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

Abstract

Embodiments of systems and methods for enhancing control of refining and product blending pool operations are disclosed. A method includes receiving sensor data, by a machine learning model, including a feedstock composition in an isomerization process and predicting a quantity of heat released by the isomerization of the feedstock in a lead reactor. The method further includes predicting an adjustment to one or more of a heat input or feedstock feed rate to the lead reactor to counter the predicted quantity of heat and implement the adjustment to one or more of a heat input or feedstock feed rate to the lead reactor.

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 light naphtha isomerization using machine learning models.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, forexample, 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 contents 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] In some embodiments, a method includes receiving feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of a naphtha feedstock entering or before entering an isomerization process and predicting a quantity of heat released by the isomerization of the naphtha feedstock in a lead reactor of the isomerization process based on the sensor data. The method further includes predicting an adjustment to one or more of a feedstock feed rate input, a feedstock temperature, a feedstock pressure, or a heat input to the lead reactor to reduce a fluctuation of temperature of the lead reactor and publishing the predicted adjustment.

[0006] In other embodiments, a method includes accessing, by a machine learning model, a historical data gathered during operation of an isomerization process and generating acontrol algorithm for a process controller that controls at least a portion of an isomerization process based on a historical data. The method further includes generating, by a machine learning model, a simulation of the isomerization process based on the control algorithm, receiving a feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of a naphtha feedstock entering or before entering an isomerization process, and generating an anticipated component distribution of a simulated isomerate from the simulation based on the feedstock sensor data.

[0007] In yet other embodiments, a method includes receiving a pre-processed feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of a naphtha feedstock entering or before entering one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a naphtha feedstock dryer, or a charge drum. The method further includes receiving a post-processed feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the naphtha feedstock or isomerate exiting or after exiting the one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the naphtha feedstock dryer, or the charge drum. The method also includes comparing the pre-processed feedstock sensor data with the post-processed feedstock sensor data to generate a processing effectiveness score, and publishing the processing effectiveness score.

[0008] In yet other embodiments, a method includes receiving sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of a naphtha feedstock before entering an isomerization process and comparing the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process. The method further includes generating a control algorithm, simulating an implementation of the control algorithm into the isomerization process, and determining a confidence level for the simulation based on a comparison of the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process and an anticipated component distribution produced by the simulation.

[0009] This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter. Additional features and advantages of embodiments of the disclosure will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of suchembodiments. The features and advantages of such embodiments may be realized and obtained by means of the instruments and combinations particularly pointed out in the appended claims. These and other features will become more fully apparent from the following description and appended claims, or may be learned by the practice of such embodiments as set forth hereinafter.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] 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.

[0011] 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.

[0012] FIG. 2 is a simplified diagram that illustrates an apparatus for enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0013] FIG. 3 is another simplified diagrams of a refining control system to enhance fluid production at a refinery, according to an embodiment of the disclosure.

[0014] 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.

[0015] FIG. 5 is a schematic diagram of processes within a refinery.

[0016] FIG. 5A is a schematic diagram of the different products of the refinery and other sources that may be added to the gasoline blending pool.

[0017] FIG. 6 is a schematic diagram of an enhanced hydrotreater control system and a distillation control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0018] FIG. 7 is a schematic diagram of a machine learning model that may be used with the various processes within a refinery.

[0019] FIG. 8 is a schematic diagram of an enhanced isomerization control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure.

[0020] FIG. 9 is a schematic diagram of a hydrotreater for preprocessing feedstock for an isomerization process.

[0021] FIG. 10 is a schematic diagram of an isomerization process.

[0022] FIG. 11 is a schematic diagram of multiple isomerization processes that may be connected to the machine learning model of FIG. 7.

[0023] FIG. 12 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.

[0024] FIG. 13 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.

[0025] FIG. 14A and FIG. 14B are simplified diagrams of control systems to enhance to enhance fluid production at refinery, according to an embodiment of the disclosure.

[0026] FIG. 15 is a flow diagram of a method, according to an embodiment of the disclosure.

[0027] FIG. 16 is a flow diagram of another method, according to an embodiment of the disclosure.

[0028] FIG. 17 is a flow diagram of yet another method, according to an embodiment of the disclosure.

[0029] FIG. 18 is a flow diagram of a method, according to an embodiment of the disclosure.

[0030] FIG. 19 is a flow diagram of another method, according to an embodiment of the disclosure.

[0031] FIG. 20 is a flow diagram of yet another method, according to an embodiment of the disclosure.

[0032] FIG. 21 is a flow diagram of a method, according to an embodiment of the disclosure.DETAILED DESCRIPTION

[0033] This disclosure generally relates to an improved isomerization conversion of naphtha into isomerate through use of a machine learning model. In some embodiments, the machine learning model receives data from sensors disposed throughout one or more isomerization processes and is provided access to the historical data from those sensors and related lab data. The machine learning model may make control and input recommendations to a user for implementation to improve or anticipate changes in the isomerization processes and related equipment. Alternatively, the machine learning model may be given limited or full authority to dynamically adjust the controls and inputs to the isomerization process.

[0034] In some embodiments, the machine learning model may receive data from sensors disposed throughout one or more hydrotreater and methane steam reformer processes that prepare feedstocks of light naphtha and hydrogen gas to be fed into the one or more isomerization processes. The machine learning model may also be provided access to the historical data from those sensors and related lab data. The machine learning model may make control and input recommendations to a user for implementation to improve or anticipate changes in the hydrotreating process. Alternatively, the machine learning model may be given limited or full authority to dynamically adjust the controls and inputs to the hydrotreating process.

[0035] In some embodiments, the machine learning model may also be given access to sensors in a gasoline blending pool and the historical data from those sensors and related lab data. The machine learning model may be given access to customer specifications for blended gasoline formulations, customer order information, business information, historical demand data for isomerate as a blending pool component, process and costing information, forecasts data, and weather information that may affect the isomerization and hydrotreating processes.

[0036] 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.

[0037] 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 include a hydrocarbon and final product may include a transportation fuel. “Hydrocarbons” or“hydrocarbon fluids” as used herein, may refer to petroleum fluids, renewable fluids, and other hydrocarbon based fluids. “Petroleum fluids” as used herein, may refer to fluid products containing crude oil, petroleum products, natural gas, renewable liquids and / or gasses, and / or distillates or refinery intermediates. For example, crude oil contains a combination of hydrocarbons having different boiling points that exists as a viscous liquid in underground geological formations and at the surface. Petroleum products, for example, may be produced by processing crude oil and other liquids at petroleum refineries, by extracting liquid hydrocarbons at natural gas processing plants, and by producing finished petroleum products at industrial facilities. For example, a petroleum product may include a transportation fuel, among other products. Refinery intermediates, for example, may refer to any refinery hydrocarbon that is not crude oil or a finished petroleum product (such as gasoline), including all refinery output from distillation (for example, distillates or distillation fractions) or from other conversion units. In some non-limiting embodiments of systems and methods, petroleum fluids may include heavy blend crude oil used at a pipeline origination station, natural gas, and / or other types of crude oil, as will be understood by one skilled in the art. Heavy blend crude oil is typically characterized as having an American Petroleum Institute (API) gravity of about 30 degrees or below. In other embodiments, the petroleum fluids may include lighter blend crude oils, for example, having an API gravity of greater than 30 degrees. “Renewable fluids” as used herein, 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.

[0038] As used herein “profit” is the potential financial gain from a potential sale of products from a refinery operation less the costs of feedstocks and operational costs of the refinery operation. The potential value of a sale may be based on current market prices for similar products or current prices paid by contracted customers. Costs of feedstocks may include market prices for similar feedstocks as well as the operational costs of upstream processes preparing the feedstocks for use in the refinery operation. Operational costs may include equipment depreciation, employee wages and benefits, and consumables used to process the feedstocks, such as hydrogen, water, catalysts, steam, natural gas, cooling, electricity, and other utilities. For example, a machine learning model may generate adjustments to one or more operational parameters of a refinery process based on thepotential 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.

[0039] 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.

[0040] 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 or exclude 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).

[0041] 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 achieve 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.

[0042] 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.

[0043] 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, isomerization 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, an isomerization unit at a first plant may exhibit different characteristics than that of an isomerization unit at a second plant. Thus, a model trained for one may not work for the other and training a model for either an isomerization unit may include utilization of historical data corresponding to that isomerization unit. Various aspects of one model may be utilized to train other models for other similar equipment though.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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) achieve a target product. Further, such adjustments may increase efficiency of the refinery equipment and / or reduce energy utilized by the refinery equipment, thus reducing cost of the refinery operation. The target product may be based on a number of factors, such as demand and / or price or cost for the product, cost of the product and / or feedstock, and / or based on a target product provided by a refinery controller or platform. Such adjustments may be determined in real-time or near real-time using data from continuous and / or ongoing refinery operations.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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 achieve a target product. The operation controller may also include the equipment and device controls 199. The equipment and device controls 199 may cause equipment and / or devices to adjust to the target setpoints.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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 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.

[0061] 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 result in 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.

[0062] 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.

[0063] 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.

[0064] 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 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 140, 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).

[0065] 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.

[0066] 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.

[0067] 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. 3-16B.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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 achieving the target product’s properties).

[0074] 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.

[0075] 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. 3-16B. 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).

[0076] 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- 16B. 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.

[0077] 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. 3-16B. The equipment and device adjustment circuitry 212 may further utilize communications circuitry 206 to transmit signals to adjust equipment and / or devices utilized.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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 3-16B) 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.

[0082] FIG. 3 is 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 310 N). Additional processing units may be positioned throughout the refinery. As illustrated though, the unit materials may flow to a “Nth” processing unit 314. Sensors (such as sensor 312A, 312B, and up to 312N) and valves (such as valve 313 A, valve 313B, and up to valve 313N) may be positioned between the feed and “Nth” processing unit 314. The final processing device (in other words, the “Nth” processing unit 314) may produce one or more end materials (such as end materials A 316A, end materials 316B, and up to end materials 316N). Sensors (such as sensor 318A, 318B, and up to 318N) and valves (such as valve 320A, valve 320B, and up to valve 320N) may be positioned between the end materials and the material destination 322.

[0083] 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).

[0084] 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 difference348) 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).

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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 achieve 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 the trained machine learning model may be re-trained or refined with a different randomized portion of the data set, and the re-training repeated as necessary, until the selected error rate is met or achieved. In another embodiment, other training schema may be utilized. In another embodiment, readiness of the trained machine learning model may be determined based on how close the trained machine learning model comes to an expected outcome, based on the test data set.

[0095] 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.

[0096] 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.

[0097] Optionally, the atmospheric distillation tower 504 may include or be connected to additional separation equipment 505, such as a splitter, separator, debutanizer, or a deisopentanizer. A deisopentanizer is a distillation column that may be used to further split lighter components, such as isopentane and lighter, from the light naphtha 536. In some applications, the deisopentanizer may include a bypass that may be used to send naphtha directly to hydrotreating or a gasoline desulfurization unit. Thus, a control variable that may be managed by a machine learning model is control of the feed rate of naphtha into deisopentanizer and the feed rate of naphtha through the bypass around the deisopentanizer. The bypass may be used when the feed rate to the deisopentanizer is increased to a point enough such that the deisopentanizer reaches a fractionation limit, which could a reboil limit, a reflux limit, or other operational limit such as high differential pressure limit in the column or flood point in the column. The controller based on this machine learning model, in this scenario, may determine to feed rate to the deisopentanizer that optimizes the value of the gasoline pool through consideration of octane-barrels, RVP, and benzene content, as the composition of the deisopentanizer bottoms stream changes with increased feed rate when the column fractionation limit is reached.

[0098] Optionally, the atmospheric distillation tower 504 may include or be connected to additional separation equipment 505, such as a splitter, a separator, a debutanizer, adeisobutanizer, or a deisopentanizer. 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. In some applications, the deisopentanizer may include a bypass that may be used to send naphtha directly to hydrotreating or a gasoline desulfurization unit. Thus, a control variable that may be managed by a machine learning model is control of the feed rate of naphtha into the deisopentanizer and the feed rate of naphtha through the bypass around a deisopentanizer. The bypass may be used when the feed rate to the deisopentanizer is increased to a point enough such that the deisopentanizer reaches a fractionation limit, which may be a reboil limit, a reflux limit, or other operational limit, such as a high differential pressure limit in the column or a flood point in the column. The machine learning model may adjust the feed rate to the deisopentanizer to increase the value of the gasoline pool through consideration of octane-barrels, RVP, and benzene content.

[0099] If the deisopentanizer is positioned to treat the light naphtha as part of atmospheric distillation 504, the lighter components from the overhead stream, such as butane and isopentane, from the light naphtha may be passed through a hydrotreater or the gasoline desulfurization unit 556 for sulfur removal before further processing or being sent to the gasoline blending pool 543. The cutoff may be set between isopentane and n-pentane as they have different boiling and condensation temperatures. If the deisopentanizer is positioned to treat the light naphtha as part of atmospheric distillation 504, the lighter components, such as butane and isopentane, from the light naphtha may be passed through a hydrotreater or the gasoline desulfurization unit 556 for sulfur removal before further processing or being sent to the gasoline blending pool 543. The n-pentane and n-hexane of the light naphtha may then be sent to the hydrotreater 538 and isomerization 540. By separating out the isopentane from the feedstock to isomerization 540, the efficiency of isomerization 540 is increased. In other words, the less isopentane in the feedstock, the more isopentane may be formed in isomerization 540. The deisopentanizer may be controlled to increase removal of isopentane and lighter molecules from the light naphtha by controlling reboil in the bottoms of the deisopentanizer and controlling reflux to improve fractionation of the vaporized naphtha components in the column of the deisopentanizer. In other words, the operating parameters of the deisopentanizer include the feed rate of the light naphtha feedstock, the heat input into the deisopentanizer to reboil the light naphtha feedstock, column pressure, and by controlling overhead cooling by use of reflux to maximize or increase removal of isopentane from the bottoms stream and the maximize or increase the removal of n-pentane from the overhead stream. Further, the efficiency of thedeisopentanizer in separating and removing isopentane may also be affected by the composition of the light naphtha feedstock, the deisopentanizer column design, and limits on available heat and cooling used to support reboil and reflux.

[0100] Gas processing 508 separates sour gas 509 from the feeds thereto, which include 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 unit 591 to be processed into isobutane 593 as a finished product or further sent to an alkylation unit 594.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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 distillation tower 504 to a hydrotreater 562 to remove sulfur. The desulfurized diesel 564 may then be sold or sent to a diesel blending pool.

[0108] 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.

[0109] 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.

[0110] The butenes and pentenes 592 from the fluid catalytic cracker 576, as well as the isobutane 593 from the C4 isomerization unit 591, may be sent to an alkylation unit 594 where the feedstocks are processed into alkylate 596. The alkylate 596 may then be sold or sent to the gasoline blending pool 543. Alkylate 596 has a high octane rating and low RVP. [OHl] 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 blendingpool 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.

[0112] 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 is not necessary for its products. The gasoline 588 may be sold or sent to the gasoline blending pool 543 shown in FIG. 5A. The diesel 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.

[0113] 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.

[0114] 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 passedthrough a hydrotreater 523 and then sent to the jet fuel blending pool 559. The diesel 513 may be sent to a hydrotreater 525 to remove sulfur and then sent to the diesel blending pool 565. The fuel oil 515 may also be processed through hydrotreater 527 and then sent to a fuel oil blending pool.

[0115] 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.

[0116] 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 the products of each process. For example, products and components of the products may be passed through isomerization, reformation, and alkylation processes not shown in FIG. 5 to process the products and components to meet regulatory requirements and customer specifications.

[0117] 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.

[0118] 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.

[0119] 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 useduring 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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 blendedgasoline 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.

[0124] 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.

[0125] 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.

[0126] 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 leakdetection 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.

[0127] 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. 7 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.

[0128] A machine learning model 800, such as shown in FIG. 7, 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 blendedformulation 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 potential formulation list for gasoline may be ordered according to the gasoline specification attributes, such as octane rating.

[0129] FIG. 6 is a schematic diagram of an enhanced hydrotreater control system and a distillation control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. As illustrated in FIG. 6, a distillation / fractionation portion of the refinery may include a distillation controller 602 and / or a hydrotreater controller 608. The distillation controller 602 may obtain data related to a fractionation / distillation column 616. For example, the distillation controller 602 may obtain temperature and / or pressure within the fractionation / distillation column 616. Further, the distillation controller 602 may initiate collection of samples of various fluids associated with the fractionation / distillation column 616 via the sample collection and analysis assembly 614. For example, the sample collection and analysis assembly 614 may obtain samples of off-gas 624, LPG 628, naphtha / gasoline 630, diesel 640, naphtha, and / or slurry 620, among other fluids associated with the fractionation / distillation column 616. Sensor packages 618, 622, 626, 630, 636 may be disposed to measure the temperature, pressure, flow rate, and composition of the products from the fractionation / distillation column 616 including off gas 624, LPG 628, gasoline 634, diesel 640, and slurry 620.

[0130] Once the sample collection and analysis assembly 614 obtains the samples, the sample collection and analysis assembly 614 may analyze the samples to produce properties or spectra indicative of the properties of each collected sample. The samplecollection and analysis assembly 614 may provide the properties and / or spectra to the distillation controller 602. The distillation controller 602 may then apply the data, properties, and / or spectra to the to one or more training machine learning models associated with one or more of a local enhancement module 604 and / or predictive controls module 606. Based on the output of the trained machine learning models, which may indicate parameter and / or feed adjustment of the fractionation / distillation column 616, the distillation controller 602 may adjust the parameters and / or the feed via the local enhancement module 604 and, in some embodiments, an equipment and device control module. The equipment and device control module may comprise a PLC or DCS. In some embodiments, the equipment and device control module may comprise a DCS-PID module, controller, or circuitry.

[0131] In an embodiment, the distillation machine learning model 604 may be trained to maximize lift within the distillation column. Such a model may utilize temperature and / or feed flow rate to maximize such a parameter (in other words, to maximize lift or pressure). Further, such a model may predict parameters based on, in part, the concave objective function for profit to determine a feed and / or temperature input that drive the distillation column to include a maximum lift in a pressure limited column. The parameters for such an application of data to a trained machine learning model may include providing more energy and / or material to the column or increasing material or energy to increase pressure if all pressure control handles are exhausted. For example, the output from one of the trained machine learning models may indicate an increase in temperature and / or feed to maximize the output of a selected one or more products from the fractionation / distillation column 616. Such a maximization of the output may optimize profit for the fractionation / distillation column 616.

[0132] The fractionation / distillation column 616 may include a vacuum column. For an vacuum column, several constraints may be considered, such as product quality, hydraulic constraints, operating limits, and column differential pressure limits. Alternatively, problems associated with operation of the atmospheric vacuum column may be formulated to manipulate other variables such as pump-around return flow, pump-around return temperatures, and stripping steam that optimize the lift in the column when the column pressure is not being controlled.

[0133] In an embodiment, properties of feedstock utilized in a distillation operation may and / or other operations described herein may include boiling point, viscosity, composition, API gravity, distillation points, Coker gas oil content, carbon residue content, nitrogencontent, sulfur content, saturates content, thiophene content, single-ring aromatics content, dual-ring aromatics content, triple-ring aromatics content, or quad-ring aromatics content. In another embodiment, fluids, target products, material, and / or unit materials produced by a fractionation / distillation column 616 may include one or more of an amount of butane- free gasoline, an amount of total butane, an amount of dry gas, an amount of coke, an amount of gasoline, octane rating, an amount of light fuel oil, an amount of heavy fuel oil, an amount of hydrogen sulfide, an amount of sulfur in light fuel oil, or an aniline point of light fuel oil. In another embodiment, properties of the fluids, target products, material, and / or unit materials produced by the fractionation / distillation column 616 may include one or more of pentane content, raw crude water content, desalted crude water content, heavy atmospheric gas oil (HAGO) content, light atmospheric gas oil (LAGO) flash, or kerosene flash point. In yet another embodiment, the distillation controller 602 may control the pentane content, the raw crude water content, the desalted crude water content, the heavy atmospheric gas oil (HAGO) content, the light atmospheric gas oil (LAGO) flash, or the kerosene flash point, one or more of: crude blend, make-up water, desalter severity, HAGO wash rate, stripping, LAGO draw rate, stripping steam, or kerosene draw of the one or more of the first processing units.

[0134] In yet another embodiment, the properties of the fluids, target products, material, and / or unit materials produced by the fractionation / distillation and absorber column 616 may include one or more of ethane content, propane content, propene content, isobutane content, or n-butane content. In such embodiments, the distillation controller 602 may control one or more of the ethane content, the propane content, the propene content, the isobutane content, or the n-butane content, one or more of: absorber pressure, lean oil flow rate, lean oil temperature, high-pressure separator temperature, reactor conversion, or stripper reboiler duty.

[0135] In yet another embodiment, the properties of the fluids, target products, material, and / or unit materials produced by the fractionation / distillation column 616 may include one or more of high-pressure separator water content or stripper bottoms water content. In such embodiments, the distillation controller 602 may control a temperature of a high- pressure separator.

[0136] In another embodiment, the trained machine learning model may also optimize deisopentanizer fractionation (“DIP”), such an optimization increasing octane-barrels in an isomerization unit. Such a trained machine learning model may be utilized to optimize DIP feed limits based on various factors, such factors being applied by the trained machinelearning model. Further, such factors may include amount of steam utilized, temperature from a reboiler, a reflux rate, feed properties, and / or output properties. The machine learning model may optimize or improve the DIP by improving the separation of isopentane from n-pentane which may be used to improve the isomerization process in producing isomerate. This type of improvement will be balanced against capacities and the use of steam in improving this separation.

[0137] In another embodiment, the distillation controller 602 (and / or, in embodiments, the local enhancement module 604 and / or predictive controls module 606) may include a trained machine learning model trained and / or configured to determine a salt point temperature for the fractionation / distillation column 616 (or, in some embodiments, a crude atmospheric distillation column). In such embodiments, the distillation controller 602 may input fractionation / distillation column 616 setpoints, valve setpoints, overhead temperature, and / or overhead reflux, among other factors, to the model. The trained machine learning model may output updates to the setpoints for the fractionation / distillation column 616 and / or valves, as well as temperature and / or overhead reflux setpoints. Such a trained machine learning model may prevent salt deposition in overhead piping and / or other downstream mechanical equipment. These salt depositions may lead to a loss of containment, premature damage of equipment, and / or premature equipment or plant shutdown.

[0138] Further, FIG. 6 illustrates a hydrotreater controller 608. The hydrotreater controller 608 may obtain data related to each hydrotreater 632 and 638. It will be noted that data obtained from each hydrotreater may be analyzed separately, as each hydrotreater performs a different function (for example, increase gasoline octane or remove sulfur and / or impurities from naphtha). In yet another embodiment, the hydrotreater controller 608 may include a machine learning model specific for and trained for each specific hydrotreater, due to the changes each piece of equipment may experience over time.

[0139] The hydrotreater controller 608 may obtain data related to each hydrotreater and / or initiate capture of samples associated with each hydrotreater. The sample collection and analysis assembly 614 may then analyze the samples to produce properties or spectra indicative of properties of the fluids associated with the hydrotreater. Once the hydrotreater controller 608 obtains data, properties, and / or spectra related to a hydrotreater, the hydrotreater controller 608 may apply the data, properties, and / or spectra to a machine learning model within one or more of the local enhancement module 610 or the predictive controls module 612. The output of the hydrotreater machine learning model may indicateadjustments to parameters and / or feed associated with the hydrotreater. Using such an output, the local enhancement module 610 may adjust the parameters and / or feed associated with the hydrotreater, for example via a PID controller, DCS controller, PLC controller, or a DCS-PID controller.

[0140] In some embodiments, the local enhancement module 610 may include programming and an algorithm configured to facilitate optimization of the hydrotreaters 632, 638 to achieve the target parameters based on the inputs, the target parameters, unit constraints, and the outputs of the hydrotreaters 632, 638 from one or more machine learning models (e.g., of the predictive controls modules 612), and inputs. The algorithm may be modeled by a machine learning model and configured to facilitate optimization of the hydrotreaters 632, 638 based on a machine learning model. In some embodiments, the local enhancement module 610 includes an optimizer comprising an algorithm configured to achieve target parameters based on the optimization (e.g. maximization) of an objective function based on the outputs from the first machine learning models (e.g., of the predictive controls modules 612), the target parameters, unit constraints, and inputs.

[0141] In an embodiment, the machine learning model utilized in the hydrotreater controller 608 may be trained to maximize sulfur removal at a lowest possible temperature. In an example, as a targeted product’s sulfur level or amount becomes lower, the hydrotreater temperature setting increase becomes even higher to achieve the same amount of sulfur removal. Thus, the output of the machine learning model of the hydrotreater controller 608 may indicate adjustment of hydrotreater severity to achieve maximum aromatic saturation of hydrotreater feed against hydrotreater operation constraints. Such an output may comprise a vector or other list of values indicative of equipment and / or device parameter settings.

[0142] In an embodiment, one of the hydrotreaters may be a naphtha hydrotreater. The naphtha hydrotreater may be utilized, in conjunction with a distillate hydrotreater, to treat wild naphtha. The treated wild naphtha may be utilized by one or more different refinery equipment, such as, but not limited to, a hydrocracker, a crude unit, and / or a gasoline desulfurization unit. In such embodiments, one trained machine learning model may be trained or configured to maximize the amount of treated naphtha produced in relation to the amount of naphtha used in the refinery equipment. The trained machine learning model may adjust the kerosene or flash target in a crude column to increase or adjust distillate transported to the naphtha or distillate hydrotreater. Further, the trained machine learning model may also determine an amount of heavy coker naphtha to transport to distillatehydrotreaters to thereby produce a minimum amount of wild naphtha via the naphtha hydrotreater.

[0143] FIG. 7 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.

[0144] 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.

[0145] 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, and process interactions. The machine learning model 800 may also be used as a refinery controller.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 operatingparameters, feedstocks, the resulting products from those processes, and the effect of weather on the storage of products within the blending pools 524.

[0151] 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.

[0152] 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 the historical data 802 and sends the approved adjusted algorithm to the targeted process controller 816.

[0153] 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.

[0154] 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.

[0155] 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 the interpolation 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.

[0156] 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 throughthe 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.

[0157] 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.

[0158] 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 the communication 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.

[0159] 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 makerecommendations 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.

[0160] 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.

[0161] 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 a recommendation may be implemented and instructions sent to the targeted process controller 816.

[0162] 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 isomerization process 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 readilypredictable. 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.

[0163] FIG. 8 is a schematic diagram of an enhanced isomerization control system to enhance fluid production at a portion of a refinery, according to an embodiment of the disclosure. A section of the refinery corresponding to isomerization may include an isomerization controller 902. Similar to previously described controllers, the isomerization controller 902 may obtain data associated with the equipment of the isomerization unit. The isomerization controller 902 may also initiate capture of samples of fluids associated with the isomerization unit. The sample collection and analysis assembly 908 may then analyze the samples and produce properties and / or a spectra for each sample. The isomerization controller 902 may apply the data, properties, and / or spectra to one or more machine learning models of the local enhancement module 904 and / or predictive controls module 906 to produce an output indicative of adjustment to parameters and / or feed. The isomerization controller 902 may then utilize the output to adjust various parameters and / or feed associated with the isomerization unit via the local enhancement module 906.

[0164] For an isomerization process, the product distribution will shift in each of the reactors depending on the reactor operating temperature due to the chemical reaction equilibrium that is satisfied for the reversible reactions. The product distribution (i.e., product composition) determined by reactor operating temperature will determine isomerate attributes such as the overall octane-barrels, Reid vapor pressure, and hydrocarbon ring content. The optimal reactor temperature(s) can be determined to produce a product with maximum octane-barrels or a maximum road octane rating, which may also yield smaller quantities of isomerate. Thus, at least one machine learning model of an isomerization process may maximize a point in octane-barrels (in other words, the change in octane above a base value multiplied by the number of product barrels) versus reactor temperature, which is a concave function with octane-barrels passing through a maximum “optimal” point. The curve for each reactor is unique because of differences in reactor equipment including catalysts and would be determined once every few years. Thus, in an embodiment, the model may be trained to maximize or be utilized for maximizing that point on a curve for a reactor and may continuously update and refine a given curve based on the current data obtained from current operation of the reactor. The machine learning model may begin with and improve this basic equation to improve the isomerization processtoward producing a maximum octane rating for each barrel of isomerate produced while accounting for the specific variability of feedstock, contaminants, temperatures, pressures, environment including weather and solar radiation, and equipment wear. The machine learning model may optimize the isomerization process to maximize or improve isomerate attributes including octane-barrels, Reid vapor pressure, or to target a desired rate of benzene conversion to cyclohexane. The machine learning model may also access business data and manage isomerization to improve the isomerate attribute of a profitable composition that may be determined based on process costs, feedstock costs, and market prices. Further, the machine learning model may also consider the inventory and composition of the gasoline blending pool to control the isomerization process to produce isomerate to lower the overall cost of blended products in the gasoline blending pool. The machine learning model may be configured to limit the recommendation if a resulting Reid vapor pressure of the anticipated isomerate is greater than a predetermined threshold.

[0165] FIG. 9 is a schematic diagram of the hydrotreater 538 of FIG. 5 for preparing light naphtha to be fed into the isomerization process 540. The hydrotreater 538 in particular is used to remove sulfur and nitrogen from the light naphtha 536, as well as remove oxygen, and to saturate the olefins in the light naphtha 536. Naphtha may be obtained from multiple sources within a refinery including the coker 597, the hydrocracker 586, and the fluid catalytic cracker 576 shown in FIG. 5. Feedstocks of naphtha may also come from a crude naphtha splitter, a crude stabilizer, or a deisopentanizer.

[0166] Within the reactor 1008, hydrogen gas 1004 is reacted with the light naphtha 536 in the presence of catalysts 1009 to form ammonia, hydrogen sulfide, and water, which is separated from the desulfurized light naphtha 1037 as off gas 1014 and off gas 1016. The hydrotreater 538 may also remove metals found in the light naphtha 536.

[0167] The hydrotreater process 538 begins with the light naphtha 536 and hydrogen gas 1004 fed into a feed heater 1006. Feed rates of light naphtha 536 may be measured by a sensor package 1022. The sensor package 1022 may include sensors and a flow control valve. The sensors may include one or more of a flow rate sensor, a temperature sensor, a pressure sensor, a speed sensor, a moisture sensor, a sampling unit, or a composition sensor, such as a gas chromatograph or spectrometer. The flow control valve may be used to control feed rates of light naphtha 536 into the feed heater 1006.

[0168] Feed rates of hydrogen gas 1004 may be measured by a sensor package 1020. The sensor package 1020 may include sensors and a flow control valve. The sensors may include one or more of a flow rate sensor, a temperature sensor, a pressure sensor, a speedsensor, a moisture sensor, a sampling unit, or a composition sensor, such as a gas chromatograph or spectrometer. The flow control valve may be used to control feed rates of hydrogen gas 1004 into the feed heater 1006.

[0169] The feed heater 1006 heats the light naphtha 536 and in some configurations, the hydrogen gas 1004. Specifically, the light naphtha 536 and the hydrogen gas 1004 may be mixed before or after the feed heater 1006. The feed heater 1006 may include a sensor package 1024 disposed within the feed heater 1006 and a sensor package 1026 disposed to gather data about the output from the feed heater 1006 that may include one or more of temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors, such as spectrometers and gas chromatographs, and sampling units. A machine learning model may control the feed rates of the feedstock into the feed heater 1006 and the operating temperature and pressure of the feed heater 1006. “Feedstock” means all of the materials fed into a process, but not including catalysts. For example, the feedstocks of hydrotreater 538 include hydrogen gas 1004 and light naphtha 536. In relation to isomerization 540 of FIG. 5, the feedstocks of the reactors 1129 include hydrogen gas 1104, desulfurized light naphtha 1037, chloride 1127, and in some embodiments, nonreacted hydrogen 1135.

[0170] From the feed heater 1006, the light naphtha 536 and hydrogen gas 1004 is passed into the reactor 1008. The reactor 1008 may include one or more reactors placed in series or parallel connections. The reactor 1008 may contain one or more catalysts 1009 selected to remove different contaminants from the light naphtha 536 and hydrogen gas 1004. The reactor 1008 may include a sensor package 1028 that includes one or more of temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors, such as spectrometers and gas chromatographs, and sampling units to obtain samples of the light naphtha 536 and hydrogen gas 1004 within the reactor 1008. The reactor 1008 may also include a sensor package 1030 that includes one or more of temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors such as spectrometers and gas chromatographs, and sampling units to obtain samples of the catalyzed light naphtha 536 and hydrogen gas 1004 at the exit of the reactor 1008. The spectrometer and samples may provide data to a machine learning model to identify the effective performance of the reactor 1008 and its catalysts 1009.

[0171] The catalyzed light naphtha 536 and hydrogen gas 1004 may be cooled and then passed into the separator 1010. Some configurations may not include a separator 1010 so that the catalyzed light naphtha 536 and hydrogen gas 1004 are passed directly to thestripper 1012 or other distillation column. The separator 1010 may include a sensor package 1032 including one or more of a temperature sensor and a pressure sensor disposed with a portion of the separator 1010. The separator 1010 separates the catalyzed light naphtha 536 from the off gas 1014, which may include hydrogen sulfide, ammonia, excess hydrogen gas, and light hydrocarbons. The separator 1010 may also include a sensor package 1034 including one or more of temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors, such as spectrometers and gas chromatographs, and sampling units to obtain samples of the catalyzed light naphtha 536 as it exits the separator 1010.

[0172] From the separator 1010, the catalyzed light naphtha 536 enters the stripper 1012. The stripper 1012 heats the catalyzed light naphtha 536 to separate contaminants as off gas 1016 from the catalyzed light naphtha 536, resulting in a desulfurized light naphtha 1037. The stripper 1012 may include a sensor package 1036 that may include one or more of temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors such as spectrometers and gas chromatographs, and sampling units. The stripper 1012 may also include a sensor package 1038 that may include one or more of temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors such as spectrometers and gas chromatographs, and sampling units to obtain samples of the desulfurized light naphtha 1037.

[0173] The off gas 1014 and off gas 1016 may be sent to gas processing 508 or amine treating 516 shown in FIG. 5. While this schematic illustrates a basic flow of material through a hydrotreater for light naphtha, a wide variety of configurations exist. Alternatively, the hydrotreater may include multiple reactors, separators, and strippers that may be organized in series or in parallel. Further, a wide variety of sensors may be used to monitor and record data about the processes within the hydrotreater 538. As will be discussed in relation to FIG. 10, for isomerization 540 to operate efficiently and properly, the hydrotreater 538 should operate effectively to remove contaminants from the desulfurized light naphtha 1037.

[0174] A deisopentanizer is a distillation tower that may be used to further split lighter components, such as butane and isopentane, from the light naphtha 536 from atmospheric distillation 504. In particular, the cutoff may be set between isopentane and n-pentane as they have different boiling and condensation temperatures. If the deisopentanizer is positioned after the atmospheric distillation tower, the lighter components and the light naphtha may be hydrotreated or passed through a gasoline desulfurization unit for sulfur removal before further processing or being sent to the gasoline blending pool 543.

[0175] As shown in FIG. 9, a deisopentanizer 1040 may optionally be placed to separate isopentane after the light naphtha 536 has been passed through the hydrotreater reactor 1008. The deisopentanizer 1040 may be used to separate isopentane from the desulfurized light naphtha 1037 and sent to the gasoline blending pool 543 in order to increase the effectiveness of the isomerization process by removing isopentane before it enters the isomerization process 540. The remainder of the desulfurized light naphtha 1037 contains a higher ratio of n-pentane to isopentane and may then be sent to isomerization 540. The deisopentanizer may be controlled to increase removal of isopentane and lighter molecules from the light naphtha by controlling reboil in the bottoms of the deisopentanizer and controlling reflux to improve fractionation of the vaporized naphtha components in column of the deisopentanizer. In other words, the operating parameters of the deisopentanizer include the feed rate of the light naphtha feedstock, the heat input into the deisopentanizer to reboil the light naphtha feedstock, column pressure, and the controlled overhead cooling by use of reflux to maximize or increase removal of isopentane in the bottoms stream and the maximize or increase the removal of n-pentane from the overhead stream. Further, the efficiency of the deisopentanizer in separating and removing isopentane may also be affected by the composition of the light naphtha feedstock, the deisopentanizer column design, and limits on available heat and cooling used to support reboil and reflux. The deisopentanizer 1040 may include a sensor package 1042 that may be used to measure the operational parameters of the deisopentanizer 1040. The sensor package 1042 may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit for obtaining samples from the deisopentanizer 1040. Heat may be provided to each of the processes of the hydrotreater 538 by steam, electricity, burning of a hydrocarbon fluid, an exothermic chemical reaction, or other known means of heating.

[0176] A machine learning model may optimize and protect the hydrotreater 538 by adjusting any of the operating parameters of the processes of the hydrotreater 538 including the flow rates of light naphtha 536 and hydrogen gas 1004 into the feed heater 1006. The machine learning model may also measure the composition of the light naphtha 536 and hydrogen gas 1004 and divert the feeds to other processing to protect the hydrotreater 538 from contaminants that may deactivate or poison the catalyst 1009. The machine learning model may also adjust the temperature, pressure, and flow rate of the mixed light naphtha 536 and hydrogen gas 1004 within the feed heater 1006 before being fed into the reactor 1008. The machine learning model may control the flow rate of mixed light naphtha 536and hydrogen gas 1004 and operating temperature and pressure of the reactor 1008. The machine learning model may also control the operating temperature and pressure within the separator 1010 and the stripper 1012. Adjusting these controls and obtaining the sensor data allows the machine learning model to develop improved algorithms. The machine learning model may adjust the hydrotreater 538 to improve operations to support isomerization 540, protect the catalysts 1009, and reduce contaminants in the desulfurized light naphtha 1037.

[0177] FIG. 10 is a schematic diagram of the isomerization 540 of FIG. 5. Isomerization 540 is used to isomerize the low octane C5 / C6 of desulfurized light naphtha 1037 into higher-octane gasoline blending components while hydrogenating benzene into cyclohexane in order to meet the fuel specifications requiring reduced benzene in blended gasolines. Isomerization may also refer to C4 isomerization process 591 (shown in FIG. 5), which is used to isomerize nbutane into isobutane for use in the alkylation 594 (shown in FIG. 5), and a C7 isomerization unit for converting nheptane to isoheptane.

[0178] As shown, the desulfurized light naphtha 1037 from the hydrotreater 538 shown in FIG. 5 and FIG. 9 is fed into naphtha feedstock dryers 1121. Naphtha may be obtained from multiple sources within a refinery including the coker 597, the hydrocracker 586, and the fluid catalytic cracker 576 shown in FIG. 5, as well as a crude naphtha splitter, a crude stabilizer, or a deisopentanizer.

[0179] Each source of naphtha fed into isomerization 540 may comprise a different composition of n-pentane, n-hexane, benzene, and other hydrocarbons. The composition of the naphtha feedstock may be determined through a sensor package including an analyzer, a composition sensor, or a sampling unit. A sample from the sampling unit may be sent to a lab and the resulting lab data provided to the machine learning model 800 or to a user.

[0180] Hydrogen gas 1104 is fed into hydrogen feedstock dryers 1123. Heat may be provided to different equipment and processes of the isomerization process 540 by steam, electricity, burning of a hydrocarbon , an exothermic chemical reaction, or other known means of heating. Pressure may be controlled through pumps, the feed rates of the feedstocks, and temperature within a process.

[0181] The hydrotreater 538, naphtha feedstock dryers 1121, and the hydrogen feedstock dryers 1123 remove impurities and contaminants that may include water, sulfur, carbon dioxide, oxygenates, olefins, diolefins, butadiene, and isobutylene depending on the feedstocks. Failure to effectively remove contaminants may lead to catalyst deactivation and potential loss of process control. Consequently, a machine learning model or theisomerization controller 902 may direct the sample collection and analysis assembly 908, shown in FIG. 8, to regularly sample and analyze the desulfurized light naphtha 1037 and hydrogen gas 1104 exiting the naphtha feedstock dryers 1121 and the hydrogen feedstock dryers 1123 to determine components and changes in the components of the desulfurized light naphtha 1037 and hydrogen gas 1104 feedstocks. The collection and analysis assembly 908 may gather samples from the output of naphtha feedstock dryers 1121 and the hydrogen feedstock dryers 1123, as well as the charge drum 1125 prior to the desulfurized light naphtha 1037 and hydrogen gas 1104 feedstocks from entering the reactors 1129. The charge drum 1125 may include multiple charge drums in order to better handle changes in flow of feedstocks from upstream processes. The data gathered by collection and analysis assembly 908 may be analyzed by the isomerization controller 902 and sent to the machine learning model, the local enhancement module 904 and / or predictive controls module 906, shown in FIG. 8. The machine learning model, the local enhancement module 904 and / or predictive controls module 906 may direct the isomerization controller 902 to change the operating parameters, such as feedstock velocity and temperatures of the naphtha feedstock dryers 1121 and the hydrogen feedstock dryers 1123. Further, the machine learning model, the local enhancement module 904 and / or predictive controls module 906 may direct the isomerization controller 902 to schedule and conduct a regeneration cycle of the dryer media 1151, 1155 and catalysts 1131 within one or more of the naphtha feedstock dryers 1121, the hydrogen feedstock dryers 1123, or the isomerization reactors 1129. In other applications, the machine learning model, the local enhancement module 904 and / or predictive controls module 906 may direct the isomerization controller 902 to schedule replacement of the dryer media 1151, 1155 and catalysts 1131 within one or more of the naphtha feedstock dryers 1121, the hydrogen feedstock dryers 1123, or the isomerization reactors 1129. As each of these changes or events are recommended or scheduled by the machine learning model, the local enhancement module 904, predictive controls module 906, or the isomerization controller 902, the machine learning model, the local enhancement module 904, predictive controls module 906, or the isomerization controller 902 may publish or send notices or other communications to a user with details regarding the data sampled and analyzed by the collection and analysis assembly 908, as well as recommendations and decisions made by the machine learning model, the isomerization controller 902, the local enhancement module 904, predictive controls module 906, and the isomerization controller 902. For example, if certain contaminants are detected exiting the naphtha feedstock dryers 1121and the hydrogen feedstock dryers 1123, the machine learning model, the local enhancement module 904, the predictive controls module 906, or the isomerization controller 902 may issue a warning to a user, change feedstock velocity from and operating temperatures of the naphtha feedstock dryers 1121, the hydrogen feedstock dryers 1123, and the charge drum 1125, or trigger regeneration of the dryer media 1151, 1155. Alternatively, the machine learning model, the local enhancement module 904, the predictive controls module 906, or the isomerization controller 902 may divert the material exiting one or more of the naphtha feedstock dryers 1121, the hydrogen feedstock dryers 1123, and charge drum 1125 to a storage unit for testing and later processing. In another alternative, the machine learning model, the local enhancement module 904, predictive controls module 906, or the isomerization controller 902 may direct one or more of the naphtha feedstock dryers 1121, the hydrogen feedstock dryers 1123, and charge drum 1125 to shut down for maintenance and divert flow to other naphtha feedstock dryers, hydrogen feedstock dryers , or charge drums.

[0182] The machine learning model may analyze and recommend adjustments to the isomerization process to obtain a desired product distribution. In particular, product distribution of the isomerization process generally correlates with temperature for many of the isomers that may be formed through the isomerization process. Each component converts at a different rate at different temperatures. Further, cracking rates of hydrocarbon rings through the isomerization process may be based on other variables, in addition to temperature. A simplified equation of this complicated control issue with the isomerization process may be octane-barrels (the change in octane above a base value multiplied by the number of product barrels) vs reactor temperature is a concave function with octane-barrels passing through a maximum “optimal” point. Alternatively, the ratio of isopentane to total C5 paraffins versus reactor temperature may be used to optimize the isomerization process. Thus, the machine learning model may begin with and improve this basic equation to improve the isomerization process toward producing a maximum octane rating for each barrel of isomerate produced while accounting for the specific variability of feedstock, contaminants, temperatures, pressures, environment, equipment wear, and sensor lag. The sensor packages 1020, 1022, 1024, 1026, 1028, 1030, 1032, 1034, 1036, 1038, 1150, 1152, 1153, 1154, 1156, 1158, 1160, 1162, 1164, 1165, 1166, 1168, 1170, and 1172 may all be used to provide data about the hydrotreater process and the isomerization process to the machine learning model 800. The machine learning model may recommend adjustments to a user through an engineering interface for implementation by a user. Alternatively, themachine learning model may make adjustments to the hydrotreating process and the isomerization process to improve component distribution in the isomerate by adjusting temperatures, pressures, feed rates of feedstocks into each subprocess of the hydrotreater process and the isomerization process to improve the resulting isomerate component distribution as desired by a user working with the machine learning model.

[0183] Testing may be conducted on the output of the naphtha feedstock dryers 1121 by sampling and lab analysis, by an analyzer, spectrometer, or by another sensor configuration used to determine contaminants or composition of the feedstocks. Sulfur contamination level in the output of the naphtha feedstock dryers 1121 may be used to adjust control settings or make determinations that the dryer media 1151, 1155 or the catalysts 1009 of the hydrotreater 538 should be replaced or regenerated. In configurations of isomerization 540 that include a separator 1133 and a recycling process for the nonreacted hydrogen 1135, additional hydrogen gas 1104 may be added to the nonreacted hydrogen 1135 before entering the reactors 1129.

[0184] As shown, the hydrogen feedstock dryers 1123 may include a sensor package 1150 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the hydrogen gas 1104 prior to entering the hydrogen feedstock dryers 1123. The sensor package 1150 may also include a valve to control the flow rate of hydrogen gas 1104 into the hydrogen feedstock dryers 1123. The hydrogen feedstock dryers 1123 may also include a sensor package 1152 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit within the hydrogen feedstock dryers 1123 . Lastly, the hydrogen feedstock dryers 1123 may include a sensor package 1153 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the hydrogen gas 1104 exiting the hydrogen feedstock dryers 1123.

[0185] The naphtha feedstock dryers 1121 may include a sensor package 1154 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the desulfurized light naphtha 1037 prior to entering the naphtha feedstock dryers 1121. The sensor package 1154 may also include a valve to control the flow rate of desulfurized light naphtha 1037 into the naphtha feedstock dryers 1121. The spectrometer may measure the components and contaminants of the desulfurized light naphtha 1037. For example, aspectrometer or gas chromatograph of the sensor package 1154 may be used to determine the weight percent of benzene in the desulfurized light naphtha 1037 to permit better control over the temperatures with the reactors 1129.

[0186] The naphtha feedstock dryers 1121 may also include a sensor package 1152 that may include one or more of a temperature sensor and a pressure sensor for measuring the temperatures and / or pressure within the naphtha feedstock dryers 1121. Lastly, the naphtha feedstock dryers 1121 may include a sensor package 1158 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the desulfurized light naphtha 1037 exiting the naphtha feedstock dryers 1121.

[0187] Once the desulfurized light naphtha 1037 is processed through the naphtha feedstock dryers 1121, the desulfurized light naphtha 1037 is sent to the charge drum 1125 . The charge drum 1125 may include a sensor package 1160 that includes one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the desulfurized light naphtha 1037 in the charge drum 1125. A sample obtained via the sensor package or measured via the spectrometer may permit the hydrocarbon species of the desulfurized light naphtha 1037 to be determined and allow the operating temperatures of the reactors 1129 to be adjusted accordingly. The charge drum 1125 may include a charge heater (not shown) that may also heat the desulfurized light naphtha 1037 to a desired temperature for introduction into the reactors 1129.

[0188] As the desulfurized light naphtha 1037 moves from the charge drum 1125, the desulfurized light naphtha 1037 may be dosed with hydrogen gas 1104 from the hydrogen feedstock dryers 1123 and with chloride 1127 as the desulfurized light naphtha 1037 is fed into the reactors 1129. As used herein, reactors 1129 refers to one or more isomerization reactors. In some embodiments, the chloride 1127 may be provided by perchloroethylene. Adding chloride 1127 to the reactors 1129 maintains catalyst activity of the catalysts 113 lin reactors 1129 in the isomerization process.

[0189] The reactors 1129 may include a sensor package 1162 that includes one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the desulfurized light naphtha 1037 entering the reactors 1129. The reactors 1129 may include one or more reactors and, in embodiments with more than one, the reactors may be connected in series and outlet temperatures may be controlled independently from other reactors. For example,a lead reactor 1130 may initially receive feedstock and begin isomerization of the feedstock. The feedstock may then be passed to a lag reactor 1132 where the feedstock completes the isomerization process, or optionally may be passed to a third reactor or additional reactors 1134 to complete the isomerization process or to provide for redundancy. In some configurations, a plurality of reactors permit one of the plurality to be taken offline to allow for the catalyst to be replaced and the reactor to be cleaned before being brought back online. In some applications, the lead reactor 1130, the lag reactor 1132, and the tail reactor 1134, may be rearranged in the process flow. For example, the lead reactor 1130 may become the lag reactor 1132 and the lag reactor 1132 may become the lead reactor 1130. In some applications, the lead reactor will have the oldest catalyst and the freshest catalyst may be found in the lag reactor. This configuration allows the oldest catalyst to be used in a more severe environment with the lag reactor operating at a lower temperature with thermodynamic equilibrium favoring isomerization.

[0190] The reactors 1129 may also include a benzene saturation unit that is used to saturate any olefins or diolefins in the desulfurized light naphtha 1037. The benzene saturation unit may permit improved temperature control throughout the following reactors by minimizing the exothermic change from benzene to cyclohexane in the following reactors.

[0191] The reactors 1129 may also include a sensor package 1164 disposed within one or more of the reactors 1129. The sensor package 1164 may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the desulfurized light naphtha 1037 within one or more of the reactors 1129. For example, the sensor package 1164 may measure temperatures and pressures within the reactors 1129.

[0192] Within the reactors 1129, the desulfurized light naphtha 1037 is isomerized into higher octane isomers in the presence of a catalyst 1131 and hydrogen gas 1104. The isomerization process is exothermic. Variation in the composition of the feedstock may greatly influence the isomerization process within the reactors 1129. For example, the composition of the desulfurized light naphtha 1037 including benzene content may be closely monitored and controlled Unexpected increases in benzene content or other changes in feedstock composition may lead to exothermic runaway.

[0193] A machine learning model may improve control of this process by receiving sensor data concerning the benzene content in the isomerization process, predict a quantity of heat released by the isomerization of the benzene in a lead reactor, predict an adjustment to the heat input to the lead reactor to counter the predicted quantity of heat, and implement theadjustment to the heat input of the lead reactor. The machine learning model may also predict a rate of adjustment to coincide with the isomerization of the measured benzene in the lead reactor to reduce temperature fluctuations with the isomerization process. The machine learning model may also adjust one or more of the operating pressure and operating temperature of one or more of the feed heater 1006, reactor 1008, separator 1010, stripper 1012, naphtha feedstock dryers 1121, hydrogen feedstock dryers 1123, and the charge drum 1125 to adjust the removal of different containments in the feedstock of the lead reactor 1130, as well as the feed rates of feedstock through those processes. The machine learning model may adjust a feed rate of chloride into the lead reactor 1130 based on the composition of the feedstocks entering the lead reactor 1130 or the composition of the materials exiting the reactors 1129. The machine learning model may also adjust the operational temperature of or flow rates of feedstock through the reactors 1129 based on weather and solar radiation received by the one or more of the reactors 1129. The machine learning model may also adjust the operational temperature of or flow rates of feedstock through one or more of the feed heater 1006, reactor 1008, separator 1010, stripper 1012, naphtha feedstock dryers 1121, hydrogen feedstock dryers 1123, and the charge drum 1125 based on weather and solar radiation received by the one or more of the feed heater 1006, reactor 1008, separator 1010, stripper 1012, naphtha feedstock dryers 1121, hydrogen feedstock dryers 1123, and the charge drum 1125.

[0194] Another isomerization feedstock that may be sampled and analyzed for control is the concentration of hydrogen gas. A molar ratio of hydrogen gas to hydrocarbon exiting the reactors 1129 may be maintained above minimums to ensure desired reactions take place and, in some embodiments, all feedstock remains in vapor phase in the reactors 1129. Further, inadequate hydrogen gas in the feedstock for the reactors 1129 may lead to hot spots and maldistribution within the reactors 1129 that may lead to undesirable temperature excursions.

[0195] Another control point for the reactors 1 129 is feedstock velocity typically described by Liquid Hourly Space Velocity (“LHSV”). The LHSV may be determined by the volume per hour of feedstock divided by the total volume of catalyst 1131 within reactors 1129. Feed rates that are too low may lead to unpredictable temperature spikes that may cascade into undesirable temperature excursions. Feed rates that are too high may not provide sufficient time for thermodynamic equilibrium of the isomerization reaction to be achieved.

[0196] The reactors 1129 may also include a sensor package 1165 disposed to measure the attributes of the isomerized light naphtha exiting the reactors 1129. The sensor package1165 may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the isomerate 542 as it exits the reactors 1129. For example, the outlet temperature of the isomerized light naphtha may be used to estimate the effectiveness of the isomerization process. Alternatively, the ratio of isomers in the desulfurized light naphtha 1037 entering a reactor to the isomers in the product exiting the reactor may also indicate the deactivation state of the catalysts 1131.

[0197] The reactors 1129 may be managed by tracking reactor temperature and to determine deactivation of the catalyst 1131. The reactors 1129 include the exothermic reactions of the isomerization process when controlling the temperature of the reactors 1129. Thus, the reactors 1129 may have a changing temperature profile from an inlet to an outlet of the reactors 1129. The operating temperature of the reactors in conjunction with feedstock data and product data may be used to indicate the relative activity of the catalyst, reaction rate, catalyst stability, and catalyst life of the catalytic reactor. Therefore, the sensor package 1164 may gather operational data and a machine learning model may be used to generate and tune an algorithm to optimize control of the reactors 1129. Within the reactors 1129, failure to control temperatures may lead to excessive hydrocracking of the desulfurized light naphtha 1037 into smaller, lighter molecules. Alternatively, the machine learning model may use the data from the sensor packages throughout the hydrotreating process and the isomerization process to optimize the isomerization process, including management of the feedstock processes. The machine learning model may optimize the isomerization process to maximize octane-barrels or octane number of the isomerate. The machine learning model may also access business data and manage isomerization to improve the profit of isomerate based on process costs, feedstock costs, and market prices. Further, the machine learning model may also consider the inventory and composition of the gasoline blending pool to control the isomerization process to produce isomerate to lower the overall cost of blended products in the gasoline blending pool.

[0198] To optimize the isomerization process, the feed rates and compositions of feedstocks may be provided to the machine learning model, as well as reactor pressures and temperatures and a determination of the composition of materials exiting the reactors 1129 to estimate the condition of the catalysts 1131. The reactor temperatures may be controlled to provide desired quantities and composition of isomerate.

[0199] Once processed, the material exiting the reactors 1129 including the isomerized desulfurized light naphtha 1037 may optionally pass into a separator 1133 that separatesthe nonreacted hydrogen 1135 and recycles the nonreacted hydrogen 1135 back to the reactors 1129. The separator 1133 may include a sensor package 1168 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit disposed within the separator 1133 to assist in maintaining the separation environment within desired parameters.

[0200] The separator 1133 may also include a sensor package 1166 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, a gas chromatograph, or a sampling unit to obtain samples of the nonreacted hydrogen 1135. Hydrogen gas 1104 may be dosed into the recycling stream of nonreacted hydrogen 1135 as the nonreacted hydrogen 1135 is passed back into the reactors 1129.

[0201] Alternatively, depending on the configuration of isomerization 540, the isomerized desulfurized light naphtha is passed into a stabilizer 1137 either from the reactors 1129 or from the separator 1133. The stabilizer 1137 separates material exiting the reactors 1129 or the separator 1133 into gases 1141, such as hydrogen, methane, ethane, propane, and butane, and the isomerate 542. The stabilizer 1137 may include a sensor package 1170 that may include one or more of a temperature sensor, a pressure sensor, a velocity sensor, a flow rate sensor, a spectrometer, or a sampling unit to obtain samples of the isomerate 542 and the gas 1141 as it moves through the stabilizer 1137. Measurements of the sensor package 1170 may include composition data. The composition data may be used by the machine learning model to optimize the isomerization process.

[0202] The gases 1141 may be passed through a scrubber 1139 and sent to other processes in the refinery. The scrubber 1139 neutralizes hydrochloric acid formed from the chloride 1127 from the gases 1141. The scrubber 1139 may include a sensor package 1172 disposed to gather data about the operation of the scrubber 1139. The sensor package 1172 may include one or more temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors, and sampling units permitting samples to be taken of the gas 1141. The isomerate 542 may be sent to a gasoline blending pool to be blended into various configurations of gasoline for sale and distribution.

[0203] A machine learning model may control the temperature, pressure, and feed rate of feedstock within the hydrogen feedstock dryers 1123, the naphtha feedstock dryers 1121, the charge drum 1125, the reactors 1129, the separator 1133, and the stabilizer 1137, as well as the chloride 1127 injection rate. The machine learning model may also control the temperature, pressure, and flow rate of the recycle flow of nonreacted hydrogen gas 1135 from the separator 1133 to the inlet of the reactors 1129. The machine learning model maybase recommendations and develop control algorithms on the data from the sensor packages 1150, 1152, 1153, 1154, 1156, 1158, 1160, 1162, 1164, 1165, 1166, 1168, and 1170.

[0204] A machine learning model may be trained to model the temperature effects and hydrogen gas needs that correspond to the hydrocarbon and contaminant composition of the feedstocks entering the reactors 1129. Due to the strong exothermic nature of the conversion of benzene to cyclohexane, all benzene should be converted in the lead reactor of the reactors 1129. Consequently, in the event benzene is detected at the exit of the reactors 1129, the benzene may indicate that at least the platinum function of the catalysts 1131 have been deactivated or poisoned. Alternatively, benzene detected at the exit of the reactors 1129 may indicate flow rates above reactor design.

[0205] FIG. 11 is a schematic diagram of an application of a machine learning model 800 of FIG. 7 applied to isomerization 540 shown in FIG. 5 and FIG. 10. In this embodiment, isomerization 540 includes three separate isomerization processes producing isomerate 542. A desulfurized light naphtha source 1540 may be a hydrotreater 538, feedstock dryers 1121, 1123, or other process that removes contaminants from the desulfurized light naphtha 1541. Chloride and hydrogen gas sources are not shown to simplify this schematic and are discussed in relation to Figure 11.

[0206] Isomerization 540 includes a first isomerization process 1542, a second isomerization process 1544, and a third isomerization process 1546 that may each have different attributes and isomerize the desulfurized light naphtha 1541 into isomerate 542 with different compositions and different attributes. These differences may result from different operating temperatures, pressures, feed rates, equipment designs, weather, operator personalities, process constraints, tolerance variations, feedstock composition, contaminants, equipment wear, and other extrinsic influences on the isomerization process within the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546.

[0207] In some embodiments, a feedstock controller 1543 may be used to control the feed rate of desulfurized light naphtha 1541 into the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. The feedstock controller 1543 may include a surge drum to compensate for irregular flow rates of desulfurized light naphtha 1541. The feedstock controller 1543 may include one or more sensors including temperature, pressure, flowrate, composition, and level sensors. The level sensors may be used to determine the fill level of feedstock in the surge drum. Thefeedstock controller 1543 may also include pumps to control the feed rate of desulfurized light naphtha 1541 to the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546.

[0208] As shown, the feedstock controller 1543 may control the flow of desulfurized light naphtha 1541 to each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 at different desired flow rates. Alternatively, the feedstock controller 1543 may feed all isomerization processes at the same rate. The feedstock controller may include a bypass line 1548 that bypasses the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 to deliver the desulfurized light naphtha 1541 to a desulfurized light naphtha holding tank 1582. The bypass line 1548 may alternatively be directed to a gasoline desulfurization unit, a separator, splitter, deisopentanizer, or other process.

[0209] The desulfurized light naphtha holding tank 1582 and the bypass line 1548 may be used to divert the desulfurized light naphtha 1541 if it is determined from data from sensor packages that its composition is outside of specifications to be fed into one or more of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. For example, if the benzene content of desulfurized light naphtha 1541 exceeds a predetermined threshold, the desulfurized light naphtha 1541 may be diverted to the desulfurized light naphtha holding tank 1582. The desulfurized light naphtha holding tank 1582 may include a feed line 1584 back to the desulfurized light naphtha source 1540 for further processing to bring the composition of the desulfurized light naphtha 1541 into compliance with pre-isomerization specifications.

[0210] As shown, the desulfurized light naphtha 1541 is passed to the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 proximate input sensor packages 1554, 1556, and 1558. The input sensor packages 1554, 1556, and 1558 may include one or more temperature sensors, pressure sensors, flow rate sensors, and composition sensors, such as spectrometers, gas chromatographs, oxygen analyzers, sulfur analyzers, and octane analyzers, as well as sampling units. The input sensor packages 1554, 1556, and 1558 may be used to track the input temperature, pressure, flow rate, and composition of the desulfurized light naphtha 1541 feedstock entering the related first isomerization process 1542, the related second isomerization process 1544, and the related third isomerization process 1546.

[0211] The first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 are heated and pressurized to a desired operatingtemperature and pressure. The operating temperature may be measured at or near the catalysts beds of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. As the components of the desulfurized light naphtha 1541 are isomerized within the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546, the sensor packages 1560, 1562, and 1564 may be disposed within to gather data from the related first isomerization process 1542, the related second isomerization process 1544, and the related third isomerization process 1546. The sensor packages 1560, 1562, and 1564 may include one or more temperature sensors, pressure sensors, velocity sensors, flow rate sensors, and composition sensors; such as spectrometers, gas chromatographs and sampling units. The sampling units may be configured to permit physical samples to be taken from the isomerization process and analyzed in a lab. The temperature sensors may provide data on a temperature profile within the isomerization processes 1542, 1544, and 1546. Pressure sensors may be disposed to measure the pressures within the isomerization processes 1542, 1544, and 1546.

[0212] Sensor packages 1566, 1568, and 1570 may be disposed to gather data on the temperatures, pressures, flow rates, and composition of the gas 1141. Sensor packages 1572, 1574, and 1576 may be disposed to measure the temperature, pressure, flow rate, composition, and attributes of the isomerate 542 processed by the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. The sensor packages 1572, 1574, and 1576 may include one or more temperature sensors, pressure sensors, velocity sensors, flow rate sensors, composition sensors, such as spectrometers, gas chromatographs and sampling units. In particular, the sensor packages 1572, 1574, and 1576 may include a sampling unit that may be used to obtain samples for further analysis at a lab. The machine learning model 800 may use the lab data, spectrometer data, or gas chromatograph data to determine the composition of the isomerate 542 from the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546, compare the composition of the isomerate 542 to the composition of the desulfurized light naphtha 1541, and adjust the operating parameters of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 to improve the composition of the isomerate 542 produced by each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546.

[0213] In some embodiments, a machine learning model may model simulations varying the flow rate, temperature, and pressure within each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. Each simulation may be compared with the historical process data to identify trends within each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546, including the condition of the catalysts and predict when the catalysts should be regenerated or replaced, or to identify improved process parameters customized to each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. Each simulation may be compared by the machine learning model against sensor data from each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 to determine a confidence level for each simulation. As new data is accrued from operation of each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546, the machine learning model may refine a control algorithm to include new trends in the gathered data.

[0214] The machine learning model 800 may also identify equipment and components that may need repair as changes in the data gathered from the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 may be used to identify trends suggesting imminent failure of equipment or components. For example, the machine learning model may receive a pre-processed feedstock sensor data from a sensor package disposed to measure a component distribution of a naphtha feedstock entering or before entering one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a naphtha feedstock dryer, or a charge drum and receive a post-processed feedstock sensor data from a sensor package disposed to measure a component distribution of the naphtha feedstock or isomerate exiting or after exiting the one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the naphtha feedstock dryer, or the charge drum. The machine learning model may compare the pre-processed feedstock sensor data with the post-processed feedstock sensor data to generate a processing effectiveness score and may publish the processing effectiveness score to the engineering gateway 812 of FIG. 7. The machine learning model may publish a recommendation to investigate one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the naphtha feedstock dryer, or the charge drum when the processing effectiveness score changes more than a predetermined amount during a predetermined time period as the change may indicate component failure, deactivation or poisoning of a catalyst, or otherissue with the process. The processing effectiveness may also compare the pre-processed feedstock sensor data and the post-processed feedstock sensor data with predetermined targets and the score may be based on the overall deviation from those targets by the pre- processed feedstock sensor data and the post-processed feedstock sensor data. As used herein, sensor data may include lab data that is generated from a physical sample that is obtained through a sampling unit of a sensor package and sent to a lab for analysis to generate the lab data.

[0215] Product yields and composition from each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 may fluctuate with changes in flowrates and composition of the feedstock, process parameters, and changes in the composition of the desulfurized light naphtha 1541. Desired compositions of isomerate 542 may change over time and result from changes in the business environment including the price of products, the price of feedstock, changes in regulatory standards, and changes in demand for different products and formulations. The machine learning model 800 of FIG. 7 may be trained with historical data and attempt to model and predict a desired composition of an aggregated pool of isomerate 542 within the isomerate tank 1580 resulting from isomerate 542 of each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 based on the measured data from the feedstocks of desulfurized light naphtha 1541, the measured process parameters, and the measured composition resulting from each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. Alternatively, the isomerate 542 may be sent to further desulfurization in a gasoline desulfurization unit.

[0216] In some embodiments, the machine learning model creates and tunes a unique control algorithm for each of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546 based on the current operating data and historical data. As a user of the machine learning model gains confidence in the control algorithm, the user may grant the machine learning model more authority to adjust operating controls for a process. Alternatively, the machine learning model may offer process change recommendations to a user to review, approve, and implement to improve and refine control over operating parameters of the first isomerization process 1542, the second isomerization process 1544, and the third isomerization process 1546. In some embodiments, the machine learning model may control the process parameters to produce isomerate 542 having reduced hydrocarbon rings or a desired composition isomers andstraight chain hydrocarbons. Alternatively, the machine learning model may simulate the isomerization processes to maximize the overall octane-barrels produced by the combined product of the isomerization processes. In some applications, the optimization for octane- barrels may also be limited by the resulting Reid vapor pressure of the isomerate. In other words, the machine learning model may be configured to limit a recommendation if a resulting Reid vapor pressure of the anticipated isomerate is greater than a predetermined threshold.

[0217] FIG. 12 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 be 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.

[0218] FIG. 13 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 aspecification, the specification including one or more of an octane number, a research octane number, a motor octane number, a Reid vapor pressure, an amount of benzene, a density, a color, a flash point, an amount and / or type of lubricant, an amount and / or type of detergents, an amount and / or type of anti-rust agents, amount and / or type of anti-icing agents, and / or amount of sulfur or other contaminants, among other properties. To achieve the properties specified, a refinery controller and / or a gasoline pool controller 2002, for example may obtain analysis of and / or other data associated with various products within a refinery and select a percentage, e.g. 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 a 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 2002 may obtain data and / or properties from the collection and analysis assembly 2018 related to other fluids produced within the refinery. Once such data and / or properties has been collected, the gasoline pool controller may apply the data to one or more trained machine learning models stored in the local enhancement module 2004 and / or the predictive controls module 2006 to produce amounts of each varying fluid and / or properties associated with a fluid that causes production of the fluid to achieve selected properties. In an embodiment, the local enhancement module 2004 may apply the output of a plurality of trained machine learning models each stored in one or more of a plurality of predictive controls modules 2006 to a trained machine learning model of the local enhancement module 2004.

[0219] Once a prediction is determined by the gasoline pool controller 2002, the gasoline pool controller 2002 may adjust one or more devices within the refinery to cause those one or more devices to provide fluids for and / or adjust parameters to produce the selected or target gasoline. The selected components of the selected or targeted gasoline may then be blended.

[0220] In an embodiment, the trained machine learning models within the gasoline pool controller 2002 may be trained to or be utilized for predicting parameters and / or properties for one or more of the units described in relation to the 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.

[0221] 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 achieve a target octane and / or volatility limit. In such embodiments, the volatility limit may comprise a RVP or vapor liquid ratio. In another embodiment, such a blend percentage of gasoline may comprise a higher percentage of gasoline from the external gasoline source 2017 and smaller percentages of gasoline and / or other fluids from other sources to achieve the octane and / or volatility limit.

[0222] In an embodiment, each controller may utilize various data points and properties to predict parameters and fluids to achieve a target product. Those controllers may each connect to a supervisory controller or refinery controller. In embodiments, the supervisory controller or refinery controller may utilize the output of each machine learning model of each of the controllers. In yet another embodiment, each of the controllers may utilize some output from the machine learning model of the supervisory controller or refinery controller. Further, each of the controllers and / or the supervisory controller may adjust a refining operation control device, and thus adjust a process, in real-time, near real-time, and / or continuously.

[0223] FIG. 14A and FIG. 14B are simplified diagrams of control systems 2700 to enhance to enhance fluid production at refinery, according to an embodiment of the disclosure. As noted, control system 2700 may include an operation controller 2701. Further, the operation controller 2701 may connect to one or more sensors 2716A, 2716B, and up to 2716N, one or more devices 2718 A, 2718B, and up to 2718N (such as flow control devices and / or temperature control devices), one or more equipment 2720A, 2720B, and up to 2720N, one or more analyzers 2722A, 2722B, and up to 2722N, and one or more predictive controls 2714A, 2714B, and up to 2714N. The operation controller 2701 may include memory 2704 and one or more processors 2702. The memory 2704 may store instructions executable by one or more processors 2702. In an example, the memory 2704 may be a non-transitory machine-readable storage medium. As noted, the memory 2704 may store or include instructions executable by the processor 2702.

[0224] 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.

[0225] The memory 2704 may include or store sample and data collection and instructions 2706. Upon execution of such instructions, the operation controller 2701 may obtain samples associated with each equipment 2720A, 2720B, and up to 2720N. Further, the operation controller 2701 may obtain data from the one or more sensors 2716A, 2716B, and up to 2716N and / or one or more flow control devices 2718 A, 2718B, and up to 2718N. Upon collection of the samples, the operation controller 2701 may send the sample to one of the one or more analyzers 2722A, 2722B, and up to 2722N. The one of the one or more analyzers 2722A, 2722B, and up to 2722N may then analyze the sample and generate properties and / or a spectra.

[0226] 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.

[0227] 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 learningmodel 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.

[0228] The memory 2704 may include or store parameter adjustment instructions 2710. Upon generation of the output, the operation controller 2701 may adjust parameters associated with equipment at the refinery. Further the memory 2704 may include or store feed adjustment instructions 2712 to adjust feed based on the output.

[0229] In FIG. 14B, predictive controls 2714 may connect to subsets of each of the components described in FIG. 14A. 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.

[0230] 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.

[0231] FIG. 15 is a flow diagram of a method, according to an embodiment of the disclosure. The method includes a machine learning model receiving a desired isomerate attribute at 2810, receiving a selected source of a naphtha feedstock at 2820, and accessing a historical database of isomerization process data of an isomerization process at 2830. The method further includes generating a recommendation for an adjustment of one or more of a feedstock feed rate, a feedstock temperature, a feedstock pressure, an operating pressure of a lead reactor, an operating pressure of a lag reactor, an operating temperature of the lead reactor, an operating temperature of the lag reactor, an operating temperature of a tail reactor, or a heat input to the lead reactor to produce an isomerate with the desired isomerate attribute based on the selected source of a naphtha feedstock and the historical database at 2840. The machine learning model may perform the step of 2840. The method may optionally include implementing the adjustment to produce an isomerate with the desired isomerate attribute at 2850.

[0232] FIG. 16 is a flow diagram of another method, according to an embodiment of the disclosure. The method includes a machine learning model receiving feedstock sensor data indicative of a component distribution of a feedstock entering or before entering an isomerization process at 2910. The method further includes predicting a quantity of heat released by the isomerization of a naphtha feedstock in a lead reactor of the isomerization process based on the sensor data at 2920, predicting an adjustment to one or more feedstocks including a feedstock feed rate, a feedstock temperature, a feedstock pressure, or a heat input to the lead reactor to reduce a fluctuation of temperature of the lead reactor at 2930, and publishing the predicted adjustment at 2940. The machine learning model may perform the steps of 2920, 2930, and 2940. The method may optionally include implementing the adjustment to one or more of a feedstock feed rate input, a feedstock temperature, a feedstock pressure, or a heat input to the lead reactor at 2950.

[0233] FIG. 17 is a flow diagram of another method, according to an embodiment of the disclosure. The method includes a machine learning model accessing a historical data gathered during operation of an isomerization process at 3010. The method further includes generating a control algorithm for a process controller that controls at least a portion of an isomerization process based on a historical data and a user’s desired isomerate attribute at 3020. The machine learning model receives a feedstock sensor data indicative of a component distribution of a naphtha feedstock entering or before entering an isomerization process at 3030 and generates a simulation of the isomerization process based on the control algorithm and the feedstock sensor data at 3040. The method includes generating an anticipated component distribution of a simulated isomerate from the simulation at 3050.

[0234] FIG. 18 is a flow diagram of another method, according to an embodiment of the disclosure. The method includes a machine learning model receiving a pre-processed feedstock sensor data indicative of a component distribution of a naphtha feedstock entering or before entering one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a deisopentanizer, a naphtha feedstock dryer, a charge drum, or an isomerization reactor at 3110. The machine learning model receives a post-processed sensor data from a sensor package disposed to measure a component or attribute of the naphtha feedstock or an isomerate exiting or after exiting the one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, the charge drum, or the isomerization reactor at 3120. The method further includes comparing the pre-processed feedstock sensor data with the post-processed sensor data to generate aprocessing effectiveness score at 3130 and publishing the processing effectiveness score at 3140.

[0235] FIG. 19 is a flow diagram of a method for enhancing control of an isomerization operation associated with a petroleum refining operation, according to an embodiment of the disclosure. The method includes supplying naphtha to an isomerization unit associated with the petroleum refining operation, the naphtha having one or more naphtha properties at 3210 and analyzing a naphtha sample via a first analyzer to provide naphtha sample properties at 3220. The method includes predicting one or more naphtha sample properties associated with the naphtha sample based on (A) the naphtha sample properties and (B) a first output from application of the naphtha sample properties to a first trained machine learning model at 3230 and operating the isomerization unit to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of isomerate, C4 and lighter hydrocarbons, or hydrogen sulfide at 3240. The method further includes analyzing the unit material sample via a second analyzer to provide unit material sample properties at 3250 and predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model at 3260. The method includes controlling, during the isomerization operation, based on the naphtha sample properties and the one or more unit material sample properties, one or more of (a) one or more naphtha properties associated with the naphtha supplied to the isomerization unit; (b) one or more unit product materials properties associated with the unit product materials; (c) operation of the isomerization unit; or (d) operation of one or more upstream equipment or downstream equipment at 3270. The controlling, during the isomerization operation, causes the isomerization operation to produce one or more of: (i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials, (ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or (iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials at 3280.

[0236] FIG. 20 is a flow diagram of another method, according to an embodiment of the disclosure. The method includes receiving at a machine learning model a first sensor data from a plurality of sensor packages at 3310. Each sensor package is disposed tomeasure one or more process parameters of one of a plurality of isomerization processes. The method further includes accessing historical data of each of the plurality of isomerization processes at 3320 and predicting an adjustment to an operational parameter of one of a plurality of duplicated processes to improve one or more of isomerate composition, a production rate of isomerate, or a process cost based on one or more of the historical data and the first sensor data at 3330. The method includes publishing the predicted adjustment at 3340 and implementing the adjustment to an operational parameter of one of a plurality of duplicated processes at 3350.

[0237] FIG. 21 is a flow diagram of another method, according to an embodiment of the disclosure. The method including receiving a sensor data from a plurality of sensor packages at a machine learning model at 3410. A first sensor package of the plurality of sensor packages is disposed to measure one or more process parameters of a first isomerization process. A second sensor package of the plurality of sensor packages is disposed to measure an isomerate attribute of the first isomerization process. A third sensor package disposed to measure one or more process parameters of a second isomerization process. A fourth sensor package of the plurality of sensor packages is disposed to measure an isomerate attribute of the second isomerization process. The method further includes accessing, by the machine learning model, historical data of the first isomerization process and the second isomerization process and the isomerate of the first isomerization process and the isomerate of the second isomerization process at 3420 and predicting, by the machine learning model, an isomerate attribute for a blend of the isomerate of the first isomerization process with the isomerate of the second isomerization process at 3430. The method includes predicting, by the machine learning model, an adjustment to an operational parameter of the first isomerization process to improve the isomerate attribute of the blend based on the historical data and the sensor data at 3440, and optionally includes predicting, by the machine learning model, an adjustment to an operational parameter of the second isomerization process to improve the isomerate attribute of the blend based on the historical data and the sensor data at 3450. The method may optionally include implementing the adjustment to an operational parameter of the first isomerization process at 3460 and implementing the adjustment to an operational parameter of the first isomerization process at 3470.

[0238] 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 oflimitation. 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 comprising: receiving, by a machine learning model, a desired isomerate attribute; receiving, by the machine learning model, a selected source of a naphtha feedstock; accessing, by the machine learning model, a historical database of isomerization process data of an isomerization process; and generating a recommendation for an adjustment of one or more of a feedstock feed rate, a feedstock temperature, a feedstock pressure, an operating pressure of a lead reactor, an operating pressure of a lag reactor, an operating temperature of the lead reactor, an operating temperature of the lag reactor, an operating temperature of a tail reactor, or a heat input to the lead reactor to produce an isomerate with the desired isomerate attribute based on the selected source of a naphtha feedstock and the historical database.

2. The method of claim 1, further comprising publishing the recommendation to a user.

3. The method of any of claims 1 to 2, further comprising implementing the adjustment to produce an isomerate with the desired isomerate attribute.

4. The method of any of claims 1 to 3, further comprising generating a plurality of isomerization process options that may produce the isomerate with the desired isomerate attribute based on the selected source of a naphtha feedstock and the historical database, wherein each of the plurality of isomerization process options includes a set of isomerization process operating parameters.

5. The method of claim 4, further comprising: accessing a business data, and generating a product cost for each of the plurality of isomerization process options.

6. The method of claim 5, further comprising labeling each of the plurality of isomerization process options with the generated product cost.

7. The method of claim 6, further comprising ordering each of the plurality of isomerization process options by the generated product cost.

8. The method of any of claims 4 to 7, wherein the recommendation includes the adjustment of two or more of the plurality of isomerization process options.

9. The method of any of claims 1 to 8, wherein the desired isomerate attribute is a first desired isomerate attribute, the method further comprising receiving, by the machine learning model, a second desired isomerate attribute; wherein generating the recommendation is for one or more of a feedstock feed rate, a feedstock temperature, a feedstock pressure, an operating pressure of a lead isomerization reactor, an operating temperature of the lead isomerization reactor, or a heat input to the lead isomerization reactor to produce an isomerate with the first desired isomerate attribute and the second desired isomerate attribute.

10. The method of any of claims 1 to 9, wherein the desired isomerate attribute is a first desired isomerate attribute, the method further comprising: receiving, by the machine learning model, a second desired isomerate attribute; and generating a plurality of isomerization process options that may produce the isomerate with the first desired isomerate attribute and the second desired isomerate attribute based on the selected source of a naphtha feedstock and the historical database, wherein each of the plurality of isomerization process options includes a set of isomerization process operating parameters.

11. The method of any of claims 1 to 10, wherein the desired isomerate attribute includes one of product cost, feedstock cost, process cost, hydrogen usage, road octane number, octane-barrels, market value, Reid vapor pressure, and composition including benzene content, aromatic content, cyclohexane content, or iso-pentane versus n-pentane content.

12. The method of any of claims 1 to 11, further comprising: removing isopentane from the naphtha feedstock; and feeding the naphtha feedstock into the lead reactor.

13. The method of any of claims 1 to 12, wherein the selected source of the naphtha feedstock includes a deisopentanizer, the method further comprising generating a recommendation to change operating parameters, by the machine learning model, of the deisopentanizer to increase removal of isopentane from the naphtha feedstock being sent to isomerization.

14. The method of any of claims 1 to 13, further comprising implementing the recommendation for one or more of a feedstock feed rate, a feedstock temperature, a feedstock pressure, an operating pressure of a lead reactor, an operating pressure of a lag reactor, an operating temperature of the lead reactor, an operating temperature of the lag reactor, an operating temperature of a tail reactor, a heat input to the lead reactor, a heat input to the lag reactor, or a heat input to the tail reactor to produce an isomerate with the desired isomerate attribute based on the selected source of a naphtha feedstock and the historical database.

15. The method of any of claims 1 to 14, wherein the feedstock is a hydrogen gas.

16. The method of any of claims 1 to 15, wherein the machine learning model is configured to predict an octane-barrels of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature or predict an road octane number of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature.

17. The method of any of claims 2 to 16, wherein the machine learning model is configured to not publish the recommendation if a resulting Reid vapor pressure of anticipated isomerate is greater than a predetermined threshold.

18. The method of any of claims 1 to 17, further comprising receiving an isomerate sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of isomerate produced by the isomerization process.

19. The method of claim 18, further comprising comparing the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process.

20. The method of any of claims 18 to 19, determining a confidence level for a simulation based on a comparison of the measured component distribution of a naphtha feedstock to a measured component distribution of the isomerate produced by the isomerization process and an anticipated component distribution produced by the simulation.

21. The method of any of claims 1 to 20, wherein predicting an adjustment to one or more of a feedstock feed rate input or a heat input to the lead reactor to reduce a fluctuation of temperature of the lead reactor includes consideration of one or more of weather data and solar radiation data received by the machine learning model.

22. The method of any of claims 1 to 21, further comprising: generating a control algorithm for controlling at least a portion of the isomerization process; predicting a component distribution of isomerate based on the control algorithm; and using the control algorithm to control one or more operational parameters of the isomerization process.

23. The method of claim 22, further comprising: comparing a measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process; and determining a confidence level for the control algorithm based on the comparison of the measured component distribution of a naphtha feedstock to the measured component distribution of an isomerate produced by the isomerization process and the predicting a component distribution of isomerate.

24. The method of any of claims 22 to 23, further comprising: generating, by the machine learning model, a simulation of the isomerization process based on the control algorithm; and predicting an anticipated component distribution of isomerate based on the simulation.

25. The method of claim 24, determining a confidence level for the control algorithm based on a comparison of the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process and the anticipated component distribution produced by the simulation.

26. The method of any of claims 18 to 25, wherein the component distribution measures a benzene content of the naphtha feedstock.

27. The method of claim 26, further comprising predicting a first quantity of heat released by a conversion of benzene to cyclohexane of the feedstock in the lead reactor.

28. The method of any of claims 1 to 27, further comprising predicting a cracking rate of hydrocarbon rings of the feedstock through the isomerization process.

29. The method of claim 28, further comprising predicting a quantity of heat released by the predicted cracking rate of hydrocarbon rings of the feedstock in the lead reactor.

30. The method of claim 29, further comprising predicting a quantity of heat released by the predicted cracking rate of hydrocarbon rings of the feedstock in a lag reactor.

31. The method of any of claims 1 to 30, further comprising predicting a quantity of heat released by isomerization of the naphtha feedstock in a lead reactor of the isomerization process.

32. The method of claim 31, further comprising predicting a period of time between receiving a feedstock sensor data indicative of a composition of naphtha feedstock and when the quantity of heat is released by the isomerization of the naphtha feedstock in the lead reactor of the isomerization process.

33. The method of any of claims 1 to 32, further comprising predicting a quantity of heat released by isomerization of the naphtha feedstock in a lag reactor of the isomerization process.

34. The method of claim 33, further comprising predicting a period of time between receiving a feedstock sensor data indicative of a composition of naphtha feedstock and when the quantity of heat is released by the isomerization of the naphtha feedstock in the lag reactor of the isomerization process.

35. The method of claim 1, further comprising estimating by the machine learning model a quantity of heat generated by one or more of the isomerization of based on a feedstock sensor data, a isomerate sensor data, or an operational data of one or more of a lead reactor or a lag reactor.

36. The method of claim 35, further comprising comparing the estimated heat generated by one or more of isomerization of benzene, cracking of hydrocarbon rings, isomerization of n-pentane, and isomerization of n-hexane with a measured quantity of heat generated by the isomerization of the naphtha feedstock within one or more of a lead reactor or a lag reactor.

37. The method of any of claims 1 to 36, further comprising predicting adjustments over time to one or more of the heat input to or the feedstock feed rate, the feedstock temperature, or the feedstock pressure into the lead reactor to counter heat generated by isomerization of light naphtha in the lead reactor to reduce temperature fluctuations with the isomerization process.

38. The method of claim 37, further comprising publishing the predicted adjustments over time to one or more of the heat input to or the feedstock feed rate, the feedstock temperature, or the feedstock pressure into the lead reactor.

39. The method of any of claims 1 to 38, further comprising implementing the adjustments over time to one or more of the heat input to or feedstock feed rate, the feedstock temperature, or the feedstock pressure into adjustments.

40. The method of any of claims 1 to 39, further comprising: simulating, by the machine learning model, an adjustment to one or more of an operating pressure of, operating temperature of, or feed rate of the naphtha feedstock into one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, adeisopentanizer, a bypass of the deisopentanizer, a naphtha feedstock dryer, or a charge drum; and predicting, by the machine learning model, an effect on a removal of different contaminants from the naphtha feedstock based on the simulated adjustment.

41. The method of claim 40, further comprising publishing the predicted effect on the removal of different contaminants from a feedstock.

42. The method of any of claims 40 to 41, further comprising adjusting one or more of the operating pressure and operating temperature of one or more of the feed heater, hydrotreater reactor, separator, stripper, deisopentanizer, naphtha feedstock dryers, hydrogen feedstock dryers, and the charge drum.

43. The method of any of claims 1 to 42, further comprising; receiving pre-processed feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the naphtha feedstock entering or before entering one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a deisopentanizer, a naphtha feedstock dryer, or a charge drum; and receiving post-processed feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the naphtha feedstock exiting or after exiting the one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, or the charge drum.

44. The method of claim 43, further comprising comparing the pre-processed feedstock sensor data with the post-processed feedstock sensor data to determine a processing effectiveness score.

45. The method of claims 43 or 44, further comprising comparing the pre-processed feedstock sensor data and the post-processed feedstock sensor data with a predetermined process target to determine a processing effectiveness score.

46. The method of any of claims 1 to 45, further comprising;receiving isomerate sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the isomerate exiting or after exiting the one or more of an isomerization reactor, a separator, or a stabilizer.

47. The method of claim 46, further comprising comparing a feedstock sensor data with the isomerate sensor data to determine a processing effectiveness score.

48. The method of claim 46, further comprising comparing a feedstock sensor data and the isomerate sensor data with a predetermined isomerization process target to determine a processing effectiveness score.

49. The method of any of claims 1 to 48, further comprising: simulating, by the machine learning model, a feed rate or temperature adjustment to one or more feed rates of a hydrogen gas into one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, or a hydrogen feedstock dryers; predicting, by the machine learning model, an effect on a removal of different contaminants from the naphtha feedstock based on the simulated hydrogen gas feed rate or temperature adjustment; and adjusting one or more feed rates of the hydrogen gas into one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, or the hydrogen feedstock dryers.

50. The method of claim 49, wherein the simulated hydrogen gas feed rate or temperature adjustment is based on a composition of the feedstocks entering an isomerization lead reactor or the composition of isomerate exiting one or more isomerization reactors.

51. The method of claim 50, wherein the simulated hydrogen gas feed rate or temperature adjustment includes consideration of one or more of weather data or solar radiation data received by the machine learning model.

52. The method of any of claims 1 to 51, further comprising retraining the machine learning model with a sensor data from after the adjustment of one or more of an operating pressure or operating temperature of one or more of a feed heater, a hydrotreater reactor, aseparator, a stripper, a deisopentanizer, a naphtha feedstock dryers, a hydrogen feedstock dryers, and a charge drum or adjustment of one or more feed rates of the feedstock into one or more of the feed heater, hydrotreater reactor, separator, stripper, deisopentanizer, naphtha feedstock dryers, hydrogen feedstock dryers, and the charge drum.

53. The method of any of claims 1 to 52, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

54. The method of any of claims 1 to 53, wherein the feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

55. The method of claim 54, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

56. The method of any of claims 1 to 55, wherein the feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

57. The method of any of claims 1 to 56, wherein the feedstock data includes one or more wherein the feedstock process data is from a feedstock process controller.

58. The method of any of claims 1 to 57, wherein the feedstock process data is from a feedstock process.

59. The method of any of claims 1 to 58, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

60. The method of any of claims 1 to 59, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

61. The method of any of claims 1 to 60, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

62. The method of any of claims 1 to 61, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

63. The method of any of claims 1 to 62, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

64. The method of any of claims 1 to 63, further comprising displaying recommendations.

65. The method of any of claims 1 to 64, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

66. The method of any of claims 1 to 65, further comprising accessing business data.

67. The method of any of claims 1 to 66, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

68. The method of any of claims 1 to 67, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

69. The method of any of claims 1 to 68, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

70. The method of any of claims 1 to 69, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

71. The method of any of claims 1 to 70, further comprising accessing a lab data.

72. The method of any of claims 1 to 71, further comprising sending instructions to an engineering gateway.

73. The method of any of claims 1 to 72, further comprising receiving instructions from an engineering gateway.

74. The method of claims 72 or 73, wherein the engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

75. The method of any of claims 72 to 74, wherein the engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to increase a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

76. The method of any of claims 72 to 75, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerizationsubprocesses by the machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

77. The method of any of claims 72 to 76, wherein the engineering gateway is used to facilitate active learning by the machine learning model.

78. The method of any of claims 1 to 77, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

79. The method of claim 78, further comprising adjusting the algorithm based on the identified changes.

80. The method of any of claims 78 to 79, wherein adjusting the algorithm is performed by the machine learning model without user input.

81. The method of claim 80, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in the historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

82. The method of any of claims 1 to 81, further comprising: analyzing one or more of a data set or a data set to be processed; and identifying an outlier and generating a processed data set.

83. The method of claim 82, wherein the processed data set excludes the identified outlier.

84. The method of any of claims 82 to 83, wherein the processed data set includes a flag for the identified outlier.

85. The method of any of claims 82 to 84, further comprising publishing one or more of the identified outlier for user review.

86. The method of any of claims 82 to 85, further comprising receiving user instructions regarding the identified outlier to do one or more of (1) excluding the identified outlier from the processed data set and (2) requesting additional information related to the identified outlier.

87. The method of any of claims 1 to 86, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

88. The method of any of claims 1 to 87, further comprising comparing at least a portion of the historical data with one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to generate a compared data set.

89. The method of claim 88, further comprising identifying at least one process change from the compared data set.

90. The method of any of claims 88 to 89, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

91. The method of claim 90, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing theidentified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

92. The method of any of claims 88 to 90, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

93. The method of any of claims 92, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

94. The method of any of claims 88 to 93, further comprising publishing at least a portion of the compared data set.

95. The method of any of claims 1 to 94, further comprising adjusting an operating parameter without user input.

96. The method of any of claims 88 to 95, further comprising storing one or more of the data set to be processed, an interpolated data set, or the compared data set.

97. The method of claim 96, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of a training data or the historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

98. The method of any of claims 1 to 97, further comprising analyzing one or more of a feedstock sensor data, a feedstock sample data, a feedstock process data, a targeted process sensor data, a targeted process sample data, a targeted process data, a subsequentprocess sensor data, a subsequent process sample data, or a subsequent process data to predict one or more changes in one or more processes.

99. The method of any of claims 1 to 98, wherein analyzing data to predict one or more changes is performed using a prediction module.

100. The method of any of claims 1 to 99, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

101. The method of claim 100, further comprising notifying a user of the predicted one or more changes.

102. The method of claim 101, wherein the user is notified of the predicted one or more changes using an engineering gateway.

103. The method of any of claims 1 to 102, further comprising applying one or more process changes automatically without user input or based on an instruction from the user.

104. The method of any of claims 1 to 103, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

105. The method of any of claims 1 to 104, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

106. The method of any of claims 104 to 105, wherein a user approves implementation of the adjustment using an engineering gateway.

107. The method of any of claims 1 to 106, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

108. The method of claim 107, further comprising notifying a user of the one or more identified maintenance procedures.

109. The method of any of claims 1 to 108, further comprising notifying a user of a recommended maintenance window for one or more identified maintenance procedures based on one or more of historical data and sensor package data.

110. The method of any of claims 1 to 109, further comprising wherein the machine learning model includes a communication module, wherein the communication module (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

111. The method of any of claims 1 to 110, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

112. The method of any of claims 1 to 111, further comprising communicating with one or more process controllers and / or other refinery models.

113. The method of any of claims 1 to 112, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

114. The method of claim 113, further comprising retraining the machine learning model on the user feedback.

115. The method of any of claims 113 to 114, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

116. The method of any of claims 1 to 115, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

117. The method of any of claims 1 to 116, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

118. The method of any of claims 1 to 117, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

119. The method of any of claims 1 to 118, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

120. The method of any of claims 1 to 119, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

121. The method of any of claims 1 to 120, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

122. The method of any of claims 1 to 121, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

123. The method of any of claims 1 to 122, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

124. The method of any of claims 1 to 123, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

125. The method of any of claims 1 to 124, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

126. The method of any of claims 1 to 125, wherein the machine learning model includes a forecasting module.

127. The method of any of claims 1 to 126, wherein a forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

128. The method of any of claims 1 to 127, wherein a forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

129. The method of any of claims 1 to 128, wherein a forecasting module forecasts pricing for one or more blend components based on one or more of the historical data or a business data and publishes the forecasted pricing via a communication module to an engineering gateway.

130. The method of any of claims 1 to 129, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

131. The method of claim 130, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

132. The method of claim 131, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

133. The method of any of claims 130 to 132, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

134. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 1 to 133.

135. 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 133.

136. A method compri sing : receiving feedstock sensor data, by a machine learning model, indicative of a component distribution of a feedstock entering or before entering an isomerization process; predicting a quantity of heat released by the isomerization of a naphtha feedstock in a lead reactor of the isomerization process based on the sensor data; predicting an adjustment to one or more feedstocks including a feedstock feed rate, a feedstock temperature, a feedstock pressure, or a heat input to the lead reactor to reduce a fluctuation of temperature of the lead reactor; and publishing the predicted adjustment.

137. The method of claim 136, further comprising implementing the adjustment to one or more of a feedstock feed rate input, a feedstock temperature, a feedstock pressure, or a heat input to the lead reactor.

138. The method of any of claims 136 or 137, wherein the feedstock sensor data further includes one or more of a temperature data, a pressure data, a velocity data, or a feed rate data of the feedstock.

139. The method of any of claims 136 to 138, wherein the feedstock is one or more of a naphtha, a hydrogen gas, or a perchloroethylene.

140. The method of any of claims 136 to 139, wherein the machine learning model is configured to predict an octane-barrels of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature or predict an road octane number of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature.

141. The method of any of claims 136 to 140, further comprising: generating, by the machine learning model, a simulation of the isomerization process based on a control algorithm; and predicting an anticipated component distribution of isomerate based on the simulation.

142. The method of any of claims 136 to 141, further comprising receiving an isomerate sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of isomerate produced by the isomerization process.

143. The method of claim 142, further comprising comparing the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process.

144. The method of any of claims 141 to 143, determining a confidence level for a simulation based on a comparison of a measured component distribution of a naphtha feedstock to a measured component distribution of the isomerate produced by the isomerization process and an anticipated component distribution produced by the simulation.

145. The method of any of claims 136 to 144, wherein predicting an adjustment to one or more of a feedstock feed rate input or a heat input to the lead reactor to reduce the fluctuation of temperature of the lead reactor includes consideration of one or more of weather data and solar radiation data received by the machine learning model.

146. The method of any of claims 136 to 145, further comprising: generating a control algorithm for controlling at least a portion of the isomerization process; predicting a component distribution of isomerate based on the control algorithm; and using the control algorithm to control one or more operational parameters of the isomerization process.

147. The method of claim 146, further comprising:comparing a measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process; and determining a confidence level for the control algorithm based on the comparison of the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process.

148. The method of any of claims 142 to 147, determining a confidence level for a control algorithm based on a comparison of the measured component distribution of a naphtha feedstock to a measured component distribution of an isomerate produced by the isomerization process and an anticipated component distribution produced by a simulation.

149. The method of any of claims 142 to 148, wherein the component distribution measures a benzene content of the naphtha feedstock.

150. The method of claim 149, further comprising predicting a first quantity of heat released by a conversion of benzene to cyclohexane of the feedstock in the lead reactor.

151. The method of any of claims 136 to 150, further comprising predicting a cracking rate of hydrocarbon rings of the feedstock through the isomerization process.

152. The method of claim 151, further comprising predicting a quantity of heat released by the predicted cracking rate of hydrocarbon rings of the feedstock in the lead reactor.

153. The method of any of claims 136 to 152, further comprising predicting a quantity of heat released by a predicted cracking rate of hydrocarbon rings of the feedstock in a lag reactor.

154. The method of any of claims 136 to 153, further comprising predicting a quantity of heat released by isomerization of the naphtha feedstock in a lead reactor of the isomerization process.

155. The method of claim 154, further comprising predicting a period of time between receiving a feedstock sensor data indicative of a composition of naphtha feedstock andwhen the quantity of heat is released by the isomerization of the naphtha feedstock in the lead reactor of the isomerization process.

156. The method of any of claims 136 to 155, further comprising predicting a quantity of heat released by isomerization of the naphtha feedstock in a lag reactor of the isomerization process.

157. The method of claim 156, further comprising predicting a period of time between receiving a feedstock sensor data indicative of a composition of naphtha feedstock and when the quantity of heat is released by the isomerization of the naphtha feedstock in the lag reactor of the isomerization process.

158. The method of claim 136, further comprising estimating by the machine learning model a heat generated by one or more of the isomerization of benzene, a cracking of hydrocarbon rings, the isomerization of n-pentane, or the isomerization of n-hexane from the feedstock sensor data, the isomerate sensor data, and the isomerization sensor data within one or more of a lead reactor or a lag reactor.

159. The method of claim 158, further comprising comparing the estimated heat generated by one or more of the isomerization of benzene, the cracking of hydrocarbon rings, the isomerization of n-pentane, and the isomerization of n-hexane with the predicted quantity of heat generated by one or more of the isomerization of benzene, the cracking of hydrocarbon rings, the isomerization of n-pentane, or the isomerization of n-hexane within one or more of a lead reactor or a lag reactor.

160. The method of any of claims 136 to 159, further comprising predicting adjustments over time to one or more of the heat input to or the feedstock feed rate, the feedstock temperature, or the feedstock pressure into the lead reactor to counter heat generated by isomerization of light naphtha in the lead reactor to reduce temperature fluctuations with the isomerization process.

161. The method of claim 160, further comprising publishing the predicted adjustments over time to one or more of the heat input to or the feedstock feed rate, the feedstock temperature, or the feedstock pressure into the lead reactor.

162. The method of any of claims 136 to 161, further comprising implementing the adjustments over time to one or more of the heat input to or feedstock feed rate, the feedstock temperature, or the feedstock pressure into adjustments.

163. The method of any of claims 136 to 162, further comprising: simulating, by the machine learning model, an adjustment to one or more of an operating pressure of, operating temperature of, or feed rate of the naphtha feedstock into one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a deisopentanizer, a bypass of the deisopentanizer, a naphtha feedstock dryers, or a charge drum; and predicting, by the machine learning model, an effect on a removal of different contaminants from the naphtha feedstock based on the simulated adjustment.

164. The method of claim 163, further comprising publishing the predicted effect on the removal of different contaminants from a feedstock.

165. The method of any of claims 163 to 164, further comprising adjusting one or more of the operating pressure and operating temperature of one or more of the feed heater, hydrotreater reactor, separator, stripper, deisopentanizer, naphtha feedstock dryers, hydrogen feedstock dryers, and the charge drum.

166. The method of any of claims 136 to 165, further comprising; receiving pre-processed feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the naphtha feedstock entering or before entering one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a deisopentanizer, a naphtha feedstock dryer, or a charge drum; and receiving post-processed feedstock sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the naphtha feedstock exiting or after exiting the one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, or the charge drum.

167. The method of claim 166, further comprising comparing the pre-processed feedstock sensor data with the post-processed feedstock sensor data to determine a processing effectiveness score.

168. The method of claims 166 or 167, further comprising comparing the pre-processed feedstock sensor data and the post-processed feedstock sensor data with a predetermined process target to determine a processing effectiveness score.

169. The method of any of claims 136 to 168, further comprising; receiving isomerate sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of the isomerate exiting or after exiting the one or more of an isomerization reactor, a separator, or a stabilizer.

170. The method of claim 169, further comprising comparing the feedstock sensor data with the isomerate sensor data to determine a processing effectiveness score.

171. The method of claim 169, further comprising comparing the feedstock sensor data and the isomerate sensor data with a predetermined isomerization process target to determine a processing effectiveness score.

172. The method of any of claims 136 to 171, further comprising: simulating, by the machine learning model, a feed rate or temperature adjustment to one or more feed rates of a hydrogen gas into one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, or a hydrogen feedstock dryers; predicting, by the machine learning model, an effect on a removal of different contaminants from the naphtha feedstock based on the simulated hydrogen gas feed rate or temperature adjustment; and adjusting one or more feed rates of the hydrogen gas into one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, or the hydrogen feedstock dryers.

173. The method of claim 172, wherein the simulated hydrogen gas feed rate or temperature adjustment is based on a composition of the feedstocks entering anisomerization lead reactor or the composition of isomerate exiting one or more isomerization reactors.

174. The method of claim 173, wherein the simulated hydrogen gas feed rate or temperature adjustment includes consideration of one or more of weather data or solar radiation data received by the machine learning model.

175. The method of any of claims 136 to 174, further comprising retraining the machine learning model with a sensor data from after the adjustment of one or more of an operating pressure or operating temperature of one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a deisopentanizer, a naphtha feedstock dryers, a hydrogen feedstock dryers, and a charge drum or adjustment of one or more feed rates of the feedstock into one or more of the feed heater, hydrotreater reactor, separator, stripper, deisopentanizer, bypass of the deisopentanizer, naphtha feedstock dryers, hydrogen feedstock dryers, and the charge drum.

176. The method of any of claims 136 to 175, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, bypasses, or isomerization subprocesses.

177. The method of any of claims 136 to 176, wherein the feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

178. The method of claim 177, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

179. The method of any of claims 136 to 178, wherein the feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data,feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

180. The method of any of claims 136 to 179, wherein the feedstock data includes one or more wherein the feedstock process data is from a feedstock process controller.

181. The method of any of claims 136 to 180, wherein the feedstock process data is from a feedstock process.

182. The method of any of claims 136 to 181, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

183. The method of any of claims 136 to 182, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

184. The method of any of claims 136 to 183, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

185. The method of any of claims 136 to 184, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

186. The method of any of claims 136 to 185, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

187. The method of any of claims 136 to 186, further comprising displaying recommendations.

188. The method of any of claims 136 to 187, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

189. The method of any of claims 136 to 188, further comprising accessing business data.

190. The method of any of claims 136 to 189, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

191. The method of any of claims 136 to 190, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

192. The method of any of claims 136 to 191, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

193. The method of any of claims 136 to 192, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

194. The method of any of claims 136 to 193, further comprising accessing a lab data.

195. The method of any of claims 136 to 194, further comprising sending instructions to an engineering gateway.

196. The method of any of claims 136 to 195, further comprising receiving instructions from an engineering gateway.

197. The method of claims 195 or 196, wherein the engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings,process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

198. The method of any of claims 195 to 197, wherein the engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect of an adjustment on one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

199. The method of any of claims 195 to 198, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses by the machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

200. The method of any of claims 136 to 199, wherein the feedstocks include crude oil received for processing into refined hydrocarbons.

201. The method of any of claims 195 to 200, wherein the engineering gateway is used to facilitate active learning by the machine learning model.

202. The method of any of claims 136 to 201, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

203. The method of claim 202, further comprising adjusting the algorithm based on the identified changes.

204. The method of any of claims 202 to 203, wherein adjusting the algorithm is performed by the machine learning model without user input.

205. The method of claim 204, further comprising:sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

206. The method of any of claims 136 to 205, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

207. The method of claim 206, wherein the processed data set excludes the identified outlier.

208. The method of claim 207, wherein the processed data set includes a flag for the identified outlier.

209. The method of any of claims 207 to 208, further comprising publishing one or more of the identified outlier for user review.

210. The method of any of claims 207 to 209, further comprising receiving user instructions regarding the identified outlier to do one or more of (1) excluding the identified outlier from the processed data set and (2) requesting additional information related to the identified outlier.

211. The method of any of claims 136 to 210, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

212. The method of any of claims 136 to 211, further comprising comparing at least a portion of historical data with one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targetedprocess data, subsequent process sensor data, subsequent process sample data, or subsequent process data to generate a compared data set.

213. The method of claim 212, further comprising identifying at least one process change from the compared data set.

214. The method of any of claims 212 to 213, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

215. The method of claim 214, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

216. The method of any of claims 212 to 214, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

217. The method of any of claims 216, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

218. The method of any of claims 112 to 217, further comprising publishing at least a portion of a compared data set.

219. The method of any of claims 136 to 218, further comprising adjusting an operating parameter without user input.

220. The method of any of claims 212 to 219, further comprising storing one or more of the data set to be processed, an interpolated data set, or the compared data set.

221. The method of claim 220, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of a training data or the historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

222. The method of any of claims 136 to 221, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

223. The method of any of claims 136 to 222, wherein analyzing data to predict one or more changes is performed using a prediction module.

224. The method of any of claims 136 to 223, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

225. The method of claim 224, further comprising notifying a user of the predicted one or more changes.

226. The method of claim 225, wherein the user is notified of the predicted one or more changes using an engineering gateway.

227. The method of any of claims 136 to 226, further comprising applying one or more process changes automatically without user input or based on an instruction from the user.

228. The method of any of claims 136 to 227, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

229. The method of any of claims 136 to 228, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

230. The method of any of claims 136 to 229, wherein a user approves implementation of the adjustment using an engineering gateway.

231. The method of any of claims 136 to 230, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

232. The method of any of claims 136 to 231, further comprising notifying a user of one or more identified maintenance procedures.

233. The method of any of claims 136 to 232, further comprising notifying a user of a recommended maintenance window for one or more identified maintenance procedures based on one or more of historical data and sensor package data.

234. The method of any of claims 136 to 233, further comprising wherein the machine learning model includes a communication module, wherein the communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

235. The method of any of claims 136 to 234, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

236. The method of any of claims 136 to 235, further comprising communicating with one or more process controllers and / or other refinery models.

237. The method of any of claims 136 to 236, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

238. The method of claim 237, further comprising retraining the machine learning model on the user feedback.

239. The method of any of claims 237 to 238, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

240. The method of any of claims 136 to 239, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

241. The method of any of claims 136 to 240, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

242. The method of any of claims 136 to 241, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

243. The method of any of claims 136 to 242, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

244. The method of any of claims 136 to 243, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

245. The method of any of claims 136 to 244, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

246. The method of any of claims 136 to 245, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

247. The method of any of claims 136 to 246, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

248. The method of any of claims 136 to 247, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

249. The method of any of claims 136 to 248, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

250. The method of any of claims 136 to 249, wherein the machine learning model includes a forecasting module.

251. The method of any of claims 136 to 250, wherein a forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

252. The method of any of claims 136 to 251, wherein a forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

253. The method of any of claims 136 to 252, wherein a forecasting module forecasts pricing for one or more blend components based on one or more of historical data or business data and publishes the forecasted pricing via a communication module to an engineering gateway.

254. The method of any of claims 136 to 253, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

255. The method of claim 254, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

256. The method of claim 255, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

257. The method of any of claims 254 to 256, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

258. The method of any of claims 136 to 257, further comprising: removing isopentane from the naphtha feedstock; and feeding the naphtha feedstock into the lead reactor.

259. The method of any of claims 136 to 258, the method further comprising generating a recommendation to change operating parameters, by the machine learning model, of a deisopentanizer to improve separation of isopentane from the naphtha feedstock being sent to isomerization.

260. 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 136 to 259.

261. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 136 to 259.

262. A method comprising: accessing, by a machine learning model, a historical data gathered during operation of an isomerization process; generating a control algorithm for a process controller that controls at least a portion of an isomerization process based on a historical data and a user’s desired isomerate attribute; receiving a feedstock sensor data, by a machine learning model, indicative of a component distribution of a naphtha feedstock entering or before entering an isomerization process; generating, by a machine learning model, a simulation of the isomerization process based on the control algorithm and the feedstock sensor data; and generating an anticipated component distribution of a simulated isomerate from the simulation.

263. The method of claim 262, further comprising publishing the anticipated component distribution of the simulated isomerate.

264. The method of any of claims 262 to 263, further comprising using the control algorithm to control one or more operational parameters of the isomerization process.

265. The method of any of claims 262 to 264, wherein the machine learning model is configured to predict an octane-barrels of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature or predict an road octane number of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature.

266. The method of any of claims 262 to 265, further comprising receiving an isomerate sensor data, by a machine learning model, from a sensor package disposed to measure a component distribution of an isomerate produced by the isomerization process.

267. The method of claim 266, further comprising generating an isomerization effectiveness score by comparing the feedstock sensor data with the isomerate sensor data.

268. The method of any of claims 266 to 267, further comprising:comparing the feedstock sensor data to the isomerate sensor data with the anticipated component distribution produced by the simulation; and determining a confidence level for the simulation based on a comparison of the isomerate sensor data with the anticipated component distribution produced by the simulation.

269. The method of any of claims 262 to 268, further comprising retraining the machine learning model based on a difference between the simulation and feedstock sensor data, the isomerate sensor data, and the isomerization sensor data.

270. The method of any of claims 262 to 269, further comprising receiving an isomerization sensor data, by a machine learning model, from a sensor package disposed to measure the isomerization process.

271. The method of claim 270, wherein each of the feedstock sensor data, the isomerate sensor data, and the isomerization sensor data include one or more of a lab data of a sample, a pressure data, a temperature data, a flow rate data, and a composition data of one or more of the feedstock, the isomerate, and process operating parameters.

272. The method of any of claims 262 to 271, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, bypasses, or isomerization subprocesses.

273. The method of any of claims 262 to 272, wherein the feedstock sensor data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

274. The method of claim 273, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

275. The method of any of claims 262 to 274, wherein the feedstock sensor data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

276. The method of any of claims 262 to 275, wherein the feedstock sensor data includes one or more wherein the feedstock process data is from a feedstock process controller.

277. The method of any of claims 262 to 276, wherein the feedstock process data is from a feedstock process.

278. The method of any of claims 262 to 277, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

279. The method of any of claims 262 to 278, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

280. The method of any of claims 262 to 279, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

281. The method of any of claims 262 to 280, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

282. The method of any of claims 262 to 281, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

283. The method of any of claims 262 to 282, further comprising displaying recommendations.

284. The method of any of claims 262 to 283, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

285. The method of any of claims 262 to 284, further comprising accessing business data.

286. The method of any of claims 262 to 285, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

287. The method of any of claims 262 to 286, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

288. The method of any of claims 262 to 287, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

289. The method of any of claims 262 to 288, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

290. The method of any of claims 262 to 289, further comprising accessing a lab data.

291. The method of any of claims 262 to 290, further comprising sending instructions to an engineering gateway.

292. The method of any of claims 262 to 291, further comprising receiving instructions from an engineering gateway.

293. The method of claims 291 or 292, wherein the engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

294. The method of any of claims 291 to 293, wherein the engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

295. The method of any of claims 291 to 294, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses by the machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

296. The method of any of claims 262 to 295, wherein the feedstocks include crude oil received for processing into refined hydrocarbons.

297. The method of any of claims 291 to 296, wherein the engineering gateway is used to facilitate active learning by the machine learning model.

298. The method of any of claims 262 to 297, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or the user.

299. The method of claim 298, further comprising adjusting the algorithm based on the identified changes.

300. The method of any of claims 298 to 299, wherein adjusting the algorithm is performed by the machine learning model without user input.

301. The method of claim 300, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in the historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

302. The method of any of claims 262 to 301, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

303. The method of claim 302, wherein the processed data set excludes the identified outlier.

304. The method of any of claims 302 to 303, wherein the processed data set includes a flag for the identified outlier.

305. The method of any of claims 302 to 304, further comprising publishing one or more of the identified outlier for user review.

306. The method of any of claims 302 to 305, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

307. The method of any of claims 262 to 306, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

308. The method of any of claims 262 to 307, further comprising comparing at least a portion of the historical data with one or more of the feedstock sensor data, feedstocksample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to generate a compared data set.

309. The method of claim 308, further comprising identifying at least one process change from the compared data set.

310. The method of any of claims 308 to 309, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

311. The method of claim 310, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

312. The method of any of claims 308 to 311, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

313. The method of any of claims 312, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

314. The method of claim 308, further comprising publishing at least a portion of the compared data set.

315. The method of any of claims 262 to 314, further comprising storing one or more of a data set to be processed, an interpolated data set, or a compared data set.

316. The method of claim 315, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of training data or the historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

317. The method of any of claims 262 to 316, further comprising analyzing one or more of the feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

318. The method of any of claims 262 to 317, wherein analyzing data to predict one or more changes is performed using a prediction module.

319. The method of any of claims 262 to 318, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

320. The method of claim 319, further comprising notifying a user of the predicted one or more changes.

321. The method of claim 320, wherein the user is notified of the predicted one or more changes using an engineering gateway.

322. The method of any of claims 262 to 321, further comprising applying one or more process changes automatically without user input or based on an instruction from the user.

323. The method of any of claims 262 to 322, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

324. The method of any of claims 262 to 323, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

325. The method of any of claims 262 to 324, wherein a user approves implementation of an adjustment using an engineering gateway.

326. The method of any of claims 262 to 325, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

327. The method of any of claims 262 to 326, further comprising notifying the user of one or more identified maintenance procedures.

328. The method of claim 327, further comprising notifying the user of a recommended maintenance window for the one or more identified maintenance procedures based on one or more of historical data and sensor package data.

329. The method of any of claims 262 to 328, further comprising wherein the machine learning model includes a communication module, wherein the communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

330. The method of any of claims 262 to 329, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

331. The method of any of claims 262 to 330, further comprising communicating with one or more process controllers and / or other refinery models.

332. The method of any of claims 262 to 331, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

333. The method of claim 332, further comprising retraining the machine learning model on the user feedback.

334. The method of any of claims 332 to 333, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

335. The method of any of claims 262 to 334, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

336. The method of any of claims 262 to 335, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

337. The method of any of claims 262 to 336, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

338. The method of any of claims 262 to 337, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

339. The method of any of claims 262 to 338, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

340. The method of any of claims 262 to 339, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

341. The method of any of claims 262 to 340, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

342. The method of any of claims 262 to 341, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

343. The method of any of claims 262 to 342, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

344. The method of any of claims 262 to 343, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

345. The method of any of claims 262 to 344, wherein the machine learning model includes a forecasting module.

346. The method of any of claims 262 to 345, wherein a forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

347. The method of any of claims 262 to 346, wherein a forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

348. The method of any of claims 262 to 347, wherein a forecasting module forecasts pricing for one or more blend components based on one or more of the historical data or business data and publishes the forecasted pricing via a communication module to an engineering gateway.

349. The method of any of claims 262 to 348, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

350. The method of claim 349, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

351. The method of claim 350, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

352. The method of any of claims 349 to 351, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

353. The method of any of claims 262 to 352, further comprising: removing isopentane from the naphtha feedstock; and feeding the naphtha feedstock into a lead reactor.

354. The method of any of claims 262 to 353, further comprising generating a recommendation to change an operating parameter, by the machine learning model, of a deisopentanizer to improve separation of isopentane from the naphtha feedstock being sent to isomerization.

355. 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 262 to 354.

356. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 262 to 354.

357. A method compri sing : receiving a pre-processed feedstock sensor data, by a machine learning model, describing a component distribution of a naphtha feedstock entering or before entering one or more of a feed heater, a hydrotreater reactor, a separator, a stripper, a deisopentanizer, a naphtha feedstock dryer, a charge drum, or an isomerization reactor;receiving a post-processed sensor data, by a machine learning model, from a sensor package disposed to measure a component or attribute of the naphtha feedstock or an isomerate exiting or after exiting the one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, the charge drum, or the isomerization reactor; comparing the pre-processed feedstock sensor data with the post-processed sensor data to generate a processing effectiveness score; and publishing the processing effectiveness score.

358. The method of claim 357, further comprising publishing a recommendation to investigate one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, the charge drum, or the isomerization reactor, when the processing effectiveness score changes more than a predetermined amount during a predetermined time period.

359. The method of claim 357, further comprising publishing a recommendation to investigate one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, the charge drum, or the isomerization reactor, when the processing effectiveness score is less than a predetermined score.

360. The method of any of claims 357 to 359, further comprising simulating, by the machine learning model, a feed rate adjustment or a temperature adjustment to a feedstock of a hydrogen gas into one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, a hydrogen feedstock dryer or the isomerization reactor.

361. The method of claim 360, further comprising predicting, by the machine learning model, an effect on a removal of different contaminants from the naphtha feedstock based on the simulated hydrogen gas feed rate or temperature adjustment.

362. The method of any of claims 357 to 361, further comprising adjusting a feed rate or temperature of hydrogen gas fed into one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, a hydrogen feedstock dryer, or the isomerization reactor.

363. The method of any of claims 360 to 362, wherein the simulated feed rate or temperature adjustment of the hydrogen gas is based on a composition of the feedstocks entering a lead isomerization reactor or the composition of isomerate exiting one or more isomerization reactors.

364. The method of any of claims 360 to 363, wherein the simulation includes consideration of one or more of weather data or solar radiation data received by the machine learning model.

365. The method of any of claims 357 to 364, further comprising retraining the machine learning model with a sensor data from one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, a hydrogen feedstock dryer, the charge drum, the isomerization reactor, or a product thereof after an adjustment of one or more of a feedstock feed rate into, an operating pressure of, or an operating temperature of one or more of the feed heater, the hydrotreater reactor, the separator, the stripper, the deisopentanizer, the naphtha feedstock dryer, the hydrogen feedstock dryer, the charge drum, or the isomerization reactor.

366. The method of any of claims 357 to 365, wherein the machine learning model is configured to predict an octane-barrels of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature or predict an road octane number of an isomerate produced by the isomerization process based on a lead reactor temperature and a lag reactor temperature.

367. The method of any of claims 357 to 366, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

368. The method of any of claims 357 to 367, wherein feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

369. The method of claim 368, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

370. The method of any of claims 357 to 369, wherein feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

371. The method of any of claims 357 to 370, wherein the feedstock process data is from a feedstock process controller.

372. The method of any of claims 357 to 371, wherein the feedstock process data is from a feedstock process.

373. The method of any of claims 357 to 372, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

374. The method of any of claims 357 to 373, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

375. The method of any of claims 357 to 374, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

376. The method of any of claims 357 to 375, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

377. The method of any of claims 357 to 376, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from asampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

378. The method of any of claims 357 to 377, further comprising displaying recommendations.

379. The method of any of claims 357 to 378, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

380. The method of any of claims 357 to 379, further comprising accessing business data.

381. The method of any of claims 357 to 380, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

382. The method of any of claims 357 to 381, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

383. The method of any of claims 357 to 382, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

384. The method of any of claims 357 to 383, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

385. The method of any of claims 357 to 384, further comprising accessing a lab data.

386. The method of any of claims 357 to 385, further comprising sending instructions to an engineering gateway.

387. The method of any of claims 357 to 386, further comprising receiving instructions from an engineering gateway.

388. The method of claims 386 or 387, wherein the engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

389. The method of any of claims 386 to 388, wherein the engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy a prediction of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

390. The method of any of claims 386 to 389, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses by the machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

391. The method of any of claims 357 to 390, wherein the feedstocks include crude oil received for processing into refined hydrocarbons.

392. The method of any of claims 386 to 391, wherein the engineering gateway is used to facilitate active learning by the machine learning model.

393. The method of any of claims 357 to 392, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

394. The method of claim 393, further comprising adjusting the algorithm based on the identified changes.

395. The method of any of claims 393 to 394, wherein adjusting the algorithm is performed by the machine learning model without user input.

396. The method of claim 395, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

397. The method of any of claims 357 to 396, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

398. The method of claim 397, wherein the processed data set excludes the identified outlier.

399. The method of any of claims 397 to 398, wherein the processed data set includes a flag for the identified outlier.

400. The method of any of claims 397 to 399, further comprising publishing one or more of the identified outlier for user review.

401. The method of any of claims 397 to 400, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

402. The method of any of claims 357 to 401, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learningmodel, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

403. The method of any of claims 357 to 402, further comprising comparing at least a portion of historical data with one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to generate a compared data set.

404. The method of any of claims 357 to 403, further comprising identifying at least one process change from a compared data set.

405. The method of any of claims 403 to 404, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

406. The method of claim 405, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

407. The method of any of claims 403 to 406, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

408. The method of any of claims 407, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a componentwill wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

409. The method of any of claims 357 to 408, further comprising publishing at least a portion of a compared data set.

410. The method of any of claims 357 to 409, further comprising adjusting an operating parameter without user input.

411. The method of any of claims 357 to 410, further comprising storing one or more of a data set to be processed, an interpolated data set, or a compared data set.

412. The method of claim 411, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of training data or historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

413. The method of claim 412, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

414. The method of any of claims 357 to 413, wherein analyzing data to predict one or more changes is performed using a prediction module.

415. The method of any of claims 357 to 414, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

416. The method of claim 415, further comprising notifying a user of the predicted one or more changes.

417. The method of claim 416, wherein the user is notified of the predicted one or more changes using an engineering gateway.

418. The method of any of claims 357 to 417, further comprising applying one or more process changes automatically without user input or based on an instruction from the user.

419. The method of any of claims 357 to 418, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

420. The method of any of claims 357 to 419, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

421. The method of any of claims 357 to 420, wherein a user approves implementation of an adjustment using an engineering gateway.

422. The method of any of claims 357 to 421, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

423. The method of any of claims 357 to 422, further comprising notifying a user of a one or more identified maintenance procedures.

424. The method of any of claims 357 to 423, further comprising notifying a user of a recommended maintenance window for a one or more identified maintenance procedures based on one or more of historical data and sensor package data.

425. The method of any of claims 357 to 424, further comprising wherein the machine learning model includes a communication module, wherein the communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

426. The method of any of claims 357 to 425, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

427. The method of any of claims 357 to 426, further comprising communicating with one or more process controllers and / or other refinery models.

428. The method of any of claims 357 to 427, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

429. The method of claim 428, further comprising retraining the machine learning model on the feedback.

430. The method of any of claims 428 to 429, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

431. The method of any of claims 357 to 430, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

432. The method of any of claims 357 to 431, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

433. The method of any of claims 357 to 432, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

434. The method of any of claims 357 to 433, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

435. The method of any of claims 357 to 434, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

436. The method of any of claims 357 to 435, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

437. The method of any of claims 357 to 436, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

438. The method of any of claims 357 to 437, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

439. The method of any of claims 357 to 438, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

440. The method of any of claims 357 to 439, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

441. The method of any of claims 357 to 440, wherein the machine learning model includes a forecasting module.

442. The method of any of claims 357 to 441, wherein an forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

443. The method of any of claims 357 to 442, wherein an forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

444. The method of any of claims 357 to 443, wherein an forecasting module forecasts pricing for one or more blend components based on one or more of historical data orbusiness data and publishes the forecasted pricing via a communication module to an engineering gateway.

445. The method of any of claims 357 to 444, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

446. The method of claim 445, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

447. The method of claim 446, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

448. The method of any of claims 445 to 447, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

449. The method of any of claims 357 to 448, further comprising: removing isopentane from the naphtha feedstock; and feeding the naphtha feedstock into a lead reactor.

450. The method of any of claims 357 to 449, further comprising generating a recommendation to change an operating parameter, by the machine learning model, of the deisopentanizer to improve separation of isopentane from the naphtha feedstock being sent to isomerization.

451. 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 357 to 450.

452. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 357 to 450.

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

454. The system of claim 453, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

455. The system of any of claims 453 to 454, wherein feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

456. The system of claim 455, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

457. The system of any of claims 453 to 456, wherein feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

458. The system of claim 457, wherein the feedstock process data is from a feedstock process controller.

459. The system of claim 458, wherein the feedstock process data is indicative of a feedstock process.

460. The system of claim 459, wherein the feedstock process includes any process preceding the dual isomerization operation.

461. The system of any of claims 457 to 460, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

462. The system of any of claims 453 to 461, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

463. The system of any of claims 453 to 462, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

464. The system of any of claims 453 to 463, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

465. The system of any of claims 453 to 464, further comprising displaying recommendations.

466. The system of any of claims 453 to 465, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

467. The system of any of claims 453 to 466, further comprising accessing business data.

468. The system of any of claims 453 to 467, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

469. The system of any of claims 453 to 468, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

470. The system of any of claims 453 to 469, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

471. The system of any of claims 453 to 470, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

472. The system of any of claims 453 to 471, further comprising accessing a lab data.

473. The system of any of claims 453 to 472, further comprising sending instructions to an engineering gateway.

474. The system of any of claims 453 to 473, further comprising receiving instructions from an engineering gateway.

475. The system of claims 473 or 474, wherein an engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

476. The system of any of claims 473 to 475, wherein an engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

477. The system of any of claims 473 to 476, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerizationsubprocesses by the machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

478. The system of any of claims 453 to 477, wherein the feedstocks include crude oil received for processing into refined hydrocarbons.

479. The system of any of claims 473 to 478, wherein an engineering gateway is used to facilitate active learning by the machine learning model.

480. The system of any of claims 453 to 479, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

481. The system of claim 480, further comprising adjusting the algorithm based on the identified changes.

482. The system of claim 481, wherein adjusting the algorithm is performed by the machine learning model without user input.

483. The system of claim 481, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

484. The system of any of claims 453 to 483, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

485. The system of claim 484, wherein the processed data set excludes the identified outlier.

486. The system of any of claims 484 to 485, wherein the processed data set includes a flag for the identified outlier.

487. The system of any of claims 484 to 486, further comprising publishing one or more of the identified outlier for user review.

488. The system of any of claims 484 to 487, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

489. The system of any of claims 453 to 488, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the dual isomerization operation.

490. The system of any of claims 453 to 489, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

491. The system of any of claims 453 to 490, further comprising identifying at least one process change from a compared data set.

492. The system of claim 491, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

493. The system of claim 492, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

494. The system of any of claims 490 to 493, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

495. The system of any of claims 494, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

496. The system of any of claims 453 to 495, further comprising publishing at least a portion of a compared data set.

497. The system of any of claims 453 to 496, further comprising adjusting an operating parameter without user input.

498. The system of any of claims 453 to 497, further comprising storing one or more of the data set to be processed, an interpolated data set, or a compared data set.

499. The system of claim 498, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of the training data or historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

500. The system of any of claims 453 to 499, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

501. The system of any of claims 453 to 500, wherein analyzing data to predict one or more changes is performed using a prediction module.

502. The system of any of claims 453 to 501, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

503. The system of claim 502, further comprising notifying a user of the predicted one or more changes.

504. The system of claim 503, wherein a user is notified of the predicted one or more changes using an engineering gateway.

505. The system of any of claims 453 to 504, further comprising applying one or more process changes automatically without user input or based on an instruction from a user.

506. The system of any of claims 453 to 505, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

507. The system of any of claims 453 to 506, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

508. The system of any of claims 453 to 507, wherein a user approves implementation of the adjustment using an engineering gateway.

509. The system of any of claims 453 to 508, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacementof a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

510. The system of any of claims 453 to 509, further comprising notifying a user of a one or more identified maintenance procedures.

511. The system of any of claims 453 to 510, further comprising notifying a user of a recommended maintenance window for a one or more identified maintenance procedures based on one or more of historical data and sensor package data.

512. The system of any of claims 453 to 511, further comprising wherein the machine learning model includes a communication module, wherein a communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

513. The system of any of claims 453 to 512, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

514. The system of any of claims 453 to 513, further comprising communicating with one or more process controllers and / or other refinery models.

515. The system of any of claims 453 to 514, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

516. The system of claim 515, further comprising retraining the machine learning model on the user feedback.

517. The system of any of claims 515 to 516, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

518. The system of any of claims 453 to 517, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or moreSHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

519. The system of any of claims 453 to 518, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

520. The system of any of claims 453 to 519, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

521. The system of any of claims 453 to 520, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

522. The system of any of claims 453 to 521, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

523. The system of any of claims 453 to 522, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

524. The system of any of claims 453 to 523, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

525. The system of any of claims 453 to 524, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

526. The system of any of claims 453 to 525, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

527. The system of any of claims 453 to 526, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

528. The system of any of claims 453 to 527, wherein the machine learning model includes a forecasting module.

529. The system of any of claims 453 to 528, wherein an forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

530. The system of any of claims 453 to 529, wherein an forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

531. The system of any of claims 453 to 530, wherein an forecasting module forecasts pricing for one or more blend components based on one or more of historical data or business data and publishes the forecasted pricing via a communication module to an engineering gateway.

532. The system of any of claims 453 to 531, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

533. The system of claim 532, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

534. The system of claim 533, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

535. The system of any of claims 532 to 534, wherein the authority module directs a communication module to request approval through an engineering gateway before arecommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

536. The system of any of claims 453 to 535, further comprising: removing isopentane from the feedstock; and feeding the feedstock into a lead reactor.

537. The system of any of claims 453 to 536, further comprising generating a recommendation to change an operating parameter, by the machine learning model, of a deisopentanizer to improve separation of isopentane from the feedstock being sent to the dual isomerization operation.

538. A method for enhancing control of an isomerization operation associated with a petroleum refining operation, the method comprising: supplying naphtha to an isomerization unit associated with the petroleum refining operation, the naphtha having one or more naphtha properties; analyzing a naphtha sample via a first analyzer to provide naphtha sample properties; predicting one or more naphtha sample properties associated with the naphtha sample based on (A) the naphtha sample properties and (B) a first output from application of the naphtha sample properties to a first trained machine learning model; operating the isomerization unit to produce one or more unit materials, the one or more unit materials having one or more unit materials properties, and the one or more unit materials comprising one or more of isomerate, C4 and lighter hydrocarbons, or hydrogen sulfide; analyzing the unit material sample via a second analyzer to provide unit material sample properties; predicting one or more unit material sample properties associated with the unit material sample based on (C) the unit material sample properties and (D) a second output from application of the unit material sample properties to a second trained machine learning model; and controlling, during the isomerization operation, based on the naphtha sample properties and the one or more unit material sample properties, one or more of:(a) one or more naphtha properties associated with the naphtha supplied to the isomerization unit;(b) one or more unit product materials properties associated with the unit product materials;(c) operation of the isomerization unit; or(d) operation of one or more upstream equipment or downstream equipment, so that the controlling, during the isomerization operation, causes the isomerization operation to produce one or more of:(i) one or more intermediate materials each having one or more properties within a range of one or more target properties of the one or more intermediate materials,(ii) one or more unit product materials each having one or more properties within a range of one or more target properties of the one or more unit product materials, or(iii) one or more downstream materials each having one or more properties within a range of one or more target properties of the one or more downstream materials.

539. The method of claim 538, wherein the machine learning model is connected to a plurality of sensors comprises at least one of a temperature sensor, a pressure sensor, a flow sensor, or a composition sensor.

540. The method of any of claims 538 to 539, wherein the isomerization unit includes one or more sample collection assemblies configured to collect samples at one or more locations selected from a group consisting of an inlet of the isomerization unit, an outlet of the isomerization unit, and an intermediate location within the isomerization unit.

541. The method of any of claims 538 to 540, wherein the machine learning model is configured to: aggregate and analyze measured parameters from a plurality of sensors and one or more collected properties of one or more collected samples from one or more sample analysis assemblies; compute an optimized target for the isomerization unit using predictive modeling and historical data trends;dynamically adjust isomerization operation control devices based on deviations from predefined quality specifications; provide real-time or near real-time feedback to operators for manual intervention when necessary; and ensure compliance with regulatory and performance constraints through automated enforcement mechanisms.

542. The method of any of claims 538 to 541, wherein the machine learning model is further configured to determine an optimized target for the one or more unit materials based on at least one of cost-efficiency, performance, or compliance with specifications.

543. The method of any of claims 538 to 542, wherein the machine learning model is further configured to adjust isomerization operation control devices to meet an optimized target.

544. The method of any of claims 538 to 543, wherein the machine learning model is configured to dynamically update an optimized target based on real-time or near real-time data.

545. The method of any of claims 538 to 544, wherein the machine learning model is further configured to adjust the one or more target properties for the isomerization unit based on aggregated results from at least one other isomerization unit to achieve a isomerate composition target.

546. The method of any of claims 538 to 545, wherein the machine learning model is configured to determine an optimized target based on dynamic refinery conditions.

547. The method of any of claims 538 to 546, further comprising a disturbance variable monitor configured to identify external factors impacting system performance.

548. The method of claim 547, further comprising a feedback mechanism that is configured to adjust one or more of refinery operation control devices, upon identifying external factors impacting system performance.

549. The method of any of claims 538 to 548, wherein disturbance variables provide predictive control insights by identifying external changes impacting system operations and proactively adjusting control settings.

550. The method of any of claims 538 to 549, further comprising receiving refinery information, wherein the refinery information includes feedstock data, wherein feedstock data includes one or more of operating pressure data or operating temperature data.

551. The method of any of claims 538 to 550, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

552. The method of any of claims 538 to 551, wherein feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

553. The method of claim 552, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

554. The method of any of claims 552 to 553, wherein feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

555. The method of claim 554, wherein the feedstock process data is from a feedstock process controller.

556. The method of claim 554, wherein the feedstock process data is indicative of a feedstock process.

557. The method of claim 556, wherein the feedstock process includes any process preceding a isomerization process under review by the machine learning model.

558. The method of any of claims 556 to 557, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

559. The method of any of claims 538 to 558, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

560. The method of any of claims 538 to 559, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

561. The method of any of claims 538 to 560, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

562. The method of any of claims 538 to 561, further comprising displaying recommendations.

563. The method of any of claims 538 to 562, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

564. The method of any of claims 538 to 563, further comprising accessing business data.

565. The method of any of claims 538 to 564, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a pastregulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

566. The method of any of claims 538 to 565, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

567. The method of any of claims 538 to 566, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

568. The method of any of claims 538 to 567, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

569. The method of any of claims 538 to 568, further comprising accessing a lab data.

570. The method of any of claims 538 to 569, further comprising sending instructions to an engineering gateway.

571. The method of any of claims 538 to 570, further comprising receiving instructions from an engineering gateway.

572. The method of claims 570 or 571, wherein an engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

573. The method of any of claims 570 to 572, wherein an engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect on an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

574. The method of any of claims 570 to 573, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses by a machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

575. The method of any of claims 538 to 574, wherein feedstocks include crude oil received for processing into refined hydrocarbons.

576. The method of any of claims 570 to 575, wherein an engineering gateway is used to facilitate active learning by the machine learning model.

577. The method of any of claims 538 to 576, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

578. The method of claim 577, further comprising adjusting the algorithm based on the identified changes.

579. The method of any of claims 577 to 578, wherein adjusting the algorithm is performed by the machine learning model without user input.

580. The method of claim 579, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

581. The method of any of claims 538 to 580, further comprising: analyzing one or more of a data set or the data set to be processed; andidentifying an outlier and generating a processed data set.

582. The method of claim 581, wherein the processed data set excludes the identified outlier.

583. The method of any of claims 581 to 582, wherein the processed data set includes a flag for the identified outlier.

584. The method of any of claims 581 to 583, further comprising publishing one or more of the identified outlier for user review.

585. The method of any of claims 581 to 584, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

586. The method of any of claims 538 to 585, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization operation.

587. The method of any of claims 538 to 586, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

588. The method of any of claims 538 to 587, further comprising identifying at least one process change from a compared data set.

589. The method of any of claims 587 to 588, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from a compared data set and publishing the identified one or more ofat least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

590. The method of claim 589, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

591. The method of any of claims 587 to 590, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

592. The method of any of claims 591, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

593. The method of any of claims 538 to 592, further comprising publishing at least a portion of a compared data set.

594. The method of any of claims 538 to 593, further comprising adjusting an operating parameter without user input.

595. The method of any of claims 538 to 594, further comprising storing one or more of a data set to be processed, a interpolated data set, or a compared data set.

596. The method of claim 595, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of training dataor historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

597. The method of any of claims 538 to 596, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

598. The method of any of claims 538 to 597, wherein analyzing data to predict one or more changes is performed using a prediction module.

599. The method of any of claims 538 to 598, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

600. The method of claim 599, further comprising notifying a user of the predicted one or more changes.

601. The method of claim 600, wherein a user is notified of the predicted one or more changes using an engineering gateway.

602. The method of any of claims 538 to 601, further comprising applying one or more process changes automatically without user input or based on an instruction from a user.

603. The method of any of claims 538 to 602, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

604. The method of any of claims 538 to 603, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

605. The method of any of claims 538 to 604, wherein a user approves implementation of a adjustment of an operational parameter using an engineering gateway.

606. The method of any of claims 538 to 605, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

607. The method of any of claims 538 to 606, further comprising notifying a user of a one or more identified maintenance procedures.

608. The method of any of claims 538 to 607, further comprising notifying a user of a recommended maintenance window for a one or more identified maintenance procedures based on one or more of historical data and sensor package data.

609. The method of any of claims 538 to 608, further comprising wherein the machine learning model includes a communication module, wherein a communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

610. The method of any of claims 538 to 609, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

611. The method of any of claims 538 to 610, further comprising communicating with one or more process controllers and / or other refinery models.

612. The method of any of claims 538 to 611, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

613. The method of claim 612, further comprising retraining the machine learning model on the user feedback.

614. The method of any of claims 612 to 613, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

615. The method of any of claims 538 to 614, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

616. The method of any of claims 538 to 615, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

617. The method of any of claims 538 to 616, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

618. The method of any of claims 538 to 617, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

619. The method of any of claims 538 to 618, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

620. The method of any of claims 538 to 619, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

621. The method of any of claims 538 to 620, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

622. The method of any of claims 538 to 621, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

623. The method of any of claims 538 to 622, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

624. The method of any of claims 538 to 623, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

625. The method of any of claims 538 to 624, wherein the machine learning model includes a forecasting module.

626. The method of any of claims 538 to 625, wherein an forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

627. The method of any of claims 538 to 626, wherein an forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

628. The method of any of claims 538 to 627, wherein an forecasting module forecasts pricing for one or more blend components based on one or more of historical data or business data and publishes the forecasted pricing via a communication module to an engineering gateway.

629. The method of any of claims 538 to 628, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

630. The method of claim 629, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

631. The method of claim 630, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

632. The method of any of claims 629 to 631, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

633. The method of any of claims 538 to 632, further comprising: removing isopentane from the naphtha; and feeding the naphtha into a lead reactor.

634. The method of any of claims 538 to 633, further comprising generating a recommendation to change an operating parameter, by the machine learning model, of a deisopentanizer to improve separation of isopentane from the naphtha being sent to isomerization.

635. 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 538 to 634.

636. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 538 to 634.

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

638. The method of claim 637, wherein predicting an adjustment includes predicting an adjustment to each process of the plurality of isomerization processes to achieve one or more of an aggregated target isomerate composition, an aggregated target production rate of isomerate, or a target average process cost.

639. The method of claims 637 and 485, wherein each adjustment is different.

640. The method of any of claims 637 to 639, wherein each process has different levels of equipment wear.

641. The method of any of claims 637 to 640, further comprising: receiving an instruction to implement the adjustment; and implementing the adjustment to the operational parameter of one of the plurality of isomerization processes.

642. The method of any of claims 637 to 641, further comprising: receiving at the machine learning model a second sensor data after the adjustment has been implemented from the plurality of sensor packages; determining what changes resulted from the adjustment; and retraining the machine learning model with the first sensor data and the second sensor data.

643. The method of any of claims 637 to 642, further comprising accessing weather data, wherein predicting an adjustment is further based on weather data.

644. The method of any of claims 637 to 643, wherein the adjustment is made to a process control algorithm of the one of a plurality of isomerization processes.

645. The method of any of claims 637 to 644, wherein publishing the predicted adjustment includes sending the predicted adjustment to a user.

646. The method of any of claims 637 to 645, further comprising receiving refinery information, wherein the refinery information includes feedstock data, wherein feedstock data includes one or more of operating pressure data or operating temperature data.

647. The method of any of claims 637 to 646, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

648. The method of any of claims 637 to 647, wherein feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

649. The method of claim 648, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

650. The method of any of claims 637 to 649, wherein feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

651. The method of claim 650, wherein the feedstock process data is from a feedstock process controller.

652. The method of claim 650, wherein the feedstock process data is indicative of a feedstock process.

653. The method of claim 652, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

654. The method of any of claims 652 to 653, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

655. The method of any of claims 637 to 654, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

656. The method of any of claims 637 to 655, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

657. The method of any of claims 637 to 656, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

658. The method of any of claims 637 to 657, further comprising displaying recommendations.

659. The method of any of claims 637 to 658, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

660. The method of any of claims 637 to 659, further comprising accessing business data.

661. The method of any of claims 637 to 660, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

662. The method of any of claims 637 to 661, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

663. The method of any of claims 637 to 662, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

664. The method of any of claims 637 to 663, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

665. The method of any of claims 637 to 664, further comprising accessing a lab data.

666. The method of any of claims 637 to 665, further comprising sending instructions to an engineering gateway.

667. The method of any of claims 637 to 666, further comprising receiving instructions from an engineering gateway.

668. The method of claims 666 or 667, wherein an engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

669. The method of any of claims 666 to 668, wherein an engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect on an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

670. The method of any of claims 666 to 669, further comprising generating a prediction of an effect on an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses by the machine learning model based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

671. The method of any of claims 637 to 670, wherein feedstocks include crude oil received for processing into refined hydrocarbons.

672. The method of any of claims 666 to 671, wherein an engineering gateway is used to facilitate active learning by the machine learning model.

673. The method of any of claims 637 to 672, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

674. The method of claim 673, further comprising adjusting the algorithm based on the identified changes.

675. The method of any of claims 673 to 674, wherein adjusting the algorithm is performed by the machine learning model without user input.

676. The method of claim 675, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in the historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

677. The method of any of claims 637 to 676, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

678. The method of claim 677, wherein the processed data set excludes the identified outlier.

679. The method of any of claims 677 to 678, wherein the processed data set includes a flag for the identified outlier.

680. The method of any of claims 677 to 679, further comprising publishing one or more of the identified outlier for user review.

681. The method of any of claims 677 to 680, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

682. The method of any of claims 637 to 681, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

683. The method of any of claims 637 to 682, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

684. The method of any of claims 637 to 683, further comprising identifying at least one process change from a compared data set.

685. The method of any of claims 683 to 684, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from a compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

686. The method of claim 685, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

687. The method of any of claims 683 to 686, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

688. The method of any of claims 687, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

689. The method of any of claims 637 to 688, further comprising publishing at least a portion of a compared data set.

690. The method of any of claims 637 to 689, further comprising adjusting an operating parameter without user input.

691. The method of any of claims 637 to 690, further comprising storing one or more of a data set to be processed, a interpolated data set, or a compared data set.

692. The method of claim 691, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of training data or historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

693. The method of any of claims 637 to 692, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

694. The method of any of claims 637 to 693, wherein analyzing data to predict one or more changes is performed using a prediction module.

695. The method of any of claims 637 to 694, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

696. The method of claim 695, further comprising notifying a user of the predicted one or more changes.

697. The method of claim 696, wherein a user is notified of the predicted one or more changes using an engineering gateway.

698. The method of any of claims 637 to 697, further comprising applying one or more process changes automatically without user input or based on an instruction from a user.

699. The method of any of claims 637 to 698, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

700. The method of any of claims 637 to 699, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

701. The method of any of claims 637 to 700, wherein a user approves implementation of the adjustment using an engineering gateway.

702. The method of any of claims 637 to 701, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

703. The method of any of claims 637 to 702, further comprising notifying a user of a one or more identified maintenance procedures.

704. The method of any of claims 637 to 703, further comprising notifying a user of a recommended maintenance window for a one or more identified maintenance procedures based on one or more of historical data and sensor package data.

705. The method of any of claims 637 to 704, further comprising wherein the machine learning model includes a communication module, wherein a communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

706. The method of any of claims 637 to 705, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

707. The method of any of claims 637 to 706, further comprising communicating with one or more process controllers and / or other refinery models.

708. The method of any of claims 637 to 707, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

709. The method of claim 708, further comprising retraining the machine learning model on the user feedback.

710. The method of any of claims 708 to 709, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

711. The method of any of claims 637 to 710, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

712. The method of any of claims 637 to 711, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewingone or more algorithms or one or more changes recommended by the machine learning model.

713. The method of any of claims 637 to 712, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

714. The method of any of claims 637 to 713, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

715. The method of any of claims 637 to 714, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

716. The method of any of claims 637 to 715, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

717. The method of any of claims 637 to 716, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

718. The method of any of claims 637 to 717, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

719. The method of any of claims 637 to 718, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

720. The method of any of claims 637 to 719, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

721. The method of any of claims 637 to 720, wherein the machine learning model includes a forecasting module.

722. The method of any of claims 637 to 721, wherein an forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

723. The method of any of claims 637 to 722, wherein an forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

724. The method of any of claims 637 to 723, wherein an forecasting module forecasts pricing for one or more blend components based on one or more of historical data or business data and publishes the forecasted pricing via a communication module to an engineering gateway.

725. The method of any of claims 637 to 724, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

726. The method of claim 725, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

727. The method of claim 726, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

728. The method of any of claims 725 to 727, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

729. The method of any of claims 637 to 728, further comprising: removing isopentane from a feedstock being sent to isomerization; andfeeding the feedstock into a lead reactor.

730. The method of any of claims 637 to 729, further comprising generating a recommendation to change an operating parameter, by the machine learning model, of a deisopentanizer to improve separation of isopentane from a feedstock being sent to isomerization.

731. A computing system including processor and a memory including instructions and the machine learning model that cause the processor to perform the instructions, wherein the instructions include the method of any of claims 637 to 730.

732. A memory including instructions that causes a processor to perform the instructions, wherein the instructions include the method of any of claims 637 to 730.

733. A method comprising: receiving a sensor data from a plurality of sensor packages at a machine learning model, wherein a first sensor package of the plurality of sensor packages is disposed to measure one or more process parameters of a first isomerization process, a second sensor package of the plurality of sensor packages is disposed to measure an isomerate attribute of the first process, a third sensor package disposed to measure one or more process parameters of a second isomerization process, and a fourth sensor package of the plurality of sensor packages is disposed to measure an isomerate attribute of the second isomerization process; accessing, by the machine learning model, historical data of the first isomerization process and the second isomerization process and the isomerate of the first isomerization process and the isomerate of the second isomerization process; predicting, by the machine learning model, an isomerate attribute for a blend of the isomerate of the first isomerization process with the isomerate of the second isomerization process; and predicting, by the machine learning model, an adjustment to an operational parameter of the first isomerization process to improve the isomerate attribute of the blend based on the historical data and the sensor data.

734. The method of claim 733, predicting, by the machine learning model, an adjustment to an operational parameter of the second isomerization process to improve the isomerate attribute of the blend based on the historical data and the sensor data.

735. The method of any of claims 733 and 970, implementing the adjustment to an operational parameter of the first isomerization process.

736. The method of any of claims 733 and 971, implementing the adjustment to an operational parameter of the second isomerization process.

737. The method of any of claims 733 and 972, further comprising publishing the predicted adjustments to a user.

738. The method of any of claims 733 and 734, wherein each adjustment is different.

739. The method of any of claims 733 to 738, wherein each isomerization process has different levels of equipment wear.

740. The method of any of claims 733 to 739, wherein the first isomerization process is different from the second process.

741. The method of any of claims 733 to 740, further comprising receiving refinery information, wherein the refinery information includes feedstock data, wherein feedstock data includes one or more of operating pressure data or operating temperature data.

742. The method of any of claims 733 to 741, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

743. The method of any of claims 733 to 742, wherein feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

744. The method of claim 743, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input, output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

745. The method of any of claims 733 to 744, wherein feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

746. The method of claim 745, wherein the feedstock process data is from a feedstock process controller.

747. The method of claim 746, wherein the feedstock process data is indicative of a feedstock process.

748. The method of claim 747, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

749. The method of any of claims 747 to 748, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

750. The method of any of claims 733 to 749, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

751. The method of any of claims 733 to 750, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

752. The method of any of claims 733 to 751, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from asampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

753. The method of any of claims 733 to 752, further comprising displaying recommendations.

754. The method of any of claims 733 to 753, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

755. The method of any of claims 733 to 754, further comprising accessing business data.

756. The method of any of claims 733 to 755, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

757. The method of any of claims 733 to 756, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

758. The method of any of claims 733 to 757, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

759. The method of any of claims 733 to 758, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

760. The method of any of claims 733 to 759, further comprising accessing a lab data.

761. The method of any of claims 733 to 760, further comprising sending instructions to an engineering gateway.

762. The method of any of claims 733 to 761, further comprising receiving instructions from an engineering gateway.

763. The method of claims 761 or 762, wherein an engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

764. The method of any of claims 761 to 763, wherein an engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect on an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

765. The method of any of claims 761 to 764, further comprising generating a prediction of an effect of an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

766. The method of any of claims 733 to 765, wherein feedstocks include crude oil received for processing into refined hydrocarbons.

767. The method of any of claims 761 to 766, wherein an engineering gateway is used to facilitate active learning by the machine learning model.

768. The method of any of claims 733 to 767, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

769. The method of claim 768, further comprising adjusting the algorithm based on the identified changes.

770. The method of any of claims 768 to 769, wherein adjusting the algorithm is performed by the machine learning model without user input.

771. The method of claim 770, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in the historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

772. The method of any of claims 733 to 771, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

773. The method of claim 772, wherein the processed data set excludes the identified outlier.

774. The method of any of claims 772 to 773, wherein the processed data set includes a flag for the identified outlier.

775. The method of any of claims 772 to 774, further comprising publishing one or more of the identified outlier for user review.

776. The method of any of claims 772 to 775, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

777. The method of any of claims 733 to 776, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learningmodel, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

778. The method of any of claims 733 to 777, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

779. The method of any of claims 733 to 778, further comprising identifying at least one process change from a compared data set.

780. The method of any of claims 778 to 779, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from a compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

781. The method of claim 780, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

782. The method of any of claims 778 to 781, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

783. The method of any of claims 782, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a componentwill wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

784. The method of any of claims 733 to 783, further comprising publishing at least a portion of a compared data set.

785. The method of any of claims 733 to 784, further comprising adjusting an operating parameter without user input.

786. The method of any of claims 733 to 785, further comprising storing one or more of a data set to be processed, a interpolated data set, or a compared data set.

787. The method of claim 786, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of training data or the historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

788. The method of any of claims 733 to 787, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

789. The method of any of claims 733 to 788, wherein analyzing data to predict one or more changes is performed using a prediction module.

790. The method of any of claims 733 to 789, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

791. The method of claim 790, further comprising notifying a user of the predicted one or more changes.

792. The method of claim 791, wherein a user is notified of the predicted one or more changes using an engineering gateway.

793. The method of any of claims 733 to 792, further comprising applying one or more process changes automatically without user input or based on an instruction from a user.

794. The method of any of claims 733 to 793, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

795. The method of any of claims 733 to 794, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

796. The method of any of claims 733 to 795, wherein a user approves implementation of the adjustment using an engineering gateway.

797. The method of any of claims 733 to 796, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

798. The method of any of claims 733 to 797, further comprising notifying a user of a one or more identified maintenance procedures.

799. The method of any of claims 733 to 798, further comprising notifying a user of a recommended maintenance window for a one or more identified maintenance procedures based on one or more of historical data and sensor package data.

800. The method of any of claims 733 to 799, further comprising wherein the machine learning model includes a communication module, wherein a communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

801. The method of any of claims 733 to 800, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

802. The method of any of claims 733 to 801, further comprising communicating with one or more process controllers and / or other refinery models.

803. The method of any of claims 733 to 802, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

804. The method of claim 803, further comprising retraining the machine learning model on the user feedback.

805. The method of any of claims 803 to 804, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

806. The method of any of claims 733 to 805, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

807. The method of any of claims 733 to 806, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

808. The method of any of claims 733 to 807, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

809. The method of any of claims 733 to 808, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

810. The method of any of claims 733 to 809, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

811. The method of any of claims 733 to 810, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

812. The method of any of claims 733 to 811, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

813. The method of any of claims 733 to 812, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

814. The method of any of claims 733 to 813, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

815. The method of any of claims 733 to 814, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

816. The method of any of claims 733 to 815, wherein the machine learning model includes a forecasting module.

817. The method of any of claims 733 to 816, wherein an forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

818. The method of any of claims 733 to 817, wherein an forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

819. The method of any of claims 733 to 818, wherein an forecasting module forecasts pricing for one or more blend components based on one or more of historical data orbusiness data and publishes the forecasted pricing via a communication module to an engineering gateway.

820. The method of any of claims 733 to 819, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

821. The method of claim 820, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

822. The method of claim 821, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

823. The method of any of claims 820 to 822, wherein the authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

824. The method of any of claims 733 to 823, further comprising generating a recommendation to change an operating parameter, by the machine learning model, of a deisopentanizer to improve separation of isopentane from the feedstock being sent to isomerization.

825. The method of any of claims 733 to 824, further comprising: removing isopentane from the feedstock; and feeding the feedstock into a lead reactor.

826. A memory including instructions that causes a processor to perform the instructions including the method of any of claims 733 to 825.

827. 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 733 to 825.

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

829. The system of claim 828, further comprising receiving refinery information, wherein the refinery information includes feedstock data, wherein feedstock data includes one or more of operating pressure data or operating temperature data.

830. The system of any of claims 828 to 829, wherein the one or more of operating pressure data, feed rates, or operating temperature data is obtained by a sensor package from one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

831. The system of any of claims 828 to 830, wherein feedstock data includes material composition data, wherein the material composition data describes material moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

832. The system of claim 831, wherein the material composition data includes quantities or percentages of one or more of contaminants, hydrogen, or hydrocarbon species input,output, or moving through one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

833. The system of any of claims 828 to 832, wherein feedstock data includes one or more of feedstock sensor data from a feedstock sensor, feedstock sampled data, feedstock process data, feedstock sampling data, feedstock testing system data, or feedstock lab data.

834. The system of any of claims 828 to 833, wherein the feedstock process data is from a feedstock process controller.

835. The system of any of claims 828 to 834, wherein the feedstock process data is from a feedstock process.

836. The system of claim 835, wherein the feedstock process includes any process preceding the isomerization process under review by the machine learning model.

837. The system of any of claims 828 to 836, wherein the feedstock process includes one or more of atmospheric distillation, vacuum distillation, filtration processes, drying processes, hydrotreating processes, mercaptan treating processes, gasoline desulfurization processes, splitting processes, stripping processes, or separating processes.

838. The system of any of claims 828 to 837, further comprising receiving targeted process data, wherein the targeted process data includes one or more of operating pressure data, operating temperature data, flow rate data, and material composition data.

839. The system of any of claims 828 to 838, wherein the one or more of operating pressure data or operating temperature data is for one or more process or subprocess.

840. The system of any of claims 828 to 839, wherein a targeted process data is received from one or more of a targeted process controller, directly from a sensor, directly from a sampling system, directly from a testing systems, or from a lab obtaining and analyzing samples from the targeted process.

841. The system of any of claims 828 to 840, further comprising displaying recommendations.

842. The system of any of claims 828 to 841, further comprising providing data to one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller.

843. The system of any of claims 828 to 842, further comprising accessing business data.

844. The system of any of claims 828 to 843, wherein business data includes demand planning information, demand forecasting information for one or more products, current pricing information, product distribution information, information regarding a past regulatory landscape, information regarding a current regulatory landscape, information regarding an anticipated regulatory landscape.

845. The system of any of claims 828 to 844, wherein business data includes information regarding one or more of costs, availability, or location of one or more of storage, disposal, or carbon capture options of waste products.

846. The system of any of claims 828 to 845, wherein business data includes one or more of historical costs, current costs, historical market pricing, or current market pricing of one or more processes or refinery products.

847. The system of any of claims 828 to 846, wherein business data includes inventory levels of various products stored in one or more storage tanks of a blending pool.

848. The system of any of claims 828 to 847, further comprising accessing a lab data.

849. The system of any of claims 828 to 848, further comprising sending instructions to an engineering gateway.

850. The system of any of claims 828 to 849, further comprising receiving instructions from an engineering gateway.

851. The system of claims 849 or 850, wherein an engineering gateway acts as a user interface for engineers to review process data, process recommendations, process warnings, process requests, machine learning model data, machine learning recommendations, machine learning warnings, or machine learning requests.

852. The system of any of claims 849 to 851, wherein an engineering gateway is configured to allow a user to assist the machine learning model in training, refining, and tuning the machine learning model to improve accuracy of a prediction of an effect on an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses.

853. The system of any of claims 849 to 852, wherein the machine learning model generates a prediction of an effect on an adjustment to one or more isomerization feedstock processes, isomerization feedstock subprocesses, isomerization processes, or isomerization subprocesses based on changes in one or more of ambient weather, demand seasonality, content of feedstocks, or quality of feedstocks.

854. The system of any of claims 828 to 853, wherein the feedstocks include crude oil received for processing into refined hydrocarbons.

855. The system of any of claims 849 to 854, wherein an engineering gateway is used to facilitate active learning by the machine learning model.

856. The system of any of claims 828 to 855, further comprising identifying changes to an algorithm used by one or more of a feedstock process controller, a targeted process controller, or a subsequent process controller based on changes identified by one or more of the machine learning model, an engineering gateway, or a user.

857. The system of claim 856, further comprising adjusting the algorithm based on the identified changes.

858. The system of any of claims 856 to 857, wherein adjusting the algorithm is performed by the machine learning model without user input.

859. The system of claim 858, further comprising: sending a request for approval to implement the adjusted algorithm, by the machine learning model requests approval, through an engineering gateway; receiving approval information to implement the adjusted algorithm, by the machine learning model, wherein upon receipt of approval, the machine learning model saves a copy of the approval information in the historical data and / or sends the approved adjusted algorithm to a targeted process controller; and implementing the adjusted algorithm.

860. The system of any of claims 828 to 859, further comprising: analyzing one or more of a data set or the data set to be processed; and identifying an outlier and generating a processed data set.

861. The system of claim 860, wherein the processed data set excludes the identified outlier.

862. The system of any of claims 860 to 861, wherein the processed data set includes a flag for the identified outlier.

863. The system of any of claims 860 to 862, further comprising publishing one or more of the identified outlier for user review.

864. The system of any of claims 860 to 863, further comprising receiving user instructions regarding the identified outlier to do one or more of excluding the identified outlier from the processed data set and requesting additional information related to the identified outlier.

865. The system of any of claims 828 to 864, further comprising interpolating one or more missing data from a data set using an interpolation module of the machine learning model, saving the data set as an interpolated data set, and using the interpolated data set to generate a simulation of at least a portion of the isomerization process.

866. The system of any of claims 828 to 865, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted processsensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

867. The system of any of claims 828 to 866, further comprising identifying at least one process change from a compared data set.

868. The system of any of claims 866 to 867, further comprising identifying one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from a compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set.

869. The system of claim 868, further comprising storing a published data and a data used to identify one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data from the compared data set and publishing the identified one or more of at least one miscalibrated sensor, at least one misprocessed sample, or at least one inaccurate test data.

870. The system of any of claims 866 to 869, further comprising: predicting one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold; and publishing the one or more of a remaining wear period before a component will wear out or a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

871. The system of any of claims 870, further comprising storing a published data and a data used to predict one or more of at least a remaining wear period before a component will wear out or at least a remaining functional period before a catalyst is deactivated or poisoned below a predetermined threshold.

872. The system of any of claims 828 to 871, further comprising publishing at least a portion of a compared data set.

873. The system of any of claims 828 to 872, further comprising adjusting an operating parameter without user input.

874. The system of any of claims 828 to 873, further comprising storing one or more of a data set to be processed, a interpolated data set, or a compared data set.

875. The system of claim 874, wherein the one or more of the data set to be processed, the interpolated data set, or the compared data set is stored in one or more of the training data or the historical data for one or more of retraining of the machine learning model, analysis of a targeted process, optimization of the targeted process, or for later use.

876. The system of any of claims 828 to 875, further comprising analyzing one or more of feedstock sensor data, feedstock sample data, feedstock process data, targeted process sensor data, targeted process sample data, targeted process data, subsequent process sensor data, subsequent process sample data, or subsequent process data to predict one or more changes in one or more processes.

877. The system of any of claims 828 to 876, wherein analyzing data to predict one or more changes is performed using a prediction module.

878. The system of any of claims 828 to 877, wherein analyzing data to predict one or more changes includes predicting temperature excursions in one or more processes.

879. The system of claim 878, further comprising notifying a user of the predicted one or more changes.

880. The system of claim 879, wherein a user is notified of the predicted one or more changes using an engineering gateway.

881. The system of any of claims 828 to 880, further comprising applying one or more process changes automatically without user input or based on an instruction from a user.

882. The system of any of claims 828 to 881, wherein a machine learning model is granted authority to automatically make process changes that fall within a predetermined range of process operating parameters.

883. The system of any of claims 828 to 882, wherein a machine learning model is not granted authority to automatically make process changes that fall outside of a predetermined range of process operating parameters.

884. The system of any of claims 828 to 883, wherein a user approves implementation of an adjustment to an operational parameter using an engineering gateway.

885. The system of any of claims 828 to 884, further comprising identifying one or more maintenance procedures including one or more of regeneration of a catalyst, replacement of a catalyst, repair of a component of a process as part of a maintenance procedure, or replacement of a component of a process.

886. The system of any of claims 828 to 885, further comprising notifying a user of a one or more identified maintenance procedures.

887. The system of any of claims 828 to 886, further comprising notifying a user of a recommended maintenance window for a one or more identified maintenance procedures based on one or more of historical data and sensor package data.

888. The system of any of claims 828 to 887, further comprising wherein the machine learning model includes a communication module, wherein a communication module one or more of (a) translates one or more of recommendations, instructions, or data from other modules from machine code into human language or (b) converts data into graphs or other visual communication elements.

889. The system of any of claims 828 to 888, further comprising publishing one or more recommendations, instructions, or data in a human language, graph, or other visual communication element to an engineering gateway.

890. The system of any of claims 828 to 889, further comprising communicating with one or more process controllers and / or other refinery models.

891. The system of any of claims 828 to 890, further comprising receiving user feedback on an analysis and recommendations of the machine learning model.

892. The system of claims 891, further comprising retraining the machine learning model on the user feedback.

893. The system of any of claims 891 to 892, further comprising assigning a confidence level to one or more of the analysis or recommendation of the machine learning model.

894. The system of any of claims 828 to 893, wherein the machine learning model includes a confidence module, wherein the confidence module generates one or more SHAP values, LIME, or anchors to analyze one or more algorithms adjusted or created by the machine learning model.

895. The system of any of claims 828 to 894, further comprising publishing one or more SHAP values, LIME, or anchors to an engineering gateway to assist a user in reviewing one or more algorithms or one or more changes recommended by the machine learning model.

896. The system of any of claims 828 to 895, further comprising: accessing business data to information; and generate regulatory constraints for products and processes.

897. The system of any of claims 828 to 896, further comprising adjusting process control algorithms with a regulatory constraint and publishing the adjusted process control algorithms for user review.

898. The system of any of claims 828 to 897, further comprising predicting one or more processes to be non-compliant in a compliance period, and publishing the predicted non- compliant one or more processes to a user.

899. The system of any of claims 828 to 898, further comprising flagging one or more processes that is predicted by a prediction module to move out of compliance.

900. The system of any of claims 828 to 899, wherein a regulatory module issues one or more warnings through a communication module to an engineering gateway.

901. The system of any of claims 828 to 900, further comprising identifying one or more windows of time when regulatory constraints are changed, and recommending changes to process operational parameters based on the one or more identified windows of time.

902. The system of any of claims 828 to 901, further comprising requesting user permission to adjust a process constraint in line with upcoming regulatory changes.

903. The system of any of claims 828 to 902, further comprising implementing changes to one or more process controllers to adjust operational parameters in line with upcoming regulatory changes.

904. The system of any of claims 828 to 903, wherein the machine learning model includes a forecasting module.

905. The system of any of claims 828 to 904, wherein an forecasting module analyzes business data and recommends adjustments to one or more process controller parameters to promote production of one or more blend components in greater demand.

906. The system of any of claims 828 to 905, wherein an forecasting module recommends maintenance windows for equipment producing products in low demand during specific time frames.

907. The system of any of claims 828 to 906, wherein an forecasting module forecasts pricing for one or more blend components based on one or more of historical data or business data and publishes the forecasted pricing via a communication module to an engineering gateway.

908. The system of any of claims 828 to 907, wherein the machine learning model includes an authority module, wherein the authority module tracks (a) user instructions, (b) approvals for one or more instructions, or (c) changes to be made by the machine learning model to one or more controllers.

909. The system of claim 908, wherein the authority module considers a recommendation from one or more modules of the machine learning model.

910. The system of claim 909, wherein the authority module automatically authorizes the machine learning model to issue one or more instructions to a targeted process controller.

911. The system of any of claims 828 to 910, wherein the machine learning model generates a recommendation to change an operating parameter of a deisopentanizer to improve separation of isopentane from the feedstock being sent to isomerization.

912. The system of any of claims 828 to 911, wherein an authority module directs a communication module to request approval through an engineering gateway before a recommendation is implemented and / or instructions are sent to a targeted process controller, wherein the machine learning model provides one or more of changes or predicted changes in a nonlinear refinery process.

913. The system of any of claims 828 to 912, further comprising: removing isopentane from the feedstock; and feeding the feedstock into a lead reactor.

Images