, wherein the feedstock process includes any process preceding a targeted process under review by the machine learning model.

216. The system of any of claims 214 to 215, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

217. The system of any of claims 215 to 216, wherein the machine learning model receives targeted process data indicative of a targeted process, wherein the targeted processdata includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data related to the targeted process.

218. The system of any of claims 215 to 217, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

219. The system of any of claims 215 to 218, wherein a targeted process data is received from one or more of a targeted process controller, directly from sensors, directly from sampling systems, directly from the testing systems, or from labs obtaining data from the targeted process.

220. The system of any of claims 207 to 219, wherein the machine learning model receives subsequent process data.

221. The system of claim 220, wherein the subsequent process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

222. The system of any of claims 220 to 221, wherein the subsequent process data includes one or more of subsequent process sensor data, subsequent process sample data, or subsequent process data.

223. The system of claim 222, wherein the subsequent process data is received from one or more of a subsequent process controller, directly from a sensor, directly from a sampling system, directly from a testing system, or from a lab.

224. The system of any of claims 207 to 223, wherein the machine learning model displays recommendations.

225. The system of any of claims 207 to 224, wherein the machine learning model provides data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

226. The system of any of claims 207 to 225, wherein the machine learning model has access to business data.

227. The system of any of claims 207 to 226, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

228. The system of any of claims 207 to 227, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

229. The system of any of claims 207 to 228, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

230. The system of any of claims 207 to 229, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

231. The system of any of claims 207 to 230, wherein the machine learning model uses the business data to generate a process adjustment for a process to increase a potential profit of a product of the process.

232. The system of any of claims 207 to 231, wherein the machine learning model accesses lab data.

233. The system of claim 232, wherein the lab data is obtained from laboratory analysis of samples collected from one or more refinery processes or one or more products produced by the one or more refinery processes.

234. The system of any of claims 207 to 233, wherein the machine learning model sends instructions to an engineering gateway.

235. The system of any of claims 207 to 234, wherein the machine learning model receives instructions from an engineering gateway.

236. The system of claim 235, wherein the engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

237. The system of any of claims 235 to 236, wherein a user may use the engineering gateway to assist the machine learning model in training, refining, and tuning the machine learning model to improve predictions or one or more processes.

238. The system of any of claims 235 to 237, wherein a user may use the engineering gateway to improve machine learning generated predictions or adjust one or more operating parameters of one or more processes in response to changes in one or more of ambient weather, demand seasonality, composition of feedstocks, or property of feedstocks.

239. The system of any of claims 235 to 238, wherein the engineering gateway is used to facilitate active learning by the machine learning model.

240. The system of any of claims 208 to 239, wherein the feedstocks include crude oil received for processing into refined hydrocarbons.

241. The system of any of claims 225 to 240, wherein the machine learning model identifies changes to an algorithm used by one or more of the feedstock process controller, the targeted process controller, or the subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

242. The system of claim 241 , wherein the machine learning model adjusts the algorithm based on the identified changes.

243. The system of any of claims 241 to 242, wherein adjusting the algorithm is performed by the machine learning model without user input.

244. The system of claim 242, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through the engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of the approval information, the machine learning model saves a copy of the approval information in the historical data and / or sends the approved adjusted algorithm to the targeted process controller; and the machine learning model implements the adjusted algorithm.

245. The system of any of claims 207 to 244, further comprising: analyzing one or more of a data set or a data set to be processed; and identifying an outlier and generating a processed data set.

246. The system of claim 245, wherein the processed data set excludes the identified outlier.

247. The system of any of claims 245 to 246, wherein the processed data set includes a flag for the identified outlier.

248. The system of any of claims 245 to 247, further comprising publishing one or more of the identified outlier for user review.

249. The system of any of claims 245 to 248, wherein the machine learning model receives user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

250. The system of any of claims 245 to 249, wherein the machine learning model interpolates one or more missing data from the data set to be processed to an interpolated data set, using an interpolation module.

251. The system of any of claims 207 to 250, wherein the machine learning model compares at least a portion of the historical data with one or more of feedstock data, targeted process data, or subsequent process data to generate a compared data set.

252. The system of claim 251, wherein the machine learning model identifies at least one process change from the compared data set.

253. The system of any of claims 251 to 252, wherein the machine learning model identifies one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

254. The system of any of claims 251 to 253, wherein the machine learning model predicts one or more of at least one component that will wear out within a remaining wear period, at least one catalyst that deactivate within a remaining deactivation period, or at least one catalyst will become poisoned within a remaining poisoned period.

255. The system of any of claims 251 to 254, wherein the machine learning model stores one or more of an identified process change, an identified miscalibrated sensor, an identified misprocessed sample, an identified inaccurate test data, an identified failed component, an identified remaining wear period, an identified deactivation state of a catalyst, or an identified catalysts remaining predicted useful period in the compared data set.

256. The system of any of claims 251 to 255, wherein the machine learning model publishes at least a portion of the compared data set.

257. The system of any of claims 207 to 256, wherein the machine learning model adjusts an operating parameter without user input.

258. The system of any of claims 207 to 257, wherein the machine learning model stores one or more of a data set to be processed, an interpolated data set, or a compared data set.

259. The system of claim 258, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of the training data or the historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

260. The system of any of claims 207 to 259, wherein the machine learning model analyzes one or more of a feedstock sensor data, a feedstock sample data, a feedstock process data, a targeted process sensor data, a targeted process sample data, a targeted process data, a subsequent process sensor data, a subsequent process sample data, or a subsequent process data to predict one or more changes in one or more processes.

261. The system of any of claims 207 to 260, wherein the machine learning model analyzes data to predict one or more changes is performed using a prediction module.

262. The system of any of claims 207 to 261, wherein the machine learning model analyzes data to predict one or more changes includes predicting temperature excursions in one or more processes.

263. The system of claim 262, wherein the machine learning model notifies a user of the predicted one or more changes.

264. The system of any of claims 262 to 263, wherein a user is notified of the predicted one or more changes using an engineering gateway.

265. The system of any of claims 260 to 263, wherein the machine learning model generates a process change based on the predicted one or more changes.

266. The system of claim 265, wherein the machine learning model applies the process change automatically without user input or based on an instruction from the user.

267. The system of any of claims 265 to 266, wherein a machine learning model is granted authority to automatically make a process change that falls within a predetermined range of process operating parameters.

268. The system of any of claims 265 to 267, wherein a machine learning model is not granted authority to automatically make a process change that falls outside of a predetermined range of process operating parameters.

269. The system of any of claims 265 to 268, wherein a user approves the process change using a engineering gateway.

270. The system of any of claims 207 to 269, wherein the machine learning model identifies one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

271. The system of claim 270, wherein the machine learning model notifies a user of the one or more identified maintenance procedures.

272. The system of any of claims 270 to 271, wherein the machine learning model notifies a user of a recommended maintenance window for the one or more identified maintenance procedures based on one or more of historical data and sensor package data.

273. The system of any of claims 270 to 272, wherein the machine learning model receives confirmation the one or more identified maintenance procedures have been completed and saves data related to the confirmation the one or more identified maintenance procedures.

274. The system of any of claims 207 to 272, wherein the machine learning model includes a communication module, wherein the communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

275. The system of any of claims 207 to 274, wherein the machine learning model publishes one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

276. The system of any of claims 207 to 275, wherein the machine learning model communicates with one or more process controllers and / or other refinery models.

277. The system of any of claims 207 to 276, wherein the machine learning model receives user feedback on the analysis and recommendations of the machine learning model.

278. The system of any of claims 207 to 277, wherein the machine learning model is retrained on user feedback.

279. The system of any of claims 207 to 278, wherein the machine learning model assigns a confidence level to one or more of the analysis or recommendation of the machine learning model.

280. The system of any of claims 207 to 279, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

281. The system of any of claims 207 to 280, wherein the machine learning model publishes one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

282. The system of any of claims 207 to 281, wherein the machine learning model: accesses business data to information; and generates regulatory constraints for products and processes.

283. The system of any of claims 207 to 282, wherein the machine learning model adjusts process control algorithms with regulatory constraints and publishing the adjusted process control algorithms for user review.

284. The system of any of claims 207 to 283, wherein the machine learning model predicts one or more processes to be non-compliant in a compliance period, and publishing the predicted non-compliant one or more processes to a user.

285. The system of any of claims 207 to 284, wherein the machine learning model flags one or more processes that is predicted by a prediction module to move out of compliance.

286. The system of any of claims 207 to 285, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

287. The system of any of claims 207 to 286, wherein the machine learning model identifies one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

288. The system of any of claims 207 to 287, wherein the machine learning model requests user permission to adjust a blending pool constraints in line with upcoming regulatory changes.

289. The system of any of claims 207 to 288, wherein the machine learning model implements changes to one or more blending pool controllers to adjust blending parameters in line with upcoming regulatory changes.

290. The system of any of claims 207 to 289, wherein one or more blending pool controllers include one or more of gasoline blending pool controllers, diesel blending pool controllers, jet fuel blending pool controllers, asphalt pool blending controllers, fuel oil blending controllers, and bio fuel blending controllers.

291. The system of any of claims 207 to 290, wherein a regulatory module makes recommendations for one or more process controllers to adjust parameters to promote production of one or more blend components based on one or more of current demand or predicted demand and compliance with regulatory changes.

292. The system of any of claims 207 to 291, wherein the machine learning model includes a forecasting module.

293. The system of any of claims 207 to 292, wherein a forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

294. The system of any of claims 207 to 293, wherein a forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

295. The system of any of claims 207 to 294, wherein a forecasting module forecasts pricing for one or more blend components based on one or more of the historical data or the business data and publishes the forecasted pricing via a communication module to an engineering gateway.

296. The system of any of claims 207 to 295, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

297. The system of any of claims 207 to 296, wherein an authority module considers a recommendation from one or more modules of the machine learning model.

298. The system of any of claims 207 to 297, wherein an authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

299. The system of any of claims 207 to 298, wherein an authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

300. A system for enhancing pooled fluid production for refining operations, the system comprising:a plurality of refining equipment each configured with refining equipment parameter settings to perform a refining sub-operation of a refinery operation on a flow of feedstock thereto; a plurality of sensors to measure a sensor parameter associated with the plurality of refining equipment and each one of the plurality of sensors positioned at one of (a) proximate one of the plurality of refining equipment or (b) within one of the plurality of refining equipment; a plurality of refining operation control devices, each one of the plurality of refining operation control devices positioned proximate one of the plurality of the refining equipment and being either downstream or upstream thereof and having refining operation control parameters to control the refining operation on either the flow of feedstock flowing to one of the plurality of refining equipment or a product flowing from one of the plurality of refining equipment; a plurality of sample collection assemblies to collect samples of the feedstock and products associated with each of the plurality of refining equipment; a plurality of one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; a plurality of operation controllers, each one of the plurality of operation controllers in signal communication with one or more of a plurality of subsets of the plurality of refining equipment, one or more of a plurality of subsets of the plurality of sensors, one or more of a plurality of subsets of the plurality of refining operations control devices, and the plurality of sample analysis assemblies, and each of the plurality of operation controllers including: a plurality of predictive control circuitries each storing one or more selected models, the plurality of predictive control circuitries configured to: determine a pooled output based on application of data from two or more of the plurality of subsets of the plurality of refining equipment, two or more of the plurality of subsets of the plurality of sensors, two or more of the plurality of subsets of the plurality of refining operation control devices, and target products and corresponding properties to the corresponding one or more selected models, and a local enhancement circuity storing a machine learning model and configured to: in response to reception of the pooled output from one or more of the plurality of predictive control circuitries, determine two or more target setpoints based on application of the output and the data from one or more of the two or moreof the plurality of subsets of the plurality of refining equipment, the two or more of the plurality of subsets of the plurality of sensors, the two or more of the plurality of subsets of the plurality of refining operation control devices to the corresponding one or more selected models, a plurality of equipment and device controllers, each of the equipment and device controllers in signal communication with the local enhancement circuitry and configured to: in response to a determination of two or more target setpoints, adjust the two or more of the plurality of subsets of the plurality of refining equipment and the two or more of the plurality of subsets of the plurality of refining operation control devices to the two or more target setpoints.

301. The system of claim 300, wherein data utilized to train each trained machine learning model stored in each of the plurality of operation controllers comprises historical data produced by a corresponding subset of the plurality of refining equipment, historical data measured by a corresponding subset of the plurality of sensors, and analysis of fluid flowing to and from the corresponding subset of the plurality of refining equipment from the plurality of sample analysis assemblies.

302. The system of claim 300, wherein the plurality of refining equipment comprises two or more of a fluid catalytic cracking (FCC) unit, a regenerator corresponding to the FCC unit, one or more hydrocracker, a fractionation column, a distillation column, a reformer, an alkylation unit, an isomerization unit, one or more hydrotreater, a desalter, one or more tanks, a blending unit, one or more heat exchangers, a solvent deasphalting unit, a residuum oil supercritical extraction unit, boilers, hydrodeoxygenation process units, a propylene splitter, an absorber, an aromatics recovery unit, a sulfur recovery unit, or a coker unit.

303. The system of claim 300, wherein the fluid comprises a hydrocarbon fluid, and wherein the fluid produced by the refining operations comprises a transportation fuel and transportation fuel by-products, and wherein the transportation fuel comprises one or more of gasoline, diesel, low sulfur diesel, ultra-low sulfur diesel, or jet.

304. The system of claim 300, wherein the sample analysis assembly comprises one or more of a spectrographic analyzer or a chromatographic analyzer.

305. The system of claim 300, wherein each of the plurality of operation controllers is in signal communication with the plurality of sample collection assemblies and is further configured to initiate collection of samples by the plurality of sample collection assemblies via a signal indicative of collection of a selected fluid.

306. The system of claim 300, wherein the refinery operation comprises a continuous operation, wherein each of the plurality of operation controllers determines the predicted properties and parameters on a continuous or substantially continuous and near real-time basis, and wherein the operation controller and each of a plurality of sub-controllers perform adjustments in near real-time.

307. A system for enhancing fluid production for a fluid catalytic cracking (FCC) operation, the system comprising: a FCC unit configured to crack a feedstock via a combination of temperature, pressure, and catalyst; a regenerator in fluid communication with the FCC unit, to receive coked catalyst from the FCC unit, regenerate the coked catalyst, and to provide regenerated catalyst to the FCC unit; a plurality of sensors to measure a parameter associated with the FCC unit and the regenerator and each positioned at one of (a) proximate one of the FCC unit or the regenerator or (b) within one of the FCC unit and the regenerator and; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the FCC unit and the regenerator and to control an amount of fluid or catalyst flowing to or from one of the FCC unit and the regenerator; a plurality of sample collection assemblies to collect two or more samples of the fluid or catalyst associated with each of the FCC unit and the regenerator; a plurality of sample analysis assemblies to analyze the two or more collected sample to provide properties of the two or more collected samples; and a FCC controller in signal communication with the FCC unit, the regenerator, the plurality of sensors, the plurality of refinery operation control devices, and the plurality of sample analysis assemblies, and storing a trained machine learning model, the FCC controller configured to: determine predicted properties of the feedstock,determine an output including parameter settings of the plurality of refinery operation control devices, the FCC unit, and the regenerator based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the plurality of refinery operation control devices, the FCC unit, and the regenerator based on the output to enhance production of cracked fluid.

308. A system for enhancing fluid production for a multi distillation operation, the system comprising: a first distillation column to receive a first feedstock and separate the first feedstock into a first plurality of fluids; a second distillation column to receive a second feedstock and separate the second feedstock into a second plurality of fluids; a plurality of sensors to measure a parameter associated with one or more of the first distillation column or the second distillation column, the plurality of sensors positioned at one of (a) proximate the first distillation column or the second distillation column, (b) proximate the first distillation column and within the second distillation column, (c) proximate the second distillation column and within the first distillation column, or (b) within the first distillation column or the second distillation column; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the first distillation column and the second distillation column to control aspects of one or more of a first fluid or a second fluid flowing to or from one or more of the first distillation column and the second distillation column; a plurality of sample collection assemblies to collect samples of the first fluid associated with the first distillation column and the second fluid associated with the second distillation column; a plurality of sample analysis assemblies to analyze each collected sample to provide properties of the collected samples; a distillation controller in signal communication with one or more of the first distillation column or the second distillation column, the plurality of sensors, the pluralityof refinery operation control devices, and the plurality of sample analysis assemblies, and storing a trained machine learning model, the distillation controller configured to: determine a pooled output from the first distillation column and the second distillation column including predicted properties of the first feedstock, predicted properties of the second feedstock, and parameter settings of the plurality of refinery operation control devices, the first distillation column, and the second distillation column based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of (a) a first amount of the first feedstock or type of first feedstock and first parameters associated with the refinery operation control device and the first distillation column and (b) a second amount of the second feedstock or type of second feedstock and second parameters associated with the refinery operation control device and the second distillation column based on the pooled output to enhance production of the first plurality of fluids and the second plurality of fluids.

309. A system for enhancing fluid production for dual hydrotreatments, the system comprising: a first hydrotreater to receive a first feedstock and refine the first feedstock into a first refined feedstock; a second hydrotreater to receive a second feedstock and refine the second feedstock into a second refined feedstock; a plurality of sensors to measure a parameter associated with one or more of the first hydrotreater or the second hydrotreater and the plurality of sensors positioned at one of (a) proximate the first hydrotreater and the second hydrotreater, (b) proximate the first hydrotreater and within the second hydrotreater, (c) proximate the second hydrotreater and within the first hydrotreater, or (d) within the first hydrotreater and the second hydrotreater; a plurality of refinery operation control devices positioned (a) proximate and downstream or upstream of the first hydrotreater and (b) proximate and downstream or upstream of the second hydrotreater to control aspects of fluid flowing to or from the first hydrotreater or the second hydrotreater;a plurality sample collection assemblies to collect samples of (a) a first fluid associated with the first hydrotreater and (b) a second fluid associated with the second hydrotreater; a plurality sample analysis assemblies to analyze each collected sample to provide properties of the collected samples; a hydrotreater controller in signal communication with one or more of the first hydrotreater and the second hydrotreater, the plurality of sensors, the plurality of refinery operation control devices, and the plurality of sample analysis assemblies, and storing a trained machine learning model, the hydrotreater controller configured to: determine a pooled output including predicted properties of the first feedstock, predicted properties of the second feedstock, and parameter settings of the plurality of refinery operation control devices, the first hydrotreater, and the second hydrotreater based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of (a) a first amount of the first feedstock or type of first feedstock and first parameters associated with the refinery operation control device and the first hydrotreater and (b) a second amount of the second feedstock or type of second feedstock and second parameters associated with the refinery operation control device and the second hydrotreater based on the pooled output to enhance production of the first refined feedstock and the second refined feedstock.

310. A system for enhancing reformate production for a dual reformer operation, the system comprising: a first reformer to receive a first feedstock and reform the first feedstock into first reformate, first hydrogen, and other first gasses; a second reformer to receive a second feedstock and reform the second feedstock into second reformate, second hydrogen, and other second gasses; a plurality of sensors to measure a parameter associated with one or more of the first reformer or the second reformer, the plurality of sensors positioned at one of (a) proximate the first reformer and the second reformer, (b) proximate the first reformer and within the second reformer, (c) proximate the second reformer and within the first reformer, or (d) within the first reformer and the second reformer;a plurality of refinery operation control devices each positioned (a) proximate and downstream or upstream of the first reformer and (b) proximate and downstream or upstream of the second reformer to control aspects of fluid flowing to or from the first reformer or the second reformer; a plurality of sample collection assemblies to collect samples of (a) a first fluid associated with the reformer and (b) a second fluid associated with the second reformer; a plurality of sample analysis assemblies to analyze each collected sample to provide properties of the collected samples; and a reformer controller in signal communication with one or more of the first reformer or the second reformer, the plurality of sensors, the plurality of refinery operation control devices, and the plurality of one or more sample analysis assemblies, and storing a trained machine learning model, the reformer controller configured to: determine a pooled output including predicted properties of the first feedstock, predicted properties of the second feedstock, and parameter settings of the plurality of refinery operation control devices, the first reformer, and the second reformer based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of (a) a first amount of (a) the first feedstock or type of first feedstock and first parameters associated with the refinery operation control device and the first reformer and (b) a second amount of the second feedstock or type of second feedstock and second parameters associated with the refinery operation control device and the second reformer based on the pooled output to enhance production of the first reformate, the second reformate, the first other gasses, and the second other gasses.

311. A system for enhancing alkylate production for a dual alkylation operation, the system comprising: a first alkylation unit to receive a first feedstock and produce a first alkylate; a second alkylation unit to receive a second feedstock and produce a second alkylate; a plurality of sensors to measure a parameter associated with one or more of the first alkylation unit or the second alkylation unit, the plurality of sensors positioned at oneof (a) proximate the first alkylation unit and the second alkylation unit, (b) proximate the first alkylation unit and within the second alkylation unit, (c) proximate the second alkylation unit and within the first alkylation unit, or (d) within the first alkylation unit and the second alkylation unit; a plurality of refinery operation control devices each positioned (a) proximate and downstream or upstream of the first alkylation unit and (b) proximate and downstream or upstream of the second alkylation unit to control aspects of fluid flowing to or from the first alkylation unit or the second alkylation unit; a plurality of sample collection assemblies to collect samples of (a) a first fluid associated with the first alkylation unit and (b) a second fluid associated with the second alkylation unit; a plurality of sample analysis assemblies to analyze each collected sample to provide properties of the collected samples; and an alkylation controller in signal communication with one or more of the first alkylation unit or the second alkylation unit, the plurality of sensors, the plurality of refinery operation control devices, and the plurality of sample analysis assemblies, and storing a trained machine learning model, the alkylation controller configured to: determine a pooled output including predicted properties of the first feedstock, predicted properties of the second feedstock, and parameter settings of the plurality of refinery operation control devices, the first alkylation unit, and the alkylation unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of (a) a first amount of (a) the first feedstock or type of first feedstock and first parameters associated with the refinery operation control device and the first alkylation unit and (b) a second amount of the second feedstock or type of second feedstock and second parameters associated with the refinery operation control device and the second alkylation unit based on the output to enhance production of the first alkylate and the second alkylate.

312. A system for enhancing isomerate production for a dual isomerization operation, the system comprising: a first isomerization unit to receive a first feedstock and produce a first isomerate;a second isomerization unit to receive a second feedstock and produce a second isomerate; a plurality of sensors to measure a parameter associated with one or more of the first isomerization unit or the second isomerization unit, the plurality of sensors positioned at one of (a) proximate the first isomerization unit and the second isomerization unit, (b) proximate the first isomerization unit and within the second isomerization unit, (c) proximate the second isomerization unit and within the first isomerization unit, or (d) within the first isomerization unit and the second isomerization unit; a plurality of refinery operation control devices each positioned (a) proximate and downstream or upstream of the first isomerization unit and (b) proximate and downstream or upstream of the second isomerization unit to control aspects of fluid flowing to or from the first isomerization unit or the second isomerization unit; a plurality of sample collection assemblies to collect samples of (a) a first fluid associated with the first isomerization unit and (b) a second fluid associated with the second isomerization unit; a plurality of sample analysis assemblies to analyze each collected sample to provide properties of the collected samples; and an isomerization controller in signal communication with one or more of the first isomerization unit or the second isomerization unit, the plurality of sensors, the plurality of refinery operation control devices, and the plurality of sample analysis assemblies, and storing a trained machine learning model, the isomerization controller configured to: determine a pooled output including predicted properties of the first feedstock, predicted properties of the second feedstock, and parameter settings of the plurality of refinery operation control devices, the first isomerization unit, and the second isomerization unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of (a) a first amount of the first feedstock or type of first feedstock and first parameters associated with the refinery operation control device and the first isomerization unit and (b) a second amount of the second feedstock or type of second feedstock and second parameters associated with the refinery operation control device and the second isomerization unit based on the output to enhance production of the first isomerate and the second isomerate.

313. A system for enhancing fluid production for a dual coker operation, the system comprising: a first coker unit and a second coker unit each having a plurality of coke drums to receive heavy distillate or other fluids and each of the plurality of coke drums configured with refining equipment parameter settings to convert the heavy distillate or other fluids; a plurality of sensors to measure a parameter associated with the first coker unit and the second coker unit, the plurality of sensors positioned at one of (a) proximate the first coker unit and the second coker unit, (b) proximate the first coker unit and within the second coker unit, (c) proximate the second coker unit and within the first coker unit, or (d) within the first coker unit and the second coker unit; a plurality of refinery operation control devices each positioned (a) proximate and downstream or upstream of the first coker unit and (b) proximate and downstream or upstream of the second coker unit to control aspects of fluid flowing to or from the first coker unit or the second coker unit; a plurality of sample collection assemblies to collect samples of (a) a first fluid associated with the first coker unit and (b) a second fluid associated with the second coker unit; a plurality of sample analysis assemblies to analyze each collected sample to provide properties of the collected samples; and a coker controller in signal communication with one or more of the first coker unit or the second coker unit, the plurality of sensors, the plurality of refinery operation control devices, and the plurality of sample analysis assemblies, and storing a trained machine learning model, the coker controller configured to: determine a pooled output including predicted properties of the heavy distillate or other fluids of the first coker unit and the second coker unit and parameter settings of the plurality of refinery operation control devices, the first coker unit, and the second coker unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the plurality of sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of (a) a first amount of heavy distillate or other fluids or type of heavy distillate or other fluids of the first coker unit and (b) a second amount of heavy distillate or other fluids or type of heavy distillate or other fluids of thesecond coker unit and parameters associated with the refinery operation control device and the second coker unit based on the output to enhance production of the first fluid from the first coker unit and the second fluid from the second coker unit.

314. A system for enhancing aromatics recovery for an aromatics recovery operation, the system comprising: an aromatics recovery unit to receive a feedstock and capture aromatics within the feedstock; a plurality of sensors to measure a parameter associated with the aromatics recovery unit and each positioned at one of (a) proximate the aromatics recovery unit or (b) within the aromatics recovery unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the aromatics recovery unit and to control aspects of fluid flowing to or from the aromatics recovery unit; one or more sample collection assemblies to collect samples of the fluid associated with the aromatics recovery unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and an aromatics recovery controller in signal communication with the aromatics recovery unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the aromatics recovery controller configured to: determine an output including predicted properties of the feedstock, and parameter settings of the refinery operation control device and the aromatics recovery unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the refinery operation control device and aromatics recovery unit based on the output to enhance capture of aromatics.

315. A system for enhancing sulfur recovery for a sulfur recovery operation, the system comprising:a sulfur recovery unit to receive a feedstock and capture sulfur within the feedstock; a plurality of sensors to measure a parameter associated with the sulfur recovery unit and each positioned at one of (a) proximate the sulfur recovery unit or (b) within the sulfur recovery unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the sulfur recovery unit and to control aspects of fluid flowing to or from the sulfur recovery unit; one or more sample collection assemblies to collect samples of the fluid associated with the sulfur recovery unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a sulfur recovery controller in signal communication with the sulfur recovery unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the sulfur recovery controller configured to: determine an output including predicted properties of the feedstock, and parameter settings of the refinery operation control device and the sulfur recovery unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the refinery operation control device and sulfur recovery unit based on the output to enhance capture of sulfur.

316. A system for enhancing fluid production for a solvent deasphalting (SDA) operation, the system comprising: a SDA unit to receive a feedstock and produce a fluid; a plurality of sensors to measure a parameter associated with the SDA unit and each positioned at one of (a) proximate the SDA unit or (b) within the SDA unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the SDA unit and to control aspects of fluid flowing to or from the SDA unit;one or more sample collection assemblies to collect samples of the fluid associated with the SDA unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a SDA controller in signal communication with the SDA unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the SDA controller configured to: determine an output including predicted properties of the feedstock, and parameter settings of the refinery operation control device and the SDA unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the refinery operation control device and SDA unit based on the output to enhance the production of fluid from the SDA unit.

317. A system for enhancing fluid production for an enhanced supercritical solvent deasphalting operation, the system comprising: a supercritical solvent deasphalting unit to receive a feedstock and produce a fluid; a plurality of sensors to measure a parameter associated with the supercritical solvent deasphalting unit and each positioned at one of (a) proximate the supercritical solvent deasphalting unit or (b) within the supercritical solvent deasphalting unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the supercritical solvent deasphalting unit and to control aspects of fluid flowing to or from the supercritical solvent deasphalting unit; one or more sample collection assemblies to collect samples of the fluid associated with the supercritical solvent deasphalting unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a supercritical solvent deasphalting controller in signal communication with the supercritical solvent deasphalting unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing atrained machine learning model, the supercritical solvent deasphalting controller configured to: determine an output including predicted properties of the feedstock, and parameter settings of the refinery operation control device and the supercritical solvent deasphalting unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the refinery operation control device and supercritical solvent deasphalting unit based on the output to enhance the production of fluid from the supercritical solvent deasphalting unit.

318. A system for enhancing fluid production for a blending operation, the system comprising: a blending unit to receive a plurality of feedstock and produce a blended fluid; a plurality of sensors to measure a parameter associated with the blending unit and each positioned at one of (a) proximate a supercritical solvent deasphalting unit or (b) within the blending unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the blending unit and to control aspects of fluid flowing to or from the blending unit; one or more sample collection assemblies to collect samples of the fluid associated with the blending unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a blending controller in signal communication with the blending unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the blending controller configured to: determine an output including predicted properties of the feedstock, and parameter settings of the refinery operation control device and the blending unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies,or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the refinery operation control device and blending unit based on the output to enhance the production of fluid from the blending unit.

319. A system for enhancing fluid production for a propylene splitter operation, the system comprising: a propylene splitter unit to receive a feedstock and produce a fluid; a plurality of sensors to measure a parameter associated with the propylene splitter unit and each positioned at one of (a) proximate the propylene splitter unit or (b) within the propylene splitter unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the propylene splitter unit and to control aspects of fluid flowing to or from the propylene splitter unit; one or more sample collection assemblies to collect samples of the fluid associated with the propylene splitter unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a propylene splitter controller in signal communication with the propylene splitter unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the propylene splitter controller configured to: determine an output including predicted properties of the feedstock, and parameter settings of the refinery operation control device and the propylene splitter unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feedstock or type of feedstock and parameters associated with the refinery operation control device and propylene splitter unit based on the output to enhance the production of fluid from the propylene splitter unit.

320. A system for enhancing utilization of steam for a refinery operation, the system comprising: one or more heat sources to produce steam; a plurality of refinery equipment to utilize the steam for the refinery operation; a plurality of sensors to measure a parameter associated with the one or more heat sources and the plurality of refinery equipment and each positioned at one of (a) proximate one of the one or more heat sources and the plurality of refinery equipment or (b) within one of the one or more heat sources and the plurality of refinery equipment; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the one or more heat sources and the plurality of refinery equipment and to control aspects of fluid flowing to or from the one of the one or more heat sources and the plurality of refinery equipment; one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a steam controller in signal communication with the one or more heat sources, the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the steam controller configured to: determine an output including predicted parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust an amount of steam produced by the one or more heat sources and an amount of steam provided to each of the plurality of refinery equipment.

321. A system for enhancing utilization of hydrogen for a refinery operation, the system comprising: one or more hydrogen sources; a plurality of refinery equipment to utilize the hydrogen for the refinery operation; a plurality of sensors to measure a parameter associated with the one or more hydrogen sources and the plurality of refinery equipment and each positioned at one of (a)proximate one of the one or more hydrogen sources and the plurality of refinery equipment or (b) within one of the one or more hydrogen sources and the plurality of refinery equipment; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the one or more hydrogen sources and the plurality of refinery equipment and to control aspects of fluid flowing to or from the one of the one or more hydrogen sources and the plurality of refinery equipment; one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a hydrogen controller in signal communication with the one or more hydrogen sources, the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the hydrogen controller configured to: determine an output including predicted parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust an amount of hydrogen produced by the one or more hydrogen sources and an amount of hydrogen provided to each of the plurality of refinery equipment.

322. A system for enhancing utilization and blends of feed for a refinery operation, the system comprising: one or more feed sources; a plurality of refinery equipment to utilize the feed for the refinery operation; a plurality of sensors to measure a parameter associated with the one or more feed sources and the plurality of refinery equipment and each positioned at one of (a) proximate one of the one or more feed sources and the plurality of refinery equipment or (b) within one of the one or more feed sources and the plurality of refinery equipment; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the one or more feed sources and the plurality of refineryequipment and to control aspects of fluid flowing to or from the one of the one or more feed sources and the plurality of refinery equipment; one or more sample collection assemblies to collect samples of the feed and the fluid associated with the plurality of refinery equipment; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a feed controller in signal communication with the one or more feed sources, the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the feed controller configured to: determine an output including predicted properties of a selected feed parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount or blend of feed provided to each of the plurality of refinery equipment.

323. A system for enhancing blends for a gasoline pool for a refinery operation, the system comprising: a plurality of refinery equipment to produce gasoline via the refinery operation; a plurality of sensors to measure a parameter associated with the plurality of refinery equipment and each positioned at one of (a) proximate one of the plurality of refinery equipment or (b) within one of the plurality of refinery equipment; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the plurality of refinery equipment and to control aspects of fluid flowing to the plurality of refinery equipment; one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment and the gasoline produced via the plurality of refinery equipment; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a gasoline pool controller in signal communication with the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one ormore sample analysis assemblies, and storing a trained machine learning model, the gasoline pool controller configured to: determine an output including predicted properties of gasoline for a selected gasoline pool and parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount or blend of gasoline to achieve properties associated with the selected gasoline pool.

324. A system for enhancing blends for a diesel pool for a refinery operation, the system comprising: a plurality of refinery equipment to produce diesel via the refinery operation; a plurality of sensors to measure a parameter associated with the plurality of refinery equipment and each positioned at one of (a) proximate one of the plurality of refinery equipment or (b) within one of the plurality of refinery equipment; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of one of the plurality of refinery equipment and to control aspects of fluid flowing to the plurality of refinery equipment; one or more sample collection assemblies to collect samples of the fluid associated with the plurality of refinery equipment and the diesel produced via the plurality of refinery equipment; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a diesel pool controller in signal communication with the plurality of refinery equipment, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the diesel pool controller configured to: determine an output including predicted properties of diesel for a selected diesel pool and parameter settings of the plurality of refinery operation control devices, based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysisassemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount or blend of diesel to achieve properties associated with the selected diesel pool.

325. A system for enhancing C3 and heavier hydrocarbon production for an absorber operation, the system comprising: an absorber unit to receive a feed and produce a or C3 and heavier hydrocarbon; a plurality of sensors to measure a parameter associated with the absorber unit and each positioned at one of (a) proximate the absorber unit or (b) within the absorber unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the absorber unit and to control aspects of fluid flowing to or from the absorber unit; one or more sample collection assemblies to collect samples of the fluid associated with the absorber unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and an absorber controller in signal communication with the absorber unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the absorber controller configured to: determine an output including predicted properties of the feed, and parameter settings of the refinery operation control device and the absorber unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feed or type of feed and parameters associated with the refinery operation control device and absorber unit based on the output to enhance production of the C3 and heavier hydrocarbons.

326. A system for enhancing fluid production for a hydrocracker operation, the system comprising:A hydrocracker unit to receive a feed and produce one or more fluids;a plurality of sensors to measure a parameter associated with the hydrocracker unit and each positioned at one of (a) proximate the hydrocracker unit or (b) within the hydrocracker unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the hydrocracker unit and to control aspects of fluid flowing to or from the hydrocracker unit; one or more sample collection assemblies to collect samples of the fluid associated with the hydrocracker unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a hydrocracker controller in signal communication with the hydrocracker unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the hydrocracker controller configured to: determine an output including predicted properties of the feed, and parameter settings of the refinery operation control device and the hydrocracker unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feed or type of feed and parameters associated with the refinery operation control device and hydrocracker unit based on the output to enhance fluid production.

327. A system for enhancing fluid production for a gasoline desulfurization operation, the system comprising: a gasoline desulfurization unit to receive a feed and produce one or more fluids; a plurality of sensors to measure a parameter associated with the gasoline desulfurization unit and each positioned at one of (a) proximate the gasoline desulfurization unit or (b) within the gasoline desulfurization unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the gasoline desulfurization unit and to control aspects of fluid flowing to or from the gasoline desulfurization unit;one or more sample collection assemblies to collect samples of the fluid associated with the gasoline desulfurization unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a gasoline desulfurization controller in signal communication with the gasoline desulfurization unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the gasoline desulfurization controller configured to: determine an output including predicted properties of the feed, and parameter settings of the refinery operation control device and the gasoline desulfurization unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an the amount of feed or type of feed and parameters associated with the refinery operation control device and gasoline desulfurization unit based on the output to enhance fluid production.

328. A system for enhancing fluid production for a hydrodeoxygenation (HDO) operation, the system comprising: a HDO unit to receive a feed and produce one or more fluids; a plurality of sensors to measure a parameter associated with the HDO unit and each positioned at one of (a) proximate the HDO unit or (b) within the HDO unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the HDO unit and to control aspects of fluid flowing to or from the HDO unit; one or more sample collection assemblies to collect samples of the fluid associated with the HDO unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a HDO controller in signal communication with the HDO unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the HDO controller configured to:determine an output including predicted properties of the feed, and parameter settings of the refinery operation control device and the HDO unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, and adjust one or more of an amount of feed or type of feed and parameters associated with the refinery operation control device and HDO unit based on the output to enhance fluid production.

329. A system for enhancing fluid production for a resid destruction operation, the system comprising: a resid destruction unit to receive a feed and produce one or more fluids; a plurality of sensors to measure a parameter associated with the resid destruction unit and each positioned at one of (a) proximate the resid destruction unit or (b) within the resid destruction unit; a plurality of refinery operation control devices each positioned proximate and downstream or upstream of the resid destruction unit and to control aspects of fluid flowing to or from the resid destruction unit; one or more sample collection assemblies to collect samples of the fluid associated with the resid destruction unit; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples; and a resid destruction controller in signal communication with the resid destruction unit, the plurality of sensors, the plurality of refinery operation control devices, and the one or more sample analysis assemblies, and storing a trained machine learning model, the resid destruction controller configured to: determine an output including predicted properties of the feed, and parameter settings of the refinery operation control device and the resid destruction unit based on application of one or more of (i) data measured by the plurality of sensors, (ii) data corresponding to analysis from the one or more sample analysis assemblies, or (iii) a target product and corresponding target properties to the trained machine learning model, andadjust one or more of an amount of feed or type of feed and parameters associated with the refinery operation control device and resid destruction unit based on the output to enhance fluid production.

330. A controller to enhance pooled fluid production of a refining operation, the controller comprising: a first plurality of inputs each in signal communication with one of a plurality of sensors to measure a set of first parameters associated with aspects of a refining operation and on or more refining sub-operations; a second plurality of inputs each in signal communication with one or more analyzers to analyze and provide properties of samples of fluids input to and output from each of a plurality of refining equipment; a first plurality of inputs / outputs each in signal communication with one of the plurality of refining equipment, the controller configured to receive a set of second parameters associated with each of the plurality of refining equipment and to transmit instructions and selected parameters to cause each of the plurality of refining equipment to operate at the selected parameters; a second plurality of inputs / outputs each in signal communication with one of a plurality of sub -controllers each configured to control one of the plurality of refining sub- operations, the controller configured to: apply one or more of the set of first parameters and one or more of the set of second parameters to a trained machine learning model, and determine an adjusted two or more of (a) one or more inputs, (b) one or more intermediaries, or (c) one or more operating parameters based on application of data received from the plurality of sensors, the one or more analyzers, the plurality of refining equipment, and the plurality of sub-controllers; and adjust, via the sub-controllers, a type and amount of refining equipment fluid inputs and refining equipment parameters based on the adjusted one or more inputs, intermediaries, or operating parameters.

331. A method for enhancing pooled fluid production of a refining operation, the method comprising:obtaining data substantially continuously for a plurality of ongoing and continuous refining operations in near real-time from one or more of (a) a plurality of sensors or (b) a plurality analyzers; determining one or more parameters for each of one or more devices or one or more refining equipment based at least in part on application of corresponding data to a corresponding machine learning model of a plurality of machine learning models at a first selected time interval; adjusting two or more of the one or more devices or one or more refining equipment based at least in part on the one or more parameters; determining an updated value for each of the one or more parameters based at least in part on application to an operations machine learning model at a second selected time interval of one or more of (a) a pooled output from each of the plurality of machine learning models, (b) current pooled product data, (c) an actual product output and pooled product properties of the refining operations, (d) a predicted amount and properties of pooled product output from the refining operations, or (e) target pooled product properties; and adjusting each of the one or more devices or one or more refining equipment based at least in part on a difference between the updated value for each of the one or more parameters and current parameters for the one or more devices or one or more refining equipment.

332. The method of claim 331, wherein the data includes one or more of (a) a type of and properties related to inputs of one of the plurality of ongoing pooled refining operations, (b) a pooled product of one of the plurality of ongoing refining operations, (c) an pooled output of one of the plurality of ongoing refining operations, or (d) analysis of inputs and pooled outputs for one or more of the plurality of ongoing refining operations.

333. The method of claim 331, wherein the plurality of machine learning models comprise trained machine learning models, wherein the trained machine learning models each comprise a neural network, wherein training of one or more of the trained machine learning models comprises: obtaining historical data corresponding to a selected refining operation and each particular unit utilized in the selected refining operation at a selected plant, normalizing the historical data, removing data corresponding to abnormal operations from the historical data,removing undesired data, training one of the trained machine learning models with a selected percentage of the historical data, testing the one of the trained machine learning models with a remaining percentage of historical data, and transmitting a resulting trained machine learning model to a corresponding one or more controllers; and wherein the historical data comprises properties and analysis input and output from each particular unit, parameters for corresponding devices, and a pooled outcome.

334. The method of claim 333, wherein the outcome includes one or more of an actual pooled outcome of the selected refining operation or a desired pooled outcome of the selected refining operation.

335. The method of claim 331, wherein the second selected time interval comprises an amount of time greater than an amount of time associated with the first selected time interval.

336. The method of claim 331, wherein the data from the one or more analyzers comprises a spectrum indicating chemical properties of a sampled fluid.

337. The method of claim 331, wherein each of the plurality of machine learning models corresponds to a refining suboperation, and wherein the refining suboperations include one or more of hydrocracking, reforming, alkylation, isomerization, hydrotreating, distillation, or blending.

338. A method for enhancing control of a dual fluid catalytic cracking operation, the method comprising: supplying a first hydrocarbon feedstock to one or more first processing units associated with a petroleum refining operation, the first hydrocarbon feedstock having one or more first hydrocarbon feedstock properties and the one or more first processing units including one or more first fractionation units; analyzing a first hydrocarbon feedstock sample via one or more analyzers to provide first hydrocarbon feedstock sample properties;supplying a second hydrocarbon feedstock to one or more second processing units associated with a petroleum refining operation, the second hydrocarbon feedstock having one or more second hydrocarbon feedstock properties and the one or more second processing units including one or more second fractionation units; analyzing a second hydrocarbon feedstock sample via one or more analyzers to provide second hydrocarbon feedstock sample properties; operating the one or more processing units to produce one or more first unit materials, the one or more first unit materials having one or more first unit materials properties, and the one or more first unit materials comprising one or more of first intermediate materials or first unit product materials; analyzing the first unit material sample via the one or more analyzers to provide first unit material sample properties; operating the one or more processing units to produce one or more second unit materials, the one or more second unit materials having one or more second unit materials properties, and the one or more second unit materials comprising one or more of second intermediate materials or second unit product materials; analyzing the second unit material sample via the one or more analyzers to provide second unit material sample properties; predicting one or more pooled hydrocarbon sample properties associated with two or more of (aa) the first hydrocarbon feedstock sample based on (a) the first hydrocarbon feedstock sample properties and (b) a first pooled output from application of the first hydrocarbon feedstock sample properties; or predicting one or more pooled unit material sample properties associated with the first unit material sample based on the first unit material sample properties and a second pooled output from application of the first unit material sample properties to a trained machine learning model; and controlling, during the petroleum refining operation, based at least in part on the predicted one or more pooled hydrocarbon sample properties and the one or more pooled unit material sample properties, two or more of:(a) one or more hydrocarbon feedstock properties associated with the first hydrocarbon feedstock supplied to the one or more first processing units;(b) one or more hydrocarbon feedstock properties associated with the second hydrocarbon feedstock supplied to the one or more second processing unit;(c) one or more first intermediate properties associated with the first intermediate materials produced by the one or more first processing units;(d) one or more second intermediate properties associated with the second intermediate materials produced by the one or more second processing units;(e) one or more first unit product materials properties associated with the first unit product materials;(f) one or more second unit product materials properties associated with the second unit product materials; or(g) operation of the one or more first processing units, so that the controlling, during the petroleum refining operation, causes the petroleum refining operation to produce one or more oi) one or more first intermediate materials each having one or more first properties within a range of one or more first pooled target properties of the one or more first intermediate materials,(ii) one or more second intermediate materials each having one or more second properties within a range of one or more second pooled target properties of the one or more second intermediate materials,(iii) one or more first unit product materials each having one or more first properties within a range of one or more first pooled target properties of the one or more first unit product materials,(iv) one or more second unit product materials each having one or more second properties within a range of one or more second pooled target properties of the one or more second unit product materials,(v) one or more first downstream materials each having one or more first properties within a range of one or more first pooled target properties of the one or more first downstream materials, or(vi) one or more second downstream materials each having one or more second properties within a range of one or more second pooled target properties of the one or more second downstream materials, thereby to cause the petroleum refining operation to achieve material pooled outputs that more accurately and responsively converge on one or more of the first pooled target properties or the second pooled target properties.

339. The method of claim 338, wherein the one or more analyzers provide a spectra indicative of fluid properties, the one or more analyzers being calibrated to generate standardized spectral responses.

340. The method of claim 338, wherein the one or more analyzers comprise one or more of a spectroscopic analyzer or a chromatographic analyzer.

341. The method of claim 338, wherein one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock comprises a blended hydrocarbon feedstock including a plurality of hydrocarbon feedstocks from respective hydrocarbon feedstock flows; and the controlling of one or more of the one or more first hydrocarbon feedstock properties associated with the first hydrocarbon feedstock supplied to the one or more first processing units or the one or more second hydrocarbon feedstock properties associated with the second hydrocarbon feedstock supplied to the one or more second processing units comprises controlling feed ratios of the respective hydrocarbon feedstock flows.

342. The method of claim 338, wherein controlling one or more of (a) the one or more first intermediate properties associated with the first intermediate materials, (b) the one or more second intermediate properties associated with the second intermediate materials, (c) the one or more first unit product materials properties associated with the first unit product materials, or (d) the one or more second unit product materials properties associated with the second unit product materials, comprises: controlling one or more of: (i) content of one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock, or (ii) operation of one or more of the one or more first processing units or the one or more second processing units.

343. The method of claim 338, wherein one or more of:(a) the predicting of the one or more hydrocarbon feedstock properties comprises predicting a boiling point associated with one or more of the first hydrocarbon feedstock sample or the second hydrocarbon feedstock sample, and the method further comprises controlling, based at least in part on the boiling point associated with one or more of the first hydrocarbon feedstock sample or the second hydrocarbon feedstock sample, operation of one or more of the one or more first processing units or the one or more second processing units; or(b) the predicting of one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises predicting one or more of a first boiling point associated with the first unit material sample or a secondboiling point associated with the second unit material sample, and the method further comprises controlling, based at least in part on one or more of the first boiling point associated with the first unit material sample or the second boiling point associated with the second unit material sample, operation of one or more of the one or more first processing units or the one or more second processing units.

344. The method of claim 338, further comprising controlling content of the one or more downstream materials via control of one or more of:(a) content of one or more of the first hydrocarbon feedstock supplied to the one or more first processing units or the second hydrocarbon feedstock supplied to the one or more second processing units;(b) the operation of the one or more first processing units;(c) content of one or more of the first intermediate materials produced by the one or more first processing units or the second intermediate materials produced by the one or more second processing units;(d) content of the unit product materials; and(e) the operation of the one or more second processing units.

345. The method of claim 338, wherein the controlling comprises controlling one or more operation parameters, the one or more operation parameters comprising one or more of:(a) a flow rate of one or more of the first hydrocarbon feedstock supplied to the one or more first processing units or the second hydrocarbon feedstock supplied to the one or more second processing units;(b) a pressure of one or more of the first hydrocarbon feedstock supplied to the one or more first processing units or the second hydrocarbon feedstock supplied to the one or more second processing unit; and(c) a preheating temperature of one or more of the first hydrocarbon feedstock supplied to the one or more first processing units or the second hydrocarbon feedstock supplied to the one or more second processing units.

346. The method of claim 338, wherein one or more of:(a) predicting the one or more pooled hydrocarbon sample properties comprises predicting a boiling point associated with one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock; or(b) predicting the one or more pooled unit material sample properties further comprises predicting a boiling point associated with one or more of the one or more first unit materials or the one or more second unit materials.

347. The method of claim 346, further comprising controlling, based at least in part on one or more of (a) the boiling point associated with one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock or (b) the boiling point associated with one or more of the one or more first unit materials or the one or more second unit materials, operation of one or more of the one or more first fractionation units or the one or more second fractionation units.

348. The method of claim 346, further comprising predicting, based at least in part on one or more of (a) the boiling point associated with one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock or (b) the boiling point associated with one or more of the one or more first unit materials or the one or more second unit materials, a yield fraction associated with one or more of the one or more first unit materials or the one or more second unit materials.

349. The method of claim 338, wherein predicting the one or more pooled hydrocarbon sample properties comprises predicting one or more properties associated with desalter crude water, and the method further comprises controlling, based at least in part on the properties associated with the desalter crude water, operation of an upstream desalter unit.

350. The method of claim 338, wherein: at least one of the one or more first processing units or the one or more second processing units comprises an atmospheric distillation unit; and one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of: API gravity, paraffin concentration, aromatic concentration, naphthenic concentration, distillation points, Coker gas oil content, carbon residue, nitrogen concentration, sulfur concentration, saturates concentration, thiophene concentration, single-ring aromatics concentration, dual-ring aromatics concentration, triple-ring aromatics concentration, or quad-ring aromatics concentration.

351. The method of claim 338, wherein one or more of the one or more first hydrocarbon feedstock sample properties or the one or more second hydrocarbon feedstock sample properties and one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprise a content ratio indicative of relative amounts of one or more hydrocarbon classes present in one or more of (a) the pooled hydrocarbon sample or (b) the pooled unit material sample.

352. The method of claim 338, wherein one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of: an amount of butane-free gasoline, an amount of total butane, an amount of dry gas, an amount of coke, an amount of gasoline, octane rating, an amount of light fuel oil, an amount of heavy fuel oil, an amount of hydrogen sulfide, an amount of sulfur in light fuel oil, or an aniline point of light fuel oil.

353. The method of claim 338, wherein: one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of: pentane concentration, raw crude water concentration, desalted crude water concentration, heavy atmospheric gas oil (HAGO) concentration, light atmospheric gas oil (LAGO) flash, or kerosene flash point; and the method further comprises controlling, based at least in part on the one or more of the pentane concentration, the raw crude water concentration, the desalted crude water concentration, the heavy atmospheric gas oil (HAGO) concentration, the light atmospheric gas oil (LAGO) flash, or the kerosene flash point, one or more of: crude blend, make-up water, desalter severity, HAGO wash rate, stripping, LAGO draw rate, stripping steam, or kerosene draw of the one or more of the first processing units.

354. The method of claim 338, wherein: one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of: ethaneconcentration, propane concentration, propene concentration, isobutane concentration, or n-butane concentration; and the method further comprises controlling, based at least in part on the one or more of the ethane concentration, the propane concentration, the propene concentration, the isobutane concentration, or the n-butane concentration, one or more of: absorber pressure, lean oil flow rate, lean oil temperature, high-pressure separator temperature, reactor conversion, or stripper reboiler duty.

355. The method of claim 338, wherein: one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of high-pressure separator water concentration or stripper bottoms water concentration; and the method further comprises controlling, based at least in part on the one or more of the high-pressure separator water concentration or the stripper bottoms water concentration, a temperature of a high-pressure separator.

356. A distillation unit control assembly to enhance control of a refining operation associated with a petroleum refining operation, the distillation unit control assembly comprising:(a) a first analyzer positioned to:(i) receive a first hydrocarbon feedstock sample of a first hydrocarbon feedstock supplied to one or more first processing units associated with the petroleum refining operation, the one or more first processing units comprising one or more fractionation units; and(ii) analyze the first hydrocarbon feedstock sample to provide first hydrocarbon feedstock sample properties;(b) a second analyzer positioned to:(i) receive a first unit material sample of one more first unit materials produced by the one or more first processing units, the one or more first unit materials comprising one or more of first intermediate materials or first unit product materials, and(ii) analyze the first unit material sample to provide first unit material sample properties;(c) a third analyzer positioned to:(i) receive a second hydrocarbon feedstock sample of a second hydrocarbon feedstock supplied to one or more second processing units associated with the petroleum refining operation, the one or more second processing units comprising one or more fractionation units; and(ii) analyze the second hydrocarbon feedstock sample to provide second hydrocarbon feedstock sample properties;(d) a fourth analyzer positioned to:(i) receive a second unit material sample of one more second unit materials produced by the one or more second processing units, the one or more second unit materials comprising one or more of second intermediate materials or second unit product materials, and(ii) analyze the second unit material sample to provide second unit material sample properties;(e) an operations controller in communication with the first analyzer, the second analyzer, the third analyzer, and the fourth analyzer, the operations controller configured to:(i) predict one or more pooled hydrocarbon sample properties associated with two or more of (aa) the first hydrocarbon feedstock sample based on the first hydrocarbon feedstock sample properties and application of the first hydrocarbon feedstock sample properties to a trained machine learning model and (bb) the second hydrocarbon feedstock sample based on the second hydrocarbon feedstock sample properties and application of the second hydrocarbon feedstock sample properties to the trained machine learning model; or(ii) predict one or more pooled hydrocarbon sample properties associated with two or more of (aa) the first hydrocarbon feedstock sample based on the first hydrocarbon feedstock sample properties and application of the first hydrocarbon feedstock sample properties to the trained machine learning model and (bb) the first unit material sample based on the first unit material sample properties and application of the first unit material sample properties to the trained machine learning model; or(iii) predict one or more pooled unit material sample properties associated with (aa) the first unit material sample based on the first unit material sample properties and application of the first unit material sample properties to the trained machine learning model and (bb) the second hydrocarbon feedstock sample basedon the second hydrocarbon feedstock sample properties and application of the second hydrocarbon feedstock sample properties to the trained machine learning model; or(iv) predict one or more pooled unit material sample properties associated with (aa) the first unit material sample based on the first unit material sample properties and application of the first unit material sample properties to a second trained machine learning model and (bb) the second unit material sample based on the second unit material sample properties and application of the second unit material sample properties to the second trained machine learning model; and(v) control, during the refining operation, based at least in part on the predicted one or more pooled hydrocarbon sample properties or the predicted one or more pooled unit material sample properties, two or more of:(aa) one or more hydrocarbon feedstock parameters associated with the first hydrocarbon feedstock supplied to the one or more first processing units;(bb) one or more hydrocarbon feedstock parameters associated with the second hydrocarbon feedstock supplied to the one or more second processing units;(cc) the one or more hydrocarbon feedstock properties associated with the first hydrocarbon feedstock supplied to the one or more first processing units;(dd) the one or more hydrocarbon feedstock properties associated with the second hydrocarbon feedstock supplied to the one or more first processing units;(ee) one or more intermediate properties associated with the first intermediate materials produced by the one or more first processing units;(ff) one or more intermediate properties associated with the second intermediate materials produced by the one or more first processing units;(gg) one or more first unit materials properties associated with the one or more first unit materials;(hh) one or more second unit materials properties associated with the one or more second unit materials;(ii) operation of the one or more first processing units; or(jj) operation of one or more second processing units positioned downstream relative to the one or more first processing units, so that controlling during the refining operation causes the refining operation to produce two or more of:(aa) one or more first intermediate materials each having one or more first properties within a selected range of one or more first target properties of the one or more first intermediate materials;(bb) one or more second intermediate materials each having one or more second properties within a selected range of one or more second target properties of the one or more second intermediate materials;(cc) one or more first unit materials each having one or more first properties within a selected range of one or more first target properties of the one or more first unit materials;(dd) one or more second unit materials each having one or more second properties within a selected range of one or more second target properties of the one or more second unit materials;(ee) one or more first downstream materials each having one or more first properties within a selected range of one or more first target properties of the one or more first downstream materials; or(ff) one or more second downstream materials each having one or more second properties within a selected range of one or more second target properties of the one or more second downstream materials, thereby to cause the refining operation to achieve material seconds that more accurately and responsively converge on one or more of the target properties.

357. The distillation unit control assembly of claim 356, wherein: one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock comprises a blended hydrocarbon feedstock including a plurality of hydrocarbon feedstocks from respective hydrocarbon feedstock flows; and the operations controller is configured to control feed ratios of the respective hydrocarbon feedstock flows.

358. The distillation unit control assembly of claim 356, wherein the operations controller is configured to control one or more of: (i) content of one or more of the firsthydrocarbon feedstock or the second hydrocarbon feedstock, or (ii) operation of one or more of the one or more first processing units or the one or more second processing units.

359. The distillation unit control assembly of claim 356, wherein one or more of the first analyzer, the second analyzer, the third analyzer, or the fourth analyzer comprises one or more of a near-infrared spectroscopic analyzer, a mid-infrared spectroscopic analyzer, a combination of a near-infrared spectroscopic analyzer and a mid-infrared spectroscopic analyzer, a Raman spectroscopic analyzer, a nuclear magnetic resonance spectroscopic analyzer, or a chromatographic analyzer.

360. The distillation unit control assembly of claim 356, wherein one or more of:(a) the analyze one or more of the first hydrocarbon feedstock sample or the second hydrocarbon feedstock sample is performed on-line and in near real-time;(b) the analyze one or more of the first hydrocarbon feedstock sample or the second hydrocarbon feedstock sample is performed off-line in a laboratory;(c) the analyze one or more of the first unit material sample or the second unit material sample is performed on-line and in near real-time; or(d) the analyze one or more of the first unit material sample or the second unit material sample is performed off-line in a laboratory setting.

361. The distillation unit control assembly of claim 356, wherein the operations controller is configured to control one or more of:(a) content of one or more of the first hydrocarbon feedstock supplied to the one or more first processing units or the second hydrocarbon feedstock supplied to the one or more second processing units;(b) content of one or more of the first intermediate materials produced by the one or more first processing units or the second intermediate materials produced by the one or more second processing units;(c) operation of the one or more first processing units;(d) content of one or more of the first unit product materials or the second unit product materials; or(e) operation of the one or more second processing units.

362. The distillation unit control assembly of claim 356, wherein the operations controller is configured to improve an accuracy of one or more of:(a) the one or more first hydrocarbon feedstock sample properties associated with the first hydrocarbon feedstock sample;(b) the one or more second hydrocarbon feedstock sample properties associated with the second hydrocarbon feedstock sample;(c) the one or more first unit material sample properties associated with the first unit material sample;(d) the one or more second unit material sample properties associated with the second unit material sample;(f) content of the first hydrocarbon feedstock supplied to the one or more first processing units;(g) content of the second hydrocarbon feedstock supplied to the one or more second processing units;(h) content of the one or more first intermediate materials produced by the one or more first processing units;(i) content of the one or more second intermediate materials produced by the one or more second processing units;(j) content of the first unit product materials produced by the one or more first processing units;(k) content of the first downstream materials produced by the one or more of the first processing units;(l) content of the one or more second intermediate materials produced by the one or more second processing units;(m) content of the one or more second intermediate materials produced by the one or more second processing units;(n) content of the second unit product materials produced by the one or more second processing units; or(o) content of the second downstream materials produced by the one or more of the second processing units.

363. The distillation unit control assembly of claim 356, wherein the operations controller is configured to control one or more of a first temperature of the first hydrocarbon feedstock sample, a second temperature of the second hydrocarbon feedstock sample, a firsttemperature of the first unit material sample, or a second temperature of the second unit material sample, thereby to substantially maintain the one or more of the first temperature of the first hydrocarbon feedstock sample, the second temperature of the second hydrocarbon feedstock, the first temperature of the first unit material sample, or the second temperature of the second unit material sample within a respective temperature range.

364. The distillation unit control assembly of claim 356, wherein the operations controller is configured to control one or more operation parameters, the one or more operation parameters comprising one or more of:(a) a first flow rate of the first hydrocarbon feedstock supplied to the one or more first processing units;(b) a second flow rate of the second hydrocarbon feedstock supplied to the one or more second processing units;(c) a first pressure of the first hydrocarbon feedstock supplied to the one or more first processing units;(d) a second pressure of the second hydrocarbon feedstock supplied to the one or more second processing units;(e) a first preheating temperature of the first hydrocarbon feedstock supplied to the one or more first processing units; or(f) a second preheating temperature of the second hydrocarbon feedstock supplied to the one or more second processing units.

365. The distillation unit control assembly of claim 356, wherein one or more of:(a) the predict the one or more pooled hydrocarbon feedstock sample properties comprises one or more of predicting a first boiling point associated with the first hydrocarbon feedstock;(b) the predict the one or more pooled hydrocarbon feedstock sample properties comprises one or more of predicting a second boiling point associated with the second hydrocarbon feedstock;(c) the predict the one or more pooled unit material sample properties comprises predicting a first boiling point associated with the one or more first unit materials; or(d) the predict the one or more pooled unit material sample properties comprises predicting a second boiling point associated with the one or more second unit materials.

366. The distillation unit control assembly of claim 365, wherein the distillation unit control assembly is configured to control, based at least in part on one or more of (a) the first boiling point associated with the first hydrocarbon feedstock, (b) the second boiling point associated with the second hydrocarbon feedstock, (c) the first boiling point associated with the one or more first unit materials, or (b) the second boiling point associated with the one or more second unit materials, operation of an atmospheric distillation unit.

367. The distillation unit control assembly of claim 365, wherein the operations controller is configured to predict a yield fraction associated with the one or more first unit materials or the one or more second unit materials, based at least in part on one or more of(a) the first boiling point associated with the first hydrocarbon feedstock, (b) the second boiling point associated with the second hydrocarbon feedstock, (c) the first boiling point associated with the one or more first unit materials, or (d) the second boiling point associated with the one or more second unit materials.

368. The distillation unit control assembly of claim 356, wherein one or more of the first unit material sample or the second unit material sample comprises naphtha, and the operations controller is configured to control, based at least in part on one or more of a first boiling point of the naphtha or a second boiling point of the naphtha, one or more of:(a) downstream flows of one or more of: (i) first intermediate materials associated with the naphtha, second intermediate materials associated with the naphtha, (iii) first unit product materials associated with the naphtha, or (iv) second unit product materials associated with the naphtha;(b) downstream flows of one or more of: (i) first intermediate materials associated with distillates, (ii) second intermediate materials associated with distillates, (iii) third unit product materials associated with distillates, or (iv) fourth unit product materials associated with distillates;(c) a ratio of downstream flows associated with the naphtha to downstream flows associated with kerosene; or(d) operation of one or more naphtha strippers.

369. The distillation unit control assembly of claim 368, wherein the control of the operation of the one or more naphtha strippers comprises adjusting one or more hydrocarbon streams into the one or more naphtha strippers to improve flash.

370. The distillation unit control assembly of claim 356, wherein the predict the one or more pooled hydrocarbon sample properties comprises predicting one or more properties associated with desalter crude water, and the operations controller is configured to control, based at least in part on the one or more properties associated with the desalter crude water, operation of one or more upstream desalter units.

371. The distillation unit control assembly of claim 370, wherein the operations controller is configured to display, via a display, one or more of: (a) the one or more pooled hydrocarbon sample properties, or (b) the one or more pooled unit material sample properties.

372. The distillation unit control assembly of claim 366, wherein the control of operation of one or more of: (a) the one or more first processing units, or (b) the one or more second processing units, comprises: comparing one or more of: (a) the one or more first hydrocarbon feedstock sample properties, (b) the one or more second hydrocarbon feedstock sample properties, (c) the one or more first unit material sample properties, or (b) the one or more second unit material sample properties, to or more of:(i) material properties of a material database;(ii) one or more threshold values associated with operation of one or more of: (aa) the one or more first processing units, or (bb) the one or more second processing units; or(iii) target properties.

373. The distillation unit control assembly of claim 372, wherein the target properties comprise target content associated with one or more of:(a) content of the first hydrocarbon feedstock supplied to the one or more first processing units;(b) content of the first intermediate materials produced by one or more of the first processing units;(c) content of the first unit product materials produced by one or more of the first processing units;(d) content of the first downstream materials produced by one or more of the first processing units;(e) content of the second hydrocarbon feedstock supplied to the one or more second processing units;(f) content of the second intermediate materials produced by one or more of the second processing units;(g) content of the second unit product materials produced by one or more of the second processing units; or(h) content of the second downstream materials produced by one or more of the second processing units.

374. The distillation unit control assembly of claim 356, wherein: at least one of the one or more first processing units or the one or more second processing units comprises an atmospheric distillation unit; and one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprise one or more of:(a) a quantitative composition of a third hydrocarbon feedstock including a mixture of one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock;(b) densities and viscosities of products of the atmospheric distillation unit; or(c) one or more of: (i) paraffinic concentration or (ii) aromatic concentration, of products of the atmospheric distillation unit.

375. The distillation unit control assembly of claim 356, wherein: at least one of the one or more first processing units or the one or more second processing units comprises an atmospheric distillation unit; and one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprise one or more of: API gravity, paraffin concentration, aromatic concentration, naphthenic concentration, distillation points, Coker gas oil content, carbon residue, nitrogen concentration, sulfur concentration, saturates concentration, thiophene concentration, single-ring aromatics concentration, dual-ringaromatics concentration, triple-ring aromatics concentration, or quad-ring aromatics concentration.

376. The distillation unit control assembly of claim 356, wherein one or more of the one or more first hydrocarbon feedstock sample properties, the one or more second hydrocarbon feedstock sample properties, the one or more first unit material sample properties, and the one or more second unit material sample properties comprise a content ratio indicative of relative amounts of one or more hydrocarbon classes present in one or more of (a) the first hydrocarbon feedstock sample, (b) the second hydrocarbon feedstock sample, (c) the first unit material sample, or (c) the second unit material sample.

377. The distillation unit control assembly of claim 356, wherein one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprise one or more of: an amount of butane-free gasoline, an amount of total butane, an amount of dry gas, an amount of coke, an amount of gasoline, octane rating, an amount of light fuel oil, an amount of heavy fuel oil, an amount of hydrogen sulfide, an amount of sulfur in light fuel oil, or an aniline point of light fuel oil.

378. The distillation unit control assembly of claim 356, wherein: one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of: pentane concentration, raw crude water concentration, desalted crude water concentration, heavy atmospheric gas oil (HAGO) concentration, light atmospheric gas oil (LAGO) flash, or kerosene flash point; and the operations controller is configured to control, based at least in part on the one or more of the pentane concentration, the raw crude water concentration, the desalted crude water concentration, the heavy atmospheric gas oil (HAGO) concentration, the light atmospheric gas oil (LAGO) flash, or the kerosene flash point, one or more of: crude blend, make-up water, desalter severity, HAGO wash rate, stripping, LAGO draw rate, stripping steam, or kerosene draw of one or more of the one or more of the first processing units or the one or more of the second processing units.

379. The distillation unit control assembly of claim 356, wherein:one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of: ethane concentration, propane concentration, propene concentration, isobutane concentration, or n-butane concentration; and the operations controller is configured to control, based at least in part on the one or more of the ethane concentration, the propane concentration, the propene concentration, the isobutane concentration, or the n-butane concentration, one or more of: absorber pressure, lean oil flow rate, lean oil temperature, high-pressure separator temperature, reactor conversion, or stripper reboiler duty.

380. The distillation unit control assembly of claim 379, wherein: one or more of the one or more first unit material sample properties or the one or more second unit material sample properties comprises one or more of high-pressure separator water concentration or stripper bottoms water concentration; and the operations controller is configured to control, based at least in part on the one or more of the high-pressure separator water concentration or the stripper bottoms water concentration, a temperature of a high-pressure separator.

381. The distillation unit control assembly of claim 356, wherein:(a) one or more of the one or more first processing units or the one or more second processing units comprises an atmospheric distillation unit including an atmospheric column;(b) the operations controller is configured to control one or more of:(i) supplying one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock to the atmospheric column;(ii) separating, via the atmospheric column, one or more of the first hydrocarbon feedstock or the second hydrocarbon feedstock into a plurality of unit materials s;(iii) separating, via a side stripper, at least one of the plurality of unit materials s from the atmospheric column;(iv) separating one or more of the one or more first hydrocarbon feedstock samples or the one or more second hydrocarbon feedstock samples from one or more locations of the atmospheric column;(v) separating one or more of the one or more first unit material samples or the one or more second unit material samples from the at least one of the plurality of unit materials;(vi) analyzing, via one or more of the first analyzer, the second analyzer, or one or more additional analyzers, one or more of the one or more first intermediate samples or the one or more second intermediate samples;(vii) predicting, based at least in part in the analyzing one or more of the one or more first intermediate samples or the one or more second intermediate samples and application of analysis of one or more of the one or more first intermediate samples or the one or more second intermediate samples to the trained machine learning model, the one or more intermediate sample properties associated with the one or more intermediate samples;(viii) analyzing, via one or more of the first analyzer, the second analyzer, or the one or more additional analyzers, one or more of the one or more first unit material samples or the one or more second unit material samples; and(ix) predicting, based at least in part in the analyzing one or more of the one or more first unit material samples or the one or more second unit material samples and application of analysis of one or more of the one or more first unit material samples or the one or more second unit material samples to the trained machine learning model, one or more unit material sample properties associated with one or more of the one or more first unit material samples or the one or more second unit material samples; and(c) the control is based at least in part on one or more of: (i) one or more of the one or more first intermediate sample properties, (ii) the one or more second intermediate sample properties, (iii) the one or more first unit material sample properties, or (iv) the one or more second unit material sample properties.

382. The distillation unit control assembly of claim 381, wherein the operations controller is configured to control supply of one or more of the plurality of unit materials to a saturated gas unit associated with the atmospheric distillation unit.

383. The distillation unit control assembly of claim 381, wherein the atmospheric distillation unit further comprises a heat exchanger and a return conduit, and the operations controller is configured to control one or more of:changing, via the heat exchanger, a temperature of at least one of the first unit material or the second unit material, thereby to provide a temperature- controlled unit materials stream; and returning, via the return conduit, at least a portion of the temperature- controlled unit materials stream to the atmospheric column.

384. The distillation unit control assembly of claim 381, wherein the operations controller is configured to control, prior to the analyzing one or more of the one or more first intermediate samples or the one or more second intermediate samples, conditioning of one or more of the one or more first intermediate samples or the one or more second intermediate samples, thereby to provide one or more conditioned intermediate samples.

385. The distillation unit control assembly of claim 381, wherein the operations controller is configured to control, prior to the analyzing one or more of the one or more first unit material samples or the one or more second unit material samples, conditioning of the one or more first unit material samples or the one or more second unit material samples, thereby to provide one or more conditioned unit material samples.

386. The distillation unit control assembly of claim 385, wherein the operations controller is configured to control one or more operating parameters associated with the atmospheric distillation unit against operating constraints of the atmospheric distillation unit.

387. The distillation unit control assembly of claim 356, wherein:(a) one or more of the one or more first processing units or the one or more second processing units further comprises a vacuum distillation unit including a vacuum column positioned to receive a residue stream from an atmospheric column;(b) the operations controller is configured to control one or more of:(i) separating, via the vacuum column, the residue stream into one or more intermediate operation feedstocks;(ii) separating one or more intermediate operation feedstock samples from the one or more intermediate operation feedstocks;(iii) analyzing, via one or more of the first analyzer, the second analyzer, or one or more additional analyzers, the one or more intermediate operation feedstock samples; and(iv) predicting, based at least in part in the analyzing the one or more intermediate operation feedstock samples and application of analysis of the one or more intermediate operation feedstocks to the trained machine learning model, one or more intermediate operation feedstock sample properties associated with the one or more intermediate operation feedstock samples; and(c) the controlling is based at least in part on the one or more intermediate operation feedstock sample properties.

388. The distillation unit control assembly of claim 387, wherein the operations controller is configured to control one or more operating parameters associated with the vacuum distillation unit against operating constraints of the vacuum distillation unit.

389. A method for enhancing control of a reforming operation associated with a petroleum refining operation, the method comprising: supplying naphtha to a reformer associated with the petroleum refining operation, the naphtha having one or more naphtha properties; analyzing a naphtha sample via a first analyzer to provide naphtha sample properties; predicting one or more naphtha sample properties associated with the naphtha sample based on (A) the naphtha sample properties and (B) a first output from application of the naphtha sample properties to a first trained machine learning model; operating the reformer to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of reformate, hydrogen, or reformer gas; analyzing the unit material sample via a second analyzer to provide unit material sample properties; predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model; andcontrolling, during the reforming operation, based on the naphtha sample properties and the one or more unit material sample properties, one or more of:(a) one or more naphtha properties associated with the naphtha supplied to the reformer;(b) one or more unit product materials properties associated with the unit product materials;(c) operation of the reformer; or(d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the reforming operation, causes the reforming operation to produce one or more of:(i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials,(ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or(iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the reforming operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

390. A method for enhancing control of an alkylation operation associated with a petroleum refining operation, the method comprising: supplying a feedstock to an alkylation unit associated with the petroleum refining operation, the feedstock having one or more feedstock properties; analyzing a feedstock sample via a first analyzer to provide feedstock sample properties; predicting one or more feedstock sample properties associated with the feedstock sample based on (A) the feedstock sample properties and (B) a first output from application of the feedstock sample properties to a first trained machine learning model; supplying one or more other input materials or intermediates to the alkylation unit associated with the petroleum refining operation, the one or more other input materials orintermediates having one or more other input materials properties or intermediates properties respectively; analyzing one or more other input materials sample via a second analyzer to provide other input materials sample properties; predicting one or more other input materials sample properties associated with the other input materials sample based on (C) the other input materials sample properties and (D) a second output from application of the other input materials sample properties to a second trained machine learning model; operating the alkylation unit to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of alkylate or iso-butane; analyzing the unit material sample via a third analyzer to provide unit material sample properties; predicting one or more unit material sample properties associated with the unit material sample based on (E) the unit material sample properties and (F) a second output from application of the unit material sample properties to a second trained machine learning model; and controlling, during the alkylation operation, based on the feedstock sample properties and the one or more unit material sample properties, one or more of:(a) one or more feedstock properties associated with the feedstock properties supplied to the alkylation unit;(b) one or more other input materials properties or intermediates properties associated with the other input materials properties or intermediates properties supplied to the alkylation unit;(c) one or more unit product materials properties associated with the unit product materials;(d) operation of the alkylation unit; or(e) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the alkylation operation, causes the alkylation operation to produce one or more of:(i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials,(ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or(iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the petroleum refining operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

391. A method for enhancing control of an isomerization operation associated with a petroleum refining operation, the method comprising: supplying naphtha to an isomerization unit associated with the petroleum refining operation, the naphtha having one or more naphtha properties; analyzing a naphtha sample via a first analyzer to provide naphtha sample properties; predicting one or more naphtha sample properties associated with the naphtha sample based on (A) the naphtha sample properties and (B) a first output from application of the naphtha sample properties to a first trained machine learning model; operating the isomerization unit to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of gasoline, C3 and lighter alkanes, or hydrogen sulfide; analyzing the unit material sample via a second analyzer to provide unit material sample properties; predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model; and controlling, during the isomerization operation, based on the naphtha sample properties and the one or more unit material sample properties, one or more of:(a) one or more naphtha properties associated with the naphtha supplied to the isomerization unit;(b) one or more unit product materials properties associated with the unit product materials;(c) operation of the isomerization unit; or(d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the isomerization operation, causes the isomerization operation to produce one or more of:(i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials,(ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or(iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the isomerization operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

392. A method compri sing : supplying feedstock to a hydrotreater associated with a petroleum refining operation, the feedstock having one or more feedstock properties; analyzing a feedstock sample via a first analyzer to provide feedstock sample properties; predicting one or more feedstock sample properties associated with the feedstock sample based on (A) the feedstock sample properties and (B) a first output from application of the feedstock sample properties to a first trained machine learning model; operating the hydrotreater to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of gas, gasoline, diesel, or isobutanes; analyzing the unit material sample via a second analyzer to provide unit material sample properties; predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model; and controlling, during the hydrotreatment operation, based on the feedstock sample properties and the one or more unit material sample properties, one or more of:(a) one or more feedstock properties associated with the feedstock supplied to the hydrotreater;(b) one or more unit product materials properties associated with the unit product materials;(c) operation of the hydrotreater; or(d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the hydrotreatment operation, causes the hydrotreatment operation to produce one or more of:(i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials,(ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or(iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the hydrotreatment operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

393. A method compri sing : receiving feed data indicative of a feed rate of a feed into a propylene splitter; receiving operational data indicative of operational parameters of the propylene splitter; receiving product data indicative of purity of a product of the propylene splitter; and generating, by a machine learning model, an adjustment to the operational parameters of the propylene splitter or a feed rate of the feed into the propylene splitter based on one or more of the feed data, operational data, or product data, wherein themachine learning model is trained on historical data of the feed data, operational data, and product data.

394. The method of claim 393, predicting, by the machine learning model, an effect of the adjustment on product purity.

395. The method of any of claims 393 to 394, further comprising implementing the adjustment to the operational parameters of the propylene splitter or a feed rate of the feed into the propylene splitter.

396. The method of any of claims 393 to 395, wherein the feed data includes sample data indicative of one or more of properties or spectra of an analyzed sample.

397. The method of any of claims 393 to 396, further comprising: initiating capture of a sample of the product of the propylene splitter; and analyzing the sample of the product of the propylene splitter to generate the product data.

398. The method of any of claims 393 to 397, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to an operational parameter of a compressor of the propylene splitter.

399. The method of any of claims 393 to 398, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to an operational parameter of a cooler of the propylene splitter.

400. The method of any of claims 393 to 399, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to a feed rate of a bottoms stream fed to a cooler of the propylene splitter and added to a reflux stream fed into the propylene splitter.

401. The method of any of claims 393 to 400, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to an operational parameter of a splitter of the propylene splitter.

402. The method of any of claims 393 to 401, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to an operational parameter of a reboiler of the splitter of the propylene splitter.

403. The method of any of claims 393 to 402, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to a reflux temperature entering the splitter of the propylene splitter.

404. The method of any of claims 393 to 403, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes an adjustment to a reflux rate of the splitter.

405. The method of any of claims 393 to 404, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes adjusting the feed rate of the feed in response to product data indicating a change in purity of the product.

406. The method of any of claims 393 to 405, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes adjusting a recycle rate of a bottoms stream from the splitter into the splitter.

407. The method of any of claims 393 to 406, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter includes adjusting a withdrawal rate of a bottoms stream from the splitter.

408. The method of any of claims 393 to 407, further comprising identifying a change in the operating parameters of the propylene splitter based on the operating data.

409. The method of claim 408, further comprising generating a prediction of a cause of the change in the operating parameters of the propylene splitter based on one or more of the feed data, operational data, or product data.

410. The method of claim 409, wherein the prediction of the cause of the change in the operating parameters of the propylene splitter is a change in weather proximate the propylene splitter.

411. The method of claim 410, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter is based on a change in weather proximate the propylene splitter.

412. The method of any of claims 409 to 411, further comprising: generating a notice of the prediction; and publishing the notice to a user.

413. The method of any of claims 393 to 412, wherein the adjustment to the operational parameters or feed rate of the feed of the propylene splitter is based on a target purity of the product.

414. The method of any of claims 393 to 413, further comprising: receiving business data indicative of current market pricing for a plurality of purities of the product; and generating a target purity of the product based on the business data, wherein the adjustment to the operational parameters or feed rate of the feed of the propylene splitter is predicted by the machine learning model to produce the product achieving the target purity.

415. The method of claim 414, further comprising generating a predicted maximum market value of the product based on a production rate of the product and the target purity, wherein the adjustment to the operational parameters or feed rate of the feed of the propylene splitter is made to achieve the predicted maximum market value of the product.

416. The method of any of claims 393 to 413, further comprising receiving a target purity, wherein the adjustment to the operational parameters or feed rate of the feed of the propylene splitter is predicted by the machine learning model to produce the product achieving the target purity.

417. The method of any of claims 414 to 416, wherein the machine learning model is programmed to increase the feed rate of feed until the target purity is achieved.

418. The method of any of claims 414 to 416, further comprising receiving a target purity, wherein generating, by the machine learning model, the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter to achieve the target purity.

419. The method of claim 418, further comprising: determining that the product exceeds the target purity; and generating, by the machine learning model, a second adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter to reduce product purity toward the target purity.

420. The method of any of claims 414 to 419, wherein the machine learning model is trained to maximize a feed rate of the feed while producing product that achieves the target purity.

421. The method of any of claims 393 to 420, wherein receiving product data indicative of purity of the product of the propylene splitter includes product data indicative of propylene content in a bottoms stream from the propylene splitter, wherein the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter results in a decrease in propylene in the bottoms stream from the propylene splitter.

422. The method of any of claims 393 to 421, wherein the product includes propylene and propane, the method further comprising: receiving business data indicative of market pricing for a grade of propylene and propane, wherein the machine learning model generates the adjustment to the operational parameters of the propylene splitter or the feed rate of the feed into the propylene splitter to increase a potential profit from operation of the propylene splitter based upon the business data indicative of market pricing for a grade of propylene and propane and the product data.

423. The method of any of claims 393 to 420, wherein the product includes propylene.

424. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 393 to 423.

425. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 393 to 423.

426. A method comprising: receiving hydrogen production data including feed date indicative of properties of the feed fed into equipment that produces hydrogen, operational data of equipment that produces hydrogen, and hydrogen product data indicative of one or more properties the hydrogen produced by the equipment that produces hydrogen; receiving hydrogen consumption data including the operational data of equipment that consume hydrogen; accessing distribution data indicative of connections between the equipment that produces hydrogen and the equipment that consumes hydrogen; and generating, by a machine learning model, an adjustment to the distribution of hydrogen from the equipment that produces hydrogen to the equipment that consumes hydrogen based on the hydrogen production data, the hydrogen consumption data, and the distribution data.

427. The method of claim 426, further comprising: receiving business data indicative of market values of the products of equipment that consumes hydrogen; and generating, by the machine learning model, priority of hydrogen distribution based on the business data.

428. The method of claim 427, further comprising generating a priority score for one or more of the products of equipment that consumes hydrogen based on a potential profit of the hydrogen consuming equipment and distributing hydrogen based on the products of equipment that consumes hydrogen.

429. The method of claim 428, further comprising generating, by the machine learning model, a prediction of a minimum hydrogen consumption for one or more of the equipment that consumes hydrogen based on the hydrogen consumption, wherein the priority score is further based on the prediction of the minimum hydrogen consumption.

430. The method of any of claims 426 to 429, wherein the adjustment to the distribution of hydrogen is based on nearness of the equipment that consumes hydrogen to the equipment that produces hydrogen.

431. The method of any of claims 426 to 430, wherein priority is given to equipment that consumes hydrogen nearer to the equipment that produces hydrogen.

432. The method of any of claims 426 to 431, further comprising implementing the adjustment to the distribution of hydrogen.

433. The method of any of claims 426 to 432, wherein the feed data includes sample data indicative of one or more of properties or spectra of an analyzed sample.

434. The method of any of claims 426 to 433, further comprising: initiating capture of a sample of the hydrogen of the equipment that produces hydrogen; and analyzing the sample of the hydrogen of the equipment that produces hydrogen to generate the product data.

435. The method of any of claims 426 to 434, wherein the adjustment to the distribution of hydrogen includes generating, by the machine learning model, an adjustment to one or more operational parameters of the equipment that produces hydrogen to increase hydrogen gas production.

436. The method of any of claims 426 to 435, wherein the equipment that produces hydrogen includes a steam methane reformer.

437. The method of claim 436, wherein the adjustment to the distribution of hydrogen includes generating, by the machine learning model, an adjustment to one or moreoperational parameters of the steam methane reformer to decrease the consumption of steam.

438. The method of any of claims 436 to 437, further comprising generating, by the machine learning model, a prediction of a state of a catalyst of the steam methane reformer, wherein the adjustment to the distribution of hydrogen includes generating, by the machine learning model, an adjustment to one or more operational temperature or pressure based on the prediction of the state of the catalyst of the steam methane reformer.

439. The method of any of claims 426 to 438, wherein the equipment that produces hydrogen includes a hydrolysis unit.

440. The method of any of claims 426 to 439, wherein the equipment that produces hydrogen includes a catalytic reformer.

441. The method of claim 440, wherein the adjustment to the distribution of hydrogen includes generating, by the machine learning model, an adjustment to one or more operational parameters of the catalytic reformer is constrained by operating parameters of the catalytic reformer used to achieve a target property of reformate produced by the catalytic reformer.

442. The method of any of claims 426 to 439, wherein the equipment that produces hydrogen includes an external hydrogen source.

443. The method of claim 442, wherein the adjustment to the distribution of hydrogen includes generating, by the machine learning model, a reduction to hydrogen used from the external hydrogen source.

444. The method of any of claims 442 to 443, wherein the machine learning model prioritizes hydrogen production from one or more of a steam methane reformer or a catalytic reformer over the external hydrogen source.

445. The method of any of claims 426 to 444, wherein the machine learning model is trained with historical data including hydrogen production data, operational data ofequipment that produces hydrogen, hydrogen product data, and hydrogen consumption data.

446. The method of any of claims 426 to 445, further comprising generating, by the machine learning model, a prediction of a minimum hydrogen consumption for one or more of the equipment that consumes hydrogen based on the hydrogen consumption.

447. The method of claim 446, wherein the adjustment to the distribution of hydrogen is constrained by the prediction of the minimum hydrogen consumption for one or more of the equipment that consumes hydrogen.

448. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 426 to 447.

449. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 426 to 447.

450. A method comprising: receiving operational data of a plurality of units of a refinery that utilize steam; generating, by a machine learning model, a prediction of a minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam based on the operational data, wherein the machine learning model is trained with historical data including steam production data and operational data of the plurality of units of the refinery that utilize steam; and generating, by the machine learning model, an adjustment to a distribution of steam to one or more of the plurality of units of the refinery that utilize steam based on the generated prediction of a minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam.

451. The method of claim 450, wherein the adjustment to the distribution of steam is based on nearness of one or more of the plurality of units of the refinery that utilize steam to a unit that produces steam.

452. The method of any of claims 450 to 451, wherein priority is given to one or more of the plurality of units of the refinery that utilize steam nearer to a unit that produces steam.

453. The method of any of claims 450 to 452, further comprising implementing the adjustment to the distribution of steam.

454. The method of any of claims 450 to 452, wherein the adjustment to the distribution of steam includes generating, by the machine learning model, an adjustment to one or more operational parameters of a unit that produces steam to increase steam production.

455. The method of any of claims 450 to 454, further comprising: receiving product data indicative of a property of a product of one of the plurality of units of the refinery that utilize steam; receiving business data indicative of market values of the product of one of the plurality of units of the refinery that utilize steam, wherein the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam is further based on the product data and the business data, wherein the historical data further includes product data and business data; and generating, by the machine learning model, a value of one or more of the plurality of units of the refinery that utilize steam based on the business data.

456. The method of claim 455, wherein the adjustment to the distribution of steam prioritizes a unit of the plurality of units of the refinery that utilize steam having a higher value than a unit of the plurality of units of the refinery that utilize steam having a lower value.

457. The method of claim 456, wherein nearness of a unit of the plurality of units of the refinery that utilize steam to a unit that produces steam represents an efficiency in steam delivery, wherein the efficiency in steam delivery is used to adjust a priority of the plurality of units of the refinery that utilize steam.

458. The method of any of claims 450 to 457, further comprising receiving weather data, wherein the adjustment to the distribution of steam is further based on weather data.

459. The method of claim 458, further comprising determining, by the machine learning model, the weather data indicates a change in ambient temperatures, wherein generating the prediction of the minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam is further based on the change in ambient temperatures.

460. The method of any of claims 450 to 459, further comprising: receiving a change in the operational data of one or more of the plurality of units of the refinery that utilize steam; updating, by the machine learning model, the prediction of minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam; and generating a second adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam.

461. The method of any of claims 450 to 460, wherein the operational data includes one or more operational goals of one or more of the plurality of units of the refinery that utilize steam.

462. The method of claim 461, wherein the one or more operational goals includes an objective function.

463. The method of any of claims 461 to 462, wherein the prediction of a minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam is based on the one or more operational goals of one or more of the plurality of units of the refinery that utilize steam.

464. The method of any of claims 461 to 463, wherein the machine learning model is programmed to reduce energy consumption while meeting the one or more operational goals of one or more of the plurality of units of the refinery that utilize steam.

465. The method of any of claims 450 to 464, wherein the machine learning model is programmed to maximize a potential profit of one or more of the plurality of units of the refinery that utilize steam.

466. The method of any of claims 450 to 465, further comprising generating, by the machine learning model, a margin above the minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam based on the historical data and a confidence interval based on the historical data that actually delivered steam to one or more of the plurality of units of the refinery that utilize steam will achieve or exceed the minimum steam consumption.

467. The method of claim 466, further comprising receiving the confidence interval from a user.

468. The method of any of claims 466 to 467, wherein the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam includes the margin above the minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam.

469. The method of any of claims 450 to 468, further comprising determining, by the machine learning model, heat losses throughout the distribution of steam to one or more of the plurality of units of the refinery that utilize steam, wherein the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam is further based on the determined heat losses.

470. The method of claim 469, further comprising receiving current weather data, wherein determining, by the machine learning model, heat losses throughout the distribution of steam to one or more of the plurality of units of the refinery that utilize steam is further based on the current weather data.

471. The method of any of claims 450 to 470, further comprising: generating, by the machine learning model, an efficiency value for each unit that produces steam, wherein generating, by the machine learning model, the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam is further based on the efficiency value for each unit that produces steam.

472. The method of claim 471, wherein generating, by the machine learning model, the adjustment to the distribution of steam to one or more of the plurality of units of the refinerythat utilize steam, the machine learning model prioritizes steam production for one or more units that produces steam that have a higher efficiency value.

473. The method of claim 471, wherein generating, by the machine learning model, the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam, the machine learning model prioritizes steam production for one or more units that produces steam that have a higher efficiency value.

474. The method of any of claims 450 to 473, further comprising: receiving business data; and generating a potential profit for one or more of the plurality of units of the refinery that utilize steam, wherein generating, by the machine learning model, the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam prioritizes the distribution of steam to one or more of the plurality of units of the refinery that utilize steam by the potential profit of one or more of the plurality of units of the refinery that utilize steam.

475. The method claim 474, wherein when steam production is less than the prediction of the minimum steam consumption for one or more of the plurality of units of the refinery that utilize steam, the adjustment to the distribution of steam to one or more of the plurality of units of the refinery that utilize steam prioritizes the distribution of steam to one or more of the plurality of units of the refinery that utilize steam by the potential profit of one or more of the plurality of units of the refinery that utilize steam.

476. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 450 to 475.

477. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 450 to 475.

478. A method compri sing : receiving one or more of (a) operational data of an absorber indicative of operational parameters of the absorber and including sensor data from one or more sensors disposed tomeasure an operational parameter of the absorber, (b) product data indicative of a property or component of a product from a process of the absorber or (c) feedstock data of a hydrocarbon feedstock being fed into the absorber; determining a change in the one or more of the operational data, the product data, or the feedstock data; generating, by a machine learning model, a prediction of an effect of the change on the operation of the absorber in advance of an actual effect being detected; and generating, by the machine learning model, an adjustment to an operating parameter of the absorber based on the predicted effect of the change, wherein the machine learning model is trained on historical data including operational data and product data of the absorber.

479. The method of claim 478, further comprising implementing the adjustment to the operating parameter of the absorber.

480. The method of any of claims 478 to 479, further comprising publishing the predicted effect of the change to a user.

481. The method of any of claims 478 to 480, further comprising receiving an instruction to implement the adjustment to the operating parameter of the absorber.

482. The method of any of claims 478 to 481, wherein the machine learning model is trained on historical data including feedstock data indicative of feedstock fed into the absorber.

483. The method of any of claims 478 to 482, wherein the adjustment is an adjustment to a feed rate of the hydrocarbon feedstock.

484. The method of any of claims 478 to 483, wherein generating, by the machine learning model, the adjustment to the operating parameter of the absorber is to increase lean oil loading efficiency.

485. The method of any of claims 478 to 484, wherein the feedstock is a vapor and a lean oil is a liquid.

486. The method of any of claims 478 to 485, wherein generating, by the machine learning model, the adjustment to the operating parameter of the absorber is to achieve vapor liquid equilibrium is achieved within an absorber column.

487. The method of any of claims 478 to 486, further comprising: generating a plurality of simulations, by the machine learning model, of the operation of the absorber based on the change in the operational data, wherein each simulation has a different adjustment to an operational parameter of the absorber; and selecting, by the machine learning model, a simulation of the plurality of simulations, wherein the selected simulation achieves a target absorption rate while not exceeding an operational constraint of the absorber.

488. The method of claim 487, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is based on the selected simulation.

489. The method of any of claims 478 to 488, further comprising generating, by the machine learning model, a prediction of lean oil loading in an absorber column of the absorber based on the operating data and the product data, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is based on the predicted lean oil loading.

490. The method of any of claims 478 to 489, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of a lean oil into an absorber column of the absorber.

491. The method of any of claims 478 to 490, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a temperature of a lean oil being fed into an absorber column of the absorber.

492. The method of any of claims 478 to 491, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operating parameter of a stripper of the absorber.

493. The method of claim 492, further comprising generating, by the machine learning model, a prediction of a property or composition of lean oil based on the operating data and the product data, wherein generating, by the machine learning model, the adjustment to the parameter of the stripper of the absorber is based on the predicted property or composition of the lean oil.

494. The method of any of claims 478 to 493, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber includes an adjustment to a feed rate of lean oil into the absorber.

495. The method of any of claims 478 to 494, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber includes an adjustment to an operating parameter of a distillation operation of the absorber that separates lean oil from a targeted material absorbed from the feedstock.

496. The method of any of claims 478 to 495, further comprising generating, by the machine learning model, a prediction of a process constraint based on the operating data.

497. The method of claim 496, wherein the prediction of the process constraint is generated on a regular periodic basis.

498. The method of claim 496, wherein the prediction of the process constraint is generated when the change in the one or more of the operational data, the product data, or the feedstock data is determined.

499. The method of any of claims 478 to 498, further comprising generating, by the machine learning model, a prediction of fouling within a process of the absorber, based on the operational data.

500. The method of claim 499, further comprising generating, by the machine learning model, a prediction of a process constraint based on the prediction of fouling within a process of the absorber.

501. The method of any of claims 496 to 500, wherein the prediction of the process constraint is generated on a regular periodic basis.

502. The method of any of claims 496 to 500, wherein the prediction of the process constraint is generated when the change in the one or more of the operational data, the product data, or the feedstock data is determined.

503. The method of any of claims 496, 497, 498, 500, 501, or 502, further comprising generating, by the machine learning model, a margin away from the process constraint based on the historical data and a confidence interval that the process of the absorber will not exceed the process constraint during operation of the absorber.

504. The method of claim 503, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber includes the margin away from the process constraint.

505. The method of any of claims 496, 497, 498, 500, 501, 502, 503, or 504, further comprising generating, by the machine learning model, an operating target for a process of the absorber based on the process constraint.

506. The method of claim 505, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment moves operation of the process to the operating target.

507. The method of any of claims 505 to 506, wherein the operational target includes a temperature of a lean oil.

508. The method of any of claims 505 to 507, wherein the operational target includes a feed rate of a lean oil.

509. The method of any of claims 505 to 508, wherein the operational target includes a pressure of the absorber.

510. The method of any of claims 505 to 509, wherein the operational target includes a target feed rate of feedstock into the absorber.

511. The method of claim 510, further comprising generating, by the machine learning model, a prediction of a maximum feed rate of feedstock into the absorber, wherein the target feed rate of feedstock into the absorber is based on the predicted maximum feed rate of feedstock.

512. The method of claim 511, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment of feed rate of feedstock into the absorber to achieve the target feed rate of feedstock into the absorber.

513. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 478 to 512.

514. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 478 to 512.

515. A method compri sing : receiving one or more of (a) operational data of an absorber indicative of operational parameters of the absorber and including sensor data from one or more sensors disposed to measure a parameter of the absorber, (b) product data indicative of a property or component of a product from a process of the absorber or (c) feedstock data of a feedstock being fed into the absorber; generating, by a machine learning model, a prediction of a process constraint based on the operating data; and generating, by the machine learning model, an adjustment to an operating parameter of the absorber based on the predicted process constraint, wherein the machine learning model is trained on historical data including operational data and product data of the absorber.

516. The method of claim 515, further comprising implementing the adjustment to the operating parameter of the absorber.

517. The method of any of claims 515 to 516, further comprising publishing the generated adjustment to the operating parameter of the absorber to a user.

518. The method of any of claims 515 to 517, further comprising receiving an instruction to implement the adjustment to the operating parameter of the absorber.

519. The method of any of claims 515 to 518, wherein the process constraint is not measured by a sensor.

520. The method of claim 519, wherein the process constraint is altered by fouling.

521. The method of any of claims 515 to 520, wherein the machine learning model is trained on historical data including feedstock data indicative of feedstock fed into the absorber.

522. The method of any of claims 515 to 521, wherein the adjustment is an adjustment to a feed rate of the feedstock.

523. The method of any of claims 515 to 522, wherein generating, by the machine learning model, the adjustment to the operating parameter of the absorber is to increase lean oil loading efficiency.

524. The method of any of claims 515 to 523, wherein the feedstock is a vapor and a lean oil is a liquid.

525. The method of any of claims 515 to 524, wherein generating, by the machine learning model, the adjustment to the operating parameter of the absorber is to achieve vapor liquid equilibrium is reached within an absorber column of the absorber.

526. The method of any of claims 515 to 522, further comprising generating, by the machine learning model, a prediction of lean oil loading in an absorber column of theabsorber based on the operating data and the product data, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is based on the predicted lean oil loading.

527. The method of any of claims 515 to 526, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of lean oil into an absorber column of the absorber.

528. The method of any of claims 515 to 527, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operating parameter of a lean oil recovery column of the absorber.

529. The method of any of claims 515 to 528, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber includes an adjustment to a feed rate of lean oil being fed into an absorber column of the absorber.

530. The method of any of claims 515 to 529, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a temperature of a lean oil being fed into an absorber column of the absorber.

531. The method of claim 530, further comprising generating, by the machine learning model, a prediction of a property or composition of the lean oil based on the operating data and the product data, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is based on the predicted property or composition of the lean oil.

532. The method of claim 531, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is an adjustment to a feed rate of lean oil into the absorber.

533. The method of any of claims 515 to 532, wherein the prediction of the process constraint is generated on a regular periodic basis.

534. The method of any of claims 515 to 533, wherein the prediction of the process constraint is generated when a change in the one or more of the operational data, the product data, or the feedstock data is determined.

535. The method of any of claims 515 to 534, further comprising generating, by the machine learning model, a prediction of fouling within a process of the absorber, based on the operational data.

536. The method of claim 535, wherein generating, by the machine learning model, the prediction of the process constraint is based on the prediction of fouling within a process of the absorber.

537. The method of any of claims 515 to 536, further comprising generating, by the machine learning model, a margin away from the process constraint based on the historical data and a confidence interval that the process of the absorber will not exceed the process constraint during operation of the absorber.

538. The method of claim 537, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber includes the margin away from the process constraint.

539. The method of any of claims 515 to 538, further comprising generating, by the machine learning model, an operating target for a process of the absorber based on the process constraint.

540. The method of claim 539, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment moves operation of the process to the operating target.

541. The method of any of claims 539 to 540, wherein the operational target includes a temperature of a lean oil.

542. The method of any of claims 539 to 541, wherein the operational target includes a feed rate of a lean oil.

543. The method of any of claims 539 to 542, wherein the operational target includes a pressure of the absorber.

544. The method of any of claims 539 to 543, wherein the operational target includes a target feed rate of feedstock into the absorber.

545. The method of any of claims 515 to 540, further comprising generating, by the machine learning model, a target feed rate of feedstock into the absorber, based on one or more of the operational data or the product data.

546. The method of claim 545, further comprising generating, by the machine learning model, a prediction of a maximum feed rate of feedstock into the absorber, wherein the target feed rate of feedstock into the absorber is based on the predicted maximum feed rate of feedstock.

547. The method of claim 546, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment of feed rate of feedstock into the absorber to achieve the target feed rate of feedstock into the absorber.

548. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 515 to 547.

549. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 515 to 547.

550. A method compri sing : receiving one or more of (a) operational data of an absorber indicative of operational parameters of the absorber and including sensor data from one or more sensors disposed to measure a parameter of the absorber, (b) product data indicative of a property or component of a product from a process of the absorber or (c) feedstock data of a feedstock being fed into the absorber;generating, by a machine learning model, a prediction of property or composition of lean oil based on the operating data; and generating, by the machine learning model, an adjustment to an operating parameter of the absorber based on the predicted property or composition of the lean oil, wherein the machine learning model is trained on historical data including operational data and product data of the absorber.

551. The method of claim 550, further comprising implementing the adjustment to the operating parameter of the absorber.

552. The method of any of claims 550 to 551, further comprising publishing the generated adjustment to the operating parameter of the absorber to a user.

553. The method of any of claims 550 to 552, further comprising receiving an instruction to implement the adjustment to the operating parameter of the absorber.

554. The method of any of claims 550 to 553, wherein the machine learning model is trained on historical data including feedstock data indicative of feedstock fed into the absorber.

555. The method of any of claims 550 to 554, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of the feedstock.

556. The method of any of claims 550 to 555, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of a lean oil regenerator.

557. The method of any of claims 550 to 556, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of a stripper.

558. The method of claim 557, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of lean oil into an absorber column of the absorber.

559. The method of any of claims 550 to 558, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of a stripper.

560. The method of any of claims 550 to 559, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of lean oil into the absorber.

561. The method of any of claims 550 to 560, further comprising generating, by the machine learning model, a prediction of lean oil loading in an absorber column of the absorber based on the operating data and the product data, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is based on the predicted lean oil loading.

562. The method of any of claims 550 to 561, further comprising generating, by the machine learning model, a prediction of a process constraint based on the operating data.

563. The method of claim 562, wherein the prediction of the process constraint is generated on a regular periodic basis.

564. The method of claim 563, wherein the prediction of the process constraint is generated when a change in the one or more of the operational data, the product data, or the feedstock data is determined.

565. The method of any of claims 550 to 564, further comprising generating, by the machine learning model, a prediction of fouling within a process of the absorber, based on the operational data.

566. The method of claim 565, further comprising generating, by the machine learning model, a prediction of a process constraint based on the prediction of fouling within a process of the absorber.

567. The method of claim 566, wherein the prediction of the process constraint is generated on a regular periodic basis.

568. The method of claims 566, wherein the prediction of the process constraint is generated when a change in the one or more of the operational data, the product data, or the feedstock data is determined.

569. The method of any of claims 562 to 568, further comprising generating, by the machine learning model, a margin away from the process constraint based on the historical data and a confidence interval that the process of the absorber will not exceed the process constraint during operation of the absorber.

570. The method of claim 569, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is constrained by the margin away from the process constraint.

571. The method of any of claims 562 to 570, further comprising generating, by the machine learning model, an operating target for a process of the absorber based on the process constraint.

572. The method of claim 571, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment moves operation of the process to the operating target.

573. The method of any of claims 562 to 572, further comprising generating, by the machine learning model, a target feed rate of feedstock into the absorber, based on the operational data.

574. The method of claim 573, further comprising generating, by the machine learning model, a prediction of a maximum feed rate of feedstock into the absorber, wherein thetarget feed rate of feedstock into the absorber is based on the predicted maximum feed rate of feedstock.

575. The method of claim 574, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment of feed rate of feedstock into the absorber to the target feed rate of feedstock into the absorber.

576. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 550 to 575.

577. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 550 to 575.

578. A method compri sing : receiving one or more of (a) operational data of an absorber indicative of operational parameters of the absorber and including sensor data from one or more sensors disposed to measure a parameter of the absorber, (b) product data indicative of a property or component of a product from a process of the absorber or (c) feedstock data of a feedstock being fed into the absorber; generating, by a machine learning model, a prediction of lean oil loading based on the operating data; and generating, by the machine learning model, an adjustment to an operating parameter of the absorber to improve lean oil loading based on the predicted lean oil loading, wherein the machine learning model is trained on historical data including operational data and product data of the absorber.

579. The method of claim 578, further comprising implementing the adjustment to the operating parameter of the absorber.

580. The method of any of claims 578 to 579, further comprising publishing the generated adjustment to the operating parameter of the absorber to a user.

581. The method of any of claims 578 to 580, further comprising receiving an instruction to implement the adjustment to the operating parameter of the absorber.

582. The method of any of claims 578 to 581, wherein the machine learning model is trained on historical data including feedstock data indicative of feedstock fed into the absorber.

583. The method of any of claims 578 to 582, further comprising generating, by the machine learning model, a prediction of a property or composition of the lean oil based on the operating data, wherein generating, by the machine learning model, the adjustment to the operating parameter of the absorber to improve lean oil loading is further based on the predicted property or composition of the lean oil.

584. The method of any of claims 578 to 583, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of the feedstock.

585. The method of any of claims 578 to 584, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of a lean oil regenerator.

586. The method of any of claims 578 to 585, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of a lean oil recovery column.

587. The method of any of claims 578 to 586, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of an absorber column.

588. The method of claim 587, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of lean oil into an absorber column of the absorber.

589. The method of any of claims 578 to 588, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to an operational parameter of a stripper.

590. The method of any of claims 578 to 589, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment to a feed rate of lean oil into the absorber.

591. The method of any of claims 578 to 590, further comprising generating, by the machine learning model, a prediction of a process constraint based on the operating data.

592. The method of claim 591, wherein the prediction of the process constraint is generated on a regular periodic basis.

593. The method of claim 592, wherein the prediction of the process constraint is generated when a change in the one or more of the operational data, the product data, or the feedstock data is determined.

594. The method of any of claims 578 to 593, further comprising generating, by the machine learning model, a prediction of fouling within a process of the absorber, based on the operational data.

595. The method of claim 594, further comprising generating, by the machine learning model, a prediction of a process constraint based on the prediction of fouling within a process of the absorber.

596. The method of claim 595, wherein the prediction of the process constraint is generated on a regular periodic basis.

597. The method of claims 595, wherein the prediction of the process constraint is generated when a change in the one or more of the operational data, the product data, or the feedstock data is determined.

598. The method of any of claims 591 to 597, further comprising generating, by the machine learning model, a margin away from the process constraint based on the historical data and a confidence interval that the process of the absorber will not exceed the process constraint during operation of the absorber.

599. The method of claim 598, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber is constrained by the margin away from the process constraint.

600. The method of any of claims 591 to 599, further comprising generating, by the machine learning model, an operating target for a process of the absorber based on the process constraint.

601. The method of claim 600, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment moves operation of the process to the operating target.

602. The method of any of claims 591 to 601, further comprising generating, by the machine learning model, a target feed rate of feedstock into the absorber, based on the operational data.

603. The method of claim 602, further comprising generating, by the machine learning model, a prediction of a maximum feed rate of feedstock into the absorber, wherein the target feed rate of feedstock into the absorber is based on the predicted maximum feed rate of feedstock.

604. The method of claim 603, wherein generating, by the machine learning model, the adjustment to the parameter of the absorber, the adjustment includes an adjustment of feed rate of feedstock into the absorber to the target feed rate of feedstock into the absorber.

605. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 578 to 604.

606. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 578 to 604.

607. A method comprising: receiving feedstock data indicative of a composition of a hydrogen sulfide feed to be processed by a sulfur recovery unit; receiving combustion feed data indicative of a composition of a sulfur dioxide product of a reaction furnace of the sulfur recovery unit; receiving reaction furnace operational data indicative of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, and a pressure of the reaction furnace; receiving reactor operational data indicative of a feed rate of hydrogen sulfide feed into a reactor of the sulfur recovery unit, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, and a pressure of the reactor; receiving product data indicative of a composition of a product of the reactor; receiving tail gas data indicative of a composition of tail gas from the sulfur recovery unit; and generating, by a machine learning model, an adjustment to one or more of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor based on one or more of the tail gas data or the product data, wherein the machine learning model is trained with historical data including feed rates of hydrogen sulfide feed into the reaction furnace, temperatures of the reaction furnace, pressures of the reaction furnace, feed rates of hydrogen sulfide feed into the reactor, feed rates of sulfur dioxide feed into the reactor, temperatures of the reactor, and pressures of the reactor.

608. The method of claim 607, further comprising implementing the adjustment to the one or more of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor.

609. The method of any of claims 607 to 608, further comprising publishing the adjustment to the one or more of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor to a user.

610. The method of any of claims 607 to 609, further comprising receiving an instruction to implement the adjustment to the to one or more of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor.

611. The method of claim 607, further comprising dynamically implementing, by the machine learning model, the adjustment to the one or more of a feed rate of hydrogen sulfide feed into the reaction furnace, a temperature of the reaction furnace, a pressure of the reaction furnace, a feed rate of hydrogen sulfide feed into the reactor, a feed rate of sulfur dioxide feed into the reactor, a temperature of the reactor, or a pressure of the reactor based on one or more of the tail gas data or the product data.

612. The method of any of claims 607 to 611, further comprising: receiving second reactor operational data indicative of a feed rate of the product of the reactor into a second reactor of the sulfur recovery unit, a temperature of the second reactor, and a pressure of the second reactor; receiving second reactor product data indicative of a composition of the second reactor product; and generating, by a machine learning model, an adjustment to one or more of the feed rate of the product of the reactor into the second reactor, a temperature of the second reactor, or a pressure of the second reactor based on one or more of the tail gas data, the product data, or the second reactor product data, wherein the historical data further includes feed rates of the product of the reactor into the second reactor, temperatures of the second reactor, or pressures of the second reactor.

613. The method of claim 612, further comprising generating, by the machine learning model, a predicted feed rate of one or more sulfur dioxide feed or hydrogen sulfide into thesecond reactor based on one or more of the tail gas data, the product data, or the second reactor product data to balance the reaction of sulfur dioxide feed with hydrogen sulfide in the second reactor.

614. The method of claim 613, further comprising feeding the one or more sulfur dioxide or hydrogen sulfide into the second reactor based on the predicted feed rate of one or more sulfur dioxide feed or hydrogen sulfide into the second reactor.

615. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 607 to 614.

616. A computing system including a processor and a memory including instructions that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 607 to 614.