Crude oil processing control method and device

Abstract

The present invention provides a crude oil processing control method and device, wherein the method includes: obtaining initial control parameters of the crude oil processing system under the current operating conditions; determining the generated product prediction results of the current operating conditions based on the initial control parameters and the generated product prediction model; determining the target control parameters of the current operating conditions based on preset optimization conditions and the generated product prediction results; and controlling the crude oil processing system based on the target control parameters; wherein the generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model. The method and device provided by the present invention can accurately predict and optimize the generated products of the crude oil, reducing hydrogen consumption in the refining process while ensuring the target product yield.

Description

Technical Field

[0001] The present invention relates to the technical field of petroleum processing, and in particular to a crude oil processing control method and device. Background Art

[0002] Crude oil processing primarily involves rebalancing the carbon, hydrogen, and other elements in the crude oil. Through hydrogenation, cracking, hydrogen transfer, and isomerization, crude oil is converted into products such as dry gas, liquefied gas, gasoline, light cycle oil, slurry oil, and coke.

[0003] A crude oil processing system typically includes a catalytic cracking unit and a hydrogenation unit. Prior art typically involves developing a mechanistic model of the catalytic cracking unit, predicting the products generated by the unit based on the model, and then performing hydrogenation based on the predicted results and operator experience. However, due to the relatively complex process of developing the mechanistic model and its low accuracy, hydrogen consumption during crude oil processing is high, making it difficult to guarantee target product yields. Summary of the Invention

[0004] The present invention provides a crude oil processing control method and device, which is used to solve the technical problems in the prior art of predicting the generated products of crude oil by establishing a mechanism model of a catalytic cracking unit, thereby controlling the crude oil processing system, resulting in high hydrogen consumption and the inability to guarantee the yield of the target product.

[0005] The present invention provides a crude oil processing control method, comprising:

[0006] Obtaining initial control parameters of the crude oil processing system under current operating conditions;

[0007] Determining a prediction result of a generated product under the current operating condition based on the initial control parameters and a generated product prediction model;

[0008] Determining target control parameters for the current operating condition based on preset optimization conditions and the generated product prediction result;

[0009] controlling the crude oil processing system based on the target control parameter;

[0010] The generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model.

[0011] According to the crude oil processing control method provided by the present invention, the generated product prediction model is determined based on the following steps:

[0012] Determine the initial model;

[0013] Training the initial model based on historical control parameters and historical product generation results under multiple operating conditions to obtain the product generation prediction model;

[0014] The historical product generation results include at least one of the historical flow rate of low-carbon hydrocarbons, the historical hydrogen content of low-carbon hydrocarbons, the historical flow rate of liquid oil and the historical hydrogen content of liquid oil.

[0015] According to the crude oil processing control method provided by the present invention, controlling the crude oil processing system based on the target control parameter includes:

[0016] Determining target operating parameters of the catalytic cracking unit and target hydrogenation depth of the hydrogenation unit based on the target control parameters;

[0017] controlling the catalytic cracking unit based on the target operating parameters, and controlling the hydrogenation unit based on the target hydrogenation depth;

[0018] Wherein, the crude oil processing system includes a catalytic cracking unit and a hydrogenation unit.

[0019] According to the crude oil processing control method provided by the present invention, the preset optimization conditions are determined based on the flow rate and hydrogen content of each product in the generated product prediction results.

[0020] According to the crude oil processing control method provided by the present invention, determining the target control parameters of the current operating condition based on the preset optimization conditions and the generated product prediction results includes:

[0021] Determining the objective function and constraint conditions in the preset optimization conditions based on the flow rate and hydrogen content of each product in the generated product prediction results;

[0022] Based on the objective function, adjusting the initial control parameter to obtain a control parameter adjustment value, and determining a generated product optimization result of the current operating condition based on the control parameter adjustment value and the generated product prediction model;

[0023] If the generated product optimization result satisfies the constraint condition, the control parameter adjustment value corresponding to the generated product optimization result is used as the target control parameter of the current working condition.

[0024] According to the crude oil processing control method provided by the present invention, the initial control parameters include raw material property parameters, initial operating parameters and an initial value of hydrogenation depth; the initial operating parameters include an initial value of reaction temperature and an initial value of reaction pressure in the catalytic cracking unit, as well as an initial value of the residence time of the crude oil in the catalytic cracking unit.

[0025] The present invention provides a crude oil processing control device, comprising:

[0026] An acquisition unit, used to acquire initial control parameters of the crude oil processing system under current working conditions;

[0027] A prediction unit, configured to determine a prediction result of a generated product under the current operating condition based on the initial control parameters and a generated product prediction model;

[0028] An optimization unit, configured to determine target control parameters for the current operating condition based on preset optimization conditions and the generated product prediction result;

[0029] a control unit, configured to control the crude oil processing system based on the target control parameters;

[0030] The generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model.

[0031] The present invention provides an electronic device comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor implements the steps of the crude oil processing control method when executing the program.

[0032] The present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the crude oil processing control method when executed by a processor.

[0033] The present invention provides a computer program product, comprising a computer program, which implements the steps of the crude oil processing control method when executed by a processor.

[0034] An embodiment of the present invention provides a crude oil processing control method and device, which generates a product prediction model to determine the generated product prediction results of the crude oil processing system under the current operating conditions, and determines the target control parameters of the current operating conditions based on preset optimization conditions and the generated product prediction results, thereby controlling the crude oil processing system. The generated product prediction model includes a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model and a liquid oil hydrogen content prediction model, which can accurately predict and optimize the generated products of the crude oil without establishing a complex mechanism model, thereby improving the accuracy of the generated product prediction results and the optimization results, and reducing the hydrogen consumption in the refining process while ensuring the yield of the target product. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A schematic flow chart of the crude oil processing control method provided by the present invention;

[0037] Figure 2 This is a schematic diagram of the modeling of the liquefied gas flow rate and hydrogen content prediction model provided by the present invention;

[0038] Figure 3 This is a schematic diagram of the gasoline flow rate and hydrogen content prediction model provided by the present invention;

[0039] Figure 4 It is a structural schematic diagram of the crude oil processing control device provided by the present invention;

[0040] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0042] Figure 1 The flow chart of the crude oil processing control method provided by the present invention is as follows: Figure 1 As shown, the method includes:

[0043] Step 110: Obtain the initial control parameters of the crude oil processing system under the current working conditions.

[0044] Specifically, the crude oil processing system in the embodiments of the present invention includes a catalytic cracking unit and a hydrogenation unit located upstream of the catalytic cracking unit. The crude oil used for refining can be either wax oil or residual oil. The hydrogenation unit is used to increase the hydrogen content in the crude oil. The catalytic cracking unit is used to perform a catalytic cracking reaction on the catalytically hydrogenated crude oil to separate various products.

[0045] The current working condition is the current working state of the oil refining. The working conditions can be divided according to the processed raw oil, reaction temperature, reaction pressure, etc.

[0046] Control parameters correspond to operating conditions and are used to control the operating status of the catalytic cracking unit and hydrogenation unit. These parameters include the operating parameters of the catalytic cracking unit and the hydrogenation depth of the hydrogenation unit. For example, for a catalytic cracking unit, the control parameters include the unit's operating parameters, such as reaction temperature, reaction pressure, and reactant residence time. Furthermore, control parameters may include analytical data for the feedstock and products, such as density, distillation range, sulfur content, nitrogen content, and hydrogen content. For a hydrogenation unit, the control parameter may be the hydrogenation depth of the feedstock.

[0047] Initial control parameters are the initial values ​​of various parameters that control the crude oil processing system when it enters the current operating state. The initial control parameters can be initial parameters determined based on the operator's operating experience or can be the default parameters of the crude oil processing system.

[0048] Step 120, based on the initial control parameters and the generated product prediction model, determine the generated product prediction result of the current operating condition; wherein the generated product prediction result includes at least one of the low carbon hydrocarbon predicted flow rate, the low carbon hydrocarbon predicted hydrogen content, the liquid oil predicted flow rate and the liquid oil predicted hydrogen content; the generated product prediction model includes at least one of the low carbon hydrocarbon flow rate prediction model, the low carbon hydrocarbon hydrogen content prediction model, the liquid oil flow rate prediction model and the liquid oil hydrogen content prediction model.

[0049] Specifically, the product prediction results are the multiple products generated after the catalytic cracking reaction, as well as the predicted flow rate and predicted hydrogen content of each product. For example, for wax oil, after the catalytic cracking reaction, it generates products such as dry gas, liquefied gas, gasoline, light cycle oil, slurry oil and coke. The product prediction results are the predicted flow rate and predicted hydrogen content of each product. The predicted flow rate is the predicted value of the flow rate of a certain product generated by the catalytic cracking unit, which can be expressed in tons per hour (t / h) and is used to measure the output of the product. The predicted hydrogen content is the predicted value of the mass ratio of the hydrogen element in a certain product generated by the catalytic cracking unit, which can be expressed in percentage (%) and is used to measure the product quality of the product.

[0050] The generated product prediction model is a model used to predict the distribution results of various products generated after the catalytic cracking reaction of the crude oil, and can be obtained using a data-driven method.

[0051] The products generated from crude oil are relatively complex and can include dry gas, liquefied gas, gasoline, light cycle oil, slurry oil, and coke. These products can be divided into low-carbon hydrocarbons and liquid oil. Low-carbon hydrocarbons include dry gas and liquefied gas, while liquid oil includes gasoline, light cycle oil, and slurry oil.

[0052] Therefore, a data-driven approach is adopted to collect the property parameters of crude oil under different working conditions, the control parameters of the crude oil processing system, and the actual flow rate and actual hydrogen content of low-carbon hydrocarbons and liquid oil in the catalytic cracking process of crude oil. After training the initial model, a product prediction model is obtained.

[0053] According to different modeling objects, the generated product prediction models may include a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model.

[0054] Step 130 : Determine target control parameters for the current operating condition based on preset optimization conditions and generated product prediction results.

[0055] Specifically, the preset optimization conditions are used to optimize the prediction results of generated products in the catalytic cracking reaction.

[0056] According to the preset optimization conditions, optimization is performed on the basis of the generated product prediction results. The optimization process can be to adjust the initial control parameters, change the flow rate and / or hydrogen content of each product to meet the preset optimization conditions, obtain the generated product optimization results, and use the control parameters corresponding to the generated product optimization results as the target control parameters.

[0057] Step 140: Control the crude oil processing system based on the target control parameters.

[0058] Specifically, the target control parameters are determined based on the optimization results of the generated products of the crude oil processing system. The crude oil processing system can be controlled by using the target control parameters.

[0059] When target control parameters are used to control the catalytic cracking unit and hydrogenation unit in the crude oil processing system, the hydrogenation unit and the catalytic cracking unit can achieve upstream and downstream coordination, so that when the hydrogenated crude oil output by the hydrogenation unit enters the catalytic cracking unit for reaction, it can not only obtain the ideal product optimization results according to the requirements of the preset optimization conditions, but also avoid adding excessive hydrogen elements to cause waste.

[0060] The crude oil processing control method provided by the embodiment of the present invention determines the generated product prediction results of the crude oil processing system under the current working conditions by generating a product prediction model, and determines the target control parameters of the current working conditions according to preset optimization conditions and the generated product prediction results, thereby controlling the crude oil processing system. The generated product prediction model includes a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model and a liquid oil hydrogen content prediction model, which can accurately predict and optimize the generated products of the crude oil without establishing a complex mechanism model, thereby improving the accuracy of the generated product prediction results and the optimization results, and reducing the hydrogen consumption in the refining process while ensuring the yield of the target product.

[0061] Based on the above embodiment, generating a product prediction model is determined based on the following steps:

[0062] Determine the initial model;

[0063] Based on the historical control parameters and historical product generation results under multiple working conditions, the initial model is trained to obtain a product generation prediction model;

[0064] The historical generated product results include at least one of the historical flow rate of low-carbon hydrocarbons, the historical hydrogen content of low-carbon hydrocarbons, the historical flow rate of liquid oil, and the historical hydrogen content of liquid oil.

[0065] Specifically, the operating conditions are determined based on at least one of the type of feedstock oil, the reaction temperature of the catalytic cracking unit, and the reaction pressure of the catalytic cracking unit.

[0066] Historical flow rates are measured flow rates, and historical hydrogen contents are measured hydrogen contents. Light hydrocarbon historical flow rates include the historical flow rates of dry gas and liquefied petroleum gas, while historical light hydrocarbon hydrogen contents include the historical hydrogen contents of dry gas and liquefied petroleum gas. Liquid oil historical flow rates include the historical flow rates of gasoline, light cycle oil, and slurry oil, while historical liquid oil hydrogen contents include the historical hydrogen contents of gasoline, light cycle oil, and slurry oil.

[0067] The generated product prediction models are all established using a data-driven approach. The initial model can be selected from various neural network learning models, and the embodiment of the present invention does not specifically limit the type of the initial model.

[0068] For example, for the low-carbon hydrocarbon flow prediction model and the low-carbon hydrocarbon hydrogen content prediction model, the modeling method may include:

[0069] Step 1: Establish a data warehouse module. This module can complete the establishment of a database for the historical working conditions and operation data of the crude oil processing system (from the processing control system), the physical and chemical properties analysis reports of crude oil and major products, and the technical monthly reports, realizing the unified storage, management and access of large-scale data.

[0070] Step 2: Establish a feature selection module. This module extracts key feature variables for modeling based on the chemical reaction mechanisms associated with the crude oil processing process, on-site operator experience, and the plant's primary control loops. If modeling accuracy does not meet requirements, a data-driven feature selection module is designed to select supplementary feature variables from relevant operating units.

[0071] Step 3: Establish a model training module. Use hydrogen content samples obtained from routine monitoring reports of catalytic cracking dry gas and liquefied gas as dependent variables for model training, and construct a low-carbon hydrocarbon hydrogen content prediction model for predicting the hydrogen content of dry gas and liquefied gas.

[0072] Similarly, the flow samples obtained from the dry gas and liquefied gas production reports are used as dependent variables for model training to construct a low-carbon hydrocarbon flow prediction model for predicting the flow of dry gas and liquefied gas.

[0073] Step 4: Establish a model evaluation module. This module implements model parameter optimization and model evaluation. This module can select hyperparameters for the XGBoost model based on cross-validation results and evaluate the model's predictive ability based on its performance on the validation set.

[0074] For another example, for a liquid phase oil hydrogen content prediction model, the modeling method may include:

[0075] Step 1: Through data collection and routine laboratory analysis data screening, quickly establish the calculation formula for hydrogen content of catalytic gasoline, light cycle oil, slurry oil, etc.;

[0076] Step 2: Construct a feature selection module method based on the rapid calculation of the hydrogen content of catalytic cracking liquid oil products to form sample points, which can select characteristic variables and key parameters related to the prediction of the hydrogen content of catalytic cracking liquid oil products, including feedstock properties, catalytic cracking liquid oil properties, and unit operating parameters;

[0077] Step 3: Hydrogen content model training;

[0078] Step 4: The parameter optimization and model evaluation module can select the hyperparameters of the GBDT model based on the cross-validation results, and can evaluate the predictive ability of the model based on the performance of the model on the validation set.

[0079] The modeling method of the liquid oil flow prediction model is similar to that of the low-carbon hydrocarbon flow prediction model and will not be described in detail here.

[0080] Based on any of the above embodiments, step 140 includes:

[0081] Determining target operating parameters of the catalytic cracking unit and target hydrogenation depth of the hydrogenation unit based on target control parameters;

[0082] Controlling the catalytic cracking unit based on target operating parameters and controlling the hydrogenation unit based on target hydrogenation depth;

[0083] Among them, the crude oil processing system includes a catalytic cracking unit and a hydrogenation unit.

[0084] Specifically, the control parameters may include the operating parameters of the catalytic cracking unit and the hydrogenation depth of the hydrogenation unit. Operating parameters include the reaction temperature, reaction pressure, and reactant residence time in the catalytic cracking unit. The reaction pressure can be selected from the outlet pressure of the unit. The hydrogenation depth refers to the completeness of the hydrotreating process, which converts unsaturated bonds in the feedstock into saturated bonds under the action of hydrogen and catalyst.

[0085] Target control parameters include the target operating parameters for the catalytic cracking unit and the target hydrogenation depth for the hydrotreating unit. Based on the target control parameters corresponding to the product optimization results under the current operating conditions, the catalytic cracking unit and the hydrotreating unit can be coordinated and controlled simultaneously, ensuring that the hydrotreated feedstock meets the requirements of the catalytic cracking reaction while avoiding the addition of excessive hydrogen and reducing hydrogen consumption.

[0086] Based on any of the above embodiments, the preset optimization conditions are determined based on the flow rate and hydrogen content of each product in the generated product prediction results.

[0087] Specifically, the preset optimization condition can be determined based on the flow rate or hydrogen content of each product in the generated product prediction results. For example, the preset optimization condition can be that the sum of the flow rates of liquefied gas and gasoline is the largest among the flow rates of each product, and / or that the sum of the hydrogen content of dry gas and coke is the smallest among the hydrogen content of each product. For another example, the preset optimization condition can be that the flow rate of one or more products is greater than a preset flow rate threshold.

[0088] Based on any of the above embodiments, step 130 includes:

[0089] Determine the objective function and constraints in the preset optimization conditions based on the flow rate and hydrogen content of each product in the generated product prediction results;

[0090] Based on the objective function, the initial control parameters are adjusted to obtain control parameter adjustment values, and based on the control parameter adjustment values ​​and the generated product prediction model, the generated product optimization result of the current working condition is determined;

[0091] If the generated product optimization result meets the constraint conditions, the control parameter adjustment value corresponding to the generated product optimization result will be used as the target control parameter of the current working condition.

[0092] Specifically, because the oil refining process generates multiple products, each with different utility values, the predicted product generation results can be optimized by setting an objective function and preset products. The first preset product is a product optimized for the target flow rate, for example, the first preset product may include liquefied petroleum gas and gasoline. The second preset product is a product optimized for hydrogen content, for example, the second preset product may include dry gas and coke.

[0093] If the preset optimization conditions include the objective function of maximizing the output of liquefied gas and gasoline and minimizing the hydrogen content in dry gas and coke, it can be expressed as follows:

[0094] miny1=(F 干气 x 干气,H +F 焦炭 x 焦炭,H ) / (F 原料油 x 原料,H )

[0095] maxy2=(F 液化气 +F 汽油 ) / F 原料油

[0096] In the formula, y1 is the objective function 1, y2 is the objective function 2, and x 原料油,H is the mass fraction of hydrogen in the feed oil, x 干气,H is the mass fraction of hydrogen in dry gas, x 焦炭,H is the mass fraction of hydrogen in coke, F 原料油 is the flow rate of crude oil, F 液化气 is the flow rate of liquefied gas, F 汽油 is the gasoline flow rate, F 干气 is the flow rate of dry gas, F 焦炭 is the flow rate of coke.

[0097] In addition, the preset optimization conditions may also include constraints, which can be determined based on the flow rate and hydrogen content of each product in the generated product prediction results. For example, the flow rate of each product must meet the mass conservation constraint, or the flow rate of a certain product must be greater than a preset flow threshold.

[0098] According to the objective function, the initial control parameters are adjusted to obtain the control parameter adjustment values, and the generated product optimization results of the current working conditions are determined based on the control parameter adjustment values ​​and the generated product prediction model.

[0099] By adjusting the initial control parameters, a multi-objective optimization mathematical model of the device can be established, an optimization algorithm can be called, and the optimization algorithm can be associated with the generated product prediction model. The optimization algorithm can include fuzzy optimization algorithm, multi-objective queue competition algorithm, genetic algorithm, neural network algorithm, etc.

[0100] If the generated product optimization result of the current working condition meets the constraint conditions, the control parameter adjustment value corresponding to the generated product optimization result is used as the target control parameter of the current working condition.

[0101] If the product generation optimization result of the current working condition does not meet the constraint conditions, it will be adjusted again according to the product generation optimization result of the current working condition and the objective function until the product generation optimization result that meets the constraint conditions is obtained, and the corresponding control parameter adjustment value will be used as the target control parameter of the current working condition.

[0102] Based on any of the above embodiments, the initial control parameters include raw material property parameters, initial operating parameters and initial value of hydrogenation depth, and the initial operating parameters include initial value of reaction temperature and initial value of reaction pressure in the catalytic cracking unit, as well as initial value of residence time of the raw oil in the catalytic cracking unit.

[0103] Specifically, the raw material property parameters are the physical or chemical properties of the raw material itself, such as density, residual carbon value, viscosity, and element mass fraction.

[0104] Initial control parameters include initial operating parameters, which are used to operate the catalytic cracking unit and provide a reaction environment for the catalytic cracking reaction. These initial operating parameters specifically include the initial values ​​of the reaction temperature and pressure in the catalytic cracking unit, as well as the initial value of the residence time of the feedstock in the catalytic cracking unit.

[0105] The initial value of the hydrogenation depth is the initial value of the hydrogenation depth set in the hydrogenation unit when entering the current operating conditions.

[0106] Based on any of the above embodiments, an embodiment of the present invention provides a wax oil processing control method, the method comprising:

[0107] Step 1: Collect basic data of the device and operating data corresponding to different working conditions, and establish a basic database.

[0108] The unit includes a hydrogenation unit and a catalytic cracking unit. The catalytic cracking unit is a parallel type with high and low reaction and regeneration. The reaction section adopts the MIP-CGP (clean gasoline production technology for increasing propylene and isomerized alkanes) process technology with an internal riser. The regeneration section adopts a parallel two-vessel regeneration technology. The first regenerator uses incomplete regeneration technology and is equipped with two sets of external heat exchangers. The second regenerator uses complete regeneration technology and is equipped with a regenerated catalyst degassing tank. The flue gases from the first and second regenerators are mixed in the flue and supplemented with air, causing the carbon monoxide to burn. The high-temperature flue gas is heated by the high heat exchanger and, after cooling, is sent to the third-stage cyclone separator.

[0109] Historical data was collated and categorized into several operating conditions based on the unit's feedstock processing volume, slag blending amount, recycled oil volume, reactor outlet temperature, and reactor outlet pressure. Taking one of these operating conditions as the current operating condition, the relevant key parameters of the data are presented. The key feedstock parameters, catalyst parameters, and operating parameters for this condition are shown in Tables 1, 2, and 3, respectively.

[0110] Table 1 Main parameters of crude oil

[0111] project Numerical project Numerical <![CDATA[Density (20 °C), kg / m 3 > 903.7 Distillation range, ℃ Residual carbon value, % 4.08 Initial distillation point 180.9 <![CDATA[Viscosity (80 °C), mm 2 / s]]> 34.32 5％ 271.5 Relative molecular mass 509 10％ 357.5 Element mass fraction, % 20％ 412.9 C 86.78 30％ 446.6 H 12.91 40％ 494.9 S 0.28 50％ 540.4 N 0.18 60％ 577.8

[0112] Table 2 Main parameters of catalyst

[0113]

[0114]

[0115] Table 3 Operating parameters

[0116]

[0117]

[0118] Step 2: Construct a data-driven mathematical model for predicting the product flow and hydrogen content of the catalytic cracking unit. Establish mathematical models for predicting the flow and hydrogen content of low-carbon hydrocarbons based on catalytic dry gas and liquefied gas, and mathematical models for predicting the flow and hydrogen content of liquid oil products based on gasoline, light cycle oil, and slurry oil.

[0119] Figure 2 This is a schematic diagram of the modeling of the liquefied gas flow rate and hydrogen content prediction model provided by the present invention, as shown in Figure 2 As shown in FIG, a mathematical model for predicting low-carbon hydrocarbon flow and hydrogen content based on catalytic liquefied petroleum gas is established, which specifically includes: a data warehouse module, a data extraction module, a feature selection module, a model training module, and a model evaluation module.

[0120] Take the hydrogen content prediction model as an example. Among them, the data warehouse module is used to build a data warehouse, that is, to extract historical raw material property parameters and historical operation parameters from the factory principle laboratory physical properties and engineering DCS monitoring data, and after data cleaning, establish corresponding MySQL databases and data tables according to each production unit, and implement a CSV cache mechanism. Then, the feature selection module performs feature selection on the parameters in the data warehouse, selects key parameters that affect the hydrogen content, and calculates the liquefied gas hydrogen content corresponding to the key parameters based on the liquefied gas gas chromatography data through the data extraction module, so that the model training module can obtain a liquefied gas hydrogen content prediction model based on the key parameters and the liquefied gas hydrogen content corresponding to the key parameters. After obtaining the liquefied gas hydrogen content prediction model, the model evaluation module can perform hydrogen content prediction and result evaluation based on the liquefied gas hydrogen content prediction model.

[0121] Figure 3 This is a modeling diagram of the gasoline flow and hydrogen content prediction model provided by the present invention, as shown in FIG. Figure 3 As shown in Figure 1, a mathematical model for predicting the liquid phase oil flow rate and hydrogen content is established for gasoline. The modeling process is similar to that for liquefied gas and will not be repeated here.

[0122] Step 3: Establish a multi-objective optimization mathematical model for the generated products, with the optimization objectives being to maximize the output of liquefied gas and gasoline and minimize the hydrogen content in dry gas and coke.

[0123] A multi-objective optimization mathematical model for the products generated by a catalytic cracking unit is established based on optimal hydrogen distribution and maximum yield of target products.

[0124] Among them, the objective function is:

[0125] miny1=(F 干气 x 干气,H +F 焦炭 x 焦炭,H ) / (F 原料油 x 原料,H )

[0126] maxy2=(F 液化气 +F 汽油 ) / F 原料油

[0127] When the optimization goal is to minimize the hydrogen content in the raw material, the objective function can also be:

[0128] miny1=x 原料,H

[0129] The constraints are:

[0130] (1) Balance constraints

[0131] F 原料油 =F干气 +F 液化气 +F 汽油 +F 轻循环油 +F 焦炭

[0132] F 原料油 x 原料油,H

[0133] =F 干气 x 干气,H +F 液化气 x 液化气,H +F 汽油 x 汽油,H

[0134] +F 轻循环油 x 轻循环油,H +F 油浆 x 油浆,H +F 焦炭 x 焦炭,H

[0135] (2) Other constraints

[0136] Liquefied gas product flow rate ≥47t / h;

[0137] Gasoline product flow rate ≥110t / h;

[0138] C3+ content constraint in dry gas, with the constraint condition being that the volume fraction of C3+ light hydrocarbons is ≤ 3%;

[0139] The C2 content in the liquefied gas is constrained, with the C2 volume fraction being ≤ 0.4%;

[0140] The C5 content in liquefied gas is constrained, with the C5 volume fraction being ≤1%;

[0141] Gasoline ASTM D86 dry point constraint, constraint conditions are 200~204℃;

[0142] Crude oil flow restriction, 160t / h≤F 原料油 ≤250t / h;

[0143] The residual carbon CT of the crude oil is limited to 3.0%≤CT≤8.0%;

[0144] Feed oil hydrogen content constraint, 11.0% ≤ x 原料油,H ≤14.0%;

[0145] Reactor outlet temperature constraint, 480℃≤t 反应器出口 ≤520℃;

[0146] Reaction pressure constraint, 0.25MPa≤P 反应 ≤0.40MPa;

[0147] Stable gasoline circulation rate, 25-45t / h;

[0148] Reabsorbent flow rate of reabsorption tower, 30-60t / h;

[0149] Reabsorbent temperature in reabsorption tower: 30-40℃;

[0150] Product hydrogen content constraints:

[0151] a. The hydrogen content in dry gas and coke is less than that in liquid oil products.

[0152] F 干气 x 干气,H +F 焦炭 x 焦炭,H

[0153] <F 液化气 x 液化气,H +F 汽油 x 汽油,H +F 轻循环油 x 轻循环油,H

[0154] +F 油浆 x 油浆,H

[0155] b. The hydrogen content in liquefied gas is greater than that in slurry oil.

[0156] F 液化气 x 液化气,H >F 油浆 x 油浆,H

[0157] Where: y1 is objective function 1; y2 is objective function 2; x 原料油,H is the mass fraction of hydrogen in the feed oil, F 原料油 is the flow rate of crude oil; F 干气 is the dry gas flow rate, t / h; x 干气,H is the mass fraction of hydrogen in dry gas, %; F 液化气 is the liquefied gas flow rate, t / h; x 液化气,H is the mass fraction of hydrogen in liquefied gas, %; F 汽油 is the gasoline flow rate, t / h; x 汽油,H is the mass fraction of hydrogen in gasoline, %; F 轻循环油 is the light circulating oil flow rate, t / h; x 轻循环油,H is the mass fraction of hydrogen in light cycle oil, %; F 油浆 is the oil slurry flow rate, t / h; x 油浆,H is the mass fraction of hydrogen in the oil slurry, %; F 焦炭 is the coke flow rate, t / h; x 焦炭 , His the mass fraction of hydrogen in coke, %; CT is the residual carbon in the feed oil, %; t 反应器出口 is the outlet temperature of reactor (No. 1, No. 2), ℃; P 反应 is the reaction pressure, MPa.

[0158] Step 4: Obtain the optimal generated products under the current operating conditions and the target control parameters. The optimal generated products under the current operating conditions are shown in Table 4. Under the premise of meeting the unit's production mission (liquefied gas + gasoline), a multi-objective optimization model for the distribution of catalytic cracking products was solved to obtain a product distribution and feedstock hydrogen content requirement plan: Under the optimized unit operation, reducing the hydrogen content of the catalytic cracking feed from 12.91% to 12.12% will not affect the unit's production mission, and the product quality is qualified. The reduction in hydrogen content in the catalytic cracking feed can further reduce the hydrogenation depth of the upstream wax oil hydrogenation unit, reducing hydrogen consumption by 15,800 tons / year.

[0159] Table 4 Optimization solution calculation results

[0160]

[0161]

[0162] Based on any of the above embodiments, Figure 4 This is a schematic diagram of the structure of the crude oil processing control device provided by the present invention. Figure 4 As shown, the device includes:

[0163] An acquisition unit 410 is used to acquire initial control parameters of the crude oil processing system under current operating conditions;

[0164] The prediction unit 420 is used to determine the prediction result of the generated product under the current working condition based on the initial control parameters and the generated product prediction model;

[0165] The optimization unit 430 is used to determine the target control parameters of the current working condition based on the preset optimization conditions and the generated product prediction results;

[0166] A control unit 440 is used to control the crude oil processing system based on target control parameters;

[0167] The generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model.

[0168] The crude oil processing control device provided by the embodiment of the present invention determines the generated product prediction results of the crude oil processing system under the current working conditions by generating a product prediction model, and determines the target control parameters of the current working conditions based on preset optimization conditions and the generated product prediction results, thereby controlling the crude oil processing system. The generated product prediction model includes a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model and a liquid oil hydrogen content prediction model, which can accurately predict and optimize the generated products of the crude oil without establishing a complex mechanism model, thereby improving the accuracy of the generated product prediction results and the optimization results, and reducing the hydrogen consumption in the refining process while ensuring the yield of the target product.

[0169] Based on any of the above embodiments, the device further includes:

[0170] A model determination unit, used for determining an initial model;

[0171] Based on the historical control parameters and historical product generation results under multiple working conditions, the initial model is trained to obtain a product generation prediction model;

[0172] The historical generated product results include at least one of the historical flow rate of low-carbon hydrocarbons, the historical hydrogen content of low-carbon hydrocarbons, the historical flow rate of liquid oil, and the historical hydrogen content of liquid oil.

[0173] Based on any of the above embodiments, the control unit is configured to:

[0174] Determining target operating parameters of the catalytic cracking unit and target hydrogenation depth of the hydrogenation unit based on target control parameters;

[0175] Controlling the catalytic cracking unit based on target operating parameters and controlling the hydrogenation unit based on target hydrogenation depth;

[0176] Among them, the crude oil processing system includes a catalytic cracking unit and a hydrogenation unit.

[0177] Based on any of the above embodiments, the preset optimization conditions are determined based on the flow rate and hydrogen content of each product in the generated product prediction results.

[0178] Based on any of the above embodiments, the optimization unit is configured to:

[0179] Determine the objective function and constraints in the preset optimization conditions based on the flow rate and hydrogen content of each product in the generated product prediction results;

[0180] Based on the objective function, the initial control parameters are adjusted to obtain control parameter adjustment values, and based on the control parameter adjustment values ​​and the generated product prediction model, the generated product optimization result of the current working condition is determined;

[0181] If the generated product optimization result meets the constraint conditions, the control parameter adjustment value corresponding to the generated product optimization result will be used as the target control parameter of the current working condition.

[0182] Based on any of the above embodiments, the initial control parameters include raw material property parameters, initial operating parameters and initial value of hydrogenation depth, and the initial operating parameters include initial value of reaction temperature and initial value of reaction pressure in the catalytic cracking unit, as well as initial value of residence time of the raw oil in the catalytic cracking unit.

[0183] Based on any of the above embodiments, Figure 5 A schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5 As shown, the electronic device may include: a processor (Processor) 510, a communication interface (Communications Interface) 520, a memory (Memory) 530 and a communication bus (Communications Bus) 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 may call the logic commands in the memory 530 to execute the following method:

[0184] Obtain initial control parameters of the crude oil processing system under the current operating conditions; determine the generated product prediction results of the current operating conditions based on the initial control parameters and the generated product prediction model; determine the target control parameters of the current operating conditions based on the preset optimization conditions and the generated product prediction results; control the crude oil processing system based on the target control parameters; wherein the generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model.

[0185] In addition, the logical commands in the above-mentioned memory 530 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several commands to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0186] The processor in the electronic device provided by the embodiment of the present invention can call the logic instructions in the memory to implement the above method. Its specific implementation method is consistent with the implementation method of the above method and can achieve the same beneficial effects, which will not be repeated here.

[0187] An embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method provided in each of the above embodiments is implemented, for example, including:

[0188] Obtain initial control parameters of the crude oil processing system under the current operating conditions; determine the generated product prediction results of the current operating conditions based on the initial control parameters and the generated product prediction model; determine the target control parameters of the current operating conditions based on the preset optimization conditions and the generated product prediction results; control the crude oil processing system based on the target control parameters; wherein the generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model.

[0189] When the computer program stored on the non-transitory computer-readable storage medium provided by the embodiment of the present invention is executed, the above method is implemented. Its specific implementation method is consistent with the implementation method of the aforementioned method and can achieve the same beneficial effects, which will not be repeated here.

[0190] An embodiment of the present invention provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0191] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0192] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of commands for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiment.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A crude oil processing control method, characterized in that: include: Obtaining initial control parameters of the crude oil processing system under current operating conditions; Determining a prediction result of a generated product under the current operating condition based on the initial control parameters and a generated product prediction model; Determining target control parameters for the current operating condition based on preset optimization conditions and the generated product prediction result; controlling the crude oil processing system based on the target control parameter; The generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model; The preset optimization conditions are determined based on the flow rate and hydrogen content of each product in the generated product prediction results; The determining of the target control parameters of the current operating condition based on the preset optimization conditions and the generated product prediction results includes: Determining the objective function and constraint conditions in the preset optimization conditions based on the flow rate and hydrogen content of each product in the generated product prediction results; Based on the objective function, adjusting the initial control parameter to obtain a control parameter adjustment value, and determining a generated product optimization result of the current operating condition based on the control parameter adjustment value and the generated product prediction model; If the generated product optimization result satisfies the constraint condition, the control parameter adjustment value corresponding to the generated product optimization result is used as the target control parameter of the current working condition.

2. The crude oil processing control method according to claim 1, characterized in that: The generated product prediction model is determined based on the following steps: Determine the initial model; Training the initial model based on historical control parameters and historical product generation results under multiple operating conditions to obtain the product generation prediction model; The historical product generation results include at least one of the historical flow rate of low-carbon hydrocarbons, the historical hydrogen content of low-carbon hydrocarbons, the historical flow rate of liquid oil and the historical hydrogen content of liquid oil.

3. The crude oil processing control method according to claim 1, characterized in that: The controlling of the crude oil processing system based on the target control parameter includes: Determining target operating parameters of the catalytic cracking unit and target hydrogenation depth of the hydrogenation unit based on the target control parameters; controlling the catalytic cracking unit based on the target operating parameters, and controlling the hydrogenation unit based on the target hydrogenation depth; Wherein, the crude oil processing system includes a catalytic cracking unit and a hydrogenation unit.

4. The crude oil processing control method according to any one of claims 1 to 3, characterized in that: The initial control parameters include raw material property parameters, initial operating parameters and initial value of hydrogenation depth. The initial operating parameters include initial value of reaction temperature and initial value of reaction pressure in the catalytic cracking unit, and initial value of residence time of raw oil in the catalytic cracking unit.

5. A crude oil processing control device, characterized in that: include: An acquisition unit, used to acquire initial control parameters of the crude oil processing system under current working conditions; A prediction unit, configured to determine a prediction result of a generated product under the current operating condition based on the initial control parameters and a generated product prediction model; An optimization unit, configured to determine target control parameters for the current operating condition based on preset optimization conditions and the generated product prediction result; a control unit, configured to control the crude oil processing system based on the target control parameters; The generated product prediction model includes at least one of a low-carbon hydrocarbon flow prediction model, a low-carbon hydrocarbon hydrogen content prediction model, a liquid oil flow prediction model, and a liquid oil hydrogen content prediction model; The preset optimization conditions are determined based on the flow rate and hydrogen content of each product in the generated product prediction results; The determining of the target control parameters of the current operating condition based on the preset optimization conditions and the generated product prediction results includes: Determining the objective function and constraint conditions in the preset optimization conditions based on the flow rate and hydrogen content of each product in the generated product prediction results; Based on the objective function, adjusting the initial control parameter to obtain a control parameter adjustment value, and determining a generated product optimization result of the current operating condition based on the control parameter adjustment value and the generated product prediction model; If the generated product optimization result satisfies the constraint condition, the control parameter adjustment value corresponding to the generated product optimization result is used as the target control parameter of the current working condition.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the crude oil processing control method as described in any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the crude oil processing control method as described in any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the crude oil processing control method as described in any one of claims 1 to 4 are implemented.

Images