Systems, analyzers, controllers, and associated methods to enhance solvent deasphalting operations

Abstract

Embodiments of systems and methods for operating a solvent deasphalting unit include generating an input comprising one or more sensor outputs from one or more sensors disposed in the solvent deasphalting unit, one or more sample analyses from sample collection and analysis assemblies disposed in the solvent deasphalting unit, and target parameters. A machine learning model may be applied to the input to generate an output comprising one or more predicted parameters. A second machine learning model may be applied to the predicted parameters and the target parameters to generate an output indicative of operating conditions of the solvent deasphalting unit to achieve the target parameters. Related methods and systems are also disclosed.

Description

SYSTEMS, ANALYZERS, CONTROLLERS, AND ASSOCIATED METHODS TO ENHANCE SOLVENT DEASPHALTING 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 production of one or more materials, such as deasphalted oil, in a solvent deasphalting unit using machine learning models during the refining operations and sub-operations associated with forming deasphalted oil and pitch.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. Furthermore, a variety of starting feedstock are utilized at a refinery and 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 objective, particularly over a period time, as equipment and materials used in the operation change over time. Such problems pose further difficulties since process changes to one operation affects other (e.g., downstream) operations 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) unit operations. However, those controllers and monitoring devices utilize algorithms that require expert personnel and take extended amounts of time to execute. For example, first- principles models require expert personnel to ensure that the first-principles model is accurately calculating some formula. In other words, expert personnel are required to maintain the first-principles model. Further still, the equipment utilized at one refinery may experience a different service or maintenance cycle, be exposed to different environmental conditions, and / or may otherwise differ from 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, such as solvent deasphalting. Particularly, the present disclosure relates to systems, analyzers, controllers, and associated methods to enhance fluid production of refining operations and suboperations 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 (e.g., deasphalted oil 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] In some embodiments, a method of operating a solvent deasphalting unit comprises generating an input comprising one or more of one or more sensor outputs from one or more sensors disposed throughout the solvent deasphalting unit, the solvent deasphalting unit configured to generate a deasphalted oil and pitch from one or more feedstock materials, one or more properties of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, or the pitch. The method further comprises receiving a target parameter comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, and applying a solvent deasphalting unit controller model to the input to generate one or more predicted parameters, the predicted parameters comprising one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, a quality of the pitch, or a solvent recovery based on the one or more predicted parameters, generate an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter, and based on the output, adjusting the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter. The solvent deasphalting unit controller model comprises a machine learning model trained to generate the output based on the input.

[0008] In some embodiments, a system for operating a solvent deasphalting unit comprises one or more sensors disposed throughout the solvent deasphalting unit, the solvent deasphalting unit configured to generate a deasphalted oil and pitch from one or more feedstock materials, one or more sample collection assemblies to collect samples of the fluid associated with the SDA unit, one or more sample collection assemblies for collectingsamples of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, or the pitch, one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples from the one or more sample collection assemblies, a plurality of refinery operation control devices configured to control aspects of fluid flowing to or from the solvent deasphalting unit or one or more operating conditions of the solvent deasphalting unit, and a solvent deasphalting unit controller in operable communication with the one or more sensors, the one or more sample collection assemblies, the one or more sample analysis assemblies, and the plurality of refinery operation control devices. The solvent deasphalting unit controller comprises at least one processor, and a computer memory including instructions that, when executed by the processor, cause the solvent deasphalting unit to carry out operations comprising applying first machine learning models of predictive controls modules to input data comprising sensor data from the one or more sensors, analysis data from the one or more sample analysis assemblies, and target parameters to generate an output comprising one or more predicted parameters, the target parameters comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, the one or more predicted parameters comprising one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, a quality of the pitch, or a solvent recovery, and applying a second machine learning model to the output of the first machine learning models to generate an output comprising or more operating conditions of the solvent deasphalting unit to achieve the target parameters.

[0009] 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 tocollect 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 (machine learning 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 of the 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.

[0010] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a solvent deasphalting (SDA) operation. The system may include an SDA unit to receive a feedstock and produce a fluid (e.g., deasphalted oil) and deasphalted asphalt (e.g., pitch). 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 ormore 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 an 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 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 SDA unit based on the output to enhance the production of fluid from the SDA unit.

[0011] Another embodiment of the disclosure is directed to a system for enhancing fluid production for a solvent deasphalting operation wherein a portion of the solvent deasphalting operation (e.g., the deasphalted oil stripper) is operated at supercritical conditions for the solvent. 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 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 supercriticalsolvent 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.

[0012] 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 one 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.

[0013] In some embodiments, a method of operating a solvent deasphalting unit comprises generating an input comprising one or more of one or more sensor outputs from one or more sensors disposed throughout the solvent deasphalting unit, the solvent deasphalting unit configured to generate a deasphalted oil and pitch from one or more feedstock materials or one or more properties of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, or the pitch. The method further comprisesreceiving a target parameter comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, or a target profit, and applying a solvent deasphalting unit controller model to the input to generate one or more predicted parameters, the predicted parameters comprising one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, a quality of the pitch, or a solvent recovery, based on the one or more predicted parameters, generate an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter, and based on the output, adjusting the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter, wherein the solvent deasphalting unit controller model comprises a machine learning model trained to generate the output based on the input.,

[0014] In some embodiments, a system for operating a solvent deasphalting unit comprises one or more sensors disposed throughout the solvent deasphalting unit, the solvent deasphalting unit configured to generate a deasphalted oil and pitch from one or more feedstock materials, one or more sample collection assemblies to collect samples of the fluid associated with the SDA unit, one or more sample collection assemblies for collecting samples of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, or the pitch, one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples from the one or more sample collection assemblies, a plurality of refinery operation control devices configured to control aspects of fluid flowing to or from the solvent deasphalting unit or one or more operating conditions of the solvent deasphalting unit, and a solvent deasphalting unit controller in operable communication with the one or more sensors, the one or more sample collection assemblies, the one or more sample analysis assemblies, and the plurality of refinery operation control devices, the solvent deasphalting unit controller comprising at least one processor, and a computer memory including instructions that, when executed by the processor, cause the solvent deasphalting unit to carry out operations comprising applying first machine learning models of predictive controls modules to input data comprising sensor data from the one or more sensors, analysis data from the one or more sample analysis assemblies, and target parameters to generate an output comprising one or more predicted parameters, the target parameters comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, or a target profit, the one or more predicted parameters comprising one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, aquality of the pitch, or a solvent recovery; and applying a second machine learning model to the output of the first machine learning models to generate an output comprising or more operating conditions of the solvent deasphalting unit to achieve the target parameters.

[0015] In some embodiments, a system for enhancing fluid production for a solvent deasphalting (SDA) operation comprises an SDA unit to receive a feedstock and produce a fluid, a plurality of sensors positioned proximate or within the SDA unit and configured to measure a parameter associated with the SDA unit, a plurality of refinery operation control devices configured 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 an 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 plurality of refinery operation control devices and the SDA unit based on application of one or more of data measured by the plurality of sensors, data corresponding to analysis from the one or more sample analysis assemblies, or 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.

[0016] In some embodiments, a system for enhancing fluid production for a supercritical solvent deasphalting operation comprises a supercritical solvent deasphalting unit to receive a feedstock and produce a fluid, a plurality of sensors positioned proximate the supercritical solvent deasphalting unit or within the supercritical solvent deasphalting unit and configured to measure a parameter associated with the supercritical solvent deasphalting unit, a plurality of refinery operation control devices configured 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 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 controller configured to determine an outputincluding 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 data measured by the plurality of sensors, data corresponding to analysis from the one or more sample analysis assemblies, or 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.

[0017] 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

[0018] 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.

[0019] 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.

[0020] FIG. 2 is a simplified diagram that illustrates an apparatus for enhanced fluid production at a refinery, according to an embodiment of the disclosure.

[0021] FIG. 3 is another simplified diagram of a refining control system to enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0022] 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.

[0023] FIG. 5 is a schematic diagram of a refinery, according to an embodiment of the disclosure.

[0024] FIG. 6 is a schematic diagram of hydrocarbon refinery products produced by the refinery and their movement into blending pools, including an asphalt binder blending pool, according to an embodiment of the disclosure.

[0025] FIG. 7 is a schematic diagram of a machine learning model that may be used with the various processes within a refinery, according to at least one embodiment of the disclosure.

[0026] FIG. 8A 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.

[0027] FIG. 8B is a simplified schematic diagram illustrating one embodiment of the solvent deasphalting unit controller, according to an embodiment of the disclosure.

[0028] FIG. 9 is a schematic diagram of supercritical solvent deasphalting control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0029] FIG. 10 is a simplified schematic diagram of a solvent deasphalting unit including a control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0030] FIG. 11A and FIG. 11B are simplified diagrams of control systems to enhance to enhance fluid production at refinery, according to an embodiment of the disclosure.

[0031] FIG. 12 is a flow chart illustrating enhanced fluid production at a refinery, according to an embodiment of the disclosure.

[0032] FIG. 13 is a simplified flow diagram of a method of operating a solvent deasphalting unit, according to at least one embodiment of the disclosure.DETAILED DESCRIPTION

[0033] 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 toprocess 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.

[0034] The disclosure herein provides embodiments of systems, analyzers, controllers, and associated methods for enhancing fluid production (e.g., production of product materials (product streams)) 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, 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 suboperations.

[0035] 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. Non-limiting examples of fluids used herein may refer to a liquids, gases, vapors, or other materials. Some materials may be solid at room temperature, but may be flowable liquids or viscous materials at higher temperatures. The fluid may include a hydrocarbon and final product may include a transportation fuel, deasphalted oil,pitch, and / or an asphalt binder. “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 exist 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, may refer 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.

[0036] In some embodiments, the disclosure is directed to systems, analyzers, controllers, and associated methods for enhancing fluid production from a solvent deasphalting unit using a machine learning model. The solvent deasphalting unit may be configured to process one or more feedstock materials (e.g., atmospheric tower bottoms material, vacuum tower bottoms materials (e.g., high viscosity vacuum tower bottoms material), gas oils, or other materials) to separate lighter components from heavier components and form, for example, a product stream (material) comprising deasphalted oil and a product structure comprising pitch. The deasphalted oil may be further processed, such as in a catalytic cracker, hydrocracker, or a gas oil hydrotreater. The solvent deasphalting unit may includea controller configured to increase the amount of deasphalted oil produced while meeting product specifications (e.g., having less than a predetermined threshold concentration of metals such as nickel and vanadium, having less than a predetermined asphaltene weight percent (e.g., content)) while also facilitating formation of pitch with desirable rheological properties such that the pitch can be pumped.

[0037] The solvent deasphalting unit may include an asphaltene separator (also referred to as a “deasphalting tower”) configured to receive the feedstock and separate heavier components from the lighter components to form the deasphalted oil and the pitch. In some embodiments, the asphaltene separator is configured to receive a solvent formulated and configured to selectively extract the lighter components from the feedstock to form an asphaltene separator overhead including the deasphalted oil and the solvent; and an asphaltene separator bottoms including the pitch and the solvent. The asphaltene separator overhead may be processed in a deasphalted oil separator and / or a deasphalted oil stripper configured to separate the solvent from the deasphalted oil; and the pitch may be separated from entrained solvent in an asphalt separator and / or asphalt stripper configured to separate the solvent from the pitch. In some embodiments, the solvent deasphalting unit comprises a supercritical solvent deasphalting unit.

[0038] One or more sensors may be disposed throughout the solvent deasphalting unit and / or other processing units of the refinery. The sensors may be configured to generate sensor data indicative of one or more properties or conditions within the solvent deasphalting unit and / or one or more properties or a composition of fluids (e.g., materials, such as liquids, vapors, or gases) within the solvent deasphalting unit and / or the refinery. By way of non-limiting example, the sensor data my include one or more of an operating condition (a temperature, a pressure) of one or more components of the solvent deasphalting unit, a temperature of the overhead stream of the asphaltene separator, a temperature and / or a pressure of a deasphalted oil stripper, a temperature and / or a pressure of a asphalt stripper, a composition of a solvent, a temperature of the solvent, a pressure of the solvent, a pressure of a flash drum, a flow rate of the feed material, a composition of the feed material, a temperature of the feed material, a metals concentration (e.g., weight percent) of the feed material, a flow rate of the overhead from the asphalt stripper, a flow rate of the pitch, a flow rate of the deasphalted oil, a composition of the deasphalted oil, a composition of the pitch, a quality of the deasphalted oil, a quality of the deasphalted asphalt, a hardness of the pitch, a softness of the pitch, or another property or condition.

[0039] The solvent deasphalting unit and / or the refinery may include one or more sample collection assemblies or systems for obtaining one or more samples of a fluid from the solvent deasphalting unit (e.g., a feedstock, an intermediate stream, the deasphalted oil, the deasphalted asphalt) and analyzing the samples to measure one or more properties thereof. One or more sample analysis assemblies may be configured to analyze the collected samples to measure, determine, and / or provide properties of the collected samples. In some embodiments, the one or more samples are analyzed in a laboratory. In some embodiments, the one or more samples (or at least one of the one or more samples) are analyzed using an in-line sensor, such as an in-line spectrometer. The one or more sample collection analysis assemblies may be configured to generate one or more properties of one or more of the feedstock, one or more intermediate streams, the deasphalted oil, or the pitch.

[0040] The solvent deasphalting unit may include a solvent deasphalting unit controller in signal communication with the solvent deasphalting unit, the one or more sensors, and the one or more sample analysis assemblies. The solvent deasphalting unit controller may include a machine learning model configured to receive input data comprising sensor data from the one or more sensors disposed throughout the solvent deasphalting unit and / or other processing units (e.g., upstream of the solvent deasphalting unit, downstream of the solvent deasphalting unit), and data corresponding to the analysis of the one or more collected samples (the one or more properties of the one or more of the feedstock, one or more intermediate streams, the deasphalted oil, or the pitch). In some embodiments, the input data includes a target parameter comprising at least one of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch yield, or a target pitch quality. In some embodiments, the input data to the machine learning model includes the data from the sensors and the analysis data (e.g., composition, property) with respect to one or more of the feed materials, the intermediate streams, the deasphalted oil, or the pitch. The machine learning model may be referred to herein as a “solvent deasphalting unit controller model.”

[0041] The solvent deasphalting unit controller may be configured to generate one or more predicted parameters, such as one or more of a predicted flow rate or a predicted quality of at least one of the deasphalted oil or the pitch based on the inputs; and, based on the predicted parameters, generate an output comprising one or more operating conditions of the solvent deasphalting unit to generate the target parameter. Based on the output, the solvent deasphalting unit controller may be configured to adjust one or more operating conditions of the solvent deasphalting unit. The machine learning model may be trained to generate the output based on the input. In some embodiments, the machine learning modelmay be trained using historical data from the solvent deasphalting unit, such as historical data from the one or more sensors and historical data from samples obtained from the one or more sample analysis assemblies.

[0042] In some embodiments, the solvent deasphalting unit controller includes at least two machine learning models. For example, a first machine learning model may be applied to the input data to generate an output comprising the predicted at least one of the flow rate of the quality of the at least one of the deasphalted oil or the pitch. The first machine learning model may include predictive control circuitry comprising a first-principles model. The first machine learning model may be trained with training data comprising first training inputs comprising the sensor output (also referred to as “sensor data”), data from the sample analysis assemblies during a training period; and first training outputs comprising a deasphalted oil yield, a deasphalted oil quality, a pitch yield, and a pitch quality during the training period. In some embodiments, the solvent deasphalting unit controller includes a plurality of the first machine learning models, each configured to be applied to the input data to generate the predicted parameters. Each first machine learning model may comprise a part of a predictive control and may be associated with a particular piece of equipment of the solvent deasphalting unit and / or a particular portion of the solvent deasphalting unit.

[0043] A second machine learning model may be configured to receive one or more inputs comprising the output from the first machine learning models; the sensor outputs, the data from the sample analysis assemblies, (e.g., data about one or more of the feed material, one or more intermediate streams, the deasphalted oil, or the pitch); and a target parameter. Based on the inputs to the second machine learning model, the second machine learning model may be configured to generate an output comprising changes in the one or more operating conditions of the solvent deasphalting unit and / or one or more upstream processes (e.g., to generate a desired feed composition) to achieve the target parameter and / or relative changes to the deasphalted oil yield, the deasphalted oil quality, the pitch yield, and the pitch quality caused by the changes in the one or more operating conditions.

[0044] In some embodiments, the solvent deasphalting unit controller comprises a local enhancement module includes an algorithm configured to facilitate optimization of solvent deasphalting unit to achieve the target parameters (e.g., the objective function) based on the outputs from the first machine learning models (e.g., of predictive controls modules of the solvent deasphalting unit controller), the target parameters, unit constraints, and inputs. The algorithm may be configured to facilitate optimization of the solvent deasphalting unit(e.g., maximization of deasphalted oil lift) based on a machine learning model. The local enhancement module may control the refinery operation control devices based on the outputs and constraints of the solvent deasphalting unit. In some embodiments, the local enhancement module 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), the target parameters, unit constraints, and inputs. The local enhancement module may control the refinery operation control devices based on the outputs and constraints of the solvent deasphalting unit.

[0045] 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 (which may form a data set) 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. The outcome may include, for example, a composition of the deasphalted oil, a composition of the pitch, a composition of an asphalt binder, one or more properties of the deasphalted oil, one or more properties of the pitch, one or more properties of the asphalt binder, a flow rate of a feedstock to the solvent deasphalting unit, operating conditions of a solvent deasphalting unit, and / or a flow rate and / or a volume of different asphalt binder components to form an asphalt binder having desired properties. 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-principles 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 may be used or generated 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 sub-operation 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 someother 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.

[0046] Once these data sets have been received by the controller (e.g., the solvent deasphalting unit 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 / or upsets), 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).

[0047] 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 achieved that threshold, then the controller may output the trained machine learning model for further use.

[0048] 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 testingand / 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.

[0049] 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, steam management, hydrogen coordination or management, absorption, propylene splitting operations or processes, aromatic recovery, sulfur recovery, coker unit operations, feed optimization, IMO blending, hydrocracker operations, other blending operations, asphalt binder blending operations, 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, an 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 an SDA unit may include utilization of historical data corresponding to that SDA unit. Various aspects of one model may be utilized to train other models for other similar equipment though. In some embodiments, an SDA unit or a supercritical solvent deasphalting unit at one refinery may exhibit different characteristics than an SDA unit or a supercritical solvent deasphalting unit at a second refinery. Thus, a model trained for an SDA unit or a supercritical solvent deasphalting unit at a first refinery may not be the same or work for an SDA unit or a supercritical solvent deasphalting unit at a second refinery. Accordingly, training a machine learning model for an SDA unit or a supercritical solvent deasphalting unit may include utilization of historical data and current data corresponding to that particular SDA unit or supercritical solvent deasphalting unit.

[0050] Once a model (e.g., a machine learning 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 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 devices 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 subcontrollers, and / or laboratory data indicative of properties and / or a composition of one or more feed materials, intermediate materials, and product materials, such as deasphalted oil, pitch, and / or asphalt binder feedstocks. In another embodiment, one or more operation controllers may obtain such data, as well as target products, target parameters, and / or other factors or parameters from a refinery controller or platform.

[0051] 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. In addition, one input to any of the models described herein may include properties of one or more deasphalted oil, pitch, asphalt binder feedstocks, and / or one or more blended asphalt binders. For example, the input may include a performance grade (PG), a high temperature compliance, a low temperature compliance, a usable temperature range, a viscosity, an m-value (before and / or after aging), a ATC, or a G* / sin(5) value of the pitch. 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.

[0052] Once the controller or controllers has / have obtained data related to each operation and / or analysis of one or more fluids (e.g., liquids, gases, vapors) associated with the operation, 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.

[0053] 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.

[0054] In another embodiment, the controller may optimize an operation based on the current demand for selected products. For example, for a particular targeted product (e.g., deasphalted oil, gasoline formed from cracking deasphalted oil), selected amounts of feed and / or intermediaries may be utilized, increasing the demand for that 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.

[0055] 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 acomparison, the controller may adjust various aspects of that operation to facilitate formation of a material (e.g., a blended asphalt binder, an asphalt binder feedstock) having desired properties.

[0056] 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) acheive 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 near real-time using data from continuous and / or ongoing refinery operations.

[0057] Thus, rather than attempting to adjust operations at a significant delay, a refinery’s operations may be adjusted in near 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. In addition, since the refinery may include multiple interrelated process units, wherein the operation of an upstream unit affect the subsequent operation of a downstream unit, the use of the controllers including the machine learning models described herein, may facilitate improved control of complex interrelated processes. A refinery controller may include multiple layers of individual controls, each individual control configured to control an operation of a particular sub-operation or processing unit. In addition, each individual control may include multiple layers, each including predictive control modules each including a machine learning model configured to receive inputs associated with particular equipment or portions of the particular sub-operation to generate a predicted parameter of the sub-operation. The individual control may further include a local enhancement circuity configured to receive, as an input, at least the outputs (the predicted parameters) from the predictive control modules to generate an output comprising operating conditions and / or feedstock conditions to achieve the target parameter.

[0058] FIG. 1 A and FIG. IB simplified diagrams of a refining control system to enhance fluid production at a refinery, such as the production of one or more product streams, 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. 1 A, 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, an SDA unit including at least an asphaltene separator, a supercritical SDA unit including at least an asphaltene separator, among other equipment. Further, each unit or equipment at the refinery 100 may be optimized using the machine learning models 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 meeting desired specifications.

[0059] 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. In some embodiments, the model comprises a classifier including one or more machine learning algorithms used to assign a class label to input data. The refinery controller 101 and / or the plurality of operation controllers 102 may individually connect to or be in signal communication (e.g., operable communication) with (a) one or more sensors, meters, transducers, and / or other measurement devices positioned throughout the refinery 100 (b) to the equipment (for example, connected to some control aspect or device associated with the equipment) positioned at the refinery 100, and / or (c) user input or data from a server, such as data related to laboratory analysis of one or more samples from the refinery 100 and / or individual operations within the refinery 100, such as from a particular operation. The refinery controller 101 may be configured to receive data via such a connection. Further, the refinery controller 101 may receive such data in 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. In some embodiments, the refinery controller is configured todetermine operating parameters to achieve a target product and / or target parameters. 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 of the refinery controller 101.

[0060] With reference to FIG. IB, in some embodiments, each of the operation controllers 102 may include a local enhancement circuitry 184, predictive controls circuitry 194, 191, and / or 195 (also simply referred to as “predictive controls”), and / or equipment and device controls 199. In embodiments, each of the local enhancement circuitry 184, the predictive controls circuitry 194, 191, 195, and the equipment and device controls 199 may be a module or instructions and may include a machine learning model. In embodiments, the operation controller 102 may include one or more varying or different predictive controls. The predictive controls circuitry 191, 194, 195 may be configured to predict at least one of a flow rate or a quality of a material (e.g., feedstock resid materials, resid material to each of a plurality of resid destruction sub-units), a composition of the material, a quality of an intermediate stream, a flow rate of an intermediate stream, or a composition of an intermediate stream based on one or more inputs. The one or more inputs may include, for example, sensor outputs from one or more sensors disposed within the refinery 100, such as within an operating unit of the refinery 100 (e.g., within a resid destruction unit). 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. In some embodiments, the trained machine learning model 193 is a trained machine learning model configured to predict one or more of a flow rate, a composition, or a quality of a product from a piece of equipment (e.g., a coker furnace, a coke drum, an asphalt separator) based on one more inputs including one or more of a flow rate, a quality, or a composition of a feed material to the piece of equipment, an operating temperature of the equipment, or a pressure of the equipment. As such, the operation controller 102 may include a plurality of predictive controls circuitry 191. In some embodiments, the trained machine learning model 193 is configured to predict one or more of a flow rate, a composition, or a quality of feedstock resid materials based on the input data. The operation controls may also include predictivecontrols circuitry 194, which includes a trained machine learning model 196 and / or a first- principle model 198 (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 102 may also include predictive controls 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. In some embodiments, the first- principles model 197 is an existing first-principles model 197 and may be used to generate data (e.g., a data set) for a refinery rather than sensor and analysis data from the refinery. In some embodiments, the machine learning model of the predicative controls 195 may be used to fit, for example, coefficients of the first-principles model 197 (such as a reaction equation coefficient) to more closely match the first-principles model 197 to the refinery or actual refinery operation.

[0061] In an embodiment, the operation controller 102 may include a local enhancement circuitry 184. The local enhancement circuitry 184 may be in operable communication with each of the predictive controls circuitry 194, 191, and / or 195. The local enhancement circuitry 184 may include a trained machine learning model 190 and target setpoint instructions 192. In some embodiments, the target setpoint instructions 192 are received from a user input or from the refinery controller 101. The trained machine learning model 190 may utilize data associated with a specific refining operation and / or the output from each predictive controls circuitry 194, 191, 195 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 achieve a target product (e.g., a target product having one or more of desired specifications, properties, or characteristics, such as a flow rate, a quality, or a composition of deasphalted oil from an SDA unit). The operation controller 102 may also include an equipment and device controls 199. The equipment and device controls 199 may cause equipment and / or devices to adjust to the target setpoints. The equipment and device controls 199 may include, for example, one or more of temperature controls, flow rate controls, pressure controls, feedstock flow rate controls, product flow rate controls, or other controls associated with equipment within the specific refining operation. By way of non-limiting example, and as described with reference to FIG. 8 A through FIG. 10, the equipment may include one or more of an asphaltene separator, a heater of a solvent deasphalting unit, a deasphalted oil stripper, an asphalt stripper, a flash drum, a heatexchanger of a solvent deasphalting unit, or another component of a solvent deasphalting unit.

[0062] 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. As described with reference to FIG. 8 A through FIG. 10, the sample analyzers 188 may be configured to determine one or more properties of a feed material to an SDA unit and / or a product of the SDA unit (e.g., of deasphalted oil). 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 near-infrared spectroscopic analyzer and a midinfrared 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. In some embodiments, the sample analyzers 188 include viscosity analyzers, such as an in-line viscometer. In some embodiments, the sample analyzers 188 include analyzers that may be used to analyze one or more properties of feedstocks to an SDA unit, deasphalted oil, or pitch, such as a concentration of metals (e.g., a metal content) of the feedstocks, a concentration of metals in the deasphalted oil, a concentration of metal in the pitch, a carbon residue (e.g., one or more of a Conradson carbon residue (CCR), micro residue carbon (MCR) (e.g., weight percent), a Ramsbottom carbon residue (RCR) (e.g., weight percent)) of the feedstocks, a carbon concentration of the deasphalted oil, a carbon concentration of the pitch, a viscosity of the feedstocks, a viscosity of the deasphalted oil, a viscosity of the pitch, or another property of the feedstocks or the product streams. In some embodiments, the sample analyzers 188 are used to analyze a feed material and / or a product material (e.g., deasphalted asphalt, pitch) and measure one or more of a shear strain (y), a complex shear modulus (G*), a phase angle (5), an m-value, an S-value (a creep stiffness), a ATC, a high temperature compliance, a low temperature compliance, a usable temperature range, a performance grade, a SARA analysis, a metals concentration, a sulfur concentration, a viscosity, or another property. In some embodiments, some of the sample analyzers 188 are located within the process unit and some of the sample analyzers 188 are located in alaboratory. As used herein, the carbon residue of a material refers to the amount (e.g., the concentration, such as the weight percent) of the carbonaceous material that remains after volatile components have been removed through heating and may be a method of measuring the tendency of the material to form carbon deposits, such as coke. The carbon residue may also be referred to as the carbon residue concentration.

[0063] 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 of programmable 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.

[0064] 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.

[0065] 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, anymachine-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.

[0066] 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 near 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.

[0067] 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, deasphalted oil, residua (residue, residuum, resid), 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 (e.g., in a fractionator column 148). 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 the 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 refinery controller 101. For example, one trained machine learning model within the predictive controls module of predictive controls circuitry 191 may be trained to maximize or be utilized for maximizing operating temperature in relation to feedstock and a threshold temperature that may cause over-cracking. 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 104 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 (or increases) the amount of one or more products (e.g., increasing a 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 of local enhancement circuitry 184 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 controls 199. Other models may be trained to determine parameters based on other relationships associated with the reactor 104 and / or other equipment.

[0068] 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 an online optimizationalgorithm (which may also be referred to as the local enhancement module) to generate or determine targets.

[0069] The refinery 100 may include a regenerator 120. While a reactor 104 with a side- by-side configuration with the regenerator 120 is illustrated in FIG. 1A, it will be understood that other configurations of the reactor 104 and regenerator 120 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 116, 124, 126, 128, 132, 134, and 138, flow control devices associated with the regenerator 120 (such as valves 118, 130, 136, and 142), and / or the regenerator 120, 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 oxygen and 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 provide (e.g., recycle) 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 enhance operation of the regenerator 120, the reactor 104, and / or the product generated. The trained machine learning models may be trained or utilized to determine parameters to maximize the amount of carbon build up 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.

[0070] 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 the refinerycontroller 101 and / or operation controllers 102 and / or one or more of the sub-controllers , each of which 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, off gas 152, LPG 156, alkylate 162, gasoline 170, diesel 176, slurry 182, 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).

[0071] In an embodiment, the refinery controller 101 and / or operation controllers 102 may obtain data in near 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 positions within the refinery 100 to be collected and analyzed. In yet another embodiment, each of the operation controllers 102 may obtain data related to a selected section (e.g., process, unit operation) 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 modules of predictive controls circuitry 194, 191, 195 to produce parameters to produce a target product. The predictive controls modules of the predictive controls circuitry 194, 191, 195 may each include one or more machine learning models configured to receive the properties and / or spectra and data and generate an output based on the properties and / or spectra and data. The local enhancement module of local enhancement circuitry 184 of the operation controller 102 may then apply, to a trained machine learning model of the local enhancement module of local enhancement circuitry 184, 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 199.

[0072] 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 101 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 102 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.

[0073] FIG. 2 is a simplified diagram that illustrates an apparatus for enhanced 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 comprise a 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 FIG. 1 A, FIG. IB, and below in connection with FIG. 3 through FIG. 12.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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 communications circuitry 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.

[0078] The apparatus 200 may include a modeling circuitry 208 configured to obtain parameters from one or more components, equipment, devices, sensors, and / or analyzersand / 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). In some embodiments, the modeling circuitry 208 may be applied to an output from another machine learning model (e.g., additional plurality of modeling circuitry that each correspond to one of a plurality of suboperations). 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.

[0079] In another embodiment, the modeling circuitry 208 may train a machine learning model to generate 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 208 may 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 achieving the target product’s properties).

[0080] 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.

[0081] 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 FIG. 1 A and FIG. IB and below in connection with FIG. 3 through FIG. 12. 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).

[0082] 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. It will be noted that “fluids” may include solid materials, slurries, and materials having a relatively high viscosity and / or that are solids at room temperature, such as pitch. 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; an operation of an SDA process; an operation of a supercritical solvent deasphalting process). 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 FIG. 1 A and FIG. IB and below in connection with FIG. 3 through FIG. 102. 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.

[0083] 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 (from the modeling circuitry 208) 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 FIG. 1 A and FIG. IB and below in connection with FIG. 3 through FIG. 12. The equipment and device adjustment circuitry 212 may further utilize communications circuitry 206 to transmit signals to adjust equipment and / or devices utilized.

[0084] 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 202-212may 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.

[0085] 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.

[0086] 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 third party 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.

[0087] 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 FIG. 1A and FIG. IB and FIG. 3 through FIG. 12) 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.

[0088] 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, which may correspond to the operation controllers 102 (FIG. 1 A, FIG. IB). 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 (e.g., be in operable communication with) 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 306 A, valve 306B, and up to valve 306N). In such embodiments, each of feed A 303A, 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, an SDA unit, a supercritical solvent deasphalting unit, 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 310 N. 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 more end 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.

[0089] In an embodiment, as each feed is fed to the next processing unit 314, 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 composition of the feed and the spectra or properties determined via spectrographic analysis and / or other analysis of the feed. For example, as illustrated, the operation controller 302 may determine or obtain feed information 324 (including, at least feed content 326 and / or feed properties 328 (e.g., metals concentration, viscosity, carbon residue concentration), among other data), unit material information 330 (including, at least unit material content 332 and / or unit material properties 334, among other data), and / or end material information 336 (including, at least end material content 338 and / or end material properties 340, among other data). Thus, the operation controller 302 may obtain data related to each feed / material in near real-time, during a refinery operation, and / or directly or indirectly (for example, spectra may be obtained via a sample or spectrographic analyzer).

[0090] 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 354 and target properties 356), and / or material differences 344 (including content differences 346 and properties differences 348) as determined via a comparator 342 (the comparator 342 positioned or configured to compare composition 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 342 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).

[0091] In another embodiment, the output of the machine learning model 360 (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 suchembodiments, if the comparator 342 determines that there is a difference between an output of the machine learning model 360, then the parameter settings of the equipment or devices at the refinery may be adjusted.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] As noted, data may be obtained in real time or near 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 generateadjusted targets after each sub-controller generates a target for a specific processing unit. Thus, the overall adjustment 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.

[0096] In another embodiment, a refinery may include a plurality of operation controllers 302. Each operation controller 302 may include a plurality of trained machine learning models 360. Each trained machine learning model 360 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.

[0097] 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.

[0098] As noted, the machine learning models described herein may be trained using data, which may be referred to as training data or training input 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., feed content), feed properties, material composition (e.g., material content), material properties, a target product or products, target composition (e.g., target 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, thedesired 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 may be 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 attribute or parameter. Another model may be trained to utilize the outputs of each of those plurality of models, in addition to data.

[0099] Once the historical equipment specific data 402, and any other current data (e.g., current and marked up equipment specific data 404), is available, that data may be pre- processed 406. In such embodiments, pre-processing of the data includes normalizing the data. 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 start-up, 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.

[0100] Once the data set has been pre-processed, a model may be trained 408 to form a trained machine learning model or a trained machine learning model 412. 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 achieve the known desired outcome and what parameters lead to the known undesired outcome and / or the weight of such parameters. Once the data has been used to train the machine learning model, 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 rateis 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.

[0101] Once the trained machine learning model 412 meets a selected error rate, the trained machine learning model 412 may be released for further use. In another embodiment, a separate 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.

[0102] FIG. 5 is a schematic diagram of a refinery 500. Crude oil 502 is initially processed by an atmospheric distillation tower 504 to separate different fractions of the crude oil 502 based, at least in part, on boiling point range. Lighter components from the atmospheric distillation tower 504 may include a gas 506, which may be sent to a gas processing unit 508. The gas processing unit 508 separates sour gas 509 from the gas 506 and other gas 507 resulting from different processes throughout the refinery. Gas processing unit 508 diverts the sour gas 509 to an amine treater 516. The remainder of the gas 506 and other gas 507 that is not sour gas may be referred to as a “fuel gas” and may be passed to a mercaptan treater 510 that separates mercaptans from the fuel gas (such as a mercaptan treater) and facilitates formation of liquid petroleum gas 512 (“LPG”) and butane 514. The butane 514 may be kept as a finished product, sent to a gasoline blending pool 543 (FIG. 6) and / or sent to a C4 isomerization unit 591 to be processed into isobutane 593 as a finished product or further sent to an alkylation unit 594.

[0103] The amine treater 516 may separate hydrogen sulfide from the sour gas 509 to form a refinery fuel 518 substantially free of hydrogen sulfide and a hydrogen sulfide gas 520. The hydrogen sulfide gas 520 and hydrogen sulfide gas collected from processes throughout the refinery 500 is sent to a sulfur plant 522, which may also be referred to as a “sulfur recovery unit” (SRU). The sulfur plant 522 converts the hydrogen sulfide gas 520 into sulfur 530.

[0104] Additionally, sour water 532 collected from processes throughout the refinery 500 may be sent to a sour water steam stripper 528. The sour water steam stripper 528 uses steam 534 to remove hydrogen sulfide gas 526 from the sour water 3532. The hydrogen sulfide gas 526 is also sent to the sulfur plant 522.

[0105] With continued reference to FIG. 5, the atmospheric distillation tower 504 separates light naphtha 536 from the crude oil 502. The light naphtha 536 may be sent to a hydrotreater 538 configured to remove sulfur from the light naphtha 536 and form desulfurized light naphtha. The desulfurized light naphtha may be sent to an isomerization unit 540 to be processed into isomerate 542. The isomerate 542 may include branched isomers of the light naphtha 536 (which may include straight chain hydrocarbons) and may exhibit a higher octane value than the straight chain hydrocarbons of the light naphtha 536. The isomerate 542 may be sent to a gasoline blending pool 543.

[0106] In addition to separating the light naphtha 536 from the crude oil 502, the atmospheric distillation tower 504 separates heavy naphtha 544 from the crude oil 502. Optionally, the heavy naphtha 544 may be provided to a splitter 545. The splitter 545 may include one or more splitter columns that separate heavier C7 or higher naphtha molecules from lighter components of the heavy naphtha 544. The heavier C7 naphtha may be sent to the hydrotreater 554 to be desulfurized and produced as jet fuel 558 or a component of jet fuel 558. The remaining lighter components of the heavy naphtha 544 may be sent to a hydrotreater 546 to remove sulfur therefrom prior to being sent to the catalytic reformer 548 to be converted into reformate 550. Alternatively, the heavy naphtha 544 may be sent directly to the hydrotreater 546 to remove sulfur from the heavy naphtha 544 prior to being sent to the catalytic reformer 548. The reformate 550 includes high-octane branched and cyclic hydrocarbons, such as benzene, toluene, xylene, and ethylbenzene. The reformate 550 may be sent to the gasoline blending pool 543.

[0107] Another product from the atmospheric distillation tower 504 is jet fuel 552. The jet fuel 552 may include kerosene and other equivalent hydrocarbons. The jet fuel 552 may be sent from the atmospheric distillation tower 504 to a hydrotreater 554 to remove contaminants from the jet fuel 552, such as sulfur and mercaptans, to form a finished jet fuel 558 meeting desired specifications. Once desulfurized, the finished jet fuel 558 may be sold or sent to a jet fuel blending pool 559 to be blended with other products and additives and then made available for sale and distribution. The jet fuel 552 may also be separated into kerosene.

[0108] With continued reference to FIG. 5, diesel 560 is another product separated from crude oil 502 by the atmospheric distillation tower 504. The diesel 560 is sent from the atmospheric distillation tower 504 to a hydrotreater (e.g., a diesel hydrotreater) 562 to remove sulfur from the diesel 560 and form desulfurized diesel 564. The desulfurized diesel 564 may then be sold or sent to a diesel blending pool 565.

[0109] The atmospheric distillation tower 504 also separates atmospheric gas oil 566 and atmospheric bottoms 568 from the crude oil 502. The atmospheric bottoms 568 may be sent to a vacuum distillation tower 570 where the atmospheric bottoms 568 may be further separated into low vacuum gas oil 572 (“LVGO”), medium vacuum gas oil 599 (“MVGO), heavy vacuum gas oil 584 (“HVGO”), and vacuum residuum 521. Vacuum distillation tower 570 may also be configured to separate the atmospheric bottoms 568 into more or less components than that described.

[0110] The vacuum residuum 521 may be sent to a solvent deasphalting unit 598 (“SDA”) or used directly in asphalt 519, which may be used in an asphalt binder. In some applications, the vacuum residuum 521 may be sent to an asphalt binder blending pool 606 (FIG. 6). The SDA 598 may be used to extract lighter components from the vacuum residuum 521 using solvents such as propane, butane (n-butane, isobutane), or combinations thereof to extract deasphalted oil 501 from the vacuum residuum 521 and form the deasphalted oil 501 and a deasphalted asphalt, also referred to as pitch 579. The deasphalted oil 501 may be sent to a hydrocracker 586 or a fluid catalytic cracker 576 for refining into hydrocarbon products including naphtha, jet fuel, diesel, and fuel oil. In some embodiments, the deasphalted oil 501 is provided to a gas oil hydrotreater. The pitch 579 includes the vacuum residuum 521 after removal of the lighter components. The pitch 579 may also be used in the asphalt binder blending pool 606 (FIG. 6).[OHl] The atmospheric gas oil 566, the LVGO 572, the MVGO 599, and deasphalted oil 501 from the SDA unit 598 may be sent to a hydrotreater 574 to remove sulfur, after which the hydrotreated material is fed into the fluid catalytic cracker 576 and / or the deasphalted oil 501 may be sent to a hydrocracker 586. The fluid catalytic cracker 576 processes the atmospheric gas oil 566, the low vacuum gas oil 572, the medium vacuum gas oil 599, and / or the deasphalted oil 501 into naphtha 578, jet fuel 581, diesel 582, fuel oil 583, and butenes and pentenes 592.

[0112] The butenes and pentenes 592 from the fluid catalytic cracker 576, as well as the isobutane 593 from the C4 isomerization unit 591, may be sent to an alkylation unit 594 where the feedstocks are processed into alkylate 596. The alkylate 596 may then be sold or sent to the gasoline blending pool 543. The alkylate 596 may have a higher octane value and a lower Reid vapor pressure than the isobutane 493 and the butenes and pentenes 592.

[0113] The naphtha 578 may be sent to a hydrotreater 580 to further remove sulfur from the naphtha 578 and form desulfurized naphtha. The desulfurized naphtha may be sold or sent to a gasoline blending pool. The jet fuel 581 may also be passed through a hydrotreater585 to remove sulfur and other contaminants and may be sent to a jet fuel blending pool. The diesel 582 may be passed through a hydrotreater 587 to remove sulfur and other contaminants and sent to a diesel blending pool. The fuel oil 583 may be passed through a hydrotreater 589 to remove sulfur and other contaminants and sent to a fuel oil blending pool. In some embodiments, the fuel oil blending pool may be used to blend formulations of low sulfur fuel oil or ultra-low sulfur fuel oil.

[0114] The MVGO 599, HVGO 584, and the deasphalted oil 501 may be sent to the hydrocracker 586 to be processed into gasoline 588, diesel 590, and jet fuel 595. The hydrocracker 586 may also produce smaller (lighter) hydrocarbons that may be sent to gas processing unit 508. The hydrocracker 586 process may integrate desulfurization and other contaminant removal such that further hydrotreating may not be necessary for the products.

[0115] The vacuum residuum 521 and pitch 579 may also be sent to a coker 597 to be processed into lighter components and / or other materials, such as naphtha 503, jet fuel 511, diesel 513, fuel oil 515, and petroleum coke 517. The naphtha 503 may be processed through a gasoline desulfurization unit 556 (“GDU”), which may include one or more processes (e.g., hydrotreating processes) to remove contaminants from the naphtha 503 and may include catalysts, particulate catches, clay treaters, salt driers, and mercaptan treaters, separators, and steam strippers. The jet fuel 511 may be passed through a hydrotreater 523 and then sent to the jet fuel blending pool. The diesel 513 may be sent to a hydrotreater 525 to remove sulfur and then sent to the diesel blending pool. The fuel oil 515 may also be processed through hydrotreater 527 and then sent to the fuel oil blending pool. The pitch 579 may also be sent to an asphalt blending operation and may form at least a portion of an asphalt binder. In addition, the pitch 579 may be sold without additional processing.

[0116] The hydrotreaters 538, 546, 554, 562, 574, 580, 585, 587, 589, 523, 525, and 527 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.

[0117] Many of the connections, feedstocks, and outputs are not shown in FIG. 5, 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, the atmospheric distillation tower 504 and the vacuum distillation tower 570 may each represent multiple units set up in parallel or series, and may separate their respective feedstocks into more or fewer 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 theproducts may be passed through isomerization, reformation, and alkylation processes not shown in FIG. 5 to process the products and components to meet regulatory requirements and customer specifications.

[0118] FIG. 6 is a schematic diagram of hydrocarbon refinery products 602 produced by the refinery and their movement into blending pools 604, including an asphalt binder blending pool 606, according to at least one embodiment of the disclosure. Each blending pool 604 stores products from various refinery product streams and products from other sources in storage tanks 608 and may use these products to blend these products into different formulations that meet various regulatory requirements, industry standards, and customer specifications. For example, materials from the asphalt binder blending pool 606 may be used to blend an asphalt binder 630 having a desired composition and / or one or more desired properties.

[0119] As shown in FIG. 6, the asphalt binder blending pool 606 may include one or more refinery products 602, such as one or more of asphalt 519, heavy vacuum gas oil 584, medium vacuum gas oil 599, low vacuum gas oil 572, vacuum gas oil that may be obtained from vacuum distillation tower 570 as a combination of medium vacuum gas oil 599 and heavy vacuum gas oil 584, atmospheric gas oil 566, vacuum residuum 521, deasphalted oil 501, or pitch 579. The asphalt binder blending pool 606 may also include components from other sources 610, including pitch 612, asphalt 614, MVGO 616, HVGO 618, polymer 620, biomaterial 622, and polyphosphoric acid 624. The polymer 620 may include polymers such as styrene-butadiene-styrene, crumb rubber, devulcanized rubber, and / or other materials.

[0120] The constituents of an asphalt formulation include oils, resins, and asphaltenes. In some embodiments, the constituents further include saturates. The oils may include relatively lighter components, such as components having a molecular weight within a range of from about 24 g / mol to about 800 g / mol. Resins are the more polar fraction and may include components having a molecular weight within a range of from about 800 g / mol to about 2,000 g / mol. Asphaltenes may include relatively higher molecular weight components having a molecular weight within a range from about 1,800 g / mol to about 8,000 g / mol and possess aromatic rings.

[0121] The composition of the asphalt binder and the blending feedstocks used to blend the asphalt binder 640 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.

[0122] Each of the feedstocks used to form the asphalt binder 630 may exhibit attributes that may be measured and specified through testing. The feedstocks may exhibit one or more of a performance grade, a high temperature compliance, a low temperature compliance, a usable temperature range, a viscosity, an m-value (before and / or after aging), ATC, ATCafter 20 hour PAV aging, ATCafter 40 hour PAV aging, G* / sin(5) value, and SARA content.

[0123] The asphalt binder 630 may be blended to exhibit one or more desired properties, such as 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, load bearing performance, performance grade, high temperature compliance, low temperature compliance, usable temperature range, viscosity, m-value before aging, m-value after aging, ATC, ATCafter 20 hour PAV aging, ATCafter 40 hour PAV aging, G* / sin(5) value, and SARA content. Each formulation of asphalt binder 630 from the asphalt binder blending pool 606 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 asphalt binder blending pool 606.

[0124] Low temperature compliance for an asphalt may be determined as the temperature at which stiffness or m-value fails. The m-value is a parameter that represents the rate of change of stiffness at low temperatures and may be indicative of thermal cracking resistance. The m-value may be determined by the bending beam rheometer test at low temperatures on asphalt binders that have been aged in a pressure aging vessel for about 20 hours or more. A usable temperature range of an asphalt represents the high temperature found through high temperature testing and the low temperature found through low temperature testing.

[0125] The different components of the asphalt binder blending pool 606 are mixed together to create the blended product attributes that comply with regulatory requirements and / or desired product specifications. All products produced via refining processes including but not limited to the refinery products 602 and products from other sources 610, including purchased products may be added to the asphalt binder blending pool 606 and blended into saleable products in compliance with regulatory and customer specified constraints. Blended formulations are often sold into markets with different specifications requiring strict product segregation, quality assurance, quality controls. Specifications for formulations may be based on location with regulations varying significantly between jurisdictions. Segregation of components within the asphalt binder blending pool 606 may be required by standards and regulatory requirements. For example, products blended with renewable products may occur at a terminal to avoid contamination of storage tanks within the asphalt binder blending pool 606.

[0126] Each asphalt binder 630 formulation and each of the feedstocks used to form the asphalt binder 630 may be tested in laboratory. Testing may include tests for high temperature compliance including original binder dynamic shear rheometer test that is used to evaluates the shear resistance of the unaged asphalt binder to determine the stiffness and elasticity of the asphalt binder at high temperatures. High temperature compliance may also be determined through rolling thin film oven aging, which simulates short-term aging, and may be followed by dynamic shear rheometer test of the short-term aged asphalt binder. The failure temperature of the short-term aged asphalt binder indicates the highest temperature at which the asphalt binder should maintain sufficient elasticity without becoming too stiff or brittle.

[0127] A complication in developing blended formulations, is that some attributes are not proportional while some are proportional to the amount contributed. For example, low temperature compliance, high temperature compliance, m-value, stiffness, and viscositymay not be proportional to the amount of each component used to form the asphalt binder 630; whereas the SARA content may be proportional to the ratio of feedstock materials used to form the asphalt binder 630.

[0128] The asphalt binder blending pool 606 may include a plurality of storage tanks 608. Each storage tank 608 may contain one or more of the refinery products 602 or products from the other sources 610. Each storage tank 608 may include a sensor package 626. Depending on the substance stored within the storage tank 608, the sensor package 626 may include level sensors, such as radar level sensors, ultrasonic level sensors, float & tape gauges, magnetostrictive sensors, and capacitive sensors. The sensor package 626 may also include temperature sensors, such as resistance temperature detectors, thermocouples, and infrared sensors, and pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors. The sensor package 626 may include gas and vapor sensors, such as volatile organic compound (“VOC”) sensors, hydrocarbon gas detectors, and oxygen sensors for monitoring leak detection and inert gas blanketing. The sensor package 626 may include flow rate sensors, such as Coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow in and out of the storage tank 608. The sensor package 626 may also include density and composition analyzers, such as refractometers, spectroscopy, and gas chromatographs that may be used to monitor the condition of the materials within the storage tank 608. In some embodiments, the sensor package 626 includes a spectrometer configured to measure one or more properties of the material within the storage tanks 608. The sensor package 626 may be configured to measure the metals concentration (e.g., nickel, vanadium), sulfur concentration, nitrogen concentration, and carbon residue concentration (e.g., MCRT). Further, the sensor package 626 may include safety and leak detection sensors, such as acoustic sensors, fiber optic sensors, and infrared gas leak detectors.

[0129] In some embodiments, a machine learning model may be used to improve (e.g., increase) the formulations produced by the asphalt binder blending pool 606 by creating simulations of various formulations and predicting the resulting attributes. In some applications, the machine learning model may seek improvements to viscosity at 140°F / 60°C, while also seeking improvements in one or more of durability, density, resistance to rutting, resistance to cracking, and altering or increasing the usable temperature range.

[0130] Data from the sensor package 626 may be used by a machine learning model to request certain refinery products 602 to be produced at faster or slower rates or recommendthat products and feedstocks from other sources 610 be provided to one or more storage tanks 608 in anticipation of blending a particular asphalt binder 630 formulation. The machine learning model may also make recommendations based on the quantities of particular products held in each storage tank 608. In other words, the machine learning model may adjust a process producing a refinery product 602 based on the inventory of the one or more materials in the asphalt binder blending pool 606. The adjustment may including changing operating parameters including one or more of temperature, pressure, and flow rates of a process, based on the inventory of a product in one of the asphalt binder blending pool 606. Alternatively, the machine learning model may adjust a process to produce more of a product or products with a desired component distribution and / or properties based on one or more of forecast information, demand predicted by the machine learning model based on the business data (e.g., business data 710 (FIG. 7)), regulatory changes, and a predicted market price for the product during a future time period. The machine learning model may create multiple simulations based on historical data (e.g., historical data 702 (FIG. 7)) and the business data that model potential prices for refinery products, then make a recommendation to adjust a process parameter based on a selected simulation. The simulation may be published on an engineering gateway (e.g., engineering gateway 712 (FIG. 7)) for approval by a user. The machine learning model may also make recommendations based on the business information available to it including forecasts, pending customer orders, and general demand in the market.

[0131] FIG. 7 is a schematic diagram of a machine learning model that may be used with the various processes within a refinery, according to at least one embodiment of the disclosure. The machine learning model may be used to optimize each blended formulation blended from the asphalt binder blending pool 606. In some embodiments, the machine learning model is used to optimize the performance of the refinery and / or a sub-operation, such as operation of an SDA unit. In some embodiments, the machine learning model obtains attribute data for each component in the asphalt binder blending pool 606 and other components that may be sourced from other refineries, third-parties, and generally available in the market that be used to create a desired blended formulation that meets a desired specifications. The machine learning model may create multiple combinations that may be compared against a specification and regulatory requirements. Each combination that meets the specifications and regulatory requirements is retained in a potential formulation list, and those that do not meet the specifications are discarded. The machine learning model may access business data to obtain pricing information for each component, calculate abase formulation cost for each combination in the potential formulation list, and order the list from lowest cost to the highest cost. Alternatively, the machine learning model may use the component attributes to extrapolate the anticipated attributes of each blended formulation and may order the potential formulation list according to an anticipated attribute. For example, a potential formulation list for an asphalt binder 630 may be ordered based on one or more of an anticipated performance grade, high temperature compliance, low temperature compliance, usable temperature range, viscosity, m-value before aging, m-value after aging, ATCbefore aging, ATCafter aging, or a G* / sin(5) value.

[0132] The machine learning model 700 may include a computer algorithm or model, such as a classification model, a regression model, a language model, an object detection model, a multi-modal model, or an artificial intelligence, that can be trained and tuned based on training input to approximate unknown functions. A machine learning model may refer to a neural network or other machine learning algorithm or architecture that learns and approximates complex functions and generates outputs based on a plurality of inputs provided to the machine learning model. Further, a “machine learning model” may refer to one or multiple machine learning models that cooperatively generate one or more outputs based on corresponding inputs. For example, a machine learning model may refer to any system architecture having multiple discrete machine learning components that consider different kinds of information or inputs.

[0133] The machine learning model 700 is connected to a historical database 702. The historical database 702 may include multiple separate databases of information including process data, incident information and analysis, business information, demand planning, historical forecast information, historical pricing and purchasing data, and process training information. In some embodiments, the historical database 702 may be a copy of historical databases that are maintained and updated by the machine learning model 700. The machine learning model 700 is also connected to a training database including training data 703 that includes the process data and historical information that is used for training of the machine learning model 700.

[0134] As discussed in relation to other figures of this disclosure, the machine learning model 700 may be used to analyze and improve specific processes, process controllers, and process interactions.

[0135] In some embodiments, the machine learning model 700 may receive feedstock sensor, sample, and process data 704 from a feedstock process controller 714 or directly from the sensors, sampling and testing systems, and labs obtaining data from the feedstockprocess. A feedstock process is any process preceding the targeted process under review by the machine learning model 700. For example, the feedstock process may include one or more of an SDA process performed within a SDA unit, an asphalt separation process, a deasphalted oil stripping process, an asphalt stripping process, or another process.

[0136] Further, the machine learning model 700 may receive targeted process sensor, sample, and process data 706 from a targeted process controller 716 or directly from the sensors, sampling and testing systems, and labs obtaining data from the targeted process. The machine learning model 700 may also receive subsequent process sensor, sample, and process data 708 from a targeted process controller 716 or directly from the sensors, sampling and testing systems, and labs obtaining data from the targeted process. The feedstock sensor, sample, and process data 704, the targeted process sensor, sample, and process data 706, and the subsequent process sensor, sample, and process data 708 may include operating pressure and temperature data for the components of each process and sub-process. The feedstock sensor, sample, and process data 704, the targeted process sensor, sample, and process data 706, and the subsequent process sensor, sample, and process data 708 may include material composition data describing the material moving through the process, such as feed rates, and quantities and percentages of contaminants, reactants, and the hydrocarbons moving through the process.

[0137] The machine learning model 700 may also access business data 710. Business data 710 may include demand planning information, forecasting information for various products, current pricing information, product distribution information, and information regarding the current and anticipated regulatory landscape. Business data 710 may also include information regarding the costs, availability, and location of storage, disposal, and in some cases carbon capture options of waste products from each process. Business data 710 may also include historical and current costs of each process and the refinery products, as well as current and historical market pricing for each product. Business data 710 may also include the inventory levels of various products that may be stored in the storage tanks 608 of the asphalt binder blending pool 606. The business data 710 may also include costs associated with utilities, such as stripping steam and fuels (e.g., natural gas) associated with forming steam.

[0138] The machine learning model 700 may also access lab data 711 that is obtained from laboratory analysis of samples collected from processes within a refinery and products produced by those processes. Lab data 711 may include chemical composition and component distribution data about each sample, as well as information about when andwhere the sample was taken, tests performed on the sample, and sensor data from the process at the time the sample was taken.

[0139] The machine learning model 700 may also access weather data 713. The machine learning model may build algorithms to predict the effect of weather on process operating parameters, feedstocks, the resulting products from those processes, and the effect of weather on the storage of products within the asphalt binder blending pool 606.

[0140] The machine learning model 700 may publish to and receive instructions from an engineering gateway 712. As used herein, “publish” means one or more of to simulate, send, or display. The engineering gateway 712 may act as a user interface for engineers to review process and machine learning model 700 data, recommendations, warnings, and requests. A user may use the engineering gateway 712 to assist the machine learning model 700 in refining and tuning its algorithms to better predict and adjust each process in response to changes in ambient weather, demand seasonality, and composition (e.g., content) and quality of feedstocks including the crude oil received for processing into refined hydrocarbons. The engineering gateway 712 may also be used to facilitate active learning by the machine learning model 700. A user may use the engineering gateway 712 to provide feedback to the machine learning model 700 to facilitate active learning. Feedback may include user approvals, user corrections, and user instructions of analysis, predictions, interpolations, data, and other recommendations that is provided by the machine learning model 700 through the engineering gateway 712.

[0141] The machine learning model 700 may access, receive data from, and publish instructions to the feedstock process controller 714, the targeting process controller 716, and a subsequent process controller 718. In some embodiments, the machine learning model 700 may adjust an algorithm used by the targeted process controller 716 based on changes identified from the adjusted algorithm. Once an adjusted algorithm has been selected by the machine learning model 700, the machine learning model 700 requests approval to implement the adjusted algorithm through the engineering gateway 712. Upon receipt of approval, the machine learning model 700 saves a copy of the approval information in the historical database 702 and sends the approved adjusted algorithm to the targeted process controller 716.

[0142] The machine learning model 700 includes a data analysis module 722. The data analysis module 722 may be used by the machine learning model 700 to review data and identify data that may be considered outliers and disregarded. Once the data set has been reviewed and amended to remove outlier data, the machine learning model 700 may savethe revised data set in either the training data 703 or the historical database 702 for retraining of the machine learning model 700, for analysis and adjustment of a targeted process, or for later use.

[0143] The machine learning model 700 may include an interpolation module 724. The interpolation module 724 may be used to analyze a data set and interpolate missing data from the data set. The interpolation module 724 may use the historical database 702 and current operational data from a process upstream from a targeted process to interpolate a composition of the feedstock that will be fed into the targeted process. For example, samples may be taken from the product of a process and the sample data recorded in connection with the operating parameters of the process. The interpolation module 724 may interpolate or infer the composition of the resulting product from the operating temperature of the process, the operating pressure of the process, or the feed rate of feedstock into the process. Consequently, based on the upstream data related to the processing of a feedstock, the machine learning model may interpolate, infer, or determine the composition of the feedstock that will be fed into a downstream process. Thus, feedstock composition data includes this upstream data related to a feedstock that may be used to determine the composition of the feedstock.

[0144] The interpolation module 724 may compare the historical database 702 with feedstock sensor, sample, and process data 704, the targeted process sensor, sample, and process data 706, and the subsequent process sensor, sample, and process data 708 to identify process changes. The interpolation module 724 may be configured to identify and flag small deviations for further investigation. The interpolation module 724 works with a communication module 728 to publish the data regarding the flagged deviation for user review and guidance. For example, the interpolation module 724 may be used to identify miscalibrated sensors, misprocessed test data, or misprocessed samples that may be inaccurate. The machine learning model 700 may accomplish this by identifying and labeling data as outliers. Labeled data may be associated with a sensor or data and then reported to a user through the engineering gateway 712. The machine learning model 700 may use the interpolation module 724 to identify components that may be wearing out and catalysts that may be deactivated or poisoned. The interpolation module 724 may also communicate through the communication module 728 with the engineering gateway 712 to identify these potential process concerns to a user for further investigation.

[0145] The machine learning model 700 may include a prediction module 726. The prediction module 726 may analyze the feedstock sensor, sample, and process data 704, thetargeted process sensor, sample, and process data 706, and the subsequent process sensor, sample, and process data 708 to predict changes in a process. For example, temperature excursions (e.g., of an asphaltene separator) may be predicted in a process and the prediction module 726 may communicate through the communication module 728 with the engineering gateway 712 to notify a user of a predicted temperature excursion and recommending process changes to avoid the temperature excursion. A user may accept the recommended process changes through the engineering gateway 712 or provide different instructions for the machine learning model 700 to implement. In predicting changes in a process, prediction module 726 may recommend regeneration or replacement of a catalyst or repair or replacement of a component of a process as part of a maintenance procedure. The prediction module 726 may provide a recommended maintenance window for the maintenance procedure to occur.

[0146] The machine learning model 700 may include the communication module 728. The communication module 728 may translate recommendations, instructions, and data from other modules from machine code into a human language or convert data into graphs and other visual communication elements. The communication module 728 may send or publish communications to the engineering gateway 712. The communication module 728 may also communicate with the various process controllers and other models used by the refinery.

[0147] In some embodiments, the machine learning model 700 includes a confidence module 730. The confidence module 730 may review the analysis and recommendations of the different modules of the machine learning model 700 and assign a confidence level to the analysis and recommendations. For example, the confidence module 730 may produce Shapley Additive Explanations (SHAP) values, use local interpretable model-agnostic explanations (LIME), or anchors to analyze each algorithm that is adjusted or created by the machine learning model 700. The confidence module 730 may compare predicted or anticipated values from a simulation or model with actual data to generate a confidence level that may include a calculation of the standard deviation between the predicted or anticipated values and the actual measured data. The results may be published by the communication module 728 to the engineering gateway 712 to assist a user in reviewing each algorithm and the changes recommended by the machine learning model 700.

[0148] In some embodiments, the machine learning model 700 includes a regulatory module 732. The regulatory module 732 may access the business data 710 to assist in regulatory compliance. For example, the regulatory module 732 may flag a process thatmay be predicted by the prediction module 726 to move out of compliance (i.e., non- compliant). The regulatory module 732 may issue a warning through the communication module 728 to the engineering gateway 712. The regulatory module 732 may also identify windows of time when regulations are lessened and recommend changes to process parameters to reduce process costs. The regulatory module 732 may make recommendations to, for example, asphalt binder blending controllers to adjust blending parameters in line with upcoming regulatory changes. Further, the regulatory module 732 may make recommendations for various process controllers to adjust their parameters to promote the production of blend components in-line with demand that may accompany regulatory changes.

[0149] In some embodiments, the machine learning model 700 includes a forecasting module 734. The forecasting module 734 may analyze business data 710 and recommend that various process controllers adjust their parameters to promote the production of components that may be in greater demand. The forecasting module 734 may also recommend maintenance windows for equipment producing products that may be in low demand during specific time frames. The forecasting module 734 may forecast pricing for various components based on the historical database 702 and the business data 710 and publish the forecasted pricing via the communication module 728 to the engineering gateway 712

[0150] In some embodiments, the machine learning model 700 may include an authority module 736 and additional modules 738, such as a display module for converting data into graphical representations of a data set or a translation module for converting data between different languages, formats, or units. The authority module 736 may track user instructions and approvals for various instructions and changes to be made by the machine learning model 700 to the various controllers throughout the refinery. In some applications, the authority module 736 may consider a recommendation from a module of the machine learning model 700 and automatically authorize the machine learning model 700 to issue an instruction to the targeted process controller 716 to make a change to an associated process. In other applications, the authority module 736 may direct the communication module 728 to request approval through the engineering gateway 712 before a recommendation may be implemented and instructions sent to the targeted process controller 716.

[0151] In some embodiments, the authority module 736 directs the communication module 728 to request approval through the engineering gateway 712 before a recommendation isimplemented and / or instructions are sent to a targeted process controller. The recommendation may include one or more of changes or predicted changes in a nonlinear refinery process, such as an SDA process where multiple variables, including pressure, temperature, and initial composition of the feedstock affect the composition of the product (e.g., deasphalted oil, pitch) of the process. A nonlinear process may include a process whose product attributes or composition are determined by a plurality of variables and thus may not be readily predictable. As one example, decreasing an asphaltene separator temperature or an overhead temperature of the asphaltene separator to increase deasphalted oil lift may not be linear. Further, changes in the deasphalted oil quality (e.g., such as the carbon reside concentration, the c7A, or the metals concentration of the deasphalted oil) may not be linearly correlated to changes in the asphaltene separator temperature and the overhead temperature of the asphaltene separator. In other words, the decrease in the temperature may not linearly change the relative volume of the deasphalted oil that is separated from the feed to the asphaltene separator or the relative quality of the lifted deasphalted oil. As another example, the amount of deasphalted oil lift may not be linearly related to the composition of the solvent, such as the strength of the solvent and / or the ratio of iso-butane to normal butane, for example. Similarly, the quality of the pitch may not change linearly with decreasing asphaltene separator temperature or overhead temperature.

[0152] FIG. 8A is a schematic diagram of a solvent deasphalting (SDA) unit 800 including a solvent deasphalting unit controller 802 configured to enhance fluid production at of the SDA unit, according to an embodiment of the disclosure. A section of the refinery corresponding to the SDA 800 may include the SDA controller 802, a furnace or boiler 816, one or more heat exchangers 810, 814, 824, 830, 840, 842, an asphaltene separator 812 (also referred to as an “deasphalting tower” or an “extractor”), an asphalt flash drum 818, an asphalt stripper 820, a deasphalted oil stripper 826, a jet condenser 832, a compressor 834, a vaporizer 836, a solvent vaporizer 838, and a solvent work drum 844 (e.g., a propane work drum where the solvent is propane). The SDA controller 802 may obtain data associated with the equipment of the SDA unit 800. The SDA controller 802 may also initiate capture of samples of fluids associated with the SDA unit 800. A sample collection and analysis assembly 808 may then analyze the samples and produce properties and / or a spectra for each sample. The SDA controller 802 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 804 and / or predictive controls module 806 to produce an output indicative of adjustment to parameters and / or feed, such as to achieve a target parameter (e.g., a target deasphalted oilflow rate, a target deasphalted oil quality). The SDA controller 802 may then utilize the output to adjust various parameters and / or feed associated with the SDA unit 800 via the local enhancement module 804. The local enhancement module 804 may be in operable communication with the equipment and device controls 199, which may be configured to control one or more refinery operation control devices to adjust the various target parameters (such as by, for example, adjusting a position of a valve, adjusting an operating temperature or operating pressure of one or more portions of the SDA unit 800). The SDA controller 802 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 802 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 802 may adjust DAO lift targets and / or DAO properties for further downstream operations. The SDA controller 802 may also be referred to herein as a solvent deasphalting unit controller model.

[0153] The SDA controller 802 may be configured to generate an output comprising one or more operating parameters of the SDA unit 800 to achieve one or more target parameters. By way of non-limiting example, the target parameters may include a target quality and / or yield of deasphalted oil, a target viscosity and / or hardness of pitch, a target utility cost (e.g., a target amount of stripping steam used in the SDA unit 800), or another target. Thus, the SDA controller 802 may be configured to receive one or more inputs (which may be received by one or more of the sample collection and analysis assemblies A through P and / or from the one or more sensor packages distributed throughout the SDA unit 800 and / or the refinery), and apply the SDA controller 802 to the one or more inputs to generate one or more outputs comprising predicted properties of one or more products (e.g., deasphalted oil, pitch) and, based on the predicted properties, generate an output comprising one or more operating conditions of the SDA unit 800 to achieve a target parameter. By way of non-limiting example, the output may include, for example, one or more of (e.g., each of) an operating condition of an asphaltene separator, a composition of a feed material 850, or a flowrate of the feed material 850 to achieve the target parameters. The SDA controller may include a machine learning model configured to generate the output based on one or more inputs. The one or more inputs may include predicted parameters including predicted properties of fluids associated with the SDA unit 800, operating conditions of the SDA unit 800, and / or operating conditions of other units in the refinery. The input may further include the target parameters. The predictive controlsmodules 806 may be configured to generate the predicted properties based on inputs from the sample collection and analysis assemblies 808, and from sensor packages disposed throughout the SDA unit 800. For example, based at least in part on current operating conditions of the SDA unit 800 based on the analysis of the samples and sensor data, the predictive controls modules 806 may be configured to apply machine learning models of the predictive controls modules 806 to generate the predicted parameters. Thus, the SDA controller 802 may facilitate operation of the SDA unit 800 at operating conditions configured to facilitate product materials having one or more target properties or flow rates.

[0154] With reference to FIG. 8A, each sample collection and analysis assembly A through P may include a sample collection assembly configured to facilitate gathering of a sample of a fluid and an analysis assembly configured to provide information about the sample to the SDA controller 802, such as to the local enhancement module 804 and / or the predictive controls module 806. In some embodiments, the sample collection and analysis assemblies A through P are configured to provide the information about the samples to the predictive controls module 806 associated with a particular portion of the SDA unit 800. The information about the samples may include one or more properties (e.g., a composition, a density, a viscosity, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon concentration, a c7A, an asphaltene concentration, a hardness, a softness) and / or one or more conditions (e.g., a flow rate) of the sample.

[0155] The SDA unit 800 may be configured to receive a feed material 850, such as from one or more units of a refinery. The feed material 850 may also be referred to herein as a feedstock material and may include one or more feedstock materials from one or more different units of the refinery and / or from a location outside the refinery. A sensor package 852 may be in fluid communication with the feed material 850 and configured to measure one or more properties, one or more conditions, and / or a flow rate of the feed material 850. The sensor package 852 may be in operable communication with the SDA controller 802, such as with the local enhancement module 804 and / or the predictive controls module 806. The sensor package 852 may include a temperature sensor configured to measure a temperature of the feed material 850, a flow meter configured to measure a flow rate of the feed material 850, a pressure sensor configured to measure a pressure of the feed material 850, and / or an in-line sensor configured to measure one or more properties of the feed material 850. The one or more properties of the feed material 850 may include one or more of a viscosity, a density (e.g., a gravity), a metals concentration (e.g., a vanadiumconcentration, a nickel concentration), a sulfur concentration, a nitrogen concentration, or a carbon residue concentration, a c7A, or an asphaltene concentration of the feed material 850. In some embodiments, the sensor package 852 includes a density meter, a viscometer, and / or a spectrometer. In some embodiments, the sensor package 852 includes a Coriolis meter configured to measure a density of the feed material 850. In some embodiments, the SDA controller 802 is configured to infer a viscosity of the feed material 850 based on the measured density of the feed material 850.

[0156] In some embodiments, the sensor package 852 includes one or more of (e.g., each of) a temperature sensor, a flow meter, a density meter, a viscometer; a sensor configured to measure a vanadium concentration; a sensor configured to measure a nickel concentration; a sensor configured to measure a sulfur concentration; a sensor configured to measure a nitrogen concentration; a sensor configured to measure a carbon residue concentration; a sensor configured to measure a c7A, or a sensor configured to measure an asphaltene concentration of the feed material 850. As used herein, the carbon residue concentration of a material may include one or more of a micro residue carbon (MCR), a Conradson carbon residue (CCR), or a Ramsbotton carbon residue (RCR) of the material. As used herein, the c7A of a material may include the weight percent of carbon atoms originating from C7 aromatics (e.g., toluene, mono-methyl-substituted benzenes) of the material and may correspond to a concentration of asphaltenes in the material and may also be referred to as the c7A content. The c7A of the material may also simply be referred to as the c7A of the material. In some embodiments, the c7A may be measured with a Raman spectrometer, such as an in-line Raman spectrometer.

[0157] In some embodiments, the sample collection and analysis assembly 808 includes a sample collection assembly A in fluid communication with the feed material 850 and configured to facilitate gathering of a sample of the feed material 850 and an analysis assembly configured to provide information about the sample of the feed material 850 to the SDA controller 802 (e.g., to the local enhancement module 804 and / or the predictive controls module 806). In some embodiments, samples of the feed material 850 may be gathered at the sample collection assembly A, analyzed at a laboratory, and the results may be provided to the analysis assembly A of the sample collection and analysis assembly A. The information may include, for example, one or more of a viscosity, a density, a composition, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), a c7A, or an asphaltene concentration of the feed material 850.

[0158] The feed material 850 may be preheated in the heat exchanger 810 and the temperature of the heated feed material 850 may be measured by the sensor package 852. The heated feed material 850 may be provided to the asphaltene separator 812. Thus, the sensor package 852 may measure a temperature of the feed material to the asphaltene separator 812. The asphaltene separator 812 may also be referred to herein as an “asphaltene separator.” A solvent 856 may be provided to the asphaltene separator 812 and may be formulated and configured to extract deasphalted oil from the feed material 850 to form an asphaltene separator overhead 858 and an asphaltene separator bottoms 860. In some embodiments, the solvent 856 is preheated in a heat exchanger 846 prior to being provided to the asphaltene separator 812.

[0159] The solvent 856 may include one or more materials formulated and configured to selectively extract lighter components from the feed material 850 to form the asphaltene separator overhead 858 and an asphaltene separator bottoms 860. The solvent 856 may include, for example, propane, butane (such as a mixture of n-butane and iso-butane), or a combinations thereof. A sensor package 862 may be in fluid communication with the solvent 856. The sensor package 862 may be configured to measure one or more of a flow rate, a temperature, a composition, a viscosity, a density, a strength of the solvent 856, or a purity of the solvent 856. In some embodiments, the sensor package 862 is configured to measure a temperature of the solvent 856. A sample collection and analysis assembly B may in fluid communication with the solvent 856 and configured to gather a sample of the solvent 856 and provide information about the solvent 856 to the SDA controller 802 (e.g., to the local enhancement module 804 and / or the predictive controls module 806). The information may include, for example, one or more of a viscosity, a density, a strength, or a composition of the solvent 856. In some embodiments, the data includes a ratio of components of the solvent 856, such as a ratio of iso-butane to n-butane in the solvent 856. In some embodiments, the data includes a concentration of contaminants (e.g., metals, deasphalted oil) in the solvent 856.

[0160] The asphaltene separator 812 may include a sensor package 864 in operable communication with the SDA controller 802. The sensor package 864 may be configured to measure one or more of a temperature or a pressure in the asphaltene separator 812. In some embodiments, the sensor package 864 is configured to measure or determine a linear velocity of the asphaltene separator overhead 858. In some embodiments, the sensor package 864 is configured to measure an overhead temperature of the asphaltene separator 812.

[0161] The asphaltene separator 812 may be configured to facilitate selective separation of lighter components (e.g., deasphalted oil) from the feed material 850. For example, the asphaltene separator 812 may be configured to facilitate contact between the feed material 850 and the solvent 856 to facilitate extraction of the lighter components of the feed material 850 into the solvent 856 to form the asphaltene separator overhead 858 and the asphaltene separator bottoms 860. The asphaltene separator bottoms 860 may have a higher density and asphaltene concentration than the asphaltene separator overhead 858.

[0162] A deasphalted oil lift (or more simply, a “lift” or a “DAO lift”) achieved by the asphaltene separator 812 may depend on one or more a temperature of the feed material 850, a composition of the feed material 850, a density of the feed material 850, a viscosity of the feed material 850, a temperature of the asphaltene separator 812, a pressure of the asphaltene separator 812, a composition of the solvent 856, a temperature of the asphaltene separator overhead 858, or a temperature of the asphaltene separator bottoms 860. In some embodiments, the deasphalted oil lift in the asphaltene separator 812 depends on the temperature of the asphaltene separator overhead 858.

[0163] With continued reference to FIG. 8A, a sensor package 866 may be in fluid communication with the asphaltene separator overhead 858 and configured to measure one or more of a flow rate, a temperature, a pressure, a composition, a viscosity, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the asphaltene separator overhead 858. A sample collection and analysis assembly P may be configured to facilitate gathering and analysis of a sample of the asphaltene separator overhead 858. In some embodiments, the sample of the asphaltene separator overhead 858 may be analyzed to measure one or more of a composition, a viscosity, a density, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the asphaltene separator overhead 858. In some embodiments, a composition of deasphalted oil 880 (and the composition of the asphaltene separator overhead 858) may depend, at least in part, on the overhead temperature of the asphaltene separator 812 (e.g., the asphaltene separator overhead 858 temperature).

[0164] The SDA unit 800 may include a sensor package 868 in fluid communication with the asphaltene separator bottoms 860 and configured to measure one or more of a flow rate, a temperature, a pressure, a composition, a solvent concentration, a viscosity, a vanadiumconcentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, a c7A, a hardness, or a softness (e.g., a softening point) of the asphaltene separator bottoms 860. A sample collection and analysis assembly C may be configured to facilitating gathering and analysis of a sample of the asphaltene separator bottoms 860. In some embodiments, the sample of the asphaltene separator bottoms 860 may be analyzed to measure one or more of a composition, a solvent concentration, a viscosity, a density, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, a c7A, a hardness, or a softness of the asphaltene separator bottoms 860. The composition and properties of the asphaltene separator bottoms 860 may depend, at least in part, on the deasphalted oil lift, such as on the overhead temperature of the asphaltene separator 812 (e.g., the asphaltene separator overhead 858 temperature) and / or the solvent composition. For example, lower temperatures of the asphaltene separator overhead 858 and / or the asphaltene separator 812 may correspond to increased lift of deasphalted oil in the asphaltene separator 812 and formation of a heavier and more viscous asphaltene separator bottoms 860. In some embodiments, the SDA controller 802 is configured to optimize an amount of DAO lift while maintaining the viscosity, the density, the carbon residue concentration (e.g., the Conradson carbon residue concentration), the softness (e.g., the softening point), and / or the hardness of the asphaltene separator bottoms 860 below a predetermined threshold such that the asphaltene separator bottoms 860 can be pumped from the asphaltene separator 812 for further processing (e.g., maintaining the properties of the asphaltene separator bottoms 860 with a threshold range such that the asphaltene separator bottoms 860 remains pumpable or within hydraulic limits of the SDA unit 800). In addition, the SDA controller 802 may be configured to optimize the amount of DAO lift while maintaining the quality of the deasphalted oil (e.g., deasphalted oil 880) within a predetermined threshold, such as while maintaining a concentration of asphaltenes, a concentration of nickel, a concentration of vanadium lower than a predetermined threshold concentration, a set metals concentration (e.g., a metal concentration or a total metals less than a predetermined amount, which may be determined and set based on downstream units (e.g., hydrotreaters (e.g., gas oil hydrotreaters), hydrocrackers, fluid catalytic crackers), and / or a threshold rate of change of deasphalted oil lift and / or one or more deasphalted oil properties, such as a rate of change of deasphalted oil quality less than a predetermined threshold with respect to the asphaltene separator 812temperature or other operating parameter of the solvent deasphalting unit 800. Accordingly, in some embodiments, the SDA controller 802 is configured to respect quality constraints of the deasphalted oil 880 (e.g., asphaltene concentration, carbon residue concentration, nickel concentration, vanadium concentration) and the constraints of the pitch 891 and / or the asphaltene separator bottoms 860 (e.g., viscosity, density, carbon residue concentration, softness, hardness). In some embodiments, the input to the SDA controller 802 (e.g., to the predictive controls module 806) includes such constraints. In some embodiments, the constraints are defined by a user (e.g., received by the engineering gateway 712. In some embodiments, the SDA controller 802 may be configured to optimize the deasphalted oil lift while preventing the quality of deasphalted oil 880 from exceeding a rate of change threshold with respect to an asphaltene separator 812 temperature or other operating parameter of the SDA unit 800. In some embodiments, the SDA controller 802 may be configured to optimize the deasphalted oil lift while preventing the quality of pitch 891 from exceeding a rate of change threshold with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800. These qualities on the pitch 891 may include higher penetration corresponding to a greater softness, the stiffness of the pitch 891 less than a predetermined threshold, and / or a viscosity of the pitch 891 lower than a predetermined threshold.

[0165] With continued reference to FIG. 8 A, the asphaltene separator overhead 858 may be received in a solvent vaporizer 838 configured to reduce a pressure of the asphaltene separator overhead 858 and at least partially vaporize the solvent and form a solvent recycle 869 and a solvent vaporizer bottoms 870 having a lower concentration of the solvent than the asphaltene separator overhead 858. Steam 871 may be provided to the solvent vaporizer 838 to strip the solvent from the asphaltene separator overhead 858. The solvent vaporizer bottoms 870 may be provided to the vaporizer 836. Steam 875 may be mixed with the solvent vaporizer bottoms 870 in the vaporizer 836, which may be configured to form a solvent recycle 876 and a vaporizer bottoms 877.

[0166] A sensor package 872 may be in fluid communication with the solvent recycle 869; a sensor package 874 may be in fluid communication with the solvent vaporizer bottoms 870; and sensor package 878 may be in fluid communication with the solvent recycle 876. Each of the sensor packages 872, 874, 878 may be configured to measure one or more a flow rate, a temperature, a pressure, a composition, a solvent concentration (e.g., a solvent purity), a viscosity, or a deasphalted oil concentration (e.g., corresponding to a deasphalted oil carryover) of the respective solvent recycle 869, solvent vaporizer bottoms 870, and thesolvent recycle 876. In addition, sample collection and analysis assemblies O, J, N may be configured to facilitating gathering and analysis of a sample of the respective solvent recycle 869, solvent vaporizer bottoms 870, and the solvent recycle 876 and provide information about the respective solvent recycle 869, solvent vaporizer bottoms 870, and the solvent recycle 876 to the SDA controller 802. The samples may each be analyzed to determined one or more of a viscosity, a composition, a solvent concentration, or a deasphalted oil concentration of the respective sample.

[0167] A sensor package 873 may be in operable communication with the solvent vaporizer 838; and a sensor package 879 may be in operable communication with the vaporizer 836. The sensor package 873 and the sensor package 879 may be configured to configured to measure one or more of a temperature or a pressure within the respective solvent vaporizer 838 and the vaporizer 836.

[0168] The vaporizer bottoms 877 may be provided to a deasphalted oil stripper 826, which may be configured to strip remaining solvent from the vaporizer bottoms 877 to form the deasphalted oil 880 and a solvent recycle 881. In some embodiments, the vaporizer bottoms 877 includes from about 70.0 weight percent to about 90.0 weight percent of the solvent, the remaining portion comprising the deasphalted oil 880. The deasphalted oil stripper 826 may be configured to receive stripping steam 827 and / or may include a reboiler configured to vaporize the vaporizer bottoms 877 to separate the solvent recycle 881 from the deasphalted oil 880.

[0169] A sensor package 882 may be in fluid communication with the solvent recycle 881 and configured to measure one or more a flow rate, a temperature, a pressure, a composition, a solvent concentration (e.g., a solvent purity), a viscosity, or a deasphalted oil concentration of the solvent recycle 881. In addition, a sample collection and analysis assembly may be configured to facilitate gathering and analyzing a sample of the solvent recycle 881, such as for one or more of a viscosity, a composition, a solvent concentration, or a deasphalted oil concentration of the sample. The deasphalted oil stripper 826 may include a sensor package 883 configured to measure one or more of a temperature or a pressure within the deasphalted oil stripper 826.

[0170] In some embodiments, the deasphalted oil stripper 826 is operated at supercritical conditions such that the solvent in the vaporizer bottoms 877 is separated from the deasphalted oil 880 at supercritical conditions. In some such embodiments, the SDA unit 800 may be referred to as a supercritical solvent deasphalting unit.

[0171] The deasphalted oil 880 exiting the bottom of the deasphalted oil stripper 826 may be in fluid communication with a sensor package 884 configured to measure one or more a flow rate, a temperature, a pressure, a composition, a solvent concentration, a density, a viscosity, a vanadium concentration, a nickel concentration a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration or a c7A of the deasphalted oil 880. In addition, a sample collection and analysis assembly G may be configured to facilitate gathering and analyzing a sample of the deasphalted oil 880. The sample of the deasphalted oil 880 may be analyzed for one or more of a composition, a solvent concentration, a density, a viscosity, a vanadium concentration, a nickel concentration a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the deasphalted oil 880.

[0172] The deasphalted oil 880 exiting the bottom of the deasphalted oil stripper 826 may be cooled with one or both of the heat exchangers 828, 830. The deasphalted oil 880 may be provided to another unit of the refinery 100, such as to a hydrotreater or a hydrotreater, a hydrocracker, and / or fluid catalytic cracker 576 (FIG. 5) where the deasphalted oil 880 is hydrotreated and / or cracked to form lighter products, such as components that may be blended into gasoline. In some embodiments, the SDA controller 802 is configured to minimize the metals in the deasphalted oil 880 and / or optimize the amount (the flow rate) of the deasphalted oil 880, which maintaining a concentration of one or more of (e.g., each of) metals (e.g., nickel, vanadium) below a threshold concentration or below a threshold amount for a given duration to minimize or reduce fouling of downstream catalysis (e.g., of fluid catalytic cracking catalyst).

[0173] With continued reference to FIG. 8A, the asphaltene separator bottoms 860 may be preheated in the heat exchanger 814 and further heated in the furnace or boiler 816. The furnace or boiler 816 may include a sensor package 815 configured to measure one or more of a temperature or a pressure of the asphaltene separator bottoms 860 exiting the furnace or boiler 816.

[0174] The heated asphaltene separator bottoms 860 may be received in the asphalt flash drum 818, which may be configured to flash at least a portion of the solvent to form a recycle solvent 885 and an asphalt flash drum bottoms 886. The recycle solvent 885 may be recycled back to the solvent work drum 844 after passing through heat exchanger 840. A sample collection and analysis assembly H may be configured to facilitate gathering and analysis of a sample of the solvent recycle 885. The sample of the solvent recycle 885 maybe analyzed for one or more of a viscosity, a composition, a solvent concentration, or a deasphalted oil concentration. A sensor package 887 may be in fluid communication with the solvent recycle 885 and configured to measure one or more a flow rate, a temperature, a pressure, a composition, a solvent concentration (e.g., a solvent purity), a viscosity, or a deasphalted oil concentration of the solvent recycle 885. The asphalt flash drum 818 may include a sensor package 888 configured to measure one or more of a temperature or a pressure within the asphalt flash drum 818.

[0175] The asphalt flash drum bottoms 886 may be in fluid communication with a sensor package 889 configured to measure one or more a flow rate, a temperature, a pressure, a composition, a solvent concentration (e.g., a solvent purity), a viscosity, a density, a softness, or a hardness of the asphalt flash drum bottoms 886. In addition, the asphalt flash drum bottoms 886 may be in fluid communication with a sample collection and analysis assembly D configured to facilitate gathering and analysis of a sample of the asphalt flash drum bottoms 886. The sample of the asphalt flash drum bottoms 886 may be analyzed for one or more of a viscosity, a density, a composition, a solvent concentration, or a deasphalted oil concentration, a softness, or a hardness.

[0176] The asphalt flash drum bottoms 886 may be received by the asphalt stripper 820, which may be configured to receive stripping steam 890 to strip (e.g., remove, separate) the solvent from the asphalt flash drum bottoms 886 to form pitch 891 (also referred to as “asphalt”) and an asphalt stripper overhead 892 comprising a solvent recycle. A sensor package 893 and a sample collection and analysis assembly I may be in fluid communication with the solvent recycle 892. The sensor package 893 and the sample collection and analysis assembly I may be substantially the same as the respective sensor package 887 and the sample collection and analysis assembly H described above.

[0177] A sensor package 894 and a sample collection and analysis assembly F may be in fluid communication with the stripping steam 890. The sensor package 894 may be configured to measure one or more of a flow rate, a pressure, a temperature, a quality, or a concentration of one or more impurities in the stripping steam 890. The sample collection and analysis assembly F may be configured to facilitate gathering and analysis of a sample of the stripping steam 890 to determine one or more of a quality or a concentration of one or more impurities in the stripping steam 890. The asphalt stripper 820 may include a sensor package 821 configured to measure one or more of a temperature or a pressure within the asphalt stripper 820.

[0178] The pitch 891 may be in fluid communication with a sensor package 896 and a sample collection and analysis assembly E. The sensor package 896 may be configured to measure one or more of a flow rate, a temperature, a pressure, a density (e.g., a gravity), a viscosity, a hardness, a softness (e.g., a softening point), a composition, a carbon residue concentration, a concentration of vanadium, a concentration of nickel, a c7A, or an asphaltene concentration of the asphalt 891. The sample collection and analysis assembly E may be configured to facilitate gathering and analysis of a sample of the asphalt 891 for one or more of a density (e.g., a gravity), a viscosity, a hardness, a softness (e.g., a softening point), a composition, a carbon residue concentration, a concentration of vanadium, a concentration of nickel, or an asphaltene concentration of the asphalt 891.

[0179] The pitch 891 exiting the bottom of the asphalt stripper 820 may be cooled in the heat exchanger 822 and the heat exchanger 824. The pitch 891 may be further processed and / or may be blended into an asphalt blending pool (e.g., as pitch 559 of the asphalt binder blending pool 606).

[0180] With continued reference to FIG. 8A, each of the asphalt stripper overhead 892 and the solvent recycle 881 may be mixed and provided to the jet condenser 832, which may be configured to condense water vapor and separate the water (from the stripping steam 827 and the stripping steam 890) from the solvent to form sour water 833 and solvent 835. The solvent 835 may be provided to the compressor 834 to compress the solvent 835 and recycle the solvent 835 back to the solvent work drum 844 after mixing the compressed solvent 835 with, for example, the solvent recycle 869 from the solvent vaporizer 838 and the solvent recycle 876 from the vaporizer 836. In some embodiments, water 837 is provided to the jet condenser 832 to facilitate the removal of the solvent 835 from the combined solvent recycle 881, 892.

[0181] A sensor package 839 and a sample collection and analysis assembly M may each be in fluid communication with the solvent 835. The sensor package 839 and the sample collection and analysis assembly M may be substantially the same as the respective sensor package 887 and the sample collection and analysis assembly H described above. The jet condenser 832 may include a sensor package 841 configured to measure one or more of a temperature or a pressure within the jet condenser 832.

[0182] Each of the sample collection and analysis assemblies A through P of the sample collection and analysis assembly 808 may be configured to facilitate gathering of a respective sample from the respective sample collection and analysis assembly, analysis of the sample (e.g., at a laboratory), and reporting of the results to the sample collection andanalysis assembly 808 and / or to the SDA controller 802, such as to the local enhancement module 804 and / or the predictive controls module 806. In some embodiments, each of the sample collection and analysis assemblies A through P are in operable communication with the predictive controls modules 806. Each of the sample collection and analysis assemblies A through P may be in operable communication with the sample collection and analysis assembly 808 and / or with the SDA controller 802.

[0183] Each of the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896 may individually be in operable communication with the SDA controller 802, such as the local enhancement module 804 and / or the predictive controls module 806. Each of the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896 may be configured to provide sensor data comprising information about the respective fluids and / or vessels with which they are in operable communication to the SDA controller 802, such as to the predictive controls modules 806.

[0184] The SDA controller 802 may be configured to one or more of optimize an deasphalted oil lift within the asphaltene separator 812, optimize an amount of deasphalted oil 880 formed while maintaining a deasphalted oil quality above a predetermined threshold (e.g., maintaining a concentration of nickel below a predetermined threshold, a concentration of vanadium below a predetermined threshold, a carbon residue concentration below a predetermined threshold, an asphaltene concentration below a predetermined threshold), maintaining a rate of change of deasphalted oil lift less than a predetermined threshold with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800, maintaining a rate of change of one or more properties (e.g., nickel concentration, vanadium concentration, carbon residue concentration, asphaltene concentration) less than a predetermined rate of change with respect to asphaltene separator 812 temperature or other operating parameter of the SDA unit 800; optimize an amount of deasphalted oil lift in the asphaltene separator 812 while maintaining rheological properties of the asphaltene separator bottoms 860 below a predetermined threshold (e.g., below a predetermined softening point, below a predetermined viscosity, below a predetermined density, below a predetermined carbon residue concentration) e.g., such that the asphaltene separator bottoms 860 remains substantially pumpable; optimize the amount of the deasphalted oil 880 formed while maintaining a metals concentration (e.g., nickel, vanadium) of the deasphalted oil 800 below a predetermined threshold; optimize the amount of the deasphalted oil 880 formedwhile maintaining an asphaltene concentration of the deasphalted oil 880 lower than a predetermined threshold asphaltene concentration; or optimize an amount of deasphalted oil 880 while maintaining a utility consumption (e.g., steam consumption, such as of stripping steam 890, steam 871, steam 875, stripping steam 827) less than a predetermined amount. In some embodiments, one or more of the predetermined thresholds are input from a user. In some embodiments, the SDA controller 802 is configured to increase the deasphalted oil lift while maintaining the quality of the deasphalted oil 880 within a predetermined threshold (e.g., the c7A less than a predetermined amount, a concentration of nickel and / or vanadium less than a predetermined amount, a carbon residue concentration less than a predetermined amount), and / or the rate of change of the quality of the deasphalted oil 880 less than a predetermined rate of change with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800. In addition, the SDA controller 802 may be configured to optimize the deasphalted oil lift while maintaining a rate of change of the quality of the pitch 891 greater than a predetermined threshold rate of change with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800. The quality of the pitch 891 may be, for example, the penetration of the pitch 891, the stiffness of the pitch 891, and / or a viscosity of the pitch 891.

[0185] The SDA controller 802 may be configured to apply a solvent deasphalting controller model to one or more inputs to generate one or more predicted parameters; and, based on the one or more predicted parameters, generate an output comprising one or more operating conditions of the SDA unit 800 to achieve a target parameter. In some embodiments, the SDA controller 802 includes one or more first machine learning models configured to apply the first machine learning model to input data to generate output data based on the input data, the output data comprising one or more predicted properties of one or more product streams (e.g., the deasphalted oil 880, the pitch 891) and / or predicted operating conditions of the SDA unit 800. The inputs may include data from one or more of the sensor packages described herein (one or more of the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896), one or more of the sample collection and analysis assemblies (e.g., sample collection and analysis assemblies A through P) of the sample collection and analysis assembly 808, and the target parameters.

[0186] The target parameter may include one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, or a target profit or target profit margin.

[0187] The SDA controller 802 may include a second machine learning model configured to receive, as inputs, the outputs from the first machine learning models (e.g., the predicted properties) and, apply the second machine learning model to the inputs of the second machine learning model to generate an output comprising one or more operating conditions of the SDA unit 800 to achieve the target parameter. The inputs to the second machine learning model may include, for example, the outputs of the first machine learning models, the inputs to the first machine learning models (e.g., data from the sensor package 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896; data from the one or more of the sample collection and analysis assemblies (e.g., sample collection and analysis assemblies A through P), and the target parameters. In some embodiments, responsive to determining the one or more operating conditions of the SDA unit 800 to achieve the target parameter, the equipment and device controls 199 may receive the one or more operating conditions from the local enhancement module 804 and cause one or more refinery control operation devices to change to cause the SDA unit 800 to achieve the target parameter.

[0188] The SDA controller 802 may be configured to maximize, for example, the amount of deasphalted oil 880 (e.g., the deasphalted oil lift in the asphaltene separator 812) until a threshold, such as until the deasphalted oil 880 exhibits an asphaltene concentration or a metal concentration greater than a threshold concentration; until the pitch 891 and / or the asphaltene separator bottoms 860 exhibits a viscosity, a density, and / or a softness a softness within a predetermined threshold (e.g., a penetration higher than a predetermined penetration (higher penetration corresponding to a greater softness), the stiffness of the pitch 891 less than a predetermined threshold); and / or until a cost (e.g., a utility cost) associated with recovery of the deasphalted oil 880 is greater than a predetermined threshold, such as per barrel of the deasphalted oil 880.

[0189] The deasphalted oil quality may include, for example, a concentration of nickel in the deasphalted oil 880, a concentration of vanadium in the deasphalted oil 880, a concentration of asphaltenes in the deasphalted oil 880, a c7A concentration of the deasphalted oil 880, and / or a carbon residue concentration of the deasphalted oil 880. The deasphalted oil yield may include a flow rate of the deasphalted oil 880 and / or a volume of the deasphalted oil 880 per volume of the feed material 850. The pitch quality may includeone or more of a density, a viscosity, or a hardness, or a softness of the pitch 891. The pitch yield may include a flow rate of the pitch 891 and / or a volume of the pitch 891 per volume of the feed material 850.

[0190] By way of non-limiting example, the inputs to the machine learning model of the SDA controller 802 may include one or more of at least one property of the feed material 850 (e.g., one or more of a flow rate, a temperature, a composition, a density, a viscosity, a carbon residue concentration, an asphaltene concentration, and / or a metals concentration of the feed material 850); at least one property of the deasphalted oil 880 (e.g., one or more of a flow rate, a composition, a density, a viscosity, a carbon residue concentration, an asphaltene concentration, and / or a metals concentration of the deasphalted oil 880); at least one property of the pitch 891 (e.g., one or more of a flow rate, a composition, a density, a viscosity, a carbon residue concentration, an asphaltene concentration, and / or a metals concentration of the pitch 891); at least one property of the asphaltene separator overhead 858 (e.g., one or more of a flow rate, a temperature, a pressure, a composition, a density, a viscosity, a carbon residue concentration, an asphaltene concentration, and / or a metals concentration of the asphaltene separator overhead 858); at least one property of the asphaltene separator bottoms 860 (e.g., one or more of a flow rate, a temperature, a pressure, a composition, a density, a viscosity, a carbon residue concentration, an asphaltene concentration, and / or a metals concentration of the asphaltene separator bottoms 860); at least one property of the asphalt flash drum bottoms 886 and / or the recycle solvent 885; an operating condition of the asphaltene separator 812 (e.g., one or more of a temperature or a pressure of the asphaltene separator 812); an overhead temperature of the asphaltene separator 812; a temperature of the asphaltene separator overhead 858; an operating condition of the deasphalted oil stripper 826 (e.g., a temperature of the deasphalted oil stripper 826, a pressure of the deasphalted oil stripper 826); a flow rate of stripping steam 827 to the deasphalted oil stripper 826; a temperature and / or a pressure of the stripping steam 827; an operating condition of the asphalt flash drum 818 (e.g., one or more of a temperature or a pressure of the asphalt flash drum 818); an operating condition of the asphalt stripper 820 (e.g., one or more of a temperature or a pressure of the asphalt stripper 820); an operating condition of one or more of the solvent work drum 844, the solvent vaporizer 838, the vaporizer 836, the compressor 834, and / or the jet condenser 832, or a ratio of the flow rate of the solvent 856 to the flow rate of the deasphalted oil 880.

[0191] In some embodiments, the inputs to the SDA controller 802 include one or more target parameters and one or more additional inputs. As described above, the SDAcontroller 802 may be configured to apply the SDA controller 802 to one or more inputs to generate one or more predicted parameters. The one or more predicted parameters may include one or more operating conditions of the SDA unit 800 to achieve the target parameters. For example, the one or more predicted parameters may include one or more of a predicted flow rate of the deasphalted oil 880, a predicted quality of the deasphalted oil 880 (e.g., a predicted concentration of nickel and / or vanadium in the deasphalted oil 880; a predicted asphaltene concentration, a predicted c7A, a predicted carbon residue concentration of the deasphalted oil 880), a predicted flow rate of the pitch 891, a predicted quality of the pitch 891 (e.g., a predicted softness, hardness, composition, density, or viscosity of the pitch 891), a predicted rate of change of the deasphalted oil lift with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800, a predicted rate of change of one or more properties of the deasphalted oil 880 with respect to at least one operating parameter of the solvent deasphalting unit 800, a predicted rate of change of one or more properties of the pitch 891 with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800, a predicted solvent recovery, a predicted flow rate of the feed material 850 to achieve the target parameter, or a predicted property of the feed material 850 (e.g., flow rate, composition, density, viscosity, temperature, nickel concentration, vanadium concentration, sulfur concentration, nitrogen concentration, carbon residue concentration, c7A, asphaltene concentration) to achieve the target parameter. The predicted solvent recovery may include, for example, a predicted flowrate of the solvent and / or a predicted mass balance of the solvent, such as whether the mass flow of the solvent flowing into the solvent work drum 844 balances or is within a predetermined range of the total mass of the solvent flowing out of the solvent work drum 844. The one or more predicted parameters may be one or more parameters that can be measured by the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896 and / or by the sample collection and analysis assemblies A through P.

[0192] In some embodiments, the one or more predicted parameters includes a predicted flow rate of the feed material 850, a predicted composition of the feed material 850, and / or a predicted metal concentration of the feed material 850. The predicted parameters may include a predicted operating condition of the asphaltene separator 812, a predicted overhead temperature of the asphaltene separator 812, and / or a predicted temperature of the asphaltene separator overhead 858. In some embodiments, the predicted parameters include a predicted flow rate of stripping steam (e.g., stripping steam 827, steam 890) tothe deasphalted oil stripper 826 and / or the asphalt stripper 820, a predicted temperature of the deasphalted oil stripper 826, a predicted pressure of the deasphalted oil stripper 826, a predicted temperature of the asphalt stripper 820, or a predicted pressure of the asphalt stripper 820.

[0193] The SDA model 802 may be configured to, based on the one or more predicted parameters, generate an output comprising one or more operating conditions of the SDA unit 800 to achieve the target parameters. In some embodiments, the SDA controller 802 includes a second machine learning model configured to receive the outputs from the first machine learning models (e.g., the one or more predicted parameters) and apply the second machine learning model to such outputs and to the one or more additional inputs to generate the output. In some embodiments, the inputs provided to the second machine learning model are different than the inputs provided to the first machine learning model. In some embodiments, at least some of the inputs to which the second machine learning model is applied are the same and at least some of the inputs to which the second machine learning model is applied are different than the inputs to which the first machine learning model is applied. The machine learning model(s) of the SDA controller 802 may be configured to generate the output based on the input(s). In some embodiments, the second machine learning model is trained for the specific SDA unit 800. In some embodiments, the SDA controller 802 is configured to generate an output comprising one or more operating conditions to generate the target parameters. In some embodiments, the local enhancement module 804 includes an algorithm configured to facilitate optimization of the SDA unit 800 to achieve the target parameters (e.g., the objective function) based on the outputs from the first machine learning models (e.g., of the predictive controls modules 806), the target parameters, unit constraints, and inputs. The algorithm may be configured to facilitate optimization of the SDA unit 800 based on a machine learning model. In some embodiments, the local enhancement module 804 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 806), the target parameters, unit constraints, and inputs

[0194] In some embodiments, the SDA controller 802 includes a plurality of predictive control modules 806, each predictive control module 806 including a unique machine learning model. The machine learning model of the predictive control module 806 may be associated with, for example, a particular piece of equipment (e.g., vessel, such as thesolvent work drum 844, the asphaltene separator 812, the deasphalted oil stripper 826, the asphalt flash drum 818, the asphalt stripper 820) and / or portion of the SDA unit 800 and configured to predict one or more properties of the associated equipment and / or portion of the SDA unit 800. Each predictive control module 806 may receive inputs associated therewith and may be trained to generate an output comprising one or more predicted parameters to produce, for example, a target parameter. In some embodiments, at least some of the predictive control modules 806 may receive, as an input, an output from at least another one of the predictive control modules 806.

[0195] By way of non-limiting example, a first predictive control module 806 may be associated with the asphaltene separator 812. The first predictive control module 806 may be configured to receive inputs comprising data from the sample collection and analysis assemblies A, B, and the sensor packages 852, 862, 864, as well as one or more target parameters. In some embodiment, the input includes at least a flow rate and / or a composition of the feed material 850 (e.g., including a carbon residue concentration, a c7A, an asphaltene concentration, and a metals concentration). The first predictive control module 806 may apply the machine learning model to the input data to generate output data to achieve the target parameters. The output data may include, for example, an operating condition of the asphaltene separator 812, such as an overhead temperature of the asphaltene separator 812 or a temperature of the asphaltene separator overhead 858, a composition and / or quality of the feed material 850, and / or another parameter. A second predictive control module 806 may be associated with the deasphalted oil stripper 826 and may be configured to receive the target parameter and the output from the first predictive control module 806 as inputs. Additional inputs to the second predictive control module 806 may include, for example, one or more of data from the sample collection and analysis assemblies P, O, J, N, and data from the sensor packages 866, 873, 872, 874, 878, 879, 882, and 883. The second predictive control module 806 may include a trained machine learning model configured to receive the inputs and apply the trained machine learning model to the inputs to generate the output. The output may include, for example, operating conditions of the deasphalted oil stripper 826 to achieve the target parameter, such as one or more of the operating conditions of the deasphalted oil stripper 826, the flow rate of the stripping steam 827, and / or another parameter to achieve the target parameter. In some embodiments, the output includes as an overhead temperature of the asphaltene separator 812 or a temperature of the asphaltene separator overhead 858, and / or a composition and / or quality of the feed material 850.

[0196] The SDA controller 802 may include the local enhancement module 804 configured to receive, as inputs, the outputs from the predictive control modules 806 and the target parameter. The local enhancement module 804 may be configured to apply a trained machine learning model to the inputs to determine operating conditions of the SDA unit 800 to achieve the target parameter.

[0197] Thus, the SDA controller 802 may include, for example, a first machine learning model that is applied to the inputs from the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896 and / or by the sample collection and analysis assemblies A through P and to the target parameter to generate an output comprising one or more predicted parameters. The one or more predicted parameters may include a predicted deasphalted oil flowrate, a predicted deasphalted oil quality, a predicted pitch flow rate, a predicted pitch quality, or a predicted solvent recovery. The SDA controller 802 may be configured to apply a second machine learning model to the outputs from one or more of the first machine learning models (e.g., the one or more predicted parameters) and the target parameters to generate an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter. The SDA controller 802 may be configured to adjust the one or more operating conditions based on the output. In some embodiments, the first machine learning model or at least one of the first machine learning models includes a first-principles model.

[0198] In some embodiments, the second machine learning model is configured to determine a change to make to one or more of the operating conditions to achieve the target parameters. For example, in some embodiments, the SDA controller 802 includes a comparator (e.g., comparator 342) configured to compare a current operating condition of one or more components of the SDA unit 800 and / or one or more materials within the SDA unit 800 to the output from the second machine learning model. The SDA controller 802 may be configured to change or cause the current operating condition of one or more components of the SDA unit 800 and / or one or more materials within the SDA unit 800 to change based on the comparison.

[0199] The first machine learning models may be trained with training data comprising first training inputs comprising outputs from the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896 and / or by the sample collection and analysis assemblies A through P. The first training inputs further include outputs comprising a deasphalted oil yield, a deasphalted oil quality, a pitch yield, and a pitch quality. The second machine learning model (e.g., of the local enhancementmodule 804) may be trained with training data comprising the first training outputs from the first machine learning models, the first training inputs of the first machine learning models, second training inputs comprising changes in the one or more operating conditions, and second training outputs comprising relative changes to the deasphalted oil yield, the deasphalted oil quality, the pitch, and the solvent recovery caused by the changes in the one or more operating conditions.

[0200] In some embodiments, the SDA controller 802 includes a first predictive control module 806 configured to predict a deasphalted oil lift out of a asphaltene separator 812 based on the one or more properties of the one or more feed materials 850 and an overhead temperature of the asphaltene separator 812 and a second predictive control module configured to predict a flowrate and a quality of the deasphalted oil 880 based on the deasphalted oil lift and operating conditions of the deasphalted oil stripper 826. The solvent deasphalting unit controller model may include a machine learning model configured generate the output based on the predicted flowrate and quality of the deasphalted oil 880 from the deasphalted oil stripper 826.

[0201] In some embodiments, the input data to the SDA controller 802 (e.g., to the predictive controls modules 806) includes one or more of (e.g., each of, any combination of two or more of) a composition of the solvent 856, a temperature of the feed material 850, an overhead temperature of the asphaltene separator 812, a temperature of the asphaltene separator overhead 858, a temperature of the deasphalted oil stripper 826, a pressure of the deasphalted oil stripper 826, a temperature of the vaporizer bottoms 877 to the deasphalted oil stripper 826, or a flow rate of the stripping steam 827 to the deasphalted oil stripper 826.

[0202] The one or more inputs may include one or more properties of the feed material 850 and may include, for example, a composition of the feed material 850, a density of the feed material 850, a metals concentration (e.g., a nickel concentration, a vanadium concentration) of the feed material 850, and / or a carbon residue concentration of the feed material 850). The input may include a flow rate and / or a density of the feed material 850, which may be received by the sensor package 852 including a Coriolis meter.

[0203] In some embodiments, the inputs include one or more properties of the deasphalted oil 880, such as a metals concentration (e.g., a nickel concentration, a vanadium concentration) of the deasphalted oil 880, a carbon residue concentration of the deasphalted oil 880, a sulfur concentration of the deasphalted oil 880, a nitrogen concentration of the deasphalted oil 880, or a c7A of the deasphalted oil 880. The carbon residue concentrationof the feed material 850 and the deasphalted oil 880 may include one or more of an MCR, a CCR, or an RCR of the respective feed material 850 or the deasphalted oil 880.

[0204] The input may include one or more properties of the pitch 891, such as the softening point, the softness, the hardness, the viscosity, the density, and / or the composition of the pitch 891.

[0205] In some embodiments, the inputs include one or more properties or conditions of the SDA unit 800, such as an input from the sensor package 852 to measure the temperature of the feed material 850 to the asphaltene separator 812, an input from the sensor package 864 to measure a temperature of the asphaltene separator 812, or an input from the sensor package 866 to measure a temperature of the asphaltene separator overhead 858.

[0206] In some embodiments, the input data includes an output from a machine learning model associated with one or more units upstream of the SDA unit 800. For example, the input data may include the output from a machine learning model associated with an upstream unit, wherein the output includes a composition (e.g., a predicted composition) of the feed material 850. The upstream unit may include an atmospheric distillation tower (e.g., the atmospheric distillation tower 504) and / or a vacuum distillation tower (e.g., vacuum distillation tower 570). The input to the machine learning model of the upstream unit may include, for example, an operating condition of the vacuum distillation tower and / or the atmospheric distillation tower.

[0207] The predicted parameters that are generated responsive to applying the machine learning model to the inputs may include, for example, a viscosity of the pitch 891, a hydraulic requirement for pumping the asphaltene separator bottoms 860 from the asphaltene separator 812, a metals concentration of the deasphalted oil 880, or at least one of a flowrate or a quality of at least one of the deasphalted oil 880 or the pitch 891.

[0208] In some embodiments, generating an output comprising one or more operating conditions of the SDA unit 800 to achieve the target parameter comprises generating an output to achieve the target parameter while maintaining a utility consumption below a predetermined threshold based on a current price of one or more refined products (e.g., gasoline, which may be formed from the deasphalted oil 880) and a current utility price.

[0209] In some embodiments, the output of the SDA controller 802 includes one or more operating conditions of the SDA unit 800 to achieve the target parameters (e.g., to maximize the objective function). The target parameters may include, for example, a deasphalted oil lift from a asphaltene separator 812 while maintaining at least one of a hardness or a viscosity of the pitch exiting a bottom of the asphaltene separator less apredetermined threshold. Adjusting the one or more operating parameters of the SDA unit 800 to achieve the target parameters may include adjusting the one or more operating conditions to reduce a difference between the predicted at least one of the flowrate or the quality and the target parameter. Adjusting the one or more parameters may include adjusting one or more of the temperature of the deasphalted oil stripper 826, the pressure of the deasphalted oil stripper 826, or a flow rate of the stripping steam 827 to the deasphalted oil stripper 826, or at least one of a temperature, a pressure, or a quality of the stripping steam 827 to the deasphalted oil stripper 826. In some embodiments, adjusting the one or more parameters includes adjusting a ratio of the solvent 856 to the deasphalted oil 880 (e.g., the solvent to oil ratio), which may reduce a concentration of one or more of nickel, vanadium, sulfur, or nitrogen in the deasphalted oil 880. In some embodiments, the composition of the solvent 854 may be adjusted. In some embodiments, the temperature and / or pressure of the asphalt stripper 820 or the deasphalted oil stripper 826 may be adjusted. In some embodiments, the SDA controller 802 is configured to adjust the one or more parameters subject to the constraint that the deasphalted oil lift or properties of the deasphalted oil remain within target parameters (or subject to the constraint that the predictive controls circuitry 804 does not predict such properties to move outside the target parameters).

[0210] The use of the SDA controller 802 including the predictive controls modules 806 and the local enhancement module 804, each including trained machine learning models, facilitates improved operation of the SDA unit 800. The SDA controller 802 may facilitate improved quality of the deasphalted oil 880 and optimization of the deasphalted oil lift in the asphaltene separator 812 to optimize the separation of the deasphalted oil 880 from the pitch 891, while facilitating the continuous and efficient operation of the SDA unit 800. For example, the flow rate of the deasphalted oil 880 may be optimized while meeting product specifications and while maintaining the quality of the deasphalted oil 880 below a predetermined threshold (e.g., below a predetermined softening point, below a predetermined viscosity, below a predetermined density, below a predetermined carbon residue concentration). The concentration of nickel and / or vanadium, which may be catalyst poisons for downstream units, such as downstream catalytic cracking units, may be maintained below a threshold value while optimizing the volume of the deasphalted oil 880. In addition, the volume of the deasphalted oil 880 may be optimized while maintaining the viscosity of the pitch 891 and the asphaltene separator bottoms 860 lower than a predetermined threshold such that the material can be sufficiently pumped.

[0211] Since the operation of the SDA unit 800 may fluctuate based on one or more parameters, the use of the SDA controller 802 to optimize the operation of the SDA unit 800 to optimize the formation of deasphalted oil 800 while remaining within processing constraints (e.g., properties of the deasphalted oil 880 remaining within target ranges, the rate of change of the deasphalted oil lift remaining less than a predetermined threshold with respect to the asphaltene separator 812 temperature or other operating condition of the solvent deasphalting units, and / or the rate of change of one or more properties of the pitch 891 (e.g., a viscosity, density, hardness, a softening point, a carbon residue concentration) with respect to the asphaltene separator 812 temperature or other operating parameter of the SDA unit 800. For example, controlling the operation of the SDA unit 800 is a complex problem since changing feedstock compositions, changing feedstock qualities (e.g., fluctuating concentrations of metals or carbon residue concentration in the feed material 850), swings from upstream units, issues with solvent quality, and operation of the components of the SDA unit 800 may suffer from operational variability and swings. In addition, the operation of one component and / or the properties of one feed material or intermediate stream may affect the operation of downstream equipment. For example, operation of upstream units may affect the quality and composition of the feed material 850, which may affect the operation of the asphaltene separator 812. Similarly, operation of the asphaltene separator 812 may affect the performance of the deasphalted oil stripper 826. The SDA controller 802 may facilitate improved operation of the SDA unit 800.

[0212] FIG. 8B is a simplified schematic diagram illustrating one embodiment of the SDA controller 802, according to at least one embodiment of the disclosure. The SDA controller 802 may include first modules including predictive controls modules 806. The predictive control modules 806 may be configured to receive input data including sensor data 801 from one or more of the sensor packages 852, 862, 864, 866, 868, 872, 873, 874, 878, 879, 882, 883, 884, 815, 887, 888, 889, 821, 893, 894, 896; analysis data from the one or more sample collection and analysis assemblies A through P; and target parameters 805. Responsive to receiving the inputs, each of the predictive control modules 806 may be configured to apply the inputs 801, 803, 805 to a respective machine learning model to generate an output comprising predicted parameters 807. The sensor data 801 from the sensor packages, the analysis data 803 from the sample collection and analysis assemblies, the target parameters 805, and the predicted parameters 807 may be the same as those described above with reference to FIG. 8A. The SDA controller 802 may include a plurality of the predictive control modules 806, as described above with reference to FIG. 8A.

[0213] The SDA controller 802 includes the local enhancement module 804. The local enhancement module 804 may include a second machine learning model configured to be applied to the predicted parameters 807, the sensor data 801, the analysis data 803, and the target parameters 805 to generate an output comprising operating conditions of the SDA unit 800 to achieve the target parameters 805. Thus, the SDA controller 802 may be configured to facilitate achieving the target parameters 805.

[0214] FIG. 9 is a schematic diagram of a solvent deasphalting unit 900 including a deasphalted oil stripper that operates at supercritical conditions and may be referred to as supercritical solvent deasphalting unit. The SDA unit 900 may include a control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. The SDA unit 900 may include a controller 902 (also referred to as a “supercritical solvent deasphalting controller”), a mixer 910 or blender, one or more separators 912, 916, 920, and / or one or more strippers 914, 918, 922. Similar to previously described controllers, the controller 902 may obtain data associated with the equipment of the SDA unit 900. The controller 902 may also initiate capture of samples of fluids associated with the SDA unit 900. The sample collection and analysis assembly 908 may then analyze the samples and produce properties and / or a spectra for each sample. The 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 controller 902 may then utilize the output to adjust various parameters and / or feed associated with the SDA unit 900 via the local enhancement module 904. The controller 902 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 controller 902 may also coordinate resid from other equipment, such as from a crude tower, a vacuum tower, and / or from a third party. The controller 902 may adjust DAO lift targets and / or DAO properties for further downstream operations.

[0215] In more detail, a feed material 950 and a solvent 956 may be provided to the mixer 910. The feed material 950 and the solvent 956 may be substantially the same as the feed material 850 and the solvent 856, respectively, described above with reference to FIG. 8A. The feed material 950 and the solvent 956 may be mixed in the mixer 910 to form a separator feed material 951 received by the separator 912. The separator 912 may be configured to separate asphaltenes from the separator feed material 951 and form a separator overhead 913 and a separator bottoms 915.

[0216] The separator bottoms 915 may include asphaltenes and some of the solvent 956. The stripper 914 may receive the separator bottoms 915 and stripping steam 917. The stripping steam 917 may be configured to strip the solvent from the asphaltenes to form asphaltenes 919 and stripper overhead 921, which may include the solvent and be recycled to the mixer 910 in the solvent 956.

[0217] The separator overhead 913 may be received by the separator 916, which may be configured to separate resins from deasphalted oil in the separator overhead 913 to form a separator overhead 923 including deasphalted oil and a separator bottoms 925 including resins. The separator bottoms 925 may be received by the stripper 918, which may receive stripping steam 927 and separate the solvent from the resins to form resins 929 and a stripper overhead 931 comprising the solvent. The stripper overhead 931 may be recycled to the mixer 910 in the solvent 956.

[0218] The separator overhead 923 may be received by the separator 920, which may be configured to separate deasphalted oil from the solvent to form separator bottoms 933 including deasphalted oil and a separator overhead 935 including the solvent. The separator overhead 935 may be recycled to the mixer 910 in the solvent 956.

[0219] The separator bottoms 933 may be received by the stripper 922, which may be configured to receive stripping steam 937 and separate deasphalted oil from the solvent to form deasphalted oil 939 and stripper overhead 941, which may include the solvent. The stripper overhead 941 may be recycled to the mixer 910, such as with the solvent 956.

[0220] With reference to FIG. 9, the SDA unit 900 may include a plurality of sample collection and analysis assemblies 908, which may be substantially the same as the sample collection and analysis assemblies A through P described above with reference to FIG. 8A. The plurality of sample collection and analysis assemblies 908 may facilitate gathering and analysis of one or more samples at one or more locations in the SDA unit 900. The samples may be analyzed to determined one or more properties of the samples, and the one or more properties may be received by the sample collection and analysis assembly 908 and / or the controller 902. In some embodiments, the sample collection and analysis assembly 908 facilitates sampling of the feed material 950, as described above with reference to the feed material 850 (e.g., to measure one or more of a density, a viscosity, a composition, a nickel concentration, a vanadium concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration, a c7A, an asphaltene concentration) of the feed material 950; sampling of the solvent 956 to measure one or more properties of the solvent 956, as described above with reference to the solvent 856; sampling of the stripping steam 917,927, 937 to measure one or more properties of the stripping steam; sampling of the asphaltenes 919 to measure one or more properties of the asphaltenes (such as softness, hardness, composition, density), as described above with reference to the asphalt 891; sampling of the resins 929 to measure one or more properties of the resins 929; and sampling of the deasphalted oil 939 to measure one or more properties of the deasphalted oil 939 (e.g., one or more of a composition, a metal concentration (a nickel concentration, a vanadium concentration), a carbon residue (e.g., a weight percent), a c7A, an asphaltene concentration (e.g., weight percent)), as described above with reference to the deasphalted oil 880.

[0221] The SDA unit 900 may include one or more sensor packages disposed throughout and configured to measure one or more properties of one or more components and / or one or more streams in the SDA unit 900. For example, the mixer 910 may include a sensor package 960; the separator 912 may include a sensor package 962; the stripper 914 may include a sensor package 964; the separator 916 may include a sensor package 966; the stripper 918 may include a sensor package 968; the separator 920 may include a sensor package 970; and the stripper 922 may include a sensor package 972. Each of the sensor packages 960, 962, 964, 966, 968, 970, 972 may be configured to measure one or more conditions or properties (e.g., a temperature, a pressure) within the respective mixed 910, separator 912, stripper 914, separator 916, stripper 918, separator 920, or stripper 922. In addition, a sensor package may be in fluid communication with one or more of the feed material 950, the solvent 956, the separator feed material 951, the separator overhead 913, the separator bottoms 915, the stripper overhead 921, the asphaltenes 919, the separator overhead 923, the separator bottoms 925, the stripper overhead 931, the resins 929, the separator overhead 935, the separator bottoms 933, the stripper overhead 941, or the resins 929, or the stripping steam 917, 927, 937. Each of such sensor packages may be configured to measure one or more of a flow rate, a temperature, a pressure, a composition, a density, a viscosity, a metals concentration, a solvent concentration, or another property of the respective stream.

[0222] The controller 902 may include the local enhancement module 904 and the predictive controls modules 906, which may be substantially similar to the local enhancement module 804 and the predictive controls modules 806 described above. For example, the predictive controls modules 906 may be configured to receive inputs including sensor data from the 960, 962, 964, 966, 968, 970, 972 and / or sensor packages in fluid communication with any of the feed material 950, the solvent 956, the separator feedmaterial 951, the separator overhead 913, the separator bottoms 915, the stripper overhead 921, the asphaltenes 919, the separator overhead 923, the separator bottoms 925, the stripper overhead 931, the resins 929, the separator overhead 935, the separator bottoms 933, the stripper overhead 941, or the resins 929, or the stripping steam 917, 927, 937. The input data to the predictive controls modules 906 may further include analysis data from the plurality of sample collection and analysis assemblies 908. The input data to the predictive controls modules 906 may further include target parameters, as described above with reference to the SDA controller 802. The predictive controls modules 906 may each be configured to apply a first machine learning model associated with the particular predictive controls module 906 to the input data to generate predicted parameters. The local enhancement module 904 may be configured to apply a second machine learning model to the predicted parameters, inputs comprising the sensor data, inputs comprising the analysis data, and the target parameters to generate an output comprising operating conditions of the SDA unit 900 to achieve the target parameters.

[0223] FIG. 10 is a simplified schematic diagram of a solvent deasphalting unit 1000 including a control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. In some embodiments, the SDA unit 1000 includes a SDA unit that operates at supercritical conditions (e.g., a deasphalted oil stripper that operates at supercritical conditions).

[0224] The SDA unit 1000 may include a mixer 1010 configured to receive a feed material 1050 and a solvent 1056. The feed material 1050 and the solvent 1056 may be substantially the same as the feed material 850 and the solvent 856 described above. For example, the feed material 1050 may include residuum, a vacuum tower bottoms material, and / or another material from one or more upstream refinery operations, such as a vacuum tower bottoms material. The mixed feed material 1050 and the solvent 1056 may form an asphaltene separator feed 1051 received by an asphaltene separator 1012.

[0225] The asphaltene separator 1012 may be substantially the same as the asphaltene separator 812 and may be configured to separate deasphalted oil from asphaltenes in the feed material 1050, such as by solvent extraction with the solvent 1056. The asphaltene separator 1012 may form an asphaltene separator bottoms 1060 including asphaltenes and some solvent and an asphaltene separator overhead 1058 including the solvent and deasphalted oil. The asphaltene separator bottoms 1060 may be heated in a heat exchanger 1009 and / or a heater (e.g., a furnace).

[0226] The heated asphaltene separator bottoms 1060 from the heat exchanger 1009 may be provided to an asphalt stripper 1020 (also referred to as an “asphaltene stripper”). The asphalt stripper 1020 may receive stripping steam 1090 and may be configured to facilitate separation of asphaltenes from the solvent to form pitch 1091 and an asphalt stripper overhead 1092 including the solvent. The pitch 1091 may be blended and / or further processed, such as in a resid destruction unit. The asphalt stripper overhead 1092 is condensed in a heat exchanger 1001 and provided to a solvent surge drum 1044.

[0227] The asphaltene separator overhead 1058 may be heated in a heat exchanger 1057 configured to increase the temperature of the asphaltene separator overhead 1058 and reduce a temperature of solvent in a deasphalted oil separator overhead 1014. The heated asphaltene separator overhead 1058 exiting the heat exchanger 1057 may be further heated in a deasphalted oil heater 1071. The deasphalted oil heater 1071 may include, for example, a furnace or other heater configured to increase the temperature of the deasphalted oil separator overhead 1014 to form a deasphalted oil separator feed 1069. The deasphalted oil separator feed 1069 exiting the deasphalted oil heater 1071 may be received by a deasphalted oil separator 1070, which may be configured to separate the solvent from the deasphalted oil to form the deasphalted oil separator overhead 1014 including the solvent and a deasphalted oil separator bottoms 1015 including deasphalted oil.

[0228] The deasphalted oil separator overhead 1014 may preheat the asphaltene separator overhead 1058 in the heat exchanger 1057. After being cooled in the heat exchanger 1057, the deasphalted oil separator overhead 1014 may be mixed with the solvent from the solvent surge drum 1044 and provided (e.g., recycled) to the mixer 1010.

[0229] The deasphalted oil separator bottoms 1015 may be received by a deasphalted oil stripper 1026. The deasphalted oil stripper 1026 may be configured to receive stripping steam 1027 to strip the solvent from the deasphalted oil and form deasphalted oil 1080 and a deasphalted oil stripper overhead 1081 including the solvent. The deasphalted oil stripper overhead 1081 may be cooled in the heat exchanger 1001 and provided to the solvent surge drum 1044. The solvent from the solvent surge drum 1044 may be recycled to the mixer 1010 with a pump 1045. In some embodiments, the deasphalted oil stripper 1026 is operated at supercritical conditions of the solvent. In some such embodiments, the SDA unit 1000 may be referred to as a supercritical SDA unit.

[0230] With continued reference to FIG. 10, the SDA unit 1000 may include a plurality of sensor packages disposed throughout the SDA unit 1000 and in operable communication with the SDA controller 1002, such as with a predictive controls modules 1006 and a localenhancement module 1004 of the SDA controller 1002. The SDA controller 1002 may include a plurality of predictive controls modules 1006, as described above with reference to the SDA controller 802 and the controller 902.

[0231] By way of non-limiting example, a sensor package 1011 may be in operable communication with the mixer 1010 and configured to measure one or more properties and / or conditions within the mixer 1010, such as a pressure and / or a temperature of the mixer 1010. A sensor package 1013 may be in operable communication with the asphaltene separator 1012 and configured to measure one or more properties and / or conditions within the asphaltene separator 1012, such as a temperature and / or a pressure of the asphaltene separator 1012. The sensor package 1013 may be substantially the same as the sensor package 864 described above with reference to the asphaltene separator 812. In some embodiments, the sensor package 1013 is configured to measure or determine a linear velocity of the asphaltene separator overhead 1058 exiting the asphaltene separator 1012. In some embodiments, the sensor package 1013 is configured to measure an overhead temperature of the asphaltene separator 1012.

[0232] A sensor package 1072 may be in operable communication with the deasphalted oil separator 1070 and configured to measure one or more properties and / or conditions within the deasphalted oil separator 1070. For example, the sensor package 1072 may be configured to measure one or more of a temperature or a pressure of the deasphalted oil separator 1070

[0233] A sensor package 1025 may be in operable communication with the deasphalted oil stripper 1026 and configured to measure one or more properties and / or conditions within the deasphalted oil stripper 1026, such as a temperature and / or a pressure within the deasphalted oil stripper 1026. The sensor package 1072 may be substantially the same as the sensor package 883 described above with reference to the deasphalted oil stripper 826.

[0234] A sensor package 1021 may be in operable communication with the asphalt stripper 1020 and configured to measure one or more properties and / or conditions within the asphalt stripper 1020, such as a temperature and / or a pressure within the asphalt stripper 1020. The sensor package 1021 may be substantially the same as the sensor package 821 described above with reference to the asphalt stripper 820.

[0235] A sensor package 1043 may be in operable communication with the solvent surge drum 1044 and configured to measure one or more properties and / or conditions within the solvent surge drum 1044, such as a temperature and / or a pressure within the asphalt stripper 1020. In some embodiments, one or more of the heat exchanger 1001, the heat exchanger1009, the heat exchanger 1057, or the deasphalted oil heater 1071 is in operable communication with a respective sensor package configured to measure one or more properties or conditions associated therewith. The one or more properties may include an inlet temperature, an outlet temperature, a delta temperature, an inlet pressure, an outlet pressure, or a pressure drop of a respective fluid through the heat exchanger (e.g., for the heat exchanger 1057, the sensor package may be configured to measure a temperature and / or pressure of the asphaltene separator overhead 1058 into the heat exchanger 1057, a temperature and / or pressure of the heated asphaltene separator overhead 1058 leaving the heat exchanger 1057, a temperature and / or pressure of the deasphalted oil separator overhead 1014 entering the heat exchanger 1057, a temperature and / or pressure of the deasphalted oil separator overhead 1014 exiting the heat exchanger 1057, or an associated pressure drop and / or temperature change through the heat exchanger 1057).

[0236] A sensor package 1052 may be in fluid communication with the feed material 1050 and configured to measure one or more conditions or properties of the feed material 1050, such as one or more of a flow rate, a temperature, a density, a viscosity, a metal concentration (e.g., a nickel concentration, a vanadium concentration), a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., a MCR, a CCR, a RCR), a c7A, or an asphaltene concentration of the feed material 1050. The sensor package 1052 may be substantially the same as the sensor package 852.

[0237] A sensor package 1059 may be in fluid communication with the asphaltene separator overhead 1058 and configured to measure one or more properties and / or conditions of the asphaltene separator overhead 1058. The sensor package 1059 may be substantially the same as the sensor package 866 described above with respect to the asphaltene separator overhead 858. For example, the sensor package 1059 may be configured to measure one or more of a flow rate, a temperature, a pressure, a composition, a viscosity, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the asphaltene separator overhead 1058.

[0238] A sensor package 1019 may be in fluid communication with the deasphalted oil separator feed 1069 and configured to measure one or more properties and / or conditions of the deasphalted oil separator feed 1069. The sensor package 1019 may be configured to measure one or more of a of a flow rate, a temperature, a pressure, a composition, a viscosity, a vanadium concentration, a nickel concentration, a sulfur concentration, anitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the deasphalted oil separator feed 1069.

[0239] A sensor package 1017 may be in fluid communication with the deasphalted oil separator bottoms 1015 and configured to measure one or more properties and / or conditions of the deasphalted oil separator bottoms 1015. The sensor package 1019 may be configured to measure one or more of a of a flow rate, a temperature, a pressure, a composition, a viscosity, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the deasphalted oil separator bottoms 1015.

[0240] A sensor package 1084 may be in fluid communication with the deasphalted oil 1080 and configured to measure one or more properties and / or conditions of the deasphalted oil 1080. The sensor package 1084 may be substantially the same as the sensor package 884 described above with reference to the deasphalted oil 880. The sensor package 1084 may be configured to measure one or more of a flow rate, a temperature, a pressure, a composition, a solvent concentration, a density, a viscosity, a vanadium concentration, a nickel concentration a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, or a c7A of the deasphalted oil 1080.

[0241] A sensor package 1028 may be in fluid communication with the stripping steam 1027 and configured to measure one or more properties and / or conditions of the stripping steam 1027. Similarly, a sensor package 1089 may be in fluid communication with the stripping steam 1090 and configured to measure one or more properties and / or conditions of the stripping steam 1090. The sensor packages 1028, 1089 may be substantially the same as the sensor package 894 described above with reference to the stripping steam 890. The sensor packages 1028, 1089 may be configured to measure one or more of a flow rate, a pressure, a temperature, a quality, or a concentration of one or more impurities in the respective stripping steam 1027, 1089.

[0242] A sensor package 1068 may be in fluid communication with the asphaltene separator bottoms 1060 and configured to measure one or more properties and / or conditions of the asphaltene separator bottoms 1060. The sensor package 1068 may be substantially the same as the sensor package 868 described above with reference to the asphaltene separator bottoms 860. The sensor package 1068 may be configured to measure one or more of a flow rate, a temperature, a pressure, a composition, a solvent concentration, aviscosity, a vanadium concentration, a nickel concentration, a sulfur concentration, a nitrogen concentration, a carbon residue concentration (e.g., one or more a MCR, a CCR, or a RCR), an asphaltene concentration, a c7A, a hardness, or a softness (e.g., a softening point) of the asphaltene separator bottoms 1060.

[0243] A sensor package 1061 may be in fluid communication with the asphaltene separator bottoms 1060 leaving the heat exchanger 1009 and provided to the asphalt stripper 1020. The sensor package 1061 may be substantially the same as the sensor package 1068. In some embodiments, the sensor package 1061 is configured to measure a temperature of the asphalt stripper feed (the temperature of the asphaltene separator bottoms 1060 provided to the asphalt stripper 1020).

[0244] A sensor package 1096 may be in fluid communication with the pitch 1091 and configured to measure one or more properties and / or conditions of the pitch 1091. The sensor package 1096 may be substantially the same as the sensor package 896 described above with reference to the pitch 891. The sensor package 1096 may be configured to measure one or more of a flow rate, a temperature, a pressure, a density (e.g., a gravity), a viscosity, a hardness, a softness (e.g., a softening point), a composition, a carbon residue concentration, a concentration of vanadium, a concentration of nickel, a c7A, or an asphaltene concentration of the pitch 1091.

[0245] A sensor package 1053 may be in fluid communication with the solvent 1056; a sensor package 1083 may be in fluid communication with the deasphalted oil stripper overhead 1081 ; a sensor package 1073 may be in fluid communication with the deasphalted oil separator overhead 1014; a sensor package 1093 may be in fluid communication with the asphalt stripper overhead 1092. Each of the sensor packages 1053, 1083, 1073, and 1093 may be configured to measure one or more properties of a respective fluid, such as one or more a flow rate, a temperature, a pressure, a composition, a solvent concentration (e.g., a solvent purity), a viscosity, or a deasphalted oil concentration of the respective fluid (the respective solvent).

[0246] As described above with reference to the SDA unit 800, the SDA unit 1000 may include a sample collection and analysis assembly 1008. The sample collection and analysis assembly 1008 may be substantially the same as the sample collection and analysis assembly 808 described above. One or more sample collection and analysis assemblies A through O may be in fluid communication with a respective fluid and configured to facilitate gathering of a sample and analysis of the sample to determine one or more properties of the sample. The sample may be analyzed in a laboratory and the propertiesmay be reported to and received by the sample collection and analysis assembly 1008 and / or the SDA controller 1002, as described above with reference to the sample collection and analysis assembly 808. The sample collection and analysis assemblies A through O may be associated with, for example, a respective sensor package and may be configured to measure one or more of the same properties described above with reference to the respective sensor package. Each of the sample collection and analysis assemblies A through O may be in operable communication with the SDA controller 1002, such as with the predictive control circuitry 1006.

[0247] The SDA unit 1000 may include additional processing equipment, such as a pump 1095 to facilitate the recirculation of the solvent to the mixer 1010.

[0248] In some embodiments, the SDA controller 1002 includes one or more machine learning models that are trained to generate an output based on one or more inputs. The SDA controller 1002 may include, for example, a plurality of predictive controls modules 1006, each including a machine learning model. The predictive controls modules 1006 may be configured to receive, as inputs, data from one or more of the sensor packages 1011, 1013, 1017, 1019, 1021, 1025, 1028, 1053, 1055, 1059, 1061, 1068, 1072, 1073, 1083,1084, 1096 and / or from one or more of the sample collection and analysis assemblies A through O. In addition, inputs to the predictive controls modules 1006 may include target parameters of the SDA unit 1000, such as a target deasphalted oil quality, a target deasphalted oil yield, or another property.

[0249] The inputs to the predictive controls modules 1006 may be substantially the same as the inputs to the predictive controls modules 806 described above with reference to the SDA controller 802. The inputs may include sensor data, analysis data, and target parameters, as described above. In some embodiments, and by way of non-limiting example, the inputs include data with respect to the feed material 1050, such as the composition, the density, the viscosity, the temperature, the flow rate, the metal concentration, the carbon residue concentration, the c7A, the asphaltene concentration of the feed material 1050. The inputs may further include, for example, the deasphalted oil 1080 quality, the deasphalted oil 1080 yield, and the pitch 1091 quality (e.g., the hardness, the softness, the viscosity, the density). The predictive controls modules 806 may be configured to apply a machine learning model to the inputs to generate an output comprising predicted parameters of the SDA unit 1000 based on the inputs.

[0250] As described above with reference to the SDA controller 802, the SDA controller 1002 may include the local enhancement module 1004 including a second machine learningmodel configured to receive, as inputs, the predicted parameters. Additional inputs to the second machine learning model of the local enhancement module 1004 may include the sensor data from the sensor packages, the analysis data from the sample collection and analysis assemblies A through O, and the target parameters. The second machine learning model may be configured to be applied to the inputs to generate an output comprising operating conditions of the SDA unit 1000 to achieve the target parameters. The SDA controller 1002 may be configured to control operation of the SDA unit 1000 to achieve the target parameters. For example, the SDA controller 1002 may be configured to facilitate changing a flow rate of the feed material 1050, a composition of the feed material 1050, a temperature of the asphaltene separator feed 1051, an operating condition of the asphaltene separator 1012 (e.g., a temperature of the asphaltene separator 1012), an operating condition of the deasphalted oil separator 1070, an operating condition of the deasphalted oil stripper 1026, a flow rate of the stripping steam 1027, or another property or condition of the SDA unit 1000. Thus, the SDA controller 1002 may be configured to facilitate control of the SDA unit 1000 to achieve the target parameters.

[0251] Each of the SDA controller 802, the controller 902, and the SDA controller 1002 may be in operable communication with the refinery controller 101 and / or with other operation controllers 102 of the refinery. In some embodiments, the refinery controller 101 includes a machine learning model configured to be applied to the outputs from a plurality of the operation controllers 102 (e.g., including one of the SDA controller 802, the controller 902, or the SDA controller 1002) to facilitate control and enhancement of operation of the refinery and multiple units of the refinery.

[0252] In an embodiment, each controller illustrated in FIG. 1A through FIG. 10 may utilize various data points and properties to predict parameters and fluids to 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 another embodiment, 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 near real-time and / or continuously.

[0253] FIG. 11A and FIG. 11B are simplified diagrams of control systems to enhance to enhance fluid production at refinery, according to an embodiment of the disclosure. As noted, control system 1100 may include an operation controller 1101. Further, the operationcontroller 1101 may connect to one or more sensors 1116A, 1116B, and up to 1116N, one or more devices 1118A, 1118B, and up to 1118N (such as flow control devices and / or temperature control devices), one or more equipment 1120 A, 1120B, and up to 1120N, one or more analyzers 1122A, 1122B, and up to 1122N, and one or more predictive controls 1114 A, 1114B, and up to 1114N. The operation controller 1101 may include memory 1104 and one or more processors 1102. The memory 114 may store instructions executable by one or more processors 1102. In an example, the memory 1104 may be a non-transitory machine-readable storage medium. As noted, the memory 1104 may store or include instructions executable by the processor 1102.

[0254] 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.

[0255] The memory 1104 may include or store sample and data collection and instructions 1106. Upon execution of such instructions, the operation controller 1101 may obtain samples associated with each equipment 1120A, 1120B, and up to 1120N. Further, the operation controller 1101 may obtain data from the one or more sensors 1116A, 1116B, and up to 1116N and / or one or more flow control devices 1118 A, 1118B, and up to 1118N. Upon collection of the samples, the operation controller 1101 may send the sample to one of the one or more analyzers 1122 A, 1122B, and up to 1122N. The one of the one or more analyzers 1122A, 1122B, and up to 1122N may then analyze the sample and generate properties and / or a spectra.

[0256] The operation controller 1101 may connect to and receive data from the one or more predictive controls 1114A, 1114B, and up to 1114N. In an embodiment, the operation controller 1101 may receive the output from each trained machine learning model of each the predictive controls 1114A, 1114B, and up to 1114N. In an embodiment, the output may comprise a vector or, in other embodiments, a value indicative of a parameter adjustment.

[0257] The memory 1104 may include or store trained machine learning models 1108. The trained machine learning models 1108 may include at least one trained machine learning model to generate an output indicative of parameter and / or feed adjustment. The operation controller 1101 may apply the data, properties, spectra, and / or the output of each trained machine learning model from one or more predictive controls 1114A, 1114B, and up to1114N to the trained machine learning models 1108 to generate an output indicative of parameter adjustments and / or feed adjustment.

[0258] The memory 1104 may include or store parameter adjustment instructions 1110. Upon generation of the output, the operation controller 1101 may adjust parameters associated with equipment at the refinery. Further the memory 1104 may include or store feed adjustment instructions 1112 to adjust feed based on the output.

[0259] In FIG. 11B, predictive controls 1114 may connect to subsets of each of the components described in FIG. 11 A. For example, the predictive controls 1114 may connect to a subset of the sensors 1136A, 1136B, and up to 1136N, a subset of the devices 1138A, 1138B, and up to 1138N, a subset of the equipment 1140A, 1140B, and up to 1140N, and / or a subset of the analyzers 1142A, 1142B, and up to 1142N. The predictive controls 1114 may include a trained machine learning model 1128 and instructions stored in a memory 1126 and executable by a processor 1124.

[0260] The instructions may include sample and data collection instructions 1130, which when executed cause the predictive controls 1114 to collect various data points and / or properties. Based on application of the data received to the trained machine learning model 1128 and, in some embodiments, an output from the operation controller 1101, the predictive controls 1114 may supply or provide the output to the operation controller 1101.

[0261] FIG. 12 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 1200 may be completed within operation controller 1101 (FIG. 11 A) and / or predictive controls 1114 (FIG. 1 IB). Specifically, method 2800 may be included in one or more programs, protocols, or instructions loaded into the memory 1204 of operation controller 1101 and executed on the processor or one or more processors of the operation controller 1101. In other embodiments, method 1200 may be implemented in or included in components of FIG. 1 A through FIG. 1 IB. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described blocks may be combined in any order and / or in parallel to implement the methods.

[0262] At block 1202, the one or more predictive controls may each obtain data from corresponding sources. In such an example, each of the 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.

[0263] At block 1204, 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.

[0264] At block 1206, 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 1208, 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 1101 (FIG. 11 A) 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 1201.

[0265] At block 1210, the operation controller 1101 (FIG. 11 A) may determine updated parameters and / or fluid compositions 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 1101, in some embodiments, may first obtain 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 1101 may obtain the output of each model of each predictive controls. Once the operation controller 1101 obtains all relevant data, the operation controller 1101 may determine the updated parameters based on application of that data to a machine learning model.

[0266] At block 1212, the operation controller 1101 (FIG. 11 A) 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 1101 may compare the values of the updated parameters to the currently set parameters. If the parameters are different, then at block 1214, the operation controller 1101 may adjust the devices, equipment, or fluid within the refinery to the updated parameters.

[0267] In an embodiment, refinery operations may occur continuously or substantially continuously. As such, method 1200 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 1200.

[0268] FIG. 13 is a simplified flow diagram of a method 1300 of operating a solvent deasphalting unit, according to at least one embodiment of the disclosure. The method 1300 includes receiving one or more sensor outputs and / or one or more properties of each of a plurality of material streams, as shown in act 1302. The one or more sensor outputs may be from one or more sensors disposed throughout the refinery, such as throughout a respective solvent deasphalting unit (e.g., one of the SDA unit 800, the SDA unit 900, or the SDA unit 1000), as described above. The materials streams may include, for example, one or more of a plurality of feedstock materials, one or more intermediate streams, deasphalted oil, or pitch, as described above. As described above, in some embodiments, one or more properties of each of the plurality of feedstock materials, one or more intermediate streams, deasphalted oil, or pitch may be may be measured, such as with one or more sample analysis and collection assemblies.

[0269] Responsive to receiving the one or more sensor outputs and / or the one or more properties of the plurality of material streams, the method 1300 may further include receiving an input comprising at least one of the one or more sensor outputs or the one or more properties of the plurality of material streams, as shown in act 1304. In some embodiments, the input is received by a machine learning model, such as a machine learning model of a predictive controls module. The inputs may be the same as those described above with reference to the SDA controllers 802, 902, 1002.

[0270] With continued reference to FIG. 13, the method 1300 may further include receiving a target parameter comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, or a target profit, as shown in act 1306. The target parameters may be substantially the same as those described above.

[0271] The method 1300 may further include applying a solvent deasphalting controller model to the input to generate an output, as shown in act 1308. The output may comprise one or more predicted parameters. The one or more predicted parameters may comprise one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, a quality of the pitch, or a solvent recovery. The SDA controller model may comprise a machine learning model trained to generate the output based on the input. In some embodiments, the output further comprises output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter.

[0272] Based on the output, the method 1300 may further include adjusting one or more operating conditions of the SDA unit to achieve the target parameter, as shown in act 1310. Adjusting the one or more operating conditions of the SDA unit may include adjusting one or more of the parameters described above with reference to the SDA controllers 802, 902, 1002. For example, adjusting the one or more parameters may include adjusting one or more of a temperature of a deasphalted oil stripper, a pressure of the deasphalted oil stripper, or a stripping steam flowrate to the deasphalted oil stripper. Adjusting the one or more parameters to achieve the parget parameter may include adjusting one or more of a temperature of the one or more feedstock materials, an overhead temperature of as asphaltene separator, a feed temperature to a deasphalted oil stripper, a pressure of the deasphalted oil stripper, a temperature of the deasphalted oil stripper, or a flowrate of stripping steam to the deasphalted oil stripper.

[0273] In the drawings and specification, several embodiments of systems and methods to provide in-line mixing of hydrocarbon liquids have been disclosed, and although specific terms are employed, the terms are used in a descriptive sense only and not for purposes of limitation. Embodiments of systems and methods have been described in considerable detail with specific reference to the illustrated embodiments. However, it will be apparent that various modifications and changes may be made within the spirit and scope of the embodiments of systems and methods as described in the foregoing specification, and such modifications and changes are to be considered equivalents and part of this disclosure.

Claims

CLAIMSWhat is claimed is:

1. A method of operating a solvent deasphalting unit, the method comprising: generating an input comprising one or more of: one or more sensor outputs from one or more sensors disposed throughout the solvent deasphalting unit, the solvent deasphalting unit configured to generate a deasphalted oil and pitch from one or more feedstock materials; or one or more properties of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, or the pitch; receiving a target parameter comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery; and applying a solvent deasphalting unit controller model to the input to: generate one or more predicted parameters, the predicted parameters comprising one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, a quality of the pitch, or a solvent recovery; based on the one or more predicted parameters, generate an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter; and based on the output, adjusting the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter; wherein the solvent deasphalting unit controller model comprises a machine learning model trained to generate the output based on the input.

2. The method of claim 1, wherein applying a solvent deasphalting unit controller model to the input comprises: applying a first machine learning model to the input to generate the one or more predicted parameters, the one or more predicted parameters comprising one or more of: a predicted deasphalted oil flowrate; a predicted deasphalted oil quality; a predicted pitch flowrate; or a predicted pitch quality; andapplying a second machine learning model to the one or more predicted parameters to generate the output comprising the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter.

3. The method of claim 2, wherein the first machine learning model comprises predictive control circuitry comprising a first-principles model.

4. The method of claim 2, further comprising training the first machine learning model with training data comprising: first training inputs comprising the sensor outputs and the one or more properties during a training period; and first training outputs comprising a deasphalted oil yield, a deasphalted oil quality, and a pitch quality during the training period.

5. The method of claim 4, further comprising training the second machine learning model with training data comprising: the first training outputs from the first machine learning model; the first training inputs of the first machine learning model; second training inputs comprising changes in the one or more operating conditions; and second training outputs comprising relative changes to the deasphalted oil yield, the deasphalted oil quality, the pitch quality, and the solvent recovery caused by the changes in the one or more operating conditions.

6. The method of claim 1, wherein the solvent deasphalting unit controller model comprises: a first predictive control module configured to predict a deasphalted oil lift out of an asphaltene separator based on the one or more properties of the one or more feedstock materials and an overhead temperature of the asphaltene separator; and a second predictive control module configured to predict a flowrate and a quality of the deasphalted oil from a deasphalted oil separator based on the deasphalted oil lift and operating conditions of the deasphalted oil separator.

7. The method of claim 6, wherein the solvent deasphalting unit controller model comprises a machine learning model configured generate the output based on the predicted flowrate and quality of the deasphalted oil from the deasphalted oil separator.

8. The method of any one of claims 1 through 7, wherein generating an input comprises generating the input comprising one or more of: a solvent composition; an asphaltene separator feed temperature; an overhead temperature of the asphaltene separator; a deasphalted oil separator feed temperature; a deasphalted oil separator pressure; a deasphalted oil stripper temperature; a deasphalted oil stripper pressure; or a stripping steam flowrate to the deasphalted oil stripper.

9. The method of any one of claims 1 through 8, wherein generating an input comprises generating the input comprising one or more of: a composition of the one or more feedstock materials; a density of the one or more feedstock materials; a metals concentration of the one or more feedstock materials; or a carbon residue concentration of the one or more feedstock materials.

10. The method of any one of claims 1 through 9, wherein the one or more properties comprises each of: a metals concentration of the one or more feedstock materials; a metals concentration of the deasphalted oil; a carbon residue concentration of the one or more feedstock materials; a carbon residue concentration of the deasphalted oil; a softening point of the pitch; a sulfur concentration of the deasphalted oil; a c7A of the deasphalted oil; and a hydraulic constraint of the pitch.

11. The method of any one of claims 1 through 10, wherein generating an input comprises receiving a sensor output from a Coriolis meter in fluid communication with the one or more feedstocks to generate an input comprising at least a density of the one or more feedstock materials.

12. The method of any one of claims 1 through 11, wherein the solvent deasphalting unit controller model is configured to infer a viscosity of the or more feedstock materials based on a density of the one or more feedstock materials, wherein the solvent deasphalting unit controller model is configured to generate the one or more predicted parameters based on the inferred viscosity of the one or more feedstock materials.

13. The method of any one of claims 1 through 12, wherein generating an input comprises generating the input comprising a Conradson carbon of the deasphalted oil.

14. The method of any one of claims 1 through 13, wherein generating an input comprises generating the input based on sensor data from a spectrometer configured to measure a c7A of the deasphalted oil.

15. The method of any one of claims 1 through 14, wherein generating in input comprises generating the input comprising one or more of a micro residue carbon (MCR), a Conradson carbon residue (CCR), or a Ramsbotton carbon residue (RCR) of the one or more feedstock materials.

16. The method of any one of claims 1 through 15, wherein generating an input comprises generating the input comprising one or more of a metals concentration, a sulfur concentration, a nitrogen concentration of the deasphalted oil.

17. The method of any one of claims 1 through 6, wherein generating an input comprises generating the input from a temperature sensor configured to measure a temperature of an asphaltene separator.

18. The method of any one of claims 1 through 17, wherein generating an input comprises generating the input from a temperature sensor configured to measure a temperature of an overhead temperature of an asphaltene separator.

19. The method of any one of claims 1 through 18, wherein the solvent deasphalting unit controller model is configured to infer a metals concentration of at least one of the one or more feedstock materials or the deasphalted oil based on a carbon residue concentration of the respective at least one of the one or more feedstock materials or the deasphalted oil.

20. The method of any one of claims 1 through 19, further comprising using a machine learning model to generate an output comprising a quality of the one or more feedstock materials based on input data from one or more sensors in one or more processing units configured to generate the one or more feedstock materials.

21. The method of claim 20, wherein the input data from the one or more sensors in the one or more processing units configured to generate the one or more feedstock materials comprises an operating condition of a vacuum distillation tower or an atmospheric distillation tower configured to generate the one or more feedstock materials.

22. The method of claim 20, wherein generating one or more predicted parameters comprises generating one or more of at least one of the flowrate or the quality of the deasphalted oil or at least one of the flowrate or the quality of the pitch based on the output of the machine learning model.

23. The method of any one of claims 1 through 22, wherein generating an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter comprises generating an output to achieve the target parameter while maintaining one or more of a utility consumption below a predetermined threshold based on a current price of one or more refined products and a current utility price, a rate of change of deasphalted oil quality less than a predetermined threshold with respect to an asphaltene separator temperature or other operating condition of the solvent deasphalting units, or a rate of change of the pitch quality less than a predetermined threshold with respect to the asphaltene separator temperature or other operating condition of the solvent deasphalting units.

24. The method of claim 23, wherein the predetermined threshold is specified by a user.

25. The method of claim 23, wherein generating an output to achieve the target parameter comprises generating the output to maintain the rate of change of the deasphalted oil quality less than the predetermined threshold with respect to an operating parameter of the solvent deasphalting unit.

26. The method of any one of claims 1 through 25, wherein generating an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter comprises increasing a deasphalted oil lift from an asphaltene separator while maintaining at least one of a softening point of the pitch exiting a bottom of the asphaltene separator within a predetermined threshold, maintaining a rate of change of the deasphalted oil quality less than a predetermined threshold with respect to an asphaltene separator temperature or other operating parameter of the solvent deasphalting unit, or maintaining a rate of change of the pitch quality less than a predetermined threshold with respect to the asphaltene separator temperature or other operating parameter of the solvent deasphalting unit.

27. The method of any one of claims 1 through 26, wherein adjusting the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter comprises adjusting the one or more operating conditions to reduce a difference between the predicted at least one of the flowrate or the quality and the target parameter.

28. The method of any one of claims 1 through 27, wherein adjusting the one or more operating conditions of the solvent deasphalting unit comprises adjusting one or more of: a temperature of a deasphalted oil stripper; a pressure of the deasphalted oil stripper; or a stripping steam flowrate to the deasphalted oil stripper.

29. The method of any one of claims 1 through 28, wherein adjusting the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter comprises adjusting one or more of:a temperature of the one or more feedstock materials; an overhead temperature of as asphaltene separator; a feed temperature to a deasphalted oil stripper; a pressure of the deasphalted oil stripper; a temperature of the deasphalted oil stripper; or a flowrate of stripping steam to the deasphalted oil stripper.

30. The method of any one of claims 1 through 29, wherein generating one or more predicted parameters comprises generating operating conditions of the solvent deasphalting unit to achieve the target parameter.

31. The method of any one of claims 1 through 30, wherein generating one or more predicted parameters comprises at least one of: predicting a viscosity of the pitch; predicting a hydraulic requirement for pumping a bottoms material from an asphaltene separator; or predicting a metals concentration of the deasphalted oil.

32. The method of any one of claims 1 through 31, wherein: generating one or more predicted parameters comprises predicting the quality the deasphalted oil; and adjusting the one or more operating conditions of the solvent deasphalting unit comprises adjusting an overhead temperature of an asphaltene separator.

33. The method of any one of claims 1 through 32, wherein adjusting the one or more operating conditions of the solvent deasphalting unit comprises adjusting one or more of a temperature of an asphaltene separator or a ratio of a solvent to the deasphalted oil in the asphaltene separator to reduce the one or more of a metals concentration, a sulfur concentration, or a nitrogen concentration of the deasphalted oil.

34. The method of any one of claims 1 through 32, wherein adjusting the one or more operating conditions of the solvent deasphalting unit comprises: adjusting a temperature of an asphaltene separator; and adjusting a ratio of a solvent to the deasphalted oil in the asphaltene separator.

35. The method of any one of claims 1 through 34, wherein: generating one or more predicted parameters comprises generating a predicted metals concentration of the deasphalted oil; and adjusting the one or more operating conditions comprises adjusting the one or more operating conditions to form the deasphalted oil having less than a predetermined threshold of the metals.

36. The method of any one of claims 1 through 35, wherein: generating one or more predicted parameters comprises generating an output comprising a predicted MCRT or a predicted Conradson carbon of the deasphalted oil; and adjusting the one or more operating conditions comprises adjusting the one or more operating conditions to form the deasphalted oil having an MCRT or a Conradson carbon lower than a threshold.

37. The method of any one of claims 1 through 36, wherein adjusting the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter comprising one or more of: changing a ratio of a solvent to the deasphalted oil in an asphaltene separator; changing a temperature of the asphaltene separator; changing a composition of the solvent; or changing at least one of a temperature or a pressure of at least one of an asphalt stripper or a deasphalted oil stripper.

38. The method of any one of claims 1 through 37, further comprising training the solvent deasphalting unit controller model with training data comprising: training inputs comprising the sensor outputs and the one or more properties during a training period; and training outputs comprising the deasphalted oil yield, the deasphalted oil quality, and the pitch quality during the training period.

39. The method of any one of claims 1 through 38, wherein the solvent deasphalting unit controller model is configured to predict one or more of the deasphalted oil yield, the deasphalted oil quality, the pitch yield, and the pitch quality based on acomposition of the one or more feedstock materials, a flowrate of the one or more feedstock materials, an asphaltene separator temperature, an asphaltene separator pressure, a composition of a solvent, a solvent to oil ratio, a temperature of a deasphalted oil stripper, or a temperature of an asphalt stripper.

40. The method of any one of claims 1 through 39, wherein the solvent deasphalting unit includes at least a portion configured to operate at supercritical conditions.

41. The method of any one of claims 1 through 40, wherein the solvent deasphalting unit comprises an asphaltene separator configured to extract the deasphalted oil from the one or more feedstocks under supercritical conditions.

42. The method of any one of claims 1 through 41, wherein applying a solvent deasphalting unit controller model to the input comprises: applying the input to a predictive control comprising a first machine learning model configured to generate a predicted control output comprising a prediction of the at least one of the flowrate or the quality of at least one of the deasphalted oil or the pitch based on the input; and applying the predicted control output to a second machine learning model of local enhancement circuitry to generate the output comprising the one or more operating conditions of the solvent deasphalting unit to achieve the target parameter.

43. The method of any one of claims 1 through 42, wherein the one or more feedstock materials comprise a vacuum tower bottoms material or an atmospheric tower bottoms material.

44. The method of any one of claims 1 through 43, wherein generating an output comprising one or more operating conditions of the solvent deasphalting unit to achieve the target parameter is based on one or more of demand, price, or cost of the one or more feedstock materials, the deasphalted oil, or the pitch.

45. The method of any of claims 1 through 44, wherein the machine learning model is trained on a historical data of the solvent deasphalting unit, the historical data including: the one or more sensor outputs from the one or more sensors disposed throughout the solvent deasphalting unit; and the one or more properties of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, and the pitch.

46. The method of claim 45, wherein the historical data includes demand, price, or cost of the one or more feedstock materials, the deasphalted oil, or the pitch.

47. A memory including instructions and a machine learning model that causes a processor to perform instructions including the method of any of claims 1 to 46.

48. 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 46.

49. A system for operating a solvent deasphalting unit, the system comprising: one or more sensors disposed throughout the solvent deasphalting unit, the solvent deasphalting unit configured to generate a deasphalted oil and pitch from one or more feedstock materials; one or more sample collection assemblies to collect samples of the fluid associated with the SDA unit; one or more sample collection assemblies for collecting samples of one or more feedstock materials, one or more intermediate streams, the deasphalted oil, or the pitch; one or more sample analysis assemblies to analyze each collected sample to provide properties of collected samples from the one or more sample collection assemblies; a plurality of refinery operation control devices configured to control aspects of fluid flowing to or from the solvent deasphalting unit or one or more operating conditions of the solvent deasphalting unit; and a solvent deasphalting unit controller in operable communication with the one or more sensors, the one or more sample collection assemblies, the one or more sampleanalysis assemblies, and the plurality of refinery operation control devices, the solvent deasphalting unit controller comprising: at least one processor; and a computer memory including instructions that, when executed by the processor, cause the solvent deasphalting unit to carry out operations comprising: applying first machine learning models of predictive controls modules to input data comprising sensor data from the one or more sensors, analysis data from the one or more sample analysis assemblies, and target parameters to generate an output comprising one or more predicted parameters, the target parameters comprising one or more of a target deasphalted oil yield, a target deasphalted oil quality, a target pitch quality, a target solvent recovery, the one or more predicted parameters comprising one or more of a flowrate of the deasphalted oil, a quality of the deasphalted oil, a flowrate of the pitch, a quality of the pitch, or a solvent recovery; and applying a second machine learning model to the output of the first machine learning models to generate an output comprising or more operating conditions of the solvent deasphalting unit to achieve the target parameters.

50. The system of claim 49, wherein the one or more target parameters comprises at least one of a target asphaltene concentration of the deasphalted oil, a target carbon residue concentration of the deasphalted oil, or a target concentration of at least one of nickel or vanadium in the deasphalted oil.

51. The system of claim 49 or claim 50, wherein the one or more operating conditions of the solvent deasphalting unit comprises one or more of: a solvent composition; an asphaltene separator feed temperature; an overhead temperature of the asphaltene separator; a deasphalted oil separator feed temperature; a deasphalted oil separator pressure; a deasphalted oil stripper temperature; a deasphalted oil stripper pressure; or a stripping steam flowrate to the deasphalted oil stripper.

52. The system of any one of claims 49 through 51, wherein the input data comprises one or more of: a composition of the one or more feedstock materials; a density of the one or more feedstock materials; a metals concentration of the one or more feedstock materials; or a carbon residue concentration of the one or more feedstock materials.

53. The system of any one of claims 49 through 52, wherein the input comprises comprising one or more of a micro residue carbon (MCR), a Conradson carbon residue (CCR), or a Ramsbotton carbon residue (RCR) of the one or more feedstock materials.

54. The system of any one of claims 49 through 53, wherein the second machine learning model is configured to generate the output while maintaining one or more of a utility consumption below a predetermined threshold based on a current price of one or more refined products and a current utility price, a rate of change of deasphalted oil quality less than a predetermined threshold with respect to a rate of change of an asphaltene separator temperature or other operating condition of the solvent deasphalting units, or a rate of change of the pitch quality less than a predetermined threshold with respect to an asphaltene separator temperature or other operating condition of the solvent deasphalting unit.

55. The system of any one of claims 49 through 54, wherein the one or more predicted parameters comprises one or more of: a viscosity of the pitch; a hydraulic requirement for pumping a bottoms material from an asphaltene separator; or a metals concentration of the deasphalted oil.

56. The system of any one of claims 49 through 55, wherein the solvent deasphalting unit includes a deasphalted oil stripper configured to operate at supercritical conditions.

57. A system for enhancing fluid production for a solvent deasphalting (SDA) operation, the system comprising: an SDA unit to receive a feedstock and produce a fluid; a plurality of sensors positioned proximate or within the SDA unit and configured to measure a parameter associated with the SDA unit; a plurality of refinery operation control devices configured 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 an 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 plurality of refinery operation control devices and the SDA unit based on application of one or more of: data measured by the plurality of sensors; data corresponding to analysis from the one or more sample analysis assemblies; or 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.

58. The system of claim 57, further comprising one or more analyzers configured to provide a spectra indicative of fluid properties the fluid.

59. The system of claim 57 or claim 58, wherein the feedstock comprises resid and the target product comprises gas oil.

60. The system of any one of claims 57 through 59, wherein the SDA controller is in signal communication with another controller in operable communication with a refinery operation upstream of the solvent deasphalting operation and configured to generate the feedstock.

61. The system of claim 60, wherein the SDA controller is configured to infer properties of the feedstock based on the data from the another controller.

62. The system of any one of claims 57 through 61, wherein the SDA controller is configured to adjust properties of deasphalted oil or an amount of deasphalted oil generated in the SDA unit.

63. The system of any one of claims 57 through 62, wherein data used to train the trained machine learning model comprises historical data produced by the plurality of sensors and historical data comprising the properties of the collected samples.

64. The system of any one of claims 57 through 63, wherein the one or more sample analysis assemblies comprises one or more of a spectrographic analyzer or a chromatographic analyzer.

65. The system of any one of claims 57 through 64, wherein the SDA controller is configured to generate the output based on one or more of demand, price, or cost of the feedstock or the fluid.

66. The system of any of claims 57 through 65, wherein the trained machine learning model is trained on a historical data of the solvent deasphalting unit, the historical data including: historical data measured by the plurality of sensors; and historical data corresponding to the analysis from the one or more sample analysis assemblies.

67. The system of claim 66, wherein the historical data includes demand, price, or cost of the feedstock or the fluid.

68. A system for enhancing fluid production for a supercritical solvent deasphalting operation, the system comprising: a supercritical solvent deasphalting unit to receive a feedstock and produce a fluid; a plurality of sensors positioned proximate the supercritical solvent deasphalting unit or within the supercritical solvent deasphalting unit and configured to measure a parameter associated with the supercritical solvent deasphalting unit; a plurality of refinery operation control devices configured 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 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 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: data measured by the plurality of sensors; data corresponding to analysis from the one or more sample analysis assemblies; or 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.

69. The system of claim 68, further comprising one or more analyzers configured to provide a spectra indicative of fluid properties the fluid.

70. The system of claim 68 or 69, wherein the feedstock comprises resid and the target product comprises gas oil.

71. The system of any one of claims 68 through 70, wherein controller is in signal communication with another controller in operable communication with a refinery operation upstream of the supercritical solvent deasphalting unit and configured to generate the feedstock.

72. The system of claim 71, wherein the controller is configured to infer properties of the feedstock based on the data from the another controller.

73. The system of any one of claims 68 through 72, wherein the controller is configured to adjust properties of deasphalted oil or an amount of deasphalted oil generated in the supercritical solvent deasphalting unit.

74. The system of any one of claims 68 through 73, wherein data used to train the trained machine learning model comprises historical data produced by the plurality of sensors and historical data comprising the properties of the collected samples.

75. The system of any one of claims 68 through 74, wherein the one or more sample analysis assemblies comprises one or more of a spectrographic analyzer or a chromatographic analyzer.

76. The system of any one of claims 68 through 75, wherein the supercritical solvent deasphalting unit comprises a mixer configured to mix vacuum residue with a stripper overhead.

77. The system of any one of claims 68 through 76, wherein the feedstock comprises vacuum residue.

78. The system of any one of claims 68 through 77, wherein the controller is configured to generate the output based on one or more of demand, price, or cost of the feedstock or the fluid.

79. The system of any of claims 68 through 78, wherein the trained machine learning model is trained on a historical data of the supercritical solvent deasphalting, the historical data including: historical data measured by the plurality of sensors; and historical data corresponding to the analysis from the one or more sample analysis assemblies.

80. The system of claim 79, wherein the historical data includes demand, price, or cost of the feedstock or the fluid.

Images