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

Abstract

Embodiments of systems and methods may include inputting data indicative of one or more spectra or properties of feedstock to be fed into an alkylation unit into a machine learning model trained on historical equipment specific data of an alkylation unit, upstream processes that supply feedstock to the alkylation unit, the feedstocks supplied to the alkylation unit, and products of the alkylation unit. Further, systems and methods may include inputting a target product property for a product desired from the alkylation unit into the machine learning model and generating parameters, by the machine learning model, for operation of the alkylation unit to enable production of the product desired from the alkylation unit based on the target product property for a product desired from the alkylation unit into the machine learning model.

Description

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

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

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

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

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

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

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

[0007] Accordingly, an embodiment of the disclosure comprises a system and method includes receiving, by a machine learning model, feedstock data indicative of a property or a composition of a feedstock to be fed into an alkylation reactor. The machine learning model is trained on a historical data set of operational parameters of an alkylation system, feedstock, feedstock properties, products of the alkylation system, and properties and composition of the products of the alkylation system. The machine learning model receiving product data indicative of one or more of a property or a composition of a product of the alkylation reactor and generating a prediction of acid strength within the alkylation reactor based on the feedstock data and the product data.

[0008] Another embodiment includes a system and method comprising a machine learning model receives feedstock data indicative of a property or a composition of a feedstock to be fed into an alkylation reactor. The machine learning model is trained on a historical data set of operational parameters of an alkylation system, the feedstock, the feedstock properties, products of the alkylation system, and properties and composition of the products of the alkylation system. The machine learning model receives input indicative of one or more of a target alkylate property or operational parameter target and generates operational parameters based on the feedstock data and the one or more of a target alkylate property or operational parameter target.

[0009]

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

[0011] Another embodiment of the disclosure is directed to a method for enhancing control of an alkylation operation associated with a petroleum refining operation. The method may include supplying a feedstock to an alkylation unit associated with the petroleum refining operation, the feedstock having one or more feedstock properties. The method may include analyzing a feedstock sample via a first analyzer to provide feedstock sample properties. The method may include predicting one or more feedstock sample properties associated with the feedstock sample based on (A) the feedstock sample properties and (B) a first output from application of the feedstock sample properties to a first trained machine learning model. The method may include supplying one or more other input materials or intermediates to the alkylation unit associated with the petroleum refining operation, the one or more other input materials or intermediates having one or more other input materials properties or intermediates properties, respectively. The method may include analyzing one or more other input materials sample via a second analyzer to provide other input materials sample properties. The method may include predicting one or more other input materials sample properties associated with the other input materials sample based on (C) the other input materials sample properties and (D) a second output from application of the other input materials sample properties to a second trained machine learning model. The method may include operating the alkylation unit to produce one or more unit materials, the one ormore unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of alkylate or iso-butane. The method may include analyzing the unit material sample via a third analyzer to provide unit material sample properties. The method may include predicting one or more unit material sample properties associated with the unit material sample based on (E) the unit material sample properties and (F) a second output from application of the unit material sample properties to a second trained machine learning model. The method may include controlling, during the alkylation operation, based on the feedstock sample properties and the one or more unit material sample properties, one or more of: (a) one or more feedstock properties associated with the feedstock properties supplied to the alkylation unit; (b) one or more other input materials properties or intermediates properties associated with the other input materials properties or intermediates properties supplied to the alkylation unit; (c) one or more unit product materials properties associated with the unit product materials; (d) operation of the alkylation unit; or (e) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the alkylation operation, causes the alkylation operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials, thereby to cause the petroleum refining operation to achieve material outputs that more accurately and responsively converge on one or more of the target properties.

[0012] 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

[0013] 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.

[0014] 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.

[0015] FIG. 2 is a simplified diagram that illustrates an apparatus for enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0016] 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.

[0017] 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.

[0018] FIG. 5 is a schematic diagram of processes within a refinery.

[0019] FIG. 5A is a schematic diagram of the different products of the refinery and other sources that may be added to each of the blending pools.

[0020] FIG. 6 is a schematic diagram of a machine learning model that may be used with the various processes within a refinery.

[0021] FIG. 7 is a schematic diagram of an alkylation control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0022] FIG. 8 is a schematic diagram of a feed control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0023] FIG. 9 is a schematic diagram of a gasoline pool control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0024] FIG. 10 and FIG. 11 are simplified diagrams of control systems to enhance fluid production at refinery, according to an embodiment of the disclosure.

[0025] FIG. 12 is a flow chart illustrating enhanced fluid production at a refinery, according to an embodiment of the disclosure.

[0026] FIG. 13 is a flow is flow chart of a method, according to at least one embodiment of the present disclosure.

[0027] FIG. 14 is a flow is flow chart of another method, according to at least one embodiment of the present disclosure.

[0028] FIG. 15 is a flow is flow chart of yet another method, according to at least one embodiment of the present disclosure.

[0029] FIG. 16 is a flow is flow chart of another method, according to at least one embodiment of the present disclosure.DETAILED DESCRIPTION

[0030] So that the manner in which the features and advantages of the embodiments of the systems and methods disclosed herein, as well as others that will become apparent, may be understood in more detail, a more particular description of embodiments of systems and methods briefly summarized above may be had by reference to the following detailed description of embodiments thereof, in which one or more are further illustrated in the appended drawings, which form a part of this specification. It is to be noted, however, that the drawings illustrate only various embodiments of the systems and methods disclosed herein and are therefore not to be considered limiting of the scope of the systems and methods disclosed herein as it may include other effective embodiments as well.

[0031] The disclosure herein provides embodiments of systems, analyzers, controllers, and associated methods for enhancing fluid production of ongoing and / or continuous refining operations, as well as refining sub-operations. Such systems, analyzers, controllers, and associated methods may include obtaining data corresponding to a refinery operation from one or more sources, such as sensors, analyzers, refining equipment, refining operation control devices, other devices, and / or other sources. The data, along with, in some embodiments, a target product, may then be applied to a machine learning model to produce an output indicative of or including parameters that indicate settings for the refining operation control devices and / or refining equipment to be set to, to accurately achieve or produce the targeted product. Such an application of data to a trained machine learning model may occur at one or more different layers in the control system of the refinery. Further, a plurality of controllers positioned throughout the refinery may each include a plurality of trained machine learning models that are trained to enhance fluid production of one or more refinery operations or sub-operations.

[0032] In embodiments, the refining operations and / or sub-operations may include the processing, converting, refining, enhancing and / or otherwise altering a fluid via the refining operation or sub-operation. The fluid may be a liquid, vapor, and / or gas and may include ahydrocarbon and final product may include a transportation fuel. “Hydrocarbons” or “hydrocarbon fluids” as used herein, may refer to petroleum fluids, renewable fluids, and other hydrocarbon based fluids. “Petroleum fluids” as used herein, may refer to fluid products containing crude oil, petroleum products, natural gas, renewable liquids and / or gasses, and / or distillates or refinery intermediates. For example, crude oil contains a combination of hydrocarbons having different boiling points that 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 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, renewable 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.

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

[0035] Once these data sets have been received by the controller, the controller may pre- process the data. For example, the controller may normalize the data (in other words, remove data points that appear to be outliers), remove data corresponding to abnormal events (for example, data generated during start-up, shut-down, turn-arounds, and / 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).

[0036] Once the data has been pre-processed, the controller may begin training a model based on a portion of the data set. For example, the controller may utilize an 80 / 20 training and testing process. Other percentages may be utilized in training, testing, and / or validation. As the model is fed data, the model may compare data received to the outcome (in other words, whether the outcome was desired based on some factor, such as an indicated positive / negative flag or classification, based on some maximum or minimum of a function generated based on the data, or based on a trend within the data). Once the training portion of data has been utilized, the controller may test and / or validate the model using the remining portion of the data set. If such testing or validation does not achieve a selected error rate or reach some other error and / or accuracy based threshold, then the controller may re-train or refine the model using a different and / or randomized portion of the data set and a remaining portion of the data set for testing. Once a model has reached that threshold, then the controller may output the trained machine learning model for further use.

[0037] Further, a trained machine learning model may be further refined using new data, as such data is generated. Such a refinement may occur while the trained machine learning model is in use. In another embodiment, the trained machine learning model may be refined in an offline environment. In another embodiment, two instances of a trained machine learning model may exist, one stored as an offline copy, while the other is utilized during refining operations. In such an embodiment, the offline copy may be refined and, if testing and / or error rating meets a selected threshold, in addition to other factors, then a controller may replace the version currently utilized to the refined version.

[0038] It will be understood that such systems and methods described herein may utilize a number of trained machine learning models (also referred to as trained models). Forexample, 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, hydrodeoxygenation, hydrocracker operations, other blending operations, residuum oil supercritical extraction operation, solvent deasphalting (SDA) operation, operations or processes for formation of specific fuels, and / or the refining operation or process overall (which may, in an embodiment, utilize outputs from models associated with each sub-operation or sub-process). The use of terms operation and process refers to the steps taken to produce a particular product from a selected feedstock (and, in some embodiments, other inputs). As such, when referring to a particular refining operation or process, the terms “operation” and “process” may be used interchangeably. Further, such models may be trained specifically for equipment at a particular plant or refinery. For example, a FCC unit at a first plant may exhibit different characteristics than that of a FCC unit at a second plant. Thus, a model trained for one may not work for the other and training a model for either FCC unit may include utilization of historical data corresponding to that FCC unit. Various aspects of one model may be utilized to train other models for other similar equipment though.

[0039] Once a model is available, the controller, one or more sub-operation controllers or sub-controllers, and / or one or more operation controllers including a local enhancement or optimization module or circuitry, predictive controls, and / or equipment and device controls may begin optimizing, enhancing, and / or adjusting an operation and / or parameters associated with that operation, in real-time, near real-time, and / or continuously or substantially continuously, at a refinery. In such embodiments, the controller may obtain data from a plurality of sensors, a plurality of refining operation control devices (such as flow control devices, temperature control devices, pressure control devices, and / or other device configured to control an aspect of a refining operation), equipment at the refinery (in other words, refining equipment), and / or one or more sample analyzers and / or, in some embodiments, one or more sub-operation controllers or sub-controllers. In anotherembodiment, one or more operation controllers may obtain such data, as well as target products and / or other factors or parameters from a refinery controller or platform.

[0040] As noted, one input to any of the models described herein may include spectra or properties of feedstock, intermediaries, products or outputs, and / or other fluids or materials utilized in a refinery, determined via one or more of a spectrographic analyzer or a chromatographic analyzer. The controller or controllers may work in conjunction with such an analyzer to further enhance fluid production (for example, transportation fuel, hydrocarbon based fluid products, and / or other fluids produced during a refining operation) of the refining operation or sub-operation. As such, spectrographic analyzers may be calibrated or standardized and results may be obtained in a faster than typical timeframe, thus enabling prompt acquisition of fluid properties. For example, for any operation described herein, the controller may obtain spectrographic or chromatographic analysis of any feedstock utilized, any intermediaries produced, and / or any products produced by first initiating sample collection. Once a sample has been obtained, the controller and / or an analyzer may initiate analysis of the sample.

[0041] Once the controller or controllers has / have obtained data related to each operation and / or analysis of one or more fluids associated with the operation, then the controller may apply such data and analysis to a corresponding machine learning model. The output of the model may indicate adjustment of one or more devices or refining operation control devices and / or refining equipment and / or adjustment of a feedstock or intermediary used in the operation or sub-operation. In some embodiments, the output may include targets and / or properties for a feedstock and / or blend of feedstock. In another embodiment, the output may be in the form of a vector, each component of the vector corresponding to a value associated with a parameter of equipment or a device or refining operation control device. In an embodiment, a refining operation control device may comprise or include a temperature control device (such as a furnace, heat exchanger, condenser, boiler, induction coil, fans, a cooling device, and / or other device capable of adjusting the temperature of a fluid and / or the temperature within refining equipment), a flow control device (such as a pump, valve, control valve, and / or other device capable of adjusting the flow rate of a fluid), a pressure control device (such as a compressor, a pump, a let-down station or valve, and / or another device configured to adjust the pressure of a fluid), and / or other devices configured to adjust some aspect of a fluid and / or aspect of refining equipment.

[0042] 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 adjustcomponents 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.

[0043] In another embodiment, the controller may optimize an operation based on the current demand for selected products. For example, for a particular targeted product, selected amounts of feed and / or intermediaries may be utilized, increasing the demand 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.

[0044] In yet another embodiment, the controller may compare the output of the model to the current properties for a selected operation. Based on that difference of such a comparison, the controller may adjust various aspects of that operation.

[0045] By utilizing the trained machine learning models, the systems and methods described herein may determine specific adjustments to a plurality of operations and parameters specific to equipment at a refinery to accurately and more frequently (as compared to typical adjustment times) reach a target product. Further, such adjustments may increase efficiency of the refinery equipment and / or reduce energy utilized by the refinery equipment, thus reducing cost of the refinery operation. The target product may be based on a number of factors, such as demand and / or price or cost for the product, cost of the product and / or feedstock, and / or based on a target product provided by a refinery controller or platform. Such adjustments may be determined in real-time or near real-time using data from continuous and / or ongoing refinery operations.

[0046] Thus, rather than attempting to adjust operations at a significant delay, a refinery’s operations may be adjusted in-real time, 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.

[0047] FIG. 1 A and FIG. IB simplified diagrams of a refining control system to enhance fluid production at a refinery, according to an embodiment of the disclosure. As illustrated in FIG. 1A, a refinery 100 may include various refining control operation devices and refining equipment. While selected equipment are illustrated in FIG. 1A, it will be understood by those skilled in the art that additional and / or different equipment may be included in or at a refinery 100, particularly based on the type of feedstock processed at the refinery. For example, the refinery 100 may include a desalter, blending tanks, storage tanks, and / or wastewater treatment units, among other equipment. Further, each unit 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.

[0048] As illustrated in FIG. 1A, a refinery 100 may include a refinery controller 101 and / or a plurality of operation controllers 102. As will be illustrated in subsequent drawings, additional components may be included, such as a refining enhancer, other circuitry, various other controllers, and / or other computing devices. In an embodiment, the refinery controller 101 and / or the plurality of operation controllers 102 may include, for example, a trained machine learning model, as well as other instructions to adjust various devices and / or operations or processes within the refinery 100. The refinery controller 101 and / or the plurality of operation controllers 102 may connect to or be in signal communication with (a) one or more sensors, meters, transducers, and / or other measurement devices positioned throughout the refinery 100 and / or (b) to the equipment (for example, connected to some control aspect or device associated with the equipment) positioned at the refinery 100. The refinery controller 101 may be configured to receive data via such a connection. Further, the refinery controller 101 may receive such data in real-time or near real-time. In an embodiment, the refinery controller 101 may determine a target product and / or other parameters for a selected period of time. The refinery controller 101 may provide such data to each of the operation controllers 102. In other embodiments, the refinery controller 101 may utilize outputs from each of the operation controllers 102 to determine parameters for a target product. In other embodiments, the refinery controller 101 may apply those outputs, as well as other data, to a machine learning model.

[0049] In another embodiment, each of the operation controllers 102 may include a local enhancement circuitry 184, predictive controls circuitry 194, 191, and / or 195, and / or equipment and device controls 199. In embodiments, the circuitry may be a module orinstructions. In embodiments, the operation controller 102 may include one or more varying or different predictive controls. For example, as illustrated, one or more of the predictive controls circuitry 191 may include a trained machine learning model 193. The trained machine learning model 193 may be trained for a specific operation and / or piece of equipment and, in some embodiments, may be trained to recognize an adjustment, maximization, and / or optimization for specified factors of the specific operation and / or piece of equipment. As such, the operation controller 102 may include a plurality of predictive control circuitry 191. The operation controls may also include predictive control circuitry 194, which includes a trained machine learning model 196 and / or a first-principle model (and / or, in some embodiments, another type of model). The trained machine learning model 196 may be trained to fill missing data for the first-principle model 198. The operation controller may also include predictive control circuitry 195, which may include a first-principle model 197. The first-principle model 197 may be a model using a known, physics based equation or formulation.

[0050] In an embodiment, the operation controller 102 may include a local enhancement circuitry 184. The local enhancement circuitry 184 may include a trained machine learning model 190 and target setpoint instructions 192. The trained machine learning model 190 may utilize data associated with a specific refining operation and / or the output from each predictive controls circuitry to produce an output. The target setpoint instructions may utilize the output of the trained machine learning model 190 to determine a set of parameters that equipment and / or devices associated with a specific refining operation should be set to, to reach a target product. The operation controller may also include the equipment and device controls 199. The equipment and device controls 199 may cause equipment and / or devices to adjust to the target setpoints.

[0051] As illustrated in Fig. IB, the operation controllers 102 may further be connected to or in signal communication with a sample collection assembly 186 and / or a sample analysis assembly or sample analyzer 188. The sample analyzers 188 may include spectrographic analyzers, standardized spectrographic analyzers, and / or chromatographic analyzers. The type of spectrographic analyzers utilized may include one or more of near-infrared spectroscopic analyzer, a mid-infrared spectroscopic analyzer, a combination of a nearinfrared spectroscopic analyzer and a mid-infrared spectroscopic analyzer, a Raman spectroscopic analyzer, or a nuclear magnetic resonance spectroscopic analyzer. The sample analyzer 188 may analyze received samples and provide corresponding spectra indicating properties or other analysis indicating components and / or properties of thesample. 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.

[0052] 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.

[0053] 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.

[0054] As used herein, a “non-transitory machine-readable storage medium” or “memory” may be any electronic, magnetic, optical, or other physical storage apparatus to contain or store information such as executable instructions, data, and the like. For example, any machine-readable storage medium described herein may be any of random access memory (RAM), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., harddrive), 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.

[0055] As used herein, a “processor” or “processing circuitry” may include, for example one processor or multiple processors included in a single device or distributed across multiple computing devices. The processor (such as, processing circuitry 202 shown in FIG. 2, and / or a processor included in, for example, refinery controller 101 and / or the operation controllers 102 (not illustrated)) may be at least one of a central processing unit (CPU), a semiconductor-based microprocessor, a graphics processing unit (GPU), a field- programmable gate array (FPGA) to retrieve and execute instructions, a real time processor (RTP), other electronic circuitry suitable for the retrieval and execution instructions stored on a machine-readable storage medium, or a combination thereof.

[0056] Turning to the equipment positioned at the refinery 100, the refinery 100 may include a reactor 104 and, in some embodiments, a regenerator 120. The reactor 104 may be a catalytic reactor and / or a fluid catalytic cracking unit or reactor. The reactor 104 may include one or more sensors or meters positioned within the reactor 104 (such as sensor or meter 108) and / or proximate the reactor (such as sensors or meters 112, 114, 110, and 144). These sensor or meters may measure some aspect of fluid or material where the sensor or meter is positioned. Further, the reactor 104 may receive feedstock and / or an amount of water / steam at one or more locations of the reactor 104. The reactor 104 may be positioned or configured to convert heavy gas oil, residua, and / or other gas oil blends to an effluent or cracked fluid including smaller molecules, the effluent, in some embodiments, being further separated downstream into different products via distillation or fractionation. The reactor 104 may be operated at or it may be beneficial to operate the reactor 104 at a selected temperature range and / or pressure range to reduce over-cracking, which may cause a loss in valuable products, as well as to reduce over-all energy usage. Further, the amount of catalyst within and / or being fed to (for example, from the regenerator 120 and / or as fresh catalyst) the reactor 104 may impact the value of product produced by the reactor 104. Further, as a catalyst is regenerated within the regenerator 120, degradation may occur and / or coke deposited on the catalyst may not be completely burned off, particularly after multiple uses, thus further impacting product from the reactor 104. The feedstock fed to the reactor 104 may also affect parameters, such as temperature and residence time, among other parameters. Thus, several factors and / or parameters may impact the product produced by a reactor 104, those factors and / or parameters including temperature, pressure, type of catalyst, quality of catalyst, amount of catalyst, flow rate of feed or feed stock and / orcatalyst, 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 191 may be trained to maximize or be utilized for maximizing operating temperature in relation feedstock and a threshold temperature that may cause overcracking. In another example, another trained machine learning model may be trained to adjust or be utilized for adjusting heater temperature and / or temperature within the reactor in relation to feedstock and process parameters, composition, and / or other aspects to maximize yield or economically optimize yield from the reactor 104. In another embodiment, the trained machine learning model may be trained to adjust or be utilized for adjusting one or more refinery operation control devices to produce a selected yield of a product that also maximizes profit. Such an application of data to such a model may generate a vector that includes parameters or parameter settings corresponding to devices and / or equipment associated with the reactor 104 and, in some embodiments, the regenerator 120. That vector may be utilized by the local enhancement model to further determine, based on the outputs from other models as well as gathered data, parameters or parameter settings that enhance production of effluent from the reactor 104, such parameters or parameter settings being applied to actual equipment and / or devices via the equipment and device controller. Other models may be trained to determine parameters based on other relationships associated with the reactor 104 and / or other equipment.

[0057] In an embodiment, a trained machine learning model may be utilized by predictive controls (which may also be referred to as a prediction model) to optimize targets and / or properties and / or the predictive controls may be utilized by a an online optimization algorithm (which may also be referred to as the local enhancement module) to generate or determine targets.

[0058] The refinery 100 may include a regenerator 120. While a reactor 104 with a side- by-side configuration is illustrated in FIG. 1A, it will be understood that other configurations may be utilized, such as a stacked configuration. In an embodiment, inaddition 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 burn coke off of spent catalyst, the coke being deposited onto the catalyst in the reactor 104. The regenerator 120 may then provide the regenerated catalyst back to the reactor 104. In embodiments, the refinery controller 101 and / or operation controllers 102 may apply the data from the regenerator 120 to produce parameters or parameter settings to adjust corresponding equipment or devices to. The trained machine learning models may be trained or be utilized to determine parameters to maximize the amount of 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.

[0059] Other equipment may be positioned throughout the refinery 100 and the refinery controller 101 and / or operation controllers 102 may connect to such equipment. The refinery controller 101 and / or operation controllers 102 may obtain or gather data related to that equipment during the refining operation. For example, the refinery controller 101 and / or operation controllers 102 may obtain data from and / or related to a fractionation column 148 or distillation column. Further, the refinery 100 may include and the refinery controller 101 and / or operation controllers 102 and / or one or more of the sub-controllers 190 may obtain data from a hydrotreater (such as hydrotreater 166 and hydrotreater 174) and / or an alkylation unit 158. The refinery controller 101 and / or operation controllers 102 may obtain data from the valve 146, sensors or meters 150, 154, 160, 164, 168, 172, 178, and 180, as well as the properties associated with the products from the fractionation column 148 (for example, 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).

[0060] In an embodiment, the refinery controller 101 and / or operation controllers 102 may obtain data in real time, 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 then analyzed. In yet another embodiment, each of the operation controllers 102 may obtain data related to a selected section of the refinery 100. Each of the operation controllers 102 may also obtain properties and / or spectra from the sample analyzer 188. After the operation controllers 102 obtain the properties and / or spectra and data, then the operation controllers 102 may apply the properties and / or spectra and data to a corresponding predictive controls module to produce parameters to produce a target product. The local enhancement module of the operation controller may then apply, to a trained machine learning model of the local enhancement module, the output of each of the predictive controls module, the data obtained throughout the refinery 100, and / or the properties and / or each spectra associated with a collected sample. Such an application may produce an enhanced or optimized set of parameters, which may then be applied to equipment or devices via the equipment and devices controls.

[0061] In yet another embodiment, the refinery controller 101 may first obtain data and the properties and / or spectra and then apply the data and the properties and / or spectra to a trained machine learning model. The refinery controller 101 may transmit the output of the trained machine learning model to each operation controller 102. In another embodiment, the refinery controller 101 may provide target products and corresponding parameters to each of the operation controllers 102, based on user input, previously utilized parameters, current cost of a target product and / or feedstock, and / or other factors. In another embodiment, the refinery controller 102 may facilitate communication between each of the operation controllers 102, facilitate data acquisition for the operation controllers 102, and / or facilitate parameter prediction and / or adjustment among the plurality of operation controllers 102. For example, if one operation controller adjusts a process to meet a selected target, that adjustment may affect upstream and / or downstream processes. The refinery controller 101 may facilitate communication and / or perform additional predictions toensure that such parameter adjustments enable the upstream and / or downstream processes to continue to produce target products.

[0062] FIG. 2 is a simplified diagram that illustrates an apparatus for enhance fluid production at a refinery, according to an embodiment of the disclosure. Such an apparatus 200 may be comprised of a processing circuitry 202, a memory 204, a communications circuitry 206, a modeling circuitry 208, a fluid adjustment circuitry 210, and an equipment and device adjustment circuitry 212, each of which will be described in greater detail below. While the various components are illustrated in FIG. 2 as being connected with processing circuitry 202, it will be understood that the apparatus 200 may further 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 FIGS. 1 A-1B and below in connection with FIGS. 3-12.

[0063] 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.

[0064] 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.

[0065] 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 memory204 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.

[0066] 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.

[0067] The apparatus 200 may include a modeling circuitry 208 configured to obtain parameters from one or more components, equipment, devices, sensors, and / or analyzers and / or apply those parameters to a trained machine learning model to obtain parameters that enable equipment to produce a target product. In other embodiments, the modeling circuitry 208 may apply, in addition to the parameters described herein, the output of other similar circuitry (in other words, an additional plurality of modeling circuitry that each correspond to one of a plurality of sub-operations). Obtaining the parameters from the one or more components, equipment, devices, sensors, and / or analyzers may occur periodically, at selected times, continuously, or substantially continuously. In an example, the modeling circuitry 208 may obtain parameters for sub-operations first, generating an output for each sub-operation. Upon generation of an output for each sub-operation, the modeling circuitry 208 may obtain each output and a current data set. The modeling circuitry 208 may poll the components, devices, sensors, and / or analyzers to obtain such parameters or, in an embodiment, receive the parameters without polling. The modeling circuitry 208 may obtain the parameters via the communications circuitry 206. Application of the parameters to the trained machine learning model may determine, generate, or cause generation of anoutput. 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.

[0068] In another embodiment, the modeling circuitry 208 may train the trained machine learning model prior to use. In such embodiments, the modeling circuitry 208 may obtain historical data, preprocess the historical data, and then train and test the machine learning model. In yet another embodiment, after a refining operation (in other words, after a selected product has been generated via the refining operation), the modeling circuitry 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 reaching the target product’s properties).

[0069] 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.

[0070] The modeling circuitry 208 may utilize processing circuitry 202, memory 204, or any other hardware component included in the apparatus 200 to perform these operations, as described above in connection with FIGS. 1A-1B and below in connection with FIGS. 3-12. 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).

[0071] In addition, the apparatus 200 further comprises the fluid adjustment circuitry 210 that may cause adjustment of feedstock and / or other fluids utilized in a refining operation. In an embodiment the output from the modeling circuitry 208 may be a matrix, a series of parameters, and / or some indicator. In an embodiment, the fluid adjustment circuitry 210 may utilize that output to adjust a blend of feedstock and / or the fluid used in other inputs (for example, an amount of hydrogen, butane, other alkanes, and / or other fluids). The fluid adjustment circuitry 210 may utilize processing circuitry 202, memory 204, or any other hardware component included in the apparatus 200 to perform these operations, as described above in connection with FIGS. 1A-1B and below in connection with FIGS. 3- 12. 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.

[0072] In addition, the apparatus 200 further comprises the equipment and device adjustment circuitry 212 that may cause adjustment of equipment and / or devices utilizedin a refining operation. In an embodiment, the equipment and device adjustment circuitry 212 may utilize that output to adjust temperature, pressure, flow rate, and / or other parameters corresponding to the equipment and / or devices positioned within the refinery (e.g., by setting valve positions, pump speeds, etc.). The equipment and device adjustment circuitry 212 may utilize processing circuitry 202, memory 204, or any other hardware component included in the apparatus 200 to perform these operations, as described above in connection with FIGS. 1A and IB and below in connection with FIGS. 3-12. The equipment and device adjustment circuitry 212 may further utilize communications circuitry 206 to transmit signals to adjust equipment and / or devices utilized.

[0073] Although components 202-212 are described in part using functional language, it will be understood that the particular implementations necessarily include the use of particular hardware. It should also be understood that certain of these components 202-212 may include similar or common hardware. For example, the modeling circuitry 208, the fluid adjustment circuitry 210, and the equipment and device adjustment circuitry 212 may, in some embodiments, each at times utilize the processing circuitry 202, memory 204, or communications circuitry 206, such that duplicate hardware is not required to facilitate operation of these physical elements of the apparatus 200 (although dedicated hardware elements may be used for any of these components in some embodiments, such as those in which enhanced parallelism may be desired). Use of the terms “circuitry,” with respect to elements of the apparatus therefore shall be interpreted as necessarily including the particular hardware configured to perform the functions associated with the particular element being described. Of course, while the terms “circuitry” should be understood broadly to include hardware, in some embodiments, the terms “circuitry” may in addition refer to software instructions that configure the hardware components of the apparatus 200 to perform the various functions described herein.

[0074] 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 modelingcircuitry 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.

[0075] 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.

[0076] As will be appreciated based on this disclosure, example embodiments contemplated herein may be implemented by an apparatus 200 (or by a refinery controller). Furthermore, some example embodiments (such as the embodiments described for FIGS. 1A-1B and 3-12) 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.

[0077] FIG. 3 a simplified diagram that illustrates example refining controllers and an example refining enhancer to enhance control of a refining process at a refinery, according to an embodiment of the disclosure. As illustrated in FIG. 3, a refinery may include one or more operation controllers 302. The operation controllers 302 may connect to, for example, a number of feeds and / or processing units (refinery equipment configured to process a feedstock or other input). As illustrated, the operation controllers 302 may connect to and receive data from feed A 303 A, feed B 303B, and up to feed 303N, sensors or other devices associated with each feed (such as sensor 304A, 304B, and up to 304N), and various flow control devices (such as valve 306A, valve 306B, and up to valve 306N). In such embodiments, each of feed A 303 A, feed B 303B, and up to feed 303N may flow to a first processing unit 308. A processing unit, for example, in this case, the first processing unit308, may include one or more refining devices or equipment positioned at a refinery (for example, a FCC unit, a distillation column, and other equipment as described herein). The first processing unit 308 may convert, process, and / or transform a feed into a unit material (such as unit material A 310A, unit material B 31 OB, and up to unit material N 3 ION). 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.

[0078] In an embodiment, as each feed is fed to the next processing unit, the operation controller 302 may determine various characteristics and / or properties of the feed. For example, the operation controller 302 may determine temperature, pressure, and / or flow rate, in addition to the composition of the feed and the spectra or properties determined via spectrographic analysis of the feed. For example, as illustrated, the operation controller 302 may determine or obtain feed information 324 (including, at least feed composition 326 and / or feed properties 328, among other data), unit material information 330 (including, at least unit material composition 332 and / or unit material properties 334, among other data), and / or end material information 336 (including, at least end material composition 338 and / or end material properties 340, among other data). Thus, the operation controller 302 may obtain data related to each feed / material in real-time or near real-time, during a refinery operation, and / or directly or indirectly (for example, spectra may be obtained via a sample or spectrographic analyzer).

[0079] 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 composition 354 and target properties 356), and / or material differences 344 (including composition differences 346 and properties difference 348) as determined via a comparator 342 (the comparator 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 anotherembodiment, these values may be fed to the comparator and then, after obtaining differences related to another material, reapplied to the machine learning model 360. The machine learning model 360 may then produce adjusted targets 370 (including adjusted target feed ratios 372 and adjusted target operation unit parameters 374).

[0080] In another embodiment, the output of the machine learning model (for example, a vector comprising a plurality of components, each component being a parameter setting for a selected or specific device or equipment) may be compared to current parameter settings for the selected or specific devices or equipment in the comparator 342. In such embodiments, if the comparator 342 determines that there is a difference between an output of the machine learning model, then the parameter settings of the equipment or devices at the refinery may be adjusted.

[0081] 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.

[0082] 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.

[0083] 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 specificmodel 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.

[0084] 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 generate adjusted 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.

[0085] In another embodiment, a refinery may include a plurality of operation controllers. Each operation controller 302 may include a plurality of trained machine learning models. Each trained machine learning model may be trained to recognize a specific or selected trend in a set of data. Thus, each operation may be adjusted based on the outputs of a plurality of models, ensuring the operation as a whole produces an accurate target product. Further, each operation controller may interact with each other operation controllers. For example, adjusted parameters from all operation controllers may be provided to each operation controller. Thus, as one operation is adjusted, a downstream and / or upstream operation may be further adjusted based on the adjustment of the one operation.

[0086] 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.

[0087] As noted, the machine learning models described herein may be trained using data. As illustrated in FIG. 4, the data may include historical, equipment specific data 402. In other embodiments, the training data may include data related to the entire operation of a refinery, as well as outputs from equipment specific models. In another embodiment, a machine learning model may be re-trained and / or refined via current and marked up equipment specific data 404. The historical equipment specific data 402 and current and marked up equipment specific data 404 may include feed composition, feed properties,material composition, material properties, a target product or products, target composition, target properties, temperatures in equipment, pressure in equipment, flow rates associated with feed and / or materials, and / or equipment parameters. In embodiments, the historical equipment specific data 402 may include or may be utilized to generate a non-linear concave function. In such embodiments, the desired outcome may be determined based on the maximum of such a function. In another embodiment, the desired outcome may be included or added to the data set. In yet another embodiment, training may include the machine learning model learning particular patterns that indicate what the desired outcome may be based on trends within the data. In another embodiment, physics-based data 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.

[0088] Once the historical data, and any other current data, is available, that data may be pre-processed 406. In such embodiments, the data may be normalized. In other words, outlying data points that are anomalies may be removed from the data set. Further, data corresponding to abnormal events may be removed, such as data generating during startup, shut-down, turn-arounds, maintenance, and / or upsets. Further, undesired data and invalid measurements may be removed. Finally, data may be segregated or separated into sequences based on time. The sequences may comprise data obtained over a consecutive time period, such as time intervals of 30 minutes, 1 hour, 2 hours, and / or 3 hours, or more or less than the time intervals listed. In another embodiment, other factors may be utilized to segregate or separate the data, such as feed used and / or target product being produced.

[0089] Once the data set has been pre-processed, a model may be trained 408. In embodiments, a portion of the data set (for example, 70%, 80%, or 90%) may be fed to the machine learning model. The machine learning model may utilize the inputs versus the known desired outcome (such as target product composition and properties) and / or known undesired outcome to “learn” what parameters can be utilized to reach the known desired outcome and what parameters lead to the known undesired outcome. Once the data has been used to train the machine learning model, then the remaining portion of the data set may be utilized to test 410 the trained machine learning model. If the trained machinelearning model does not meet or achieve a selected error rate, then trained machine learning model may be re-trained or refined with a different randomized portion of the data set, and the re-training repeated as necessary, until the selected error rate is met or achieved. In another embodiment, other training schema may be utilized. In another embodiment, readiness of the trained machine learning model may be determined based on how close the trained machine learning model comes to an expected outcome, based on the test data set.

[0090] Once the trained machine learning model 412 meets a selected error rate, then the trained machine learning model may be released for further use. In another embodiment, 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.

[0091] FIG. 5 is a schematic diagram of a refinery 500. Crude oil 502 is initially processed by an atmospheric distillation tower 504 into its constituent parts. Some of the lightest parts from the atmospheric distillation tower 504 are a gas 506 that is sent to gas processing 508.

[0092] Optionally, the atmospheric distillation tower 504 may include or be connected to additional separation equipment 551, such as a splitter, a separator, a debutanizer, a deisobutanizer, a deisopentanizer, or other distillation column designed for a specific cutoff. A deisopentanizer is a distillation column that may be used to further split lighter components, such as isopentane and lighter molecules from the light naphtha 536.

[0093] Gas processing 508 separates sour gas 509 from feeds thereto, which include the gas 506 and other gas 507 resulting from different processes throughout the refinery. Gas processing 508 diverts the sour gas 509 to amine treating 516. The remainder of the gas 506 and other gas 507 that is not sour gas is passed to the mercaptan treater 510 that separates mercaptans from the fuel gas. The fuel gas may be finished as liquid petroleum gas (“LPG”) 512. The separated butane 514 may be kept as a finished product, sent to the gasoline blending pool 543, or sent to the C4 isomerization 591 to be processed into isobutane 593 as a finished product or further sent to an alkylation unit 594.

[0094] Amine treating 516 separates the hydrogen sulfide gas 520 from the refinery fuel 518. The hydrogen sulfide gas 520 and the hydrogen sulfide gas collected from processes throughout the refinery 500 is sent to the sulfur plant 522. The sulfur plant 522 converts the hydrogen sulfide gas 520 into sulfur 530 as a finished product.

[0095] Additionally, sour water 532 collected from processes throughout the refinery 500 is sent to the sour water steam stripper 528. The sour water steam stripper 528 uses steam 534 to remove hydrogen sulfide gas 526 from the sour water 532. The hydrogen sulfide gas 526 is also sent to the sulfur plant 522.

[0096] The atmospheric distillation tower 504 separates light naphtha 536 from the crude oil 502. The light naphtha 536 is sent to a hydrotreater 538 that removes sulfur from the light naphtha 536. The desulfurized light naphtha is then sent to isomerization 540 to be processed into isomerate 542. Isomerate 542 are isomers of the light naphtha that have higher octane values. The isomerate 542 may then be sent to the gasoline blending pool 543.

[0097] The atmospheric distillation tower 504 separates heavy naphtha 544 from the crude oil 502. Optionally, the heavy naphtha 544 may be sent to a splitter 545. The splitter 545 may include one or more splitter columns that separate heavier C7+ 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. The remaining lighter components of the heavy naphtha may be sent to a hydrotreater 546 to remove sulfur from the heavy naphtha 544 prior to being sent to the catalytic reformer 548 to be converted into reformate 550.

[0098] 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. From the hydrotreater 546, the desulfurized heavy naphtha is sent to a catalytic reformer 548 to be processed into reformate 550. Reformate 550 includes high-octane branched and cyclic hydrocarbons, such as benzene, toluene, xylene, and ethylbenzene. The reformate 550 may then be sent to the gasoline blending pool 543.

[0099] 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. Once desulfurized, the finished jet fuel 558 may be sold or sent to a jet fuel blending pool 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.

[0100] Further, diesel 560 is another product separated from crude oil 502 by the atmospheric distillation tower 504. The diesel 560 is sent from the atmospheric distillationtower 504 to a hydrotreater 562 to remove sulfur. The desulfurized diesel 564 may then be sold or sent to a diesel blending pool.

[0101] 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 vacuum distillation 570 where the atmospheric bottoms 568 may be further separated into light vacuum gas oil 572 (“LVGO”), medium vacuum gas oil 599 (“MVGO), heavy vacuum gas oil 584 (“HVGO”), and vacuum residuum 521. Vacuum distillation 570 may also be configured to separate the atmospheric bottoms 568 into more or less components.

[0102] The atmospheric gas oil 566, the LVGO 572, the MVGO 599, and deasphalted oil 501 from solvent deasphalting 598 (“SDA”) may be sent to a hydrotreater 574 to remove sulfur, then fed into a fluid catalytic cracker 576. The fluid catalytic cracker 576 processes the atmospheric gas oil 566 and the light vacuum gas oil 572 into naphtha 578, jet fuel 581, diesel 582, fuel oil 583, and butenes and pentenes 592.

[0103] The butenes and pentenes 592 from the fluid catalytic cracker 576, as well as the isobutane 593 from the C4 isomerization 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. Alkylate 596 has a high octane rating and low RVP.

[0104] The naphtha 578 may be sent to a hydrotreater 580 to further remove sulfur from the naphtha 578. The desulfurized naphtha may then be sold or sent to the gasoline blending pool 543. The jet fuel 581 may also be passed through a hydrotreater 585 to remove sulfur and other contaminants and then may be sent to a jet fuel blending pool. The diesel 582 may also be passed through a hydrotreater 587 to remove sulfur and other contaminants and then sent to a diesel blending pool and may be sold or stored for later sale and distribution. Lastly, the fuel oil 583 may also be passed through a hydrotreater 585 to remove sulfur and other contaminants and then 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.

[0105] 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 hydrocarbons that may be sent to gas processing 508. The hydrocracker 586 process integrates desulfurization and other contaminant removal, so further hydrotreating may not necessary for its products. The gasoline 588 may be sold or sent to the gasoline blending pool 543 shown in FIG. 5A. Thediesel 590 may be sold or sent to a diesel blending pool. The jet fuel 595 may be sold or sent to a jet fuel blending pool.

[0106] The vacuum residuum 521 may be sent to solvent deasphalting 598 (“SDA”) or used directly in asphalt 519. In some applications, the vacuum residuum 521 may be sent to an asphalt blending pool. The SDA 598 may be used to extract lighter components from the vacuum residuum 521 using solvents such as propane, butane, pentane, or a combination of these hydrocarbons to extract deasphalted oil 501 from the vacuum residuum 521. As discussed above, the deasphalted oil 501 may be sent to the hydrocracker 586 or the fluid catalytic cracker 576 for refining into hydrocarbon products including naphtha, jet fuel, diesel, and fuel oil. Once the lighter components are removed, the remaining components may be referred to as pitch 579. The pitch 579 may also be used in the asphalt blending pool 573.

[0107] The vacuum residuum 521 and pitch 579 may also be sent to the coker 597 to be processed into naphtha 503 and processed through a gasoline desulfurization unit 556 (“GDU”). The GDU 556 may include one or more processes useful to remove contaminants from the naphtha 503 in addition to gasoline desulfurization, including hydrotreating processes, catalysts, particulate catches, clay treaters, salt driers, and mercaptan treaters, separators, and steam strippers. The naphtha 503 may then be sent to the gasoline blending pool 543. The coker 597 also processes the vacuum residuum 521 and pitch 579 into jet fuel 511, diesel 513, fuel oil 515, and petroleum coke 517. 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 a fuel oil blending pool.

[0108] 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, filtration systems, and particulate catches.

[0109] Many of the connections, feedstocks, and outputs are not shown, and those of skill in the art recognize that different configurations are possible and processes may be added or replaced by other processes known in the art. For example, atmospheric distillation tower 504 and vacuum distillation 570 may each represent multiple units set up in parallel or series, and may separate their feedstocks into more or fewer crude oil components. Additional equipment may be added to each process to further refine and separate theproducts of each process. For example, products and components of the products may be passed through gasoline desulfurization, isomerization, reformation, and alkylation processes not shown in FIG. 5 to process the products and components to meet regulatory requirements and customer specifications.

[0110] FIG. 5 A is a schematic diagram of hydrocarbon refinery products 505 produced by the refinery 500 and their movement into blending pools 524, including a gasoline blending pool 543. Each blending pool 524 stores products from various refinery product streams and products from other sources in storage tanks 575 and may use these products to blend these products into different formulations that meet various regulatory requirements, industry standards, and customer specifications.[OHl] As shown, the butane 514, the naphtha 503, naphtha 578, the isomerate 542, the reformate 550, the alkylate 596, and the gasoline 588 may all be sent to the gasoline blending pool 543. Additionally, materials may be obtained from other sources 529 including other refineries, third parties, or off the open market. Gasoline specifications may include research octane number (RON), motor octane number (MON), volatility or Reid vapor pressure (“RVP”), sulfur content, benzene content, aromatic content, olefin content, driveability index, distillation curve, vapor-liquid ratio, stability, and corrosion resistance.

[0112] For example, butane 531, naphtha 533, isomerate 535, reformate 537, alkylate 539, and gasoline 541 may be obtained from other sources 529 and added to the gasoline blending pool 543. Butane 531 may be blended in the gasoline blending pool 543 for use during seasons of cold weather because butane 531 increases the Reid Vapor Pressure (“RVP”) helping the gasoline blend vaporize and ignite in cold gasoline engines. Coker naphtha 503 may be included in a blended gasoline after hydrotreating but may include a higher proportion of olefins. Naphtha 578 from the fluid catalytic cracker 576, also known as FCC gasoline, may be a large contributor to the gasoline blending pool 543 and may also contain olefins and aromatic molecules. Thus, naphtha 503 and naphtha 578 may be passed through a catalytic reformer 548 to saturate the olefins and aromatics before being sent to the gasoline blending pool 543.

[0113] Isomerate 542 increases the octane rating of a blended gasoline without increasing aromatic content and is useful in meeting regulatory limits on benzene. Reformate 550 also increases the octane rating of a blended gasoline, but contains benzene. Alkylate 596 is a useful blending component of gasoline that increases octane rating and contains few, if any, aromatics. Hydrocracked gasoline 588, also known as hydrocracked naphtha, is low in sulfur and may be used to reduce sulfur content in a blended gasoline.

[0114] Additionally, natural gasoline 547, oxygenates 549, such as MTBE, ETBE, or ethanol may be sent to the gasoline blending pool 543. Natural gasoline 547 may be derived from natural gas liquids during gas processing. Natural gasoline 547 typically has a low octane rating and may be used as a low cost component in blended gasolines. Oxygenates 549 may help increase octane rating in blended gasolines and may help reduce carbon monoxide emissions.

[0115] The different components of the gasoline blending pool 543 are mixed to create the blended product attributes ordered by customers and that comply with regulatory requirements. In many applications, higher-octane components, like reformate and alkylate, balance lower-octane product streams. Further, aromatics, benzene, and olefins are often limited to meet regulatory standards.

[0116] In general, inputs into the gasoline blending pool 543 may include reformate, isomerate, alkylate, naphtha from different sources, butane, oxygenates, and other additives. Each formulation of blended gasoline from the gasoline blending pool 543 has attributes that may be measured and specified through testing including Reid vapor pressure (“RVP”) at different temperatures, olefin content, oxygenate content, benzene content, deposit formation potential, knock resistance index, long-term storage stability, aromatics content, vapor liquid ratio, vapor lock index, sulfur content, mercaptan sulfur, gum content, oxidation stability, corrosion, sulfur compliance risk score, fuel economy impact, driveability index, blend volatility control, and density. Each formulation of blended gasoline from the gasoline blending pool may be selected for production based on the current market price for similar formulations, forecasted demand, predicted profit per batch, regulatory constraints, and current inventory levels in the storage tanks of the gasoline blending pool 543.

[0117] All products produced via refining processes including but not limited to the refinery products 505 and products from other sources 529, including purchased products may be added to the blending pools 524 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 blending pools 524 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 blending pool.

[0118] A complication in developing blended formulations, is that some attributes are not proportional while some are proportional to the amount contributed. For example, density, sulfur content, and percent of aromatics, benzene, and olefins are generally proportional with the amount blended. In contrast, flash point, flash point stability, flash point variance, freeze point, viscosity, cetane number, and octane number are not perfectly linear due to interactions between components. In some applications, the presence of lower flash point components may significantly impact the resulting flash point of a blended formulation. Smoke point can be heavily influenced by high-smoke components. Reid Vapor pressure does not blend linearly because of vapor-liquid equilibrium effects. Pour point is not proportional because some components have disproportionate effects.

[0119] The gasoline blending pool 543 includes a plurality of storage tanks 575. Each storage tank 575 may contain one or more of the refinery products 505 or products from other sources 529. Each storage tank 575 may include a sensor package 577. Depending on the substance stored within, the sensor package 577 may include level sensors, such as radar level sensors, ultrasonic level sensors, float & tape gauges, magnetostrictive sensors, and capacitive sensors. The sensor package 577 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 577 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 577 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 575. The sensor package 577 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 575. Further, the sensor package 577 may include safety and leak detection sensors, such as acoustic sensors, fiber optic sensors, and infrared gas leak detectors.

[0120] Data from the sensor package 577 may be used by a machine learning model to request certain refinery products to be produced at faster or slower rates or recommend that products and feedstocks from other sources, be ordered to fill a storage tank 575 in anticipation of blending a particular formulation for a client. The machine learning model may also make recommendations based on the quantities held in each storage tank 575 of particular products. In other words, the machine learning model may adjust a process producing a product based on the inventory of the product in one of the blending pools 524.The adjustment may be to change operating parameters, including one or more of temperature, pressure, and flowrates of a process, based on the inventory of a product in one of the blending pools 524. Alternatively, the machine learning model 800 of FIG. 6 may adjust a process to produce more of a product or products with a desired component distribution based on one or more of forecast information, demand predicted by the machine learning model 800 based on the business data 810 including regulatory changes and a predicted market price for the product during a future time period. The machine learning model 800 may create multiple simulations (e.g., published simulations, displayed simulations, transmitted simulations, published projections, displayed projections, and transmitted projections) based on the historical data 802 and the business data 810 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 the engineering gateway 812 for approval or permission 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.

[0121] A machine learning model 800, such as shown in FIG. 6, may be used to optimize each blended formulation blended from the gasoline blending pool 543. In some embodiments, the machine learning model obtains attribute data for each component in the blending pool 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 customer’s specifications and regulatory requirements. The machine learning model may create multiple combinations that may be compared against the customer’s specifications and regulatory requirements. Each combination that meets the customer’s specifications and regulatory requirements are retained in a potential formulation list, and those that do not meet the customer’s specifications and regulatory requirements are discarded. The machine learning model may then access business data to obtain pricing information for each component, calculate a base 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 a diesel fuel may be ordered based on an anticipated cetane number, sulfur content, cold flow properties, or energy content, and then secondarily when multiple formulations have the same cetane number on another attribute. Similarly, a potentialformulation list for gasoline may be ordered according to the gasoline specification attributes, such as octane rating.

[0122] Data from the sensor package 577 may be used by a machine learning model to request certain refinery products to be produced at faster or slower rates or recommend that products and feedstocks from other sources, be ordered to fill a storage tank 575 in anticipation of blending a particular formulation for a client. The machine learning model may also make recommendations based on the quantities held in each storage tank 575 of particular products. In other words, the machine learning model may adjust a process producing a product based on the inventory of the product in one of the blending pools 524. The adjustment may be to change operating parameters, including one or more of temperature, pressure, and flowrates of a process, based on the inventory of a product in one of the blending pools 524. Alternatively, the machine learning model 800 of FIG. 6 may adjust a process to produce more of a product or products with a desired component distribution based on one or more of forecast information, demand predicted by the machine learning model 800 based on the business data 810 including regulatory changes and a predicted market price for the product during a future time period. The machine learning model 800 may create multiple simulations (e.g., published simulations, displayed simulations, transmitted simulations, published projections, displayed projections, and transmitted projections) based on the historical data 802 and the business data 810 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 the engineering gateway 812 for approval or permission 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.

[0123] A machine learning model 800, such as shown in FIG. 6, may be used to optimize each blended formulation blended from the gasoline blending pool 543. In some embodiments, the machine learning model obtains attribute data for each component in the blending pool 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 customer’s specifications and regulatory requirements. The machine learning model may create multiple combinations that may be compared against the customer’s specifications and regulatory requirements. Each combination that meets the customer’s specifications and regulatory requirements are retained in a potential formulation list, and those that do not meet the customer’s specifications and regulatoryrequirements are discarded. The machine learning model may then access business data to obtain pricing information for each component, calculate a base 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 a diesel fuel may be ordered based on an anticipated cetane number, sulfur content, cold flow properties, or energy content, and then secondarily when multiple formulations have the same cetane number on another attribute. Similarly, a potential formulation list for gasoline may be ordered according to the gasoline specification attributes, such as octane rating.

[0124] FIG. 6 is a schematic diagram of a machine learning model 800 according to one embodiment. As used herein, a “machine learning model” refers to 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. For example, 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.

[0125] The machine learning model 800 is connected to a historical database 802. The historical database 802 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 802 may be a copy of historical databases that are maintained and updated by the machine learning model 800. The machine learning model 800 is also connected to a training database 803 that includes the process data and historical information that is used for training of the machine learning model 800.

[0126] As discussed in relation to other figures of this disclosure, the machine learning model 800 may be used to analyze and improve specific processes, process controllers, andprocess interactions. The machine learning model 800 may also be used as a refinery controller.

[0127] In this embodiment, the machine learning model 800 may receive feedstock sensor, sample, and process data 804 from a feedstock process controller 814 or directly from the sensors, sampling and testing systems, and labs obtaining data from the feedstock process. A feedstock process is any process preceding the targeted process under review by the machine learning model 800. For example, the feedstock process may include one or more of atmospheric distillation, vacuum distillation, filtration, hydrotreater, mercaptan treater, splitter, stripper, and separator.

[0128] Further, the machine learning model 800 may receive targeted process sensor, sample, and process data 806 from a targeted process controller 816 or directly from the sensors, sampling and testing systems, and labs obtaining data from the targeted process. The machine learning model 800 may also receive subsequent process sensor, sample, and process data 808 from a targeted process controller 816 or directly from the sensors, sampling and testing systems, and labs obtaining data from the targeted process. The feedstock sensor, sample, and process data 804, the targeted process sensor, sample, and process data 806, and the subsequent process sensor, sample, and process data 808 may include operating pressure and temperature data for the components of each process and sub-process. The feedstock sensor, sample, and process data 804, the targeted process sensor, sample, and process data 806, and the subsequent process sensor, sample, and process data 808 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.

[0129] The machine learning model 800 may also access business data 810. Business data 810 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 810 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 810 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 810 may also include the inventory levels of various products that may be stored in the storage tanks 575 of the various blending pools.

[0130] The machine learning model 800 may also access lab data 811 that is obtained from laboratory analysis of samples collected from processes within a refinery and products produced by those processes. Lab data 811 may include chemical composition and component distribution data about each sample, as well as information about when and where the sample was taken, tests performed on the sample, and sensor data from the process at the time the sample was taken.

[0131] The machine learning model 800 may also access weather data 813 as the ambient temperature, pressure, and solar radiation may also affect the temperature and pressure of feedstocks, products, processes, and storage tanks within a refinery. 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 blending pools 524.

[0132] The machine learning model 800 may publish to and receive instructions from an engineering gateway 812. As used herein, “publish” means one or more of to simulate, send, or display. The engineering gateway 812 may act as a user interface for engineers to review process and machine learning model 800 data, recommendations, warnings, and requests. A user may use the engineering gateway 812 to assist the machine learning model 800 in refining and tuning its algorithms to better predict and adjust each process in response to changes in ambient weather, demand seasonality, and composition and quality of feedstocks including the crude oil received for processing into refined hydrocarbons. The engineering gateway 812 may also be used to facilitate active learning by the machine learning model 800. A user may use the engineering gateway 812 to provide feedback to the machine learning model 800. 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 800 through the engineering gateway 812.

[0133] The machine learning model 800 may access, receive data from, and publish instructions to a feedstock process controller 814, a targeted process controller 816, and a subsequent process controller 818. In some embodiments, the machine learning model 800 may adjust an algorithm used by the targeted process controller 816 based on changes identified from the adjusted algorithm. Once an adjusted algorithm has been selected by the machine learning model 800, the machine learning model 800 requests approval to implement the adjusted algorithm through the engineering gateway 812. Upon receipt of approval, the machine learning model 800 saves a copy of the approval information in thehistorical data 802 and sends the approved adjusted algorithm to the targeted process controller 816.

[0134] The machine learning model 800 includes a data analysis module 822. The data analysis module 822 may be used by the machine learning model 800 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 800 may save the revised data set in either the training data 803 or the historical data 802 for retraining of the machine learning model 800, for analysis and adjustment of a targeted process, or for later use.

[0135] The machine learning model 800 includes an interpolation module 824. The interpolation module 824 may be used to analyze a data set and interpolate missing data from the data set. The interpolation module 824 may use the historical data 802 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 824 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.

[0136] The interpolation module 824 may compare the historical data 802 with feedstock sensor, sample, and process data 804, the targeted process sensor, sample, and process data 806, and the subsequent process sensor, sample, and process data 808 to identify process changes. The interpolation module 824 may be able to identify and flag small deviations for further investigation. The interpolation module 824 works with the communication module 828 to publish the data regarding the flagged deviation for user review and guidance. For example, the interpolation module 824 may be used to identify miscalibrated sensors, misprocessed test data, or misprocessed samples that may be inaccurate. The machine learning model 800 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 812. The machine learning model 800 may use theinterpolation module 824 to identify components that may be wearing out and catalysts that may be deactivated or poisoned. The interpolation module 824 may also communicate through the communication module 828 with the engineering gateway 812 to identify these potential process concerns to a user for further investigation.

[0137] The machine learning model 800 includes a prediction module 826. The prediction module 826 may analyze the feedstock sensor, sample, and process data 804, the targeted process sensor, sample, and process data 806, and the subsequent process sensor, sample, and process data 808 to predict changes in a process. For example, temperature excursions may be predicted in a process and the prediction module 826 may communicate through the communication module 828 with the engineering gateway 812 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 812 or provide different instructions for the machine learning model 800 to implement. In predicting changes in a process, prediction module 826 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 826 may provide a recommended maintenance window for the maintenance procedure to occur.

[0138] The machine learning model 800 includes a communication module 828. The communication module 828 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 828 may send or publish communications to the engineering gateway 812. The communication module 828 may also communicate with the various process controllers and other models used by the refinery.

[0139] In some embodiments, the machine learning model 800 includes a confidence module 830. The confidence module 830 may review the analysis and recommendations of the different modules of the machine learning model 800 and assign a confidence level to the analysis and recommendations. For example, the confidence module 830 may produce SHAP values, or use LIME or anchors to analyze each algorithm that is adjusted or created by the machine learning model 800. The confidence module 830 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 thecommunication module 828 to the engineering gateway 812 to assist a user in reviewing each algorithm and the changes recommended by the machine learning model 800.

[0140] In some embodiments, the machine learning model 800 includes a regulatory module 832. The regulatory module 832 may access the business data 810 to assist in regulatory compliance. For example, the regulatory module 832 may flag a process that may be predicted by the prediction module 826 to move out of compliance (i.e., non- compliant). The regulatory module 832 may issue a warning through the communication module 828 to the engineering gateway 812. The regulatory module 832 may also identify windows of time when regulations are lessened and recommend changes to process parameters to reduce process costs. The regulatory module 832 may make recommendations to gasoline blending pool controllers, diesel blending pool controllers, and jet fuel blending pool controllers to adjust blending parameters in line with upcoming regulatory changes. Further, the regulatory module 832 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.

[0141] In some embodiments, the machine learning model 800 includes a forecasting module 834. The forecasting module 834 may analyze business data 810 and recommend that various process controllers adjust their parameters to promote the production of components that may be in greater demand. The forecasting module 834 may also recommend maintenance windows for equipment producing products that may be in low demand during specific time frames. The forecasting module 834 may forecast pricing for various components based on the historical data 802 and the business data 810 and publish the forecasted pricing via the communication module 828 to the engineering gateway 812.

[0142] In some embodiments, the machine learning model 800 may include an authority module 836 and additional modules 838, 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 836 may track user instructions and approvals for various instructions and changes to be made by the machine learning model 800 to the various controllers throughout the refinery. In some applications, the authority module 836 may consider a recommendation from a module of the machine learning model 800 and automatically authorize the machine learning model 800 to issue an instruction to the targeted process controller 816 to make a change to an associated process. In other applications, the authority module 836 may direct the communication module 828 to request approval through the engineering gateway 812 before arecommendation may be implemented and instructions sent to the targeted process controller 816.

[0143] In some embodiments, the authority module 836 directs the communication module 828 to request approval through the engineering gateway 812 before a recommendation is implemented 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 the gasoline desulfurization processes where multiple variables, including pressure, temperature, and initial composition of the feedstock affect the composition of the product of the process. A nonlinear process is a process whose product attributes or composition are determined by a plurality of variables and thus may not be readily predictable. Additionally, a nonlinear product attribute is an attribute that does not blend on a linear basis. For example, when two jet fuels are blended together, many resulting attributes, such as flash point, of the blended jet fuel are not one-to-one by volume on a resulting attribute because of the effect of certain components in the blended jet fuels.

[0144] FIG. 7 is a schematic diagram of an alkylation system 900 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to alkylation may include an alkylation controller 902. Similar to previously described controllers, the alkylation controller 902 may obtain data associated with the equipment of the alkylation unit. The alkylation controller 902 may also initiate capture of samples of fluids associated with the alkylation unit. The sample collection and analysis assembly 908 may then analyze the samples and produce properties and / or a spectra for each sample. The alkylation controller 902 may apply the data, properties, and / or spectra to one or more machine learning model of the local enhancement module 904 and / or the predictive controls module 906 to produce an output indicative of adjustment to parameters and / or feed. The alkylation controller 902 may then utilize the output to adjust various parameters and / or feed associated with the alkylation system 900 via the local enhancement module 904.

[0145] As shown, the alkylation system 900 includes an alkylation reactor 910, an acid settler 912, a caustic scrubber 914, and distillation system 916. Other combinations of processes are possible including multiple reactors, distillation and fractionation units, and other processes ordered in parallel or series.

[0146] Feedstock 920 for the alkylation system 900 may come from a plurality of feedstock sources 918. Feedstock sources 918 include isobutane from a deisobutanizer, a C4 isomerization unit, gas processing, splitter, separator, or distillation, such as distillationsystem 916. Feedstock sources 918 also include light olefins, including propylene, butene, and pentene from one or more of a fluid catalytic cracker, a coker, fractionation, propylene splitter, and other processes.

[0147] The feedstock 920 may optionally be passed through various feedstock treatments 919 prior to being fed into the alkylation reactor 910. Feed treatments 919 may include amine treating, mercaptan treating, caustic wash, water wash column, hydroisomerization, alumina drying, molecular sieve drying, and fractionation drying. Feed treatments 919 may be used to remove contaminants including water, sulfur, nitrogen, oxygen, silicon, chlorides, hydrogen gas, mercury, arsenic, methane, ethane, ethylene, diolefins, amylenes, and heavy hydrocarbons from the feedstock 920. If contaminants are not removed, contaminants may cause corrosion, increased consumption of acid, increased acid regeneration, and may result in poorer product quality. Water in excess amounts may affect acid strength in an alkylation reactor 910 where sulfuric or hydrofluoric acid is used as the catalyst for the alkylation process. However, feedstock treatments 919 may increase overall process costs, so a machine learning model may be trained on the available historical data for these processes to ensure sufficient feedstock treatments 919 occur while reducing costs associated with the feedstock treatments 919.

[0148] Before the feedstock 920 is fed into the alkylation reactor 910, a sensor package 940 may disposed to measure different properties and composition of the feedstock 920. A sensor package 942 may be disposed to measure, analyze, or sample the fresh acid 924 and the recycle acid 926 before being fed into the alkylation reactor 910. The sensor packages 940, 942 may include may include temperature sensors; such as resistance temperature detectors, thermocouples, and infrared sensors; pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors; flow rate sensors, such as coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow; density and composition analyzers, such as sulfur analyzers, refractometers, spectrometers, including near infrared spectrometry, and gas chromatographs; and sampling units and sample analysis assemblies for analyzing the composition of a sample through testing, distillation, or obtaining physical samples from the feedstocks 920 to be analyzed in a lab or by the sample collection and analysis assembly 908. All of this data may be referred to as feedstock data may be sent to the alkylation controller 902 and a machine learning model installed in the controller as part of local enhancement 904, predictive controls 906, or a machine learning model in communication with the alkylation controller 902.

[0149] Once the feedstock 920 is fed into the alkylation reactor 910, the feedstock 920 is reacted in the presence of one or more catalysts. Catalysts may include sulfuric acid, hydrofluoric acid, solid acid catalysts, and ionic liquid catalysts.

[0150] In general, light olefins, including butene, propylene, isobutylene, amylene, are reacted with isobutane to form alkylate composed of of isoheptane and isooctane. In particular, the alkylation reaction begins with the initiation step to form tert-butyl cations.

[0151] With the formation of tert-butyl cations, the tert-butyl cations react with olefins to form larger molecules. For example, tert-butyl cation reacts with 2-butene to form isooctane, and more tert-butyl cations. Further, propylene may react with isobutane to form isoheptane and propane.

[0152] The formation of alkylate may be increased where higher isobutane to olefin ratios exist and lower concentrations of propane are found in the reactor. Propane as a contaminant may be fed into the alkylation reactor 910 as part of the recycled isobutane from the distillation system 916. Propane does not react to form alkylate, so occupies reaction space within the alkylation reactor 910 reducing production. Lower concentrations of propane in the recycled isobutane 922 may be obtained by a sharper cutoff in the distillation system 916 to obtain a purer cut of isobutane 922 from the products of the alkylation process. A smaller percentage of propane in the feedstock may increase the production of alkylate.

[0153] Production of alkylate may increase in applications with higher acid strength and higher acid to hydrocarbon ratios. At the end of the residence time within the reactor 910, the hydrocarbons and acid 930 are passed to the acid settler 912. Residence time may range from 5 minutes to 40 minutes and depends on the catalysts used. The exiting hydrocarbons and acid 930 may be measured and sampled by sensor package 944.

[0154] The alkylation reactor 910 is controlled by alkylation controller 902 and may include one or more sensor packages disposed to measure, analyze, or sample the operational parameters, feedstocks, catalysts, and processes within the alkylation reactor 910. The alkylation reactor sensor packages may include the sensor package 944 measuring, analyzing, and sampling the products of the alkylation reactor 910. The reactor data collected from the alkylation reactor 910 may include sensor data from the sensor packages, sample and lab data collected from samples taken from the alkylation reactor 910, the instructions and control signals provided by the alkylation controller 902, and the data from the sensor package 944. The sensor packages disposed around and within the alkylation reactor and the sensor package 944 may include PH sensors, temperaturesensors; such as resistance temperature detectors, thermocouples, and infrared sensors; pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors; flow rate sensors, such as coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow; density and composition analyzers, such as sulfur analyzers, refractometers, spectrometers, including near infrared spectrometry, and gas chromatographs; and sampling units and sample analysis assemblies for analyzing the composition of a sample through testing, distillation, or obtaining physical samples from the hydrocarbons and hydrofluoric acid 930 to be analyzed in a lab or by the sample collection and analysis assembly 908. Data from the sensor package 944 may be sent to one or more of the sample collection and analysis assembly 908, the alkylation controller 902, a machine learning model installed in the controller as part of local enhancement 904, predictive controls 906, or a machine learning model in communication with the alkylation controller 902.

[0155] Depending on the type of catalysts used, the operational parameters of the alkylation reactor 910 that affect the efficiency of the process and the composition of the products include the ratio of isobutane to light olefins, acid strength, acid to hydrocarbon ratio, good mixing of the liquid hydrocarbons with the acid, residence time of the hydrocarbons within the alkylation reactor 910, and temperature within the alkylation reactor 910.

[0156] The higher the ratio of isobutane to light olefins, the more benefits may be seen in the operation of the alkylation reactor 910. The benefits include increased alkylate octane number, increased alkylate yield, reduced side reactions, and reduced acid consumption. However, increasing the ratio of isobutane to light olefins may increase process costs and may overload the processing capacity of the isobutane separation portion of the distillation system 916. In some applications, the machine learning model may reduce the ratio of isobutane to light olefins, while maintaining the alkylate’s octane barrels or octane number above a desired threshold. Additionally, by reducing the ratio of isobutane to light olefins, more light olefins may be fed into the alkylation reactor 910 to increase the quantity of alkylate produced. The machine learning model, in some applications, may optimize both olefin feed rate and isobutane to olefin ratio to maximize octane-barrels produced by the alkylation unit. Balancing alkylation product properties and yield quantities, and financial costs and benefits, while operating the alkylation process within process constraints may be accomplished through use of a machine learning model.

[0157] With acid catalysts, when the acid to hydrocarbon ratio falls too low or conversely the olefin space velocity is too high, alkylate yields may decrease, acid consumption mayincrease, and the resulting octane number of the alkylate may decrease. Olefin space velocity is the feed rate of olefin divided by the volume of acid. Additionally, maintaining acid concentrations above an operating threshold for the alkylation reactor 910 may increase the operating costs of the alkylation reactor 910 through the purchase of excess fresh acid. Lower acid ratios may be used but may require tighter control of feedstock quality or use of feedstock treatments to reduce contaminant concentrations. Consequently, operating thresholds may be set with a margin to prevent acid runaway, and periodic samples are taken to determine acid to hydrocarbon ratios to ensure the ratio is within tolerances. A machine learning model may be trained on the historical operating parameters and data of the alkylation system 900, the feedstock processes, and the composition of the products to provide better predictive modeling to allow narrower tolerances to be used to prevent use of excess acid and thus, reduce the operating costs of the alkylation system 900.

[0158] Acid strength may be another operating parameter of the alkylation system 900. Acid strength depends on the water content in the alkylation reactor 910. Lower strengths may be compensated by increased agitation or mixing of the acid with the hydrocarbons. Water content above a threshold may lower the catalytic effectiveness of the acid. Acid strength may increase the octane number and quality of the produced alkylate. Further, lower acid strengths may increase the chance of acid runaway. Acid strength may be controlled through the addition of fresh acid, operation of acid regeneration 960, and removal of water as a contaminant in the feedstocks.

[0159] Acid runaway refers to a condition where acid purity deteriorates quickly to produce large amounts of tar and acid soluble oil. As the acid strength decreases the alkylation reaction ceases causing a shut down and requiring restart of the alkylation system 900.

[0160] Further, temperature within the alkylation reactor 910 is another operating parameter of the alkylation system 900. The alkylation reaction within the alkylation reactor 910 is exothermic so temperature control is provided through cooling of the alkylation reactor 910. Seasonal changes may affect temperature control with cooling of the alkylation reactor 910 maximized. During the winter, cooling of the alkylation reactor 910 may be adjusted to prevent excessively low temperatures. Operating the alkylation reactor at lower temperatures may result in increased octane barrels from the alkylation system 900. Therefore, a machine learning model may receive weather data, including solar radiation data and ambient temperature data, and use the data to adjust operational temperatures within the alkylation reactor 910 and feed rates of feedstocks into the alkylation reactor based on the received weather data.

[0161] The alkylation reactor 910 may include one or more sensor packages disposed to measure the operating parameters, catalyst, feedstocks, and reaction products of the alkylation reactor 910. The sensor packages may include may include PH sensors; temperature sensors; such as resistance temperature detectors, thermocouples, and infrared sensors; pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors; flow rate sensors, such as coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow; density and composition analyzers, such as sulfur analyzers, refractometers, spectrometers, including near infrared spectrometry, and gas chromatographs; and sampling units and sample analysis assemblies for analyzing the composition of a sample through testing, distillation, or obtaining physical samples from the feedstocks to be analyzed in a lab or by the sample collection and analysis assembly 908.

[0162] A machine learning model may be used to generate the operational parameters to optimize the octane-barrels or octane number of the produced alkylate while minimizing the isobutane to olefin ratio in order to reduce the costs of producing the alkylate or increase olefin feed rates into the alkylation system. Increased olefin charge running with a lower isobutane to olefin ratio, may allow for increased octane-barrels in the alkylate product, which will increase profit from the alkylation system. Thus, the machine learning model may generate an isobutane to olefin ratio and a charge rate which maximizes the octane- barrel value of the alkylate product. Additionally, the machine learning model may also minimize fresh acid input into the alkylation reactor 910 to further reduce alkylate production costs, while managing the process constraints and protecting against negative process conditions including acid runaway and generating excessive amounts of acid soluble oil.

[0163] The machine learning model may receive feedstock data indicative of feedstock supplied to an alkylation unit. The feedstock data indicative of one or more feedstock properties. The feedstock data may include an upstream operational parameter of a process supplying the feedstock to the alkylation unit that may be used to predict one or more feedstock properties. The machine learning model may be trained on historical data of the operational parameters of the alkylation unit, the feedstock, the feedstock properties, one or more processes upstream of the alkylation unit, products of the alkylation unit, and properties of the products of the alkylation unit.

[0164] The machine learning model receives operational data indicative of the current operational parameters of alkylation unit, including acid properties, to determine thecondition of the alkylation process. The operational data and feedstock data may be used to predict a highest octane number of an alkylate that may be produced by the alkylation unit and generate adjustments to the operational parameters to drive the alkylation process toward the predicted octane number of alkylate. Alternatively, the machine learning model may generate target operational parameters for operation of the alkylation unit to produce a predetermined or received target of octane-barrels of alkylate or a target octane number of alkylate. The target octane-barrels or target octane number of alkylate may be generated from blending pool data or provided by a blending pool controller.

[0165] The machine learning model may use the feedstock data, operating data, and the product data to generate a prediction of acid strength within the alkylation reactor. The prediction of acid strength may be used by the machine learning model to reduce acid strength to an acid strength limit that permits the alkylation unit to achieve production of alkylate that meets the target of octane-barrels of alkylate or target octane number. The acid strength limit may be a lower limit predetermined by users or may be generated by the machine learning model based on the historical data. The acid strength limit may be selected to include a margin above an acid strength where the risk of acid runaway is above a confidence level or unacceptable to a user. The margin may be selected based on the normal system noise in controlling the alkylation unit.

[0166] The machine learning model may be programmed to reduce an isobutane to olefin ratio while still achieving a target of octane-barrels of alkylate or target octane number. A target isobutane to olefin ratio may be generated and may include a margin to accommodate normal system noise in controlling the alkylation unit.

[0167] The machine learning model may generate target operational parameters based on current costs of a target product and feedstock, wherein the machine learning model is programmed to reduce costs of operating the alkylation unit constrained by producing the target of octane-barrels of alkylate. Additionally, the machine learning model may be programmed to reduce energy utilized by the alkylation unit while producing the target of octane-barrels of alkylate. The machine learning model may also be programmed to minimize butane in the feedstock wherein generating target operational parameters includes generating operational parameters for reducing butane in isobutane received from a distillation column or C4 isomerization unit. The operational parameters may be for a distillation unit, such as a debutanizer and may permit the distillation unit to sharpen its cut to reduce the butane in the isobutane cut. In some configurations, the machine learning model may seek to predict a minimum isobutane feed rate into an alkylation reactor basedon the feedstock data, including composition of the feedstock and the feed rate of feedstock into the alkylation reactor. The machine learning model may then drive the feed rate of isobutane toward the minimum isobutane feed rate, but at a margin above the minimum isobutane feed rate. The margin may be set by a user or determined by the machine learning model based on the normal noise in controlling the alkylation unit. Alternatively, the machine learning model may be programmed to meet isobutane demand associated with the alkylation unit while producing the target of octane-barrels of alkylate or target octane number of alkylate.

[0168] In application, the machine learning model may receive feedstock data and one or more of a target alkylate property or operational parameter target. The machine learning model may use the feedstock data and one or more of a target alkylate property or operational parameter target to generate operational parameters, including operational temperatures, isobutane feed rates, acid feed rates.

[0169] Optionally, the machine learning model may publish the operational parameters to a user by displaying the operational parameters on a display screen or sending the operational parameters to a user for review. The machine learning model may wait to receive instructions from a user to adjust or approve the generated operational parameters. The user may approve the operational parameters permitting the machine learning model to implement the operational parameters.

[0170] In some configurations, the machine learning model may generate a plurality of simulations with different operational parameters or product property targets that are published for a user to select. Upon selection, the machine learning model may generate operating parameters from the selection to be implemented in the alkylation controller to move the operating parameters toward the generated operating parameters.

[0171] Alternatively, the machine learning model automatically implements the operational parameters by sending the operational parameters to the alkylation controller 902, feedstock controllers, and feedstock operations upstream from the alkylation reactor 910. As the operational parameters are implemented, the machine learning model may receive one or more operational data or product data. The machine learning model may adjust the generated operational parameters based on the one or more operational data or product data. The machine learning model may also delay implementing additional adjustments for a predetermined period of time to allow the generated operational parameters to be implemented. Thus, the machine learning model may begin implementingadjustments to the generated operational parameters based on the product data after the predetermined period of time has passed.

[0172] The acid settler 912 receives the hydrocarbons and acid 930 and separates the acid from the hydrocarbons 934. The acid may include process by products that may be separated out at an acid regenerator 960 that may recycle the purified acid 926 to be mixed with fresh acid 924 and fed into the alkylation reactor 910. Additionally, the acid regenerator 960 may remove rejected acid 932, which may include acid soluble oil, polymer, water, and other contaminants.

[0173] The acid settler 912 may include one or more sensor packages, such as sensor package 946, to measure and sample the operation of the acid settler 912, the acid removed from the acid settler 912, and the hydrocarbons 934. The sensor packages may include may include PH sensors; temperature sensors; such as resistance temperature detectors, thermocouples, and infrared sensors; pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors; flow rate sensors, such as coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow; density and composition analyzers, such as sulfur analyzers, refractometers, spectrometers, including near infrared spectrometry, and gas chromatographs; and sampling units and sample analysis assemblies for analyzing the composition of a sample through testing, distillation, or obtaining physical samples from the feedstocks to be analyzed in a lab or by the sample collection and analysis assembly 908.

[0174] The machine learning model may also use the feedstock data and one or more of a target alkylate property or operational parameter target to generate a prediction of the acid strength within the alkylation reactor 910 and generate an operational parameter for the injection rate of fresh acid into the alkylation reactor. The product data from the alkylation reactor may be used to adjust the prediction of acid strength within the alkylation reactor 910 and to adjust the generated operational parameter for the injection rate of fresh acid into the alkylation reactor.

[0175] The hydrocarbons 934 may then be passed to a caustic scrubber 914 to neutralize any acid that may have been included with the hydrocarbons 934. The caustic scrubber 914 may include a stripper to separate acid from the hydrocarbons 934. Various alkaline materials may be used to neutralize the acid including potassium hydroxide, sodium hydroxide, and calcium hydroxide. Once neutralized, the hydrocarbons 936 may then be passed to a distillation system 916. Like the acid settler 912, sensor packages, including sensor package 948, may be disposed to analyze, measure, and sample the processes withinthe caustic scrubber 914 and may be disposed to measure the hydrocarbons 936. The sensor packages may include PH sensors; temperature sensors; such as resistance temperature detectors, thermocouples, and infrared sensors; pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors; flow rate sensors, such as coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow; density and composition analyzers, such as sulfur analyzers, refractometers, spectrometers, including near infrared spectrometry, and gas chromatographs; and sampling units and sample analysis assemblies for analyzing the composition of a sample through testing, distillation, or obtaining physical samples from the feedstocks to be analyzed in a lab or by the sample collection and analysis assembly 908.

[0176] The distillation system 916 splits the hydrocarbons 936 into isobutane 922, propane 939, butane 938, and alkylate 937. The distillation system 916 may be a single unit or may include a number of separate splitters, separators, deisobutanizers, depropanizers, strippers, stabilizers, and other distillation columns in parallel or series. In some configurations, the distillation system 916 may also include an acid stripper column. The distillation system 916 may also include one or more sensor packages to analyze, measure, and sample the operation of the distillation system 916 as well as measure the products of distillation. The sensor packages 950, 952, 954, 956 may be disposed to measure, analyze, or sample the products of the alkylation system 900. The sensor packages 950, 952, 954, 956 may include PH sensors; temperature sensors; such as resistance temperature detectors, thermocouples, and infrared sensors; pressure sensors, such as hydrostatic pressure sensors and differential pressure sensors; flow rate sensors, such as coriolis flow meters, ultrasonic flow meters, and turbine flow meters for metering flow; density and composition analyzers, such as sulfur analyzers, refractometers, spectrometers, including near infrared spectrometry, and gas chromatographs; and sampling units and sample analysis assemblies for analyzing the composition of a sample through testing, distillation, or obtaining physical samples from the feedstocks to be analyzed in a lab or by the sample collection and analysis assembly 908.

[0177] The isobutane 922 may be recycled back to the alkylation reactor 910. The isobutane 922 may be analyzed, measured, and sampled by a sensor package 952. In particular, the sensor package 952 may be used to determine the purity of the isobutane 922. A machine learning model may be applied to the distillation system 916 to increase isobutane purity reducing propane in the isobutane 922 recycled back to the alkylation reactor 910. Increased purity may allow increased olefin feed rates into the alkylationreactor 910, and thus increased alkylate production. Additionally, propane does not react in the alkylation reactor 910 and thus, reduces available capacity in the alkylation reactor 910. Additionally, a machine learning model may be used to reduce loss of isobutane to the butane product stream through sharper cuts in the distillation system 916.

[0178] Propane 939 may be produced as a byproduct of the alkylation process and may also be present as an impurity in the feedstock. Propane 939 may be sold as a finished product or used to heat processes within the refinery. The butane 938 may be present as an impurity in the feedstock and from the recycled isobutane. The butane 938 may be sent to C4 isomerization to isomerize into isobutane which may then be fed into the alkylation reactor 910.

[0179] Alkylate 937 generally has a high road octane number and a low Reid vapor pressure. Further, alkylate 937 generally contains few aromatic and olefin hydrocarbons and has a low sulfur and nitrogen content. Consequently, alkylate may be used in premium gasoline blends.

[0180] In some embodiments, a simplified control algorithm based on the octane-barrels (in other words, the change in octane above a base value multiplied by the number of product barrels) versus iso-butane to olefin feed ratio is a concave function with octane- barrels passing through a maximum “optimal” point may be used. The alkylate octane will decrease as the iso-butane to olefin ratio is decreased. An optimal maximum point in terms of octane-barrels in the alkylate will be reached as olefin feed is increased (and, in embodiments, the iso-butane to olefin ratio is decreased) from a minimum feed to a maximum feed. Thus, in an embodiment, a machine learning model may be trained to maximize or utilized for maximizing that point on the curve.

[0181] One trained machine learning model may be based on the non-linear relationship of olefin feed to acid strength and another may be based on the non-linear relationship of fresh acid to acid strength. The alkylation controller 902 may, based on the trained machine learning model of acid purity, control parameters in the acid regenerator 960 and minimize acid consumption. In embodiments, controlling acid strength in the alkylation unit reduces polymerization which, if occurring, may result in a unit shutdown and lost economic opportunity. The alkylation controller 902 may, based on the trained machine learning model, also be used to achieve a higher alkylate octane in a product. The relationship between acid strength and alkylate octane is nonlinear. Thus, the controller will be able to determine the acid strength that maximizes alkylate octane-barrels or an octane number while maintaining process control at that acid strength. Running at a lower acid strengthoperates the unit closer to acid runaway where polymerization could occur. Thus, the alkylation controller 902 may, based on the trained machine learning models therein, enable operation of an alkylation unit at a lower acid strength that minimizes acid consumption, while preventing polymerization and unit shutdown. This process control by the machine learning model at a lower acid strength may also include a margin above a predicted minimum in order to accommodate unforeseen swings in acid purity or acid strength.

[0182] FIG. 8 is a schematic diagram of a feed control system 1900 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. Each refinery operation utilizes a feed stream or feedstock. Such a feed stream or feedstock may, in some examples, be adjusted, to optimize or enhance fluid production of a corresponding refinery operation. Similar to previously described controllers, the feed controller 1902 may obtain data associated with the equipment that produces a feed or intermediary, blends a feed or intermediary, and / or utilizes a feed and / or intermediary, such as from one or more blend tanks 1908, one or more in-line blend pipes 1910, one or more feedstock sources 1912, one or more intermediary sources 1914, one or more sample collection and analysis assemblies 1916, and / or refinery equipment 1918. The feed controller 1902 may also initiate capture of samples of fluids associated with the devices and / or equipment that produce, blend, and / or utilize feed. The sample collection and analysis assembly (not illustrated) may then analyze the samples and produce properties and / or a spectra for each sample. The feed controller 1902 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 1904 and / or predictive controls module 1906 to produce an output indicative of adjustment to parameters and / or feed. The feed controller 1902 may then utilize the output to adjust various parameters and / or blends of a feed or intermediary associated with the refinery equipment 1918 via the local enhancement module 1906. The trained machine learning model utilized for the feed controller 1902 may be trained to or utilized to predict feed, blend, and / or intermediary properties and / or components that produce a maximum or greater than typical yield for a particular refinery operation.

[0183] FIG. 9 is a schematic diagram of a gasoline pool control system 2000 to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. After processing various feeds via one or more different operations or sub-operations, various products from those operations or sub-operations may be combined to produce a selected gasoline or to form a selected gasoline pool. Such a gasoline pool may include a specification, the specification including one or more of an octane number, a researchoctane number, a motor octane number, a Reid vapor pressure, an amount of benzene, a density, a color, a flash point, an amount and / or type of lubricant, an amount and / or type of detergents, an amount and / or type of anti-rust agents, amount and / or type of anti-icing agents, and / or amount of sulfur or other contaminants, among other properties. To reach the properties specified, a refinery controller and / or a gasoline pool controller 2002, for example may obtain analysis of and / or other data associated with various products within a refinery and select a percentage, the percentage in relation to the whole final gasoline product, of each product for combination or blending. As such, the refinery controller and / or gasoline pool controller 2002 may obtain data from a variety of sources. For example, the gasoline pool controller 2002 may obtain data from an FCC unit 2008, a fractionation / distillation column 2010, an alkylation unit 2012, a gasoline desulfurization unit 2014, an isomerization unit 2015, a reformer 2016 or catalytic reformer, and / or an external gasoline source 2017 (for example, the external gasoline source 2017 may include a source that a refinery purchases and / or obtains gasoline from). Further, the gasoline pool controller 2002 may obtain data from the sample collection and analysis assembly 2018 and / or other refinery equipment 2020. In other embodiments, the gasoline pool controller 2002 may connect to a refinery controller and / or other controllers or sub-operation controllers within the refinery to obtain data related to that operation or sub-operation. Further, the gasoline pool controller 2004 may obtain data and / or properties from the collection and analysis assembly 2018 related to other fluids produced within the refinery. Once such data and / or properties has been collected, the gasoline pool controller may apply the data to one or more trained machine learning models stored in the local enhancement module 2004 and / or the predictive controls module 2006 to produce amounts of each varying fluid and / or properties associated with a fluid that causes production of the fluid to reach selected properties. In an embodiment, the local enhancement module 2004 may apply the output of a plurality of trained machine learning models each stored in one or more of a plurality of predictive controls modules 2006 to a trained machine learning model of the local enhancement module 2004.

[0184] Once a prediction is determined by the gasoline pool controller 2004, the gasoline pool controller 2004 may adjust one or more devices within the refinery to cause those one or more devices to provide fluids for and / or adjust parameters to produce the selected or target gasoline. The selected components of the selected or targeted gasoline may then be blended.

[0185] In an embodiment, the trained machine learning models within the gasoline pool controller 2002 may be trained to or utilized for predicting parameters and / or properties for one or more of the units described in relation to the gasoline pool controller 2002. For example, if a specific property of a target gasoline pool is known or input into the trained machine learning model, along with other related data, then the gasoline pool controller 2002 may determine, based on application of that specific property and / or data to a trained machine learning model, process parameters and / or feed and / or intermediary properties for that particular process. In an embodiment, another controller specific for that operation may utilize the output to drive that operation to produce a fluid that accurately exhibits that specific parameter. In further embodiments, the gasoline pool controller 2002 may determine such parameters and / or properties for a plurality of other operations. In other embodiments, the gasoline pool controller 2002 may work in conjunction with other controllers to produce selected fluids. Thus, the gasoline pool controller 2002, in embodiments, may coordinate targeted outputs, by adjusting or causing adjustment of one or more refinery operations or sub-operations and / or by blending selected components from the refinery operations or sub-operations, from a plurality of operations to meet a selected gasoline pool specification.

[0186] In another embodiment, the gasoline pool controller 2002 may select a source of gasoline based on an output from the trained machine learning models. The trained machine learning models may output a blend percentage of gasoline from the sources to reach a target octane and / or volatility limit. In such embodiments, the volatility limit may comprise a RVP or vapor liquid ratio. In another embodiment, such a blend percentage of gasoline may comprise a higher percentage of gasoline from the external gasoline source 2017 and smaller percentages of gasoline and / or other fluids from other sources to reach the octane and / or volatility limit.

[0187] FIG. 10 and FIG. 11 are simplified diagrams of control systems 2700 to enhance fluid production at refinery, according to an embodiment of the disclosure. As noted, control system 2700 may include an operation controller 2701. Further, the operation controller 2701 may connect to one or more sensors 2716A, 2716B, and up to 2716N, one or more devices 2718 A, 2718B, and up to 2718N (such as flow control devices and / or temperature control devices), one or more equipment 2720A, 2720B, and up to 2720N, one or more analyzers 2722A, 2722B, and up to 2722N, and one or more predictive controls 2714A, 2714B, and up to 2714N. The operation controller 2701 may include memory 2704 and one or more processors 2702. Memory 2704 may store instructions executable by oneor more processors 2702. In an example, the memory 2704 may be a non-transitory machine-readable storage medium. As noted, memory 2704 may store or include instructions executable by the processor 2702.

[0188] 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.

[0189] Memory 2704 may include or store sample and data collection and instructions 2706. Upon execution of such instructions, the operation controller 2701 may obtain samples associated with each equipment 2720A, 2720B, and up to 2720N. Further, the operation controller 2701 may obtain data from the one or more sensors 2716A, 2716B, and up to 2716N and / or one or more flow control devices 2718 A, 2718B, and up to 2718N. Upon collection of the samples, the operation controller 2701 may send the sample to one of the one or more analyzers 2722A, 2722B, and up to 2722N. The one of the one or more analyzers 2722A, 2722B, and up to 2722N may then analyze the sample and generate properties and / or a spectra.

[0190] The operation controller 2701 may connect to and receive data from the one or more predictive controls 2714A, 2714B, and up to 2714N. In an embodiment, the operation controller 2701 may receive the output from each trained machine learning model of each the predictive controls 2714A, 2714B, and up to 2714N. In an embodiment, the output may comprise a vector or, in other embodiments, a value indicative of a parameter adjustment.

[0191] The memory 2704 may include or store trained machine learning models 2708. The trained machine learning models 2708 may include at least one trained machine learning model to generate an output indicative of parameter and / or feed adjustment. The operation controller 2701 may apply the data, properties, spectra, and / or the output of each trained machine learning model from one or more predictive controls 2714A, 2714B, and up to 2714N to the trained machine learning models 2708 to generate an output indicative of parameter adjustments and / or feed adjustment.

[0192] Memory 2704 may include or store parameter adjustment instructions 2710. Upon generation of the output, the operation controller 2701 may adjust parameters associated with equipment at the refinery. Further the memory 2704 may include or store feed adjustment instructions 2712 to adjust feed based on the output.

[0193] In FIG. 11, predictive controls 2714 may connect to subsets of each of the components described in FIG. 10. For example, the predictive controls 2714 may connect to a subset of the sensors 2736A, 2736B, and up to 2736N, a subset of the devices 2738A, 2738B, and up to 2738N, a subset of the equipment 2740A, 2740B, and up to 2740N, and / or a subset of the analyzers 2742A, 2742B, and up to 2742N. The predictive controls 2714 may include a trained machine learning model 2728 and instructions stored in a memory 2726 and executable by a processor 2724.

[0194] The instructions may include sample and data collection instructions 2730, which when executed cause the predictive controls 2714 to collect various data points and / or properties. Based on application of the data received to the trained machine learning model 2728 and, in some embodiments, an output from the operation controller 2701, the predictive controls 2714 may supply or provide the output to the operation controller 2701.

[0195] 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 2800 may be completed within an operation controller and / or predictive controls. Specifically, method 2800 may be included in one or more programs, protocols, or instructions loaded into the memory 2704 of operation controller 2701 and executed on the processor 2702 or one or more processors of the operation controller 2701 of FIG. 10. In other embodiments, method 2800 may be implemented in or included in components of FIGS. 1 A-16. 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.

[0196] At block 2802, 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.

[0197] At block 2804, once each sub-controller has obtained data, each sub-controller may apply that data, which may also include one or more different properties and / or spectra, to a corresponding machine leaning model stored therein. In another embodiment, the targeted product and / or targeted properties may be applied, in addition to the data described above,to the machine learning model of the predictive controls. The machine learning model may produce vectors, indicators, and / or other values indicative of one or more parameters that may cause the corresponding source to produce a targeted product. Each of the parameters output from the trained machine learning model may correspond to some aspect of the source. For example, the parameters may include temperature, amounts of other fluids used in the operation (for example, hydrogen or alkanes, among others), pressure, flow rate, residence time, feedstock used, and / or intermediaries used.

[0198] At block 2806, each of the predictive control may determine whether the subparameters are different than currently set parameters. If the parameters are different, then, in some embodiments and at block 2808, each of the predictive controls may adjust one or more of the equipment, devices, or fluids. In such embodiments, the predictive controls may provide the adjustments to an equipment and device controller. In another embodiment, the predictive controls may provide the adjustments to the operation controller 2701 (FIG. 10) to perform such adjustments. In another embodiment, rather than or in addition to adjusting the equipment or devices, the predictive controls may provide the trained machine learning model output to the operation controller 2701.

[0199] At block 2810, the operation controller 2701 (FIG. 10) 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 2701, in some embodiments, may first obtain data from all, substantially all, a portion of the refinery, or from a corresponding operation. Data, as noted above, may include data from sensors, meters, equipment, and / or other devices, as well as properties and / or spectra obtained from samples taken from each unit within the refinery. Further, the operation controller 2701 may obtain the output of each model of each predictive control. Once the operation controller 2701 obtains all relevant data, the operation controller 2701 may determine the updated parameters based on application of that data to a machine learning model.

[0200] At block 2812, the operation controller 2701 (FIG. 10) 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, operation controller 2701 may compare the values of the updated parameters to the currently set parameters. If the parameters are different, then at block 2814, the operation controller 2701 may adjust the devices, equipment, or fluid within the refinery to the updated parameters.

[0201] In an embodiment, refinery operations may occur continuously or substantially continuously. As such, method 2800 may be an iterative and continuous process that occurs in real-time or near real-time. As target products change and / or other aspects of the refinery change, parameters may continue to be adjusted via method 2800.

[0202] FIG. 13 is a flow chart of a method, according to at least one embodiment of the present disclosure. The method includes inputting data indicative of one or more spectra or properties of feedstock to be fed into an alkylation unit into a machine learning model trained on historical equipment specific data of an alkylation unit, upstream processes that supply feedstock to the alkylation unit, the feedstocks supplied to the alkylation unit, and products of the alkylation unit at 2910. The method further includes inputting a target product property for a product desired from the alkylation unit into the machine learning model at 2920 and generating parameters, by the machine learning model, for operation of the alkylation unit to enable production of the product desired from the alkylation unit based on the target product property for a product desired from the alkylation unit into the machine learning model at 2930. The method may optionally include outputting the parameters to an operation controller at 2940.

[0203] FIG. 14 is a flow chart of another method, according to at least one embodiment of the present disclosure. The method includes supplying a feedstock to an alkylation unit, the feedstock having one or more feedstock properties at 3010 and inputting an upstream operational parameter of a process supplying the feedstock to the alkylation unit to a machine learning model at 3020. The machine learning model is trained on a historical data set of the operational parameters of the alkylation unit, the feedstock, the feedstock properties, products of the alkylation unit, and properties of the products of the alkylation unit. The method further comprising predicting, by the machine learning model one or more feedstock properties based on the upstream operational parameter of a process supplying the feedstock to the alkylation unit at 3030 and supplying an acid to the alkylation unit at 3040. The method further includes inputting an acid property of the acid to the machine learning model at 3050 and inputting a current measured operational property of the alkylation unit to the machine learning model at 3060. The machine learning model predicts a highest octane number of an alkylate that may be produced by the alkylation unit based on the upstream operational parameter, the one or more acid properties, and the current measured operational property of the alkylation unit at 3070 and generates target operational parameters for operation of the alkylation unit to produce a target of octane- barrels of alkylate at 3080.

[0204] FIG. 15 is a flow chart of another method, according to at least one embodiment of the present disclosure. The method includes receiving, by a machine learning model, feedstock data indicative of a property or a composition of a feedstock to be fed into an alkylation reactor at 3110. The machine learning model is trained on a historical data set of operational parameters of an alkylation system, the feedstock, the feedstock properties, products of the alkylation system, and properties and composition of the products of the alkylation system. The method further includes the machine learning model receiving input indicative of one or more of a target alkylate property or operational parameter target at 3120 and generating operational parameters based on the feedstock data and the one or more of a target alkylate property or operational parameter target 3130.

[0205] FIG. 16 is a flow chart of another method, according to at least one embodiment of the present disclosure. The method including receiving, by a machine learning model, feedstock data indicative of a property or a composition of a feedstock to be fed into an alkylation reactor at 3210. The machine learning model is trained on a historical data set of operational parameters of an alkylation system, feedstock, feedstock properties, products of the alkylation system, and properties and composition of the products of the alkylation system. The machine learning model receives product data indicative of one or more of a property or a composition of a product of the alkylation reactor at 3220 and generates a prediction of acid strength within the alkylation reactor based on the feedstock data and the product data at 3230.

[0206] 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 compri sing : receiving, by a machine learning model, feedstock data indicative of a property or a composition of a feedstock to be fed into an alkylation reactor, wherein the machine learning model is trained on a historical data set of operational parameters of an alkylation system, the feedstock, the feedstock properties, products of the alkylation system, and properties and composition of the products of the alkylation system; receiving, by the machine learning model, input indicative of one or more of a target alkylate property or operational parameter target; and generating, by the machine learning model, operational parameters based on the feedstock data and the one or more of a target alkylate property or operational parameter target.

2. The method of claim 1, further comprising publishing the generated operational parameters to a user.

3. The method of claim 2, further comprising waiting, by the machine learning model, to receive instructions from a user to adjust or approve the generated operational parameters.

4. The method of any of claims 1 to 3, further comprising implementing the generated operational parameters to adjust the operational parameters of the alkylation system toward the generated operational parameters.

5. The method of claim 4, further comprising delaying, by the machine learning model, implementing additional adjustments for a predetermined period of time to allow the generated operational parameters to be implemented.

6. The method of claim 5, wherein adjusting, by the machine learning model, the generated operational parameters based on the product data takes place after the predetermined period of time has passed.

7. The method of any of claims 1 to 6, further comprising receiving product data from a sensor package disposed to measure or sample a product stream from the alkylation system.

8. The method of claim 7, further comprising adjusting, by the machine learning model, the generated operational parameters based on the product data.

9. The method of any of claims 1 to 8, wherein the target alkylate property is an octane number.

10. The method of any of claims 1 to 9, wherein the target alkylate property is a number of octane-barrels.

11. The method of any of claims 1 to 10, wherein the operational parameter target are isobutane feed rates.

12. The method of any of claims 1 to 11, wherein the operational parameter target are acid feed rates.

13. The method of claim 12, wherein the acid is hydrofluoric acid.

14. The method of claim 12, wherein the acid is sulfuric acid.

15. The method of any of claims 1 to 12, wherein the operational parameter target are light olefin feed rates.

16. The method of any of claims 1 to 15, wherein the operational parameter target are alkylation reactor temperatures.

17. The method of any of claims 1 to 16, wherein the feedstock data is indicative of an isobutane to olefin ratio, wherein the input is an instruction to reduce the isobutane to olefin ratio while maintaining an octane number of produced alkylate above a threshold, the method further comprising generating the operational parameter target of the reduced isobutane to olefin ratio.

18. The method of any of claims 1 to 17, wherein the feedstock data is indicative of an isobutane to olefin ratio, wherein the input is an instruction to adjust the isobutane to olefin ratio in relation to alkylate octane-barrels to increase alkylate octane-barrels, the method further comprising generating the operational parameter target of a isobutane to olefin ratio.

19. The method of any of claims 1 to claim 75, further comprising generating, by the machine learning model, an olefin feed rate supporting an operational parameter target of a isobutane to olefin ratio.

20. The method of claim 19, further comprising adjusting the olefin feed rate based on the generated olefin feed rate.

21. The method of any of claims 1 to 20, wherein the feedstock data is indicative of an isobutane to olefin ratio, wherein the input indicative of one or more of a target alkylate property or operational parameter target is an instruction to minimize a fresh acid feed rate into the alkylation reactor, while maintaining an octane number of produced alkylate above a threshold, the method further comprising generating the operational parameter target of the minimized fresh acid feed rate into the alkylation reactor.

22. The method of any of claims 1 to 21, further comprising generating, by the machine learning model, a prediction of a minimum feed rate of fresh acid into the alkylation reactor to maintain acid strength above a target acid strength.

23. The method of claim 22, wherein generating the operational parameter target of the prediction of a minimum feed rate of fresh acid into the alkylation reactor is constrained by a margin above the prediction of a minimum feed rate of fresh acid.

24. The method of any of claims 22 to 23, further comprising generating, by the machine learning model, the target acid strength based on historical data of the alkylation reactor.

25. The method of any of claims 22 to 24, further comprising controlling the fresh acid feed rate to the operational parameter target of the minimum fresh acid feed rate.

26. The method of any of claims 21 to 25, wherein the acid is hydrofluoric acid.

27. The method of any of claims 21 to 25, wherein the acid is sulfuric acid.

28. The method of any of claims 1 to 27, further comprising receiving weather data, wherein generating, by the machine learning model, operational parameters is further based on the weather data.

29. The method of any of claims 1 to 28, further comprising receiving one or more operational data or product data and adjusting the generated operational parameters based on the one or more operational data or product data.

30. The method of any of claims 1 to 29, wherein the generated operational parameters include a control algorithm for controlling an alkylation controller.

31. The method of claim 30, further comprising implementing the control algorithm on the alkylation controller and controlling the alkylation system with the control algorithm.

32. The method of any of claims 1 to 31, further comprising generating, by the machine learning model, a predicted feed rate of fresh acid to produce a target octane-barrels of produced alkylate based on the feedstock data and the product data.

33. The method of claim 32, wherein the target octane-barrels of produced alkylate is determined by the machine learning model to be an optimized octane-barrels of produced alkylate based on the feedstock data, acid strength, acid to hydrocarbon ratio, temperature within the alkylation reactor in view of process constraints.

34. The method of any of claims 1 to 33, further comprising: receiving gasoline blending pool data at the machine learning model; and generating the target property of the product of the alkylation system based on the gasoline blending pool data.

35. The method of claim 34, wherein the gasoline blending pool data includes a customer specification for a blended formulation.

36. The method of any of claims 34 to 35, wherein the target property is a target octane- barrels of alkylate.

37. The method of any of claims 34 to 36, wherein the target property is a target octane number of alkylate.

38. The method of any of claims 34 to 37, wherein the target property is measured or sampled proximate an exit of a reactor of the alkylation system.

39. The method of any of claims 34 to 37, wherein the target property is measured or sampled proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the alkylation system.

40. The method of any of claims 34 to 39, wherein generating operational parameters of the alkylation system includes generating an adjustment to an operating temperature of a reactor of the alkylation system.

41. The method of claim 40, further comprising predicting, by the machine learning model, an acid strength of the reactor of the alkylation system, wherein generating an adjustment to an operating temperature of a reactor of the alkylation system is further based on the predicted an acid strength of the reactor of the alkylation system.

42. The method of any of claims 34 to 41, further comprising implementing the generated operational parameters to adjust operational parameters of the alkylation system.

43. The method of any of claims 40 to 41, further comprising publishing a notification by the machine learning model that the target property of the product is not achievable based on constraints of the reactor of the alkylation system.

44. The method of any of claims 40 to 43, further comprising;generating, by the machine learning model, a possible property of the product closest to the target property of the product; and publishing a notification of a possible property of the product closest to the target property of the product.

45. The method of any of claims 40 to 44, further comprising generating, by the machine learning model, a determination to not implement the adjustment to a parameter of the alkylation system.

46. A memory including instructions and a machine learning model that causes a processor to perform the instructions including the method of any of claims 1 to 45.

47. 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 45.

48. A method comprising: receiving, by a machine learning model, feedstock data indicative of a property or a composition of a feedstock to be fed into an alkylation reactor, wherein the machine learning model is trained on a historical data set of operational parameters of an alkylation system, feedstock, feedstock properties, products of the alkylation system, and properties and composition of the products of the alkylation system; receiving, by the machine learning model, product data indicative of one or more of a property or a composition of a product of the alkylation reactor; and generating, by the machine learning model, a prediction of acid strength within the alkylation reactor based on the feedstock data and the product data.

49. The method of claim 48, further comprising generating an operational parameter for a feed rate of fresh acid into the alkylation reactor based on the prediction.

50. The method of claim 49, wherein the operational parameter is a control algorithm controlling the feed rate of fresh acid into the alkylation reactor based on the prediction.

51. The method of any of claims 48 to 50, further comprising generating an operational parameter for an acid regenerator.

52. The method of claim 51, further comprising receiving, by the machine learning model, recycled acid data indicative of recycled acid produced by of the acid regenerator.

53. The method of any of claims 48 to 52, further comprising receiving acid data indicative of one or more properties of acid removed from an acid settler, wherein generating, by the machine learning model, a prediction of the acid strength within the alkylation reactor is further based on the acid data.

54. The method of claim 52, further comprising adjusting the operational parameters for the acid regenerator based on the recycled acid data.

55. The method of any of claims 52 to 54, further comprising generating a prediction of acid consumption by the alkylation system based on the feedstock data and the product data.

56. The method of claim 55, wherein generating a prediction of acid consumption by the alkylation system based on the feedstock data, the product data, and the recycled acid data.

57. The method of claim 55, further comprising generating, by the machine learning model, a prediction of a fresh acid feed rate into the alkylation reactor based on the prediction of acid consumption.

58. The method of any of claims 48 to 56, wherein the acid is hydrofluoric acid.

59. The method of any of claims 48 to 56, wherein the acid is sulfuric acid.

60. The method of any of claims 49 to 59, further comprising: generating, by the machine learning model, a prediction of a minimum acid strength within the alkylation reactor based on the feedstock data and the product data; andgenerating, by the machine learning model, a prediction of a fresh acid feed rate into the alkylation reactor to maintain the acid strength within the alkylation reactor above the prediction of the minimum acid strength within the alkylation reactor, wherein the prediction of a fresh acid feed rate is based on a margin above the prediction of the minimum acid strength.

61. The method of claim 60, further comprising generating, by the machine learning model, the margin above the prediction of the minimum acid strength based on the historical data set.

62. The method of any of claims 49 to 61, further comprising generating, by the machine learning model, a predicted feed rate of fresh acid to produce a target octane- barrels of produced alkylate based on the prediction of acid strength within the alkylation reactor, the feedstock data, and the product data.

63. The method of claim 62, further comprising generating, by the machine learning model, the target octane-barrels of produced alkylate based on the feedstock data, acid strength, acid to hydrocarbon ratio, and temperature within the alkylation reactor in view of process constraints.

64. The method of claim 63, wherein the target octane-barrels of produced alkylate based is an optimized octane-barrels of produced alkylate.

65. The method of any of claims 62 to 64, further comprising adjusting the operational parameters, feedstock feed rates, and fresh acid feed rate to produce the target octane- barrels of produced alkylate.

66. The method of any of claims 49 to 62, further comprising generating, by the machine learning model, a predicted feed rate of fresh acid to produce a target octane number of produced alkylate based on the prediction of acid strength within the alkylation reactor.

67. The method of claim 66, wherein generating, by the machine learning model, a predicted feed rate of fresh acid to produce a target octane number of produced alkylate is further based on the feedstock data and the product data.

68. The method of any of claims 66 to 67, further comprising generating, by the machine learning model, the target octane number of produced alkylate based on the feedstock data, acid strength, acid to hydrocarbon ratio, and temperature within the alkylation reactor in view of process constraints.

69. The method of claim 68, wherein the target octane number of produced alkylate based is an optimized octane-barrels of produced alkylate.

70. The method of any of claims 62 to 69, further comprising adjusting one or more of the operational parameters, feedstock feed rates, or fresh acid feed rate to produce a target octane number of produced alkylate.

71. The method of any of claims 48 to 70, further comprising: receiving gasoline blending pool data at the machine learning model; and generating a target property of the product of the alkylation system based on the gasoline blending pool data; and generating an adjustment to an operational parameter of the alkylation system to achieve the target property of the product of the alkylation system.

72. The method of claim 71, wherein the gasoline blending pool data includes a customer specification for a blended formulation.

73. The method of any of claims 71 to 72, wherein the target property is a target octane- barrels of alkylate.

74. The method of any of claims 71 to 73, wherein the target property is a target octane number of alkylate.

75. The method of any of claims 71 to 74, wherein the target property is measured or sampled proximate an exit of a reactor of the alkylation system.

76. The method of any of claims 71 to 74, wherein the target property is measured or sampled proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the alkylation system.

77. The method of any of claims 71 to 76, wherein generating, by the machine learning model, the adjustment to the operational parameter of the alkylation system includes generating an adjustment to an operating temperature of a reactor of the alkylation system.

78. The method of claim 77, further comprising predicting, by the machine learning model, an acid strength of the reactor of the alkylation system, wherein generating the adjustment to the operating temperature of a reactor of the alkylation system is further based on the predicted an acid strength of the reactor of the alkylation system.

79. The method of any of claims 71 to 78, further comprising implementing the generated adjustment to adjust the parameter of the alkylation system.

80. The method of any of claims 77 to 78, further comprising publishing a notification by the machine learning model that the target property of the product is not achievable based on constraints of the reactor of the alkylation system.

81. The method of any of claims 77 to 80, further comprising; generating, by the machine learning model, a possible property of the product closest to the target property of the product; and publishing a notification of a possible property of the product closest to the target property of the product.

82. The method of any of claims 77 to 81, further comprising generating, by the machine learning model, a determination to not implement the adjustment to a parameter of the alkylation system.

83. A memory including instructions and a machine learning model that causes a processor to perform the instructions including the method of any of claims 48 to 82.

84. 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 48 to 82.

85. A method compri sing : inputting data indicative of one or more spectra or properties of feedstock to be fed into an alkylation unit into a machine learning model trained on historical equipment specific data of an alkylation unit, upstream processes that supply feedstock to the alkylation unit, the feedstocks supplied to the alkylation unit, and products of the alkylation unit; inputting a target product property for a product desired from the alkylation unit into the machine learning model; and generating parameters, by the machine learning model, for operation of the alkylation unit to enable production of the product desired from the alkylation unit based on the target product property for a product desired from the alkylation unit into the machine learning model.

86. The method of claim 85, further comprising outputting the parameters to an operation controller.

87. The method of any of claims 85 to 86, wherein outputting the parameters includes outputting parameters to an operation controller upstream of the alkylation unit.

88. The method of claim 87, wherein the output parameters to operation controllers upstream of the alkylation unit include predicted adjustments to the parameters of the operation controllers upstream of the alkylation unit to enable the alkylation unit to produce the product desired from the alkylation unit.

89. The method of any of claims 86 to 88, wherein the operation controller upstream of the alkylation unit includes one or more of an operation controller for a fractionation column, an FCC unit, a C4 isomerization unit, a propylene splitter, or a C4 splitter.

90. The method of any of claims 86 to 89, wherein outputting the parameters includes outputting parameters to operation controllers downstream of the alkylation unit.

91. The method of any of claims 86 to 88, wherein the operation controller downstream of the alkylation unit is a gasoline pool controller.

92. The method of any of claims 85 to 91, further comprising adjusting the alkylation unit to operate at the parameters to produce the product desired from the alkylation unit.

93. The method of claim 92, wherein adjusting the parameters of the alkylation unit to the generated parameters of the alkylation unit, the adjustments are made in-real time or near real-time based on the input data.

94. The method of claim 92, further comprising: sampling the product produced by the alkylation unit; analyzing the sample to generate sample data; and inputting the sample data into the machine learning model.

95. The method of claim 94, further comprising training the machine learning model on the sample data and the parameters of the alkylation unit used to produce the product sampled.

96. The method of claims 94 or 95, further comprising generating, by the machine learning model, new parameters of the alkylation unit to produce the product desired from the alkylation unit based on the sample data.

97. The method of claim 96, further comprising adjusting the parameters of the alkylation unit to the new parameters of the alkylation unit.

98. The method of any of claims 85 to 97, wherein generating parameters is based on current cost of a target product and feedstock, wherein the machine learning model is programmed to reduce costs of operating the alkylation unit while producing the product desired from the alkylation unit with the target product property.

99. The method of any of claims 85 to 98, wherein the machine learning model is programmed to reduce energy utilized by the alkylation unit while producing the product desired from the alkylation unit with the target product property.

100. The method of any of claims 85 to 99, wherein the machine learning model is programmed to minimize butane in a recycled isobutane stream being fed into an alkylation reactor of the alkylation unit while producing the product desired from the alkylation unit with the target product property.

101. The method of any of claims 85 to 100, wherein the machine learning model is programmed to minimize isobutane in a butane product stream from the alkylation unit while producing the product desired from the alkylation unit with the target product property.

102. The method of any of claims 85 to 101, wherein the machine learning model is programmed to meet isobutane demand associated with the alkylation unit while producing the product desired from the alkylation unit with the target product property.

103. The method of any of claims 85 to 102, wherein the machine learning model is programmed to enhance isobutane production from a C4 isomerization unit as a feedstock for the alkylation unit while producing the product desired from the alkylation unit with the target product property.

104. The method of any of claims 85 to 103, wherein the machine learning model is programmed to enable operation the alkylation unit at a lower acid strength that reduces acid consumption while inhibiting polymerization and producing the product desired from the alkylation unit with the target product property.

105. The method of claims 85 to 103, further comprising predicting, by the machine learning model, an acid strength based on the input data.

106. The method of claims 85 to 103, wherein generating parameters, the machine learning model generates parameters to maintain an acid strength at or above a selected threshold.

107. The method of any of claims 85 to 106, wherein the machine learning model is programmed to enable an acid strength to produce a desired alkylate octane while producing the product desired from the alkylation unit with the target product property.

108. The method of any of claims 85 to 107, wherein the machine learning model is programmed to maximize alkylate octane in the product while producing the product desired from the alkylation unit with the target product property.

109. The method of any of claims 85 to 108, wherein the machine learning model is programmed to increase olefin feed rates into the alkylation unit to produce the product desired from the alkylation unit with the target product property while reducing acid strength.

110. The method of any of claims 85 to 109, wherein the target product property is a desired alkylate octane.

111. The method of any of claims 85 to 110, wherein the machine learning model is programmed to reduce a fresh acid feed rate while maintaining acid strength and producing the product desired from the alkylation unit with the target product property.

112. The method of any of claims 85 to 111, further comprising: receiving gasoline blending pool data at the machine learning model; and generating the target property of the product of the alkylation unit based on the gasoline blending pool data.

113. The method of claim 112, wherein the gasoline blending pool data includes a customer specification for a blended formulation.

114. The method of any of claims 112 to 113, wherein the target property is a target octane-barrels of alkylate.

115. The method of any of claims 112 to 114, wherein the target property is a target octane number of alkylate.

116. The method of any of claims 112 to 115, wherein the target property is measured or sampled proximate an exit of a reactor of the alkylation unit.

117. The method of any of claims 112 to 115, wherein the target property is measured or sampled proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the alkylation unit.

118. The method of any of claims 112 to 117, wherein generating parameters of the alkylation unit includes generating an adjustment to an operating temperature of a reactor of the alkylation unit.

119. The method of claim 118, further comprising predicting, by the machine learning model, an acid strength of the reactor of the alkylation unit, wherein generating an adjustment to an operating temperature of a reactor of the alkylation unit is further based on the acid strength of the reactor of the alkylation unit.

120. The method of any of claims 112 to 119, further comprising implementing the generated parameters to adjust the parameters of the alkylation unit.

121. The method of any of claims 118 to 119, further comprising publishing a notification by the machine learning model that the target property of the product is not achievable based on constraints of the reactor of the alkylation unit.

122. The method of any of claims 118 to 121, further comprising; generating, by the machine learning model, a possible property of the product closest to the target property of the product; and publishing a notification of a possible property of the product closest to the target property of the product.

123. The method of any of claims 118 to 122, further comprising generating, by the machine learning model, a determination to not implement the adjustment to a parameter of the alkylation unit.

124. A memory including instructions and a machine learning model that causes a processor to perform the instructions including the method of any of claims 85 to 123.

125. 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 85 to 123.

126. A method compri sing : supplying a feedstock to an alkylation unit, the feedstock having one or more feedstock properties; inputting an upstream operational parameter of a process supplying the feedstock to the alkylation unit to a machine learning model, the machine learning model being trained on a historical data set of the operational parameters of the alkylation unit, the feedstock, the feedstock properties, products of the alkylation unit, and properties of the products of the alkylation unit; predicting, by the machine learning model one or more feedstock properties based on the upstream operational parameter of a process supplying the feedstock to the alkylation unit; supplying an acid to the alkylation unit; inputting an acid property of the acid to the machine learning model; inputting a current measured operational property of the alkylation unit to the machine learning model; predicting by the machine learning model a highest octane number of an alkylate that may be produced by the alkylation unit based on the upstream operational parameter, the one or more acid properties, and the current measured operational property of the alkylation unit; and generating, by the machine learning model, target operational parameters for operation of the alkylation unit to produce a target of octane-barrels of alkylate.

127. The method of claim 126, further comprising: obtaining a feedstock sample from the feedstock; analyzing the feedstock sample to determine feedstock properties; inputting the feedstock properties into the machine learning model; andadjusting, by the machine learning model, the target operational parameters for operation of the alkylation unit to produce the target of octane-barrels of alkylate based on the feedstock properties.

128. The method of claims 126 or 127, wherein the feedstock includes olefins and isobutane.

129. The method of any of claims 126 to 128, wherein the feedstock properties include data indicating a contaminant and properties of the contaminant.

130. The method of claim 129, wherein contaminant properties include a concentration of contaminants within the feedstock.

131. The method of claim 129, wherein contaminant is propane.

132. The method of any of claims 126 to 131, wherein the target operational parameters include an acid strength within the alkylation unit.

133. The method of any of claims 126 to 132, wherein the machine learning model is programmed to reduce acid strength to an acid strength limit to produce the target of octane- barrels of alkylate.

134. The method of any of claims 126 to 133, wherein the machine learning model is programmed to reduce acid strength constrained by preventing acid runaway.

135. The method of any of claims 126 to 134, wherein the feedstock properties include an isobutane to olefin ratio.

136. The method of any of claims 126 to 135, wherein the machine learning model is programmed to reduce an isobutane to olefin ratio while achieving the target of octane- barrels of alkylate.

137. The method of any of claims 126 to 136, further comprising operating the alkylation unit to produce alkylate.

138. The method of claim 137, further comprising: obtaining an alkylate sample from the alkylate; analyzing the alkylate sample to determine alkylate properties; inputting the alkylate properties into the machine learning model; and adjusting, by the machine learning model, the target operational parameters for operation of the alkylation unit to produce the target of octane-barrels of alkylate based on the alkylate properties.

139. The method of any of claims 126 to 138, wherein generating target operational parameters is based on current costs of a target product and a feedstock, wherein the machine learning model is programmed to reduce costs of operating the alkylation unit constrained by producing the target of octane-barrels of alkylate.

140. The method of any of claims 126 to 139, wherein the machine learning model is programmed to reduce energy utilized by the alkylation unit while producing the target of octane-barrels of alkylate.

141. The method of any of claims 126 to 140, wherein the machine learning model is programmed to minimize butane in the feedstock wherein generating target operational parameters includes generating operational parameters for reducing butane in isobutane received from a distillation column or C4 isomerization unit.

142. The method of any of claims 126 to 141, wherein the machine learning model is programmed to minimize isobutane in a butane product stream from the alkylation unit while producing the target of octane-barrels of alkylate .

143. The method of any of claims 126 to 142, wherein the machine learning model is programmed to meet isobutane demand associated with the alkylation unit while producing the target of octane-barrels of alkylate .

144. The method of any of claims 126 to 143, wherein the machine learning model is programmed to enhance isobutane production from a C4 isomerization unit as a feedstock for the alkylation unit while producing the target of octane-barrels of alkylate.

145. The method of any of claims 126 to 144, wherein the machine learning model is programmed to enable operation the alkylation unit at a lower acid strength that reduces acid consumption constrained to inhibit polymerization and by producing the target of octane-barrels of alkylate.

146. The method of claim 145, further comprising predicting, by the machine learning model, an acid strength within the alkylation unit.

147. The method of claim 146, wherein generating parameters, the machine learning model generates parameters to maintain an acid strength at or above a selected threshold.

148. The method of any of claims 126 to 147, wherein the machine learning model is programmed to increase olefin feed rates into the alkylation unit constrained by producing the target of octane-barrels of alkylate.

149. The method of any of claims 126 to 148, wherein the machine learning model is programmed to reduce fresh acid introduction while maintaining acid strength sufficient to produce the target of octane-barrels of alkylate.

150. The method of any of claims 126 to 149, further comprising: receiving gasoline blending pool data at the machine learning model; and generating the target property of the product of the alkylation unit based on the gasoline blending pool data.

151. The method of claim 150, wherein the gasoline blending pool data includes a customer specification for a blended formulation.

152. The method of any of claims 150 to 151, wherein the target property is a target octane-barrels of alkylate.

153. The method of any of claims 150 to 152, wherein the target property is a target octane number of alkylate.

154. The method of any of claims 150 to 153, wherein the target property is measured or sampled proximate an exit of a reactor of the alkylation unit.

155. The method of any of claims 150 to 153, wherein the target property is measured or sampled proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the alkylation unit.

156. The method of any of claims 150 to 155, wherein adjusting target operational parameters for operation of the alkylation unit includes adjusting an operating temperature of a reactor of the alkylation unit.

157. The method of claim 156, further comprising predicting, by the machine learning model, an acid strength of the reactor of the alkylation unit, wherein generating an adjustment to an operating temperature of a reactor of the alkylation unit is further based on the predicted acid strength of the reactor of the alkylation unit.

158. The method of any of claims 156 to 157, further comprising publishing a notification by the machine learning model that the target property of the product is not achievable based on constraints of the reactor of the alkylation unit.

159. The method of any of claims 156 to 158, further comprising; generating, by the machine learning model, a possible property of the product closest to the target property of the product; and publishing a notification of a possible property of the product closest to the target property of the product.

160. The method of any of claims 156 to 159, further comprising generating, by the machine learning model, a determination to not implement the adjustment to a parameter of the alkylation unit.

161. A memory including instructions and a machine learning model that causes a processor to perform the instructions including the method of any of claims 126 to 160.

162. 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 126 to 160.

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

164. The system of claim 163, wherein the alkylation controller is configured to: receive gasoline blending pool data at the machine learning model; and generate a target property of the first alkylate and a target property of the second alkylate of the alkylation system based on the gasoline blending pool data.

165. The system of claim 164, wherein the gasoline blending pool data includes a customer specification for a blended formulation.

166. The system of any of claims 164 to 165, wherein the target property of the first alkylate and a target property of the second alkylate includes a target octane-barrels of alkylate.

167. The system of any of claims 164 to 166, wherein the target property of the first alkylate and a target property of the second alkylate includes a target octane number of alkylate.

168. The system of any of claims 164 to 167, wherein the alkylation controller is configured to measure the target property of the first alkylate proximate an exit of a reactor of the first alkylation system.

169. The system of any of claims 164 to 167, wherein the alkylation controller is configured to measure the target property of the first alkylate proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the first alkylation unit.

170. The system of any of claims 164 to 169, wherein the alkylation controller is configured to adjust a parameter of the first alkylation unit includes adjusting an operating temperature of a reactor of the first alkylation unit.

171. The system of claim 170, wherein the alkylation controller is configured to predict a predicted acid strength of the reactor of the first alkylation unit, wherein adjusting the operating temperature of the reactor of the first alkylation unit is further based on the predicted acid strength of the reactor of the first alkylation unit.

172. The system of any of claims 170 to 171, wherein the alkylation controller is configured to: generate, by the machine learning model, a possible property of the first alkylate closest to the target property of the first alkylate; and publish a notification of a possible property of the product closest to the target property of the first alkylate.

173. The system of any of claims 170 to 172, wherein the alkylation controller is configured to: generate, by the machine learning model, a determination to not implement the adjustment to a parameter of the first alkylation unit.

174. The system of claim 163, wherein the alkylation controller is configured to: receive gasoline blending pool data at the machine learning model; and generate a target property of the first alkylate and a target property of the second alkylate of the alkylation unit based on the gasoline blending pool data.

175. The system of claim 174, wherein the gasoline blending pool data includes a customer specification for a blended formulation.

176. The system of any of claims 174 to 175, wherein the target property of the first alkylate and a target property of the second alkylate includes a target octane-barrels of alkylate.

177. The system of any of claims 174 to 176, wherein the target property of the first alkylate and a target property of the second alkylate includes a target octane number of alkylate.

178. The system of any of claims 174 to 177, wherein the alkylation controller is configured to measure the target property of the first alkylate proximate an exit of a reactor of the first alkylation unit.

179. The system of any of claims 174 to 177, wherein the alkylation controller is configured to measure the target property of the first alkylate proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the first alkylation unit.

180. The system of any of claims 174 to 179, wherein the alkylation controller is configured to generate the adjustment to a parameter of the first alkylation unit includes generating an adjustment to an operating temperature of a reactor of the first alkylation unit.

181. The system of claim 180, wherein the alkylation controller is configured to predict a predicted acid strength of the reactor of the first alkylation unit, wherein adjusting an operating temperature of a reactor of the first alkylation unit is further based on the predicted acid strength of the reactor of the first alkylation unit.

182. The system of any of claims 180 to 181, wherein the alkylation controller is configured to publish a notification that the target property of the product is not achievable based on constraints of the reactor of the first alkylation unit.

183. The system of any of claims 180 to 182, wherein the alkylation controller is configured to: generate a possible property of the first alkylate closest to the target property of the first alkylate; and publish a notification of a possible property of the product closest to the target property of the first alkylate.

184. The system of any of claims 180 to 183, wherein the alkylation controller is configured to generate a determination to not implement the adjustment to a parameter of the first alkylation unit.

185. The system of any of claims 174 to 184, wherein the alkylation controller is configured to measure the target property of the second alkylate proximate an exit of a reactor of the second alkylation unit.

186. The system of any of claims 174 to 185, wherein the alkylation controller is configured to measure the target property of the second alkylate proximate an exit of a separator, a distillation unit, a stripper, or a stabilizer of the second alkylation unit.

187. The system of any of claims 174 to 186, wherein the alkylation controller is configured to generate the adjustment to a parameter of the second alkylation unit includes generating an adjustment to an operating temperature of a reactor of the second alkylation unit.

188. The system of claim 187, wherein the alkylation controller is configured to predict a predicted acid strength of the reactor of the second alkylation unit, wherein generating the adjustment to an operating temperature of a reactor of the alkylation unit is further based on the predicted acid strength of the reactor of the second alkylation unit.

189. The system of any of claims 187 to 188, wherein the alkylation controller is configured to implement the generated adjustment to adjust the parameter of the second alkylation unit.

190. The system of any of claims 187 to 189, wherein the alkylation controller is configured to publish a notification that the target property of the product is not achievable based on constraints of the reactor of the second alkylation unit.

191. The system of any of claims 187 to 190, wherein the alkylation controller is configured to: generate a possible property of the second alkylate closest to the target property of the second alkylate; and publish a notification of a possible property of the product closest to the target property of the second alkylate.

192. The system of any of claims 187 to 191, wherein the alkylation controller is configured to generate a determination to not implement the adjustment to a parameter of the second alkylation unit.

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

Images