Petrochemical reactor device molecular level model self-tuning method and related equipment

Abstract

The invention provides a petrochemical reactor device molecular level model self-tuning method and related equipment, the petrochemical reactor device molecular level model self-tuning method comprises the following steps: acquiring on-site working condition data and test components, determining simulation data of a target component in the recontact tank bottom oil based on the field working condition data and the test component; acquiring test data of the target component, and determining whether self-tuning is needed or not based on the test data and the simulation data; and if necessary, optimizing the reaction rate in a molecular-level reactor model based on the test data, the field working condition data and the test components to obtain a target molecular-level reaction rate, and performing self-tuning based on the target molecular-level reaction rate. According to the method, the reaction rate is optimized, so that rapid and real-time self-tuning is realized.

Description

Technical Field

[0001] The invention relates to the technical field of chemical industry, and in particular to a molecular level model self-tuning method for a petrochemical reactor device and related equipment. Background Art

[0002] Petrochemical plants convert raw materials such as naphtha into high-octane gasoline components and other valuable chemicals through catalytic reactions. This process involves complex chemical reactions and physical separations, so precise control and optimization are required to ensure the best production results and economy. The petrochemical plant simulation and optimization system simulates the petrochemical plant process according to the input control parameters, predicts the product results, and avoids risks such as material waste, long debugging time, and substandard product quality caused by manual control. It can also provide the optimal operation plan based on production indicators to help workshop operators optimize petrochemical plants, reduce enterprise costs and improve energy efficiency.

[0003] The existing scheme for optimizing petrochemical plants is to obtain a set of parameters based on production-related data, and then adjust the operating parameters. This set of parameters does not need to be changed for a period of time. When the field operating data changes, another set of parameters needs to be obtained to adjust the operating parameters to ensure that the simulation results are consistent with the actual results. However, production-related data will change over time or batch by batch, and the existing optimization scheme is difficult to quickly adapt to these changes. Summary of the invention

[0004] The present invention provides a molecular level model self-tuning method and related equipment for a petrochemical reactor device, which are used to solve the defects in the prior art, achieve rapid adaptation to changes in production-related data, and achieve rapid and real-time self-tuning.

[0005] The present invention provides a molecular level model self-tuning method for a petrochemical reactor device, comprising: Acquiring on-site operating data and assay components, and determining simulation data of target components in the bottom oil of the re-contact tank based on the on-site operating data and the assay components; Acquiring assay data of the target component, and determining whether self-tuning is required based on the assay data and the simulation data; If necessary, based on the assay data, the field operating data and the assay components, the reaction rate in the molecular-level reactor model is optimized to obtain a target molecular-level reaction rate, and self-tuning is performed based on the target molecular-level reaction rate.

[0006] According to a petrochemical reactor device molecular level model self-tuning method provided by the present invention, the reaction rate in the molecular level reactor model is optimized based on the test data, the field operating data and the test components to obtain a target molecular level reaction rate, including: determining an optimization target based on the assay data; Based on the optimization target, the test data, the on-site operating data and the test components, the reaction rate is optimized by sequential quadratic programming to obtain the target molecular-level reaction rate.

[0007] According to a molecular-level model self-tuning method for a petrochemical reactor device provided by the present invention, the reaction rate is optimized by a sequential quadratic programming method based on the optimization target, the test data, the field operating data and the test components to obtain the target molecular-level reaction rate, including: Determining an initial reaction rate based on the field operating data and the assay data; constructing constraints on the reaction rate; Constructing an objective function based on the optimization target and the reaction rate; Based on the initial reaction rate and the objective function, the reaction rate is iteratively optimized within the constraints by using the sequential quadratic programming method until a convergence condition is reached, thereby obtaining the target molecular-level reaction rate of the optimal solution.

[0008] According to a molecular-level model self-tuning method for a petrochemical reactor device provided by the present invention, the convergence condition includes that a change in an objective function value obtained during two adjacent optimization iterations is lower than a preset threshold.

[0009] According to a molecular-level model self-tuning method for a petrochemical reactor device provided by the present invention, the field operating data includes DCS data, the assay components include reforming feed components; the simulation data for determining the target components in the bottom oil of the re-contact tank based on the field operating data and the assay components includes: Inputting the DCS data and the reforming feed components into a petrochemical plant model for calculation to obtain corresponding calculation results; Simulation data of the target component is determined based on the calculation results.

[0010] According to a molecular level model self-tuning method for a petrochemical reactor device provided by the present invention, the target components include benzene, toluene, and xylene; the determining whether self-tuning is required based on the test data and the simulation data includes: Compare the simulation data and the test data for benzene, toluene and xylene respectively to obtain corresponding comparison results; If at least one of the comparison results indicates that the percentage change between the simulation data and the test data is greater than a preset change threshold, it is determined that self-tuning is required.

[0011] According to a method for self-tuning a molecular-level model of a petrochemical reactor device provided by the present invention, after self-tuning based on the target molecular-level reaction rate, the method further comprises: Based on the target molecular-level reaction rate, the self-tuning result is verified.

[0012] The present invention also provides a molecular level model self-tuning system for a petrochemical reactor device, comprising the following modules: The present invention also provides 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 method for self-tuning the molecular-level model of a petrochemical reactor device as described in any one of the above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for self-tuning a molecular-level model of a petrochemical reactor device as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for self-tuning a molecular-level model of a petrochemical reactor device as described in any one of the above is implemented.

[0015] The present invention provides a molecular-level model self-tuning method and related equipment for a petrochemical reactor device. The present invention determines simulation data of a target component in the bottom oil of a re-contact tank based on field operating data and assay components, determines whether self-tuning is required based on the assay data and simulation data of the target component, and when self-tuning is required, optimizes the reaction rate in the molecular-level reactor model based on the assay data, field operating data, and assay components to obtain a target molecular-level reaction rate, and implements self-tuning based on the target molecular-level reaction rate. Through the technical solution provided by the present application, when production conditions, environment, equipment status, etc. change, the parameters of the system also change accordingly, and the present invention can quickly and accurately track these changes, thereby implementing rapid and real-time self-tuning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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 creative work.

[0017] Figure 1 The present invention is a schematic flow chart of a molecular level model self-tuning method for a petrochemical reactor device.

[0018] Figure 2 It is a structural schematic diagram of a molecular level model self-tuning system for a petrochemical reactor device provided by the present invention.

[0019] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Combine the following Figure 1-Figure 3 The present invention describes the molecular level model self-tuning method and related equipment of a petrochemical reactor device.

[0022] Figure 1 FIG. 1 is a flow chart showing a method for self-tuning a molecular model of a petrochemical reactor device according to an exemplary embodiment. Figure 1 As shown, in an exemplary embodiment, the molecular level model self-tuning method of a petrochemical reactor device includes steps 110 to 130, which are described in detail as follows.

[0023] Step 110, obtaining on-site operating data and assay components, and determining simulation data of target components in the re-contact tank bottom oil based on the on-site operating data and the assay components.

[0024] In an embodiment of the present invention, field operating data is obtained, such as DCS (Distributed Control System) data of a petrochemical device model; wherein the DCS data may be production control data and sensor data in a real-time database within the plant area. After the DCS data is obtained, the DCS data may be classified by bit number, and the bit number type may include pressure, temperature, mass flow, etc. After the DCS data is classified by bit number, the DCS data to be processed corresponding to each bit number type may be obtained, as shown in Table 1 below.

[0025] The test components include the reforming feed components tested by LIMS (Laboratory Information Management System), and the reforming feed components refer to the raw material components for catalytic reforming. The reforming feed components include the reforming feed molar fraction and the reforming feed mass fraction. The molar fraction refers to the proportion of each molecular level in the material. The mass fraction refers to the mass proportion of the components in the material, such as circulating hydrogen. Circulating hydrogen refers to the hydrogen that does not fully participate in the reaction in the molecular-level reactor model, and is recycled after purification and pressurization.

[0026] The molecular-level petrochemical process is simulated based on the field operating data and the test components. Taking the reforming reaction as an example, the reforming reaction product enters the separator tank after heat exchange and cooling for gas-liquid separation. The liquid at the bottom of the separator tank (i.e., the bottom oil of the re-contact tank) is pumped into the re-contact system. In the re-contact tank, the bottom oil of the re-contact tank is mixed with the gas from the top of the separator tank, and the gas-liquid separation is performed again to determine the simulation data of the target components in the bottom oil of the re-contact tank.

[0027] Step 120, obtaining the test data of the target component, and determining whether self-tuning is required based on the test data and the simulation data.

[0028] In an embodiment of the present invention, the test data of the target component is obtained, and the test data is the data obtained by actually testing the target component in the laboratory. Based on the test data and the simulation data, it is determined whether self-tuning is required, that is, when the test data and the simulation data are inconsistent, self-tuning is required.

[0029] Step 130, if necessary, based on the test data, the field operating data and the test components, the reaction rate in the molecular-level reactor model is optimized to obtain a target molecular-level reaction rate, and self-tuning is performed based on the target molecular-level reaction rate.

[0030] In the embodiment of the present invention, when self-tuning is required, the reaction rate in the molecular-level reactor model is optimized based on the test data, the field operating data and the test components to obtain the target molecular-level reaction rate, and then self-tuning is performed based on the target molecular-level reaction rate. The molecular-level reactor model means that in the process of developing molecular management technology, the raw material characterization and model calculation directly use molecules as the basic unit to calculate the behavior of molecules in separation, reaction and blending processes.

[0031] In the embodiment of the present invention, the simulation data of the target component in the bottom oil of the re-contact tank is determined based on the field working condition data and the assay components, and it is determined whether self-tuning is needed based on the assay data and the simulation data of the target component. When self-tuning is needed, the reaction rate in the molecular-level reactor model is optimized based on the assay data, the field working condition data and the assay components to obtain the target molecular-level reaction rate, and self-tuning is achieved based on the target molecular-level reaction rate. Through the technical solution provided by the present application, molecular-level self-tuning is achieved, continuous and real-time optimization is achieved, and the optimal state of control is maintained in a dynamic environment. With the changes in production conditions, environment, and equipment status, the parameters of the system also change accordingly. The present invention can quickly and accurately track these changes, so that the stability of the system can be guaranteed. In particular, in the face of multivariable, nonlinear, and time-varying systems, the effect of automatic adjustment is better, and the control process is stable. When the process conditions change frequently, the system can automatically adjust to adapt to the changes in conditions and reduce maintenance costs. It also solves the problems of complex field conditions, mutual influence of multi-parameter adjustment, and difficulty in manual adjustment.

[0032] In the process of developing molecular management technology, raw material characterization and model calculation directly use molecules as basic units to calculate the behavior of molecules in separation, reaction and blending processes. Compared with traditional lumped models, the advantage of using molecular management technology is that molecules are the smallest units that maintain chemical and physical properties of substances. The use of molecular composition information is sufficient to distinguish the characteristics of different raw materials. Property prediction methods such as the coordination group contribution method can achieve accurate prediction of product properties and calculate key properties of nonlinear mixtures such as the octane number of gasoline products. Through molecular-level process simulation, seamless connection of different operation unit models can be achieved.

[0033] In an exemplary embodiment of the present invention, the reaction rate in the molecular-level reactor model is optimized based on the test data, the field operating data and the test components to obtain a target molecular-level reaction rate, including: determining an optimization target based on the assay data; Based on the optimization target, the test data, the on-site operating data and the test components, the reaction rate is optimized by sequential quadratic programming to obtain the target molecular-level reaction rate.

[0034] In an embodiment of the present invention, the optimization target can be set to adjust the reaction rate so that the simulation data of the components in the re-contact tank bottom oil are as close as possible to the test data. The components in the re-contact tank bottom oil include toluene, o-xylene, p-xylene and m-xylene, that is, the optimization target is set to the simulation data of the components in the re-contact tank bottom oil.

[0035] The field condition data and the test components are used as calculation inputs, and the reaction rate is optimized using the sequential quadratic programming (SQP) method, and finally the target molecular-level reaction rate closest to the optimization target is obtained. The sequential quadratic programming method is a method that converts the original nonlinear optimization problem into a series of quadratic programming problems for solution.

[0036] In an exemplary embodiment of the present invention, the reaction rate is optimized based on the optimization target, the test data, the field condition data and the test components by sequential quadratic programming to obtain the target molecular-level reaction rate, including: Determining an initial reaction rate based on the field operating data and the assay data; constructing constraints on the reaction rate; Constructing an objective function based on the optimization target and the reaction rate; Based on the initial reaction rate and the objective function, the reaction rate is iteratively optimized within the constraints by using the sequential quadratic programming method until a convergence condition is reached, thereby obtaining the target molecular-level reaction rate of the optimal solution.

[0037] In the embodiment of the present invention, an initial reaction rate R is determined based on DCS data, test components and test data. 0 , and used as initial conditions. Set optimization variables and constraints. The optimization variable is the reaction rate R. By adjusting the reaction rate, the composition of the product is controlled. Constraints include upper and lower limits of the reaction rate and process constraints. The upper and lower limits of the reaction rate are set to a reasonable range of the reaction rate, for example: The process limitations are the material balance, temperature, pressure, hydrogen-to-carbon ratio, etc. of the reactor.

[0038] The SQP method decomposes the problem into a series of quadratic programming (QP) sub-problems and uses the approximate solution of each iteration for optimization. Specifically, the initial reaction rate R is set 0 and convergence conditions, setting the ideal content of each component in the product, which is obtained from the assay data obtained from LIMS.

[0039] Construct the objective function, which is used to calculate the current reaction rate R k Under this condition, calculate the objective function value f(R k ) and the content of each component. Specifically, the objective function can calculate the sum of the squares of the differences in the contents of toluene, o-xylene, p-xylene and m-xylene in the product, and the formula of the objective function is expressed as: ; Where R represents the reaction rate (variable); It represents the content of the i-th component (toluene, o-xylene, p-xylene, m-xylene) in the product at a given reaction rate; Represents the expected value of the i-th component, that is, the corresponding value in the LIMS test data.

[0040] At the current reaction rate R K Linearized reaction condition constraints. At the current reaction rate R K The objective function is approximated quadratically to obtain the quadratic optimization subproblem Q(R): ; Where H is the Hessian matrix of the objective function, is the gradient of the objective function. Solve the subproblem: Use the quadratic programming algorithm to solve the quadratic approximation problem and get the update step size .

[0041] Update reaction rate ,in, is the step size, which is usually determined by line search. The updated objective function value is used to determine whether the convergence condition is met. If not, iterative optimization is continued. Otherwise, the target molecular-level reaction rate of the optimal solution is obtained.

[0042] By optimizing the reaction rate through the SQP method, the toluene, o-xylene, p-xylene and m-xylene contents in the product can be made as close to the target values ​​as possible, thereby achieving precise reaction control.

[0043] In an exemplary embodiment of the present invention, the convergence condition includes that a change in the objective function value obtained during two adjacent optimization iterations is lower than a preset threshold.

[0044] In the embodiment of the present invention, the convergence condition is that the change in the objective function value obtained in two adjacent optimization iterations is lower than a preset threshold, such as less than 10 -6 The convergence condition may also be that the number of iterative optimization reaches a maximum number of iterations.

[0045] In an exemplary embodiment of the present invention, the field operating data includes DCS data, and the assay components include reforming feed components; the simulation data for determining the target components in the re-contact tank bottom oil based on the field operating data and the assay components includes: Inputting the DCS data and the reforming feed components into a petrochemical plant model for calculation to obtain corresponding calculation results; Simulation data of the target component is determined based on the calculation results.

[0046] In the embodiment of the present invention, the petrochemical unit is an important unit in the oil refining and chemical process, which is used to convert low-octane naphtha or light distillate oil into high-octane reformed gasoline through catalytic reforming technology, and produce by-products such as hydrogen and aromatics. The core concept of the petrochemical unit model calculation is to model and analyze the raw material conversion, energy consumption and product distribution of the unit in detail through theories such as material balance, heat balance and reaction kinetics.

[0047] The DCS data and reforming feed components are brought into the petrochemical plant model for calculation, and the simulation data of benzene, toluene and xylene in the bottom oil of the re-contact tank are obtained from the calculation results.

[0048] In an exemplary embodiment of the present invention, the target components include benzene, toluene, and xylene; the determining whether self-tuning is required based on the test data and the simulation data includes: Compare the simulation data and the test data for benzene, toluene and xylene respectively to obtain corresponding comparison results; If at least one of the comparison results indicates that the percentage change between the simulation data and the test data is greater than a preset change threshold, it is determined that self-tuning is required.

[0049] In the embodiment of the present invention, when comparing the model data and the test data of benzene, toluene, and xylene, if the percentage change of the two is greater than the preset change threshold, it is determined that self-tuning is required. For example, if the result of subtracting the test data from the simulation data of benzene and dividing it by the simulation data of benzene is greater than the preset change threshold, it is determined that self-tuning is required, and the preset change threshold can be set to 1%.

[0050] In an exemplary embodiment of the present invention, after performing self-tuning based on the target molecular-level reaction rate, the method further includes: Based on the target molecular-level reaction rate, the self-tuning result is verified.

[0051] In an embodiment of the present invention, the pulled DCS data, reforming feed components, circulating hydrogen components and target molecular-level reaction rate obtained by self-tuning are used as input parameters of a petrochemical plant model for simulation and measurement. Simulation data of benzene, toluene and xylene are extracted from the re-contact tank bottom oil of the measurement results, and then compared with the test data of benzene, toluene and xylene in the laboratory in the factory production environment, and it is checked again whether self-tuning is needed. If self-tuning is no longer needed, the self-tuning ends.

[0052] The following is a description of the molecular-level model self-tuning system for a petrochemical reactor device provided by the present invention. The molecular-level model self-tuning system for a petrochemical reactor device described below and the molecular-level model self-tuning method for a petrochemical reactor device described above can be referred to each other. It should be noted that the system provided in the following embodiment and the method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here.

[0053] In an exemplary embodiment of the present invention, see Figure 2 , Figure 2 A molecular-level model self-tuning system for a petrochemical reactor device is shown according to an exemplary embodiment, and includes the following modules.

[0054] A first acquisition module 210 is configured to acquire field operating data and assay components, and determine simulation data of target components in the bottom oil of the re-contact tank based on the field operating data and the assay components; A second acquisition module 220, configured to acquire the test data of the target component, and determine whether self-tuning is required based on the test data and the simulation data; The optimization module 230 is configured to optimize the reaction rate in the molecular-level reactor model based on the test data, the field operating data and the test components, if necessary, to obtain a target molecular-level reaction rate, and perform self-tuning based on the target molecular-level reaction rate.

[0055] In an exemplary embodiment of the present invention, the optimization module 230 includes: A first determination submodule, configured to determine an optimization target based on the assay data; The optimization submodule is configured to optimize the reaction rate by sequential quadratic programming based on the optimization target, the test data, the field operating data and the test components to obtain the target molecular-level reaction rate.

[0056] In an exemplary embodiment of the present invention, the optimization submodule includes: a determination unit configured to determine an initial reaction rate based on the field operating condition data and the assay data; A first construction unit is configured to construct a constraint condition for the reaction rate; A second construction unit is configured to construct an objective function based on the optimization target and the reaction rate; The optimization unit is configured to optimize the reaction rate iteratively within the constraints based on the initial reaction rate and the objective function through the sequential quadratic programming method until a convergence condition is reached to obtain the target molecular-level reaction rate of the optimal solution.

[0057] In an exemplary embodiment of the present invention, the convergence condition includes that a change in the objective function value obtained during two adjacent optimization iterations is lower than a preset threshold.

[0058] In an exemplary embodiment of the present invention, the field operating data includes DCS data, and the assay components include reforming feed components; the first acquisition module 210 includes: A calculation submodule is configured to input the DCS data and the reforming feed components into a petrochemical plant model for calculation to obtain corresponding calculation results; The second determination submodule is configured to determine simulation data of the target component based on the calculation result.

[0059] In an exemplary embodiment of the present invention, the target components include benzene, toluene, and xylene; the second acquisition module 220 includes: A comparison submodule, configured to compare the simulation data and the test data for benzene, toluene, and xylene, respectively, to obtain corresponding comparison results; The third determination submodule is configured to determine that self-tuning is required if at least one of the comparison results indicates that a percentage change between the simulation data and the test data is greater than a preset change threshold.

[0060] In an exemplary embodiment of the present invention, the molecular level model self-tuning system of a petrochemical reactor device further includes: The verification module is configured to verify the self-tuning result based on the target molecular-level reaction rate.

[0061] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communications bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other via the communications bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the molecular level model self-tuning method of the petrochemical reactor device, the method comprising: acquiring field operating data and assay components, and determining simulation data of target components in the bottom oil of the re-contact tank based on the field operating data and the assay components; Acquiring assay data of the target component, and determining whether self-tuning is required based on the assay data and the simulation data; If necessary, based on the assay data, the field operating data and the assay components, the reaction rate in the molecular-level reactor model is optimized to obtain a target molecular-level reaction rate, and self-tuning is performed based on the target molecular-level reaction rate.

[0062] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0063] On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the molecular level model self-tuning method of the petrochemical reactor device provided by the above methods, the method includes: obtaining field operating data and assay components, and determining simulation data of target components in the bottom oil of the re-contact tank based on the field operating data and the assay components; Acquiring assay data of the target component, and determining whether self-tuning is required based on the assay data and the simulation data; If necessary, based on the assay data, the field operating data and the assay components, the reaction rate in the molecular-level reactor model is optimized to obtain a target molecular-level reaction rate, and self-tuning is performed based on the target molecular-level reaction rate.

[0064] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the molecular-level model self-tuning method for a petrochemical reactor device provided by the above methods, the method comprising: acquiring field operating data and assay components, and determining simulation data of a target component in the bottom oil of a re-contact tank based on the field operating data and the assay components; Acquiring assay data of the target component, and determining whether self-tuning is required based on the assay data and the simulation data; If necessary, based on the assay data, the field operating data and the assay components, the reaction rate in the molecular-level reactor model is optimized to obtain a target molecular-level reaction rate, and self-tuning is performed based on the target molecular-level reaction rate.

[0065] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for 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 some parts of the embodiments.

[0067] 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 embodiments of the present invention.

Claims

1. A molecular level model self-tuning method for a petrochemical reactor device, characterized in that: include: Acquiring on-site operating data and assay components, and determining simulation data of target components in the bottom oil of the re-contact tank based on the on-site operating data and the assay components; Acquiring assay data of the target component, and determining whether self-tuning is required based on the assay data and the simulation data; If necessary, based on the assay data, the field operating data and the assay components, the reaction rate in the molecular-level reactor model is optimized to obtain a target molecular-level reaction rate, and self-tuning is performed based on the target molecular-level reaction rate.

2. The molecular level model self-tuning method for a petrochemical reactor device according to claim 1, characterized in that: The step of optimizing the reaction rate in the molecular-level reactor model based on the test data, the field operating data and the test components to obtain a target molecular-level reaction rate includes: determining an optimization target based on the assay data; Based on the optimization target, the test data, the on-site operating data and the test components, the reaction rate is optimized by sequential quadratic programming to obtain the target molecular-level reaction rate.

3. The molecular level model self-tuning method for a petrochemical reactor device according to claim 2, characterized in that: The step of optimizing the reaction rate based on the optimization target, the test data, the field operating data and the test components by sequential quadratic programming to obtain the target molecular-level reaction rate includes: Determining an initial reaction rate based on the field operating data and the assay data; constructing constraints on the reaction rate; Constructing an objective function based on the optimization target and the reaction rate; Based on the initial reaction rate and the objective function, the reaction rate is iteratively optimized within the constraints by the sequential quadratic programming method until a convergence condition is reached, thereby obtaining the target molecular-level reaction rate of the optimal solution.

4. The molecular level model self-tuning method for a petrochemical reactor device according to claim 3, characterized in that: The convergence condition includes that the change in the objective function value obtained in two adjacent optimization iterations is lower than a preset threshold.

5. The molecular level model self-tuning method for a petrochemical reactor device according to claim 1, characterized in that: The field operating data includes DCS data, and the assay components include reforming feed components; the simulation data for determining the target components in the re-contact tank bottom oil based on the field operating data and the assay components includes: Inputting the DCS data and the reforming feed components into a petrochemical plant model for calculation to obtain corresponding calculation results; Simulation data of the target component is determined based on the calculation results.

6. The molecular level model self-tuning method for a petrochemical reactor device according to claim 1, characterized in that: The target components include benzene, toluene, and xylene; and determining whether self-tuning is required based on the test data and the simulation data includes: Compare the simulation data and the test data for benzene, toluene and xylene respectively to obtain corresponding comparison results; If at least one of the comparison results indicates that the percentage change between the simulation data and the test data is greater than a preset change threshold, it is determined that self-tuning is required.

7. The molecular level model self-tuning method for a petrochemical reactor device according to any one of claims 1 to 6, characterized in that: After the self-tuning based on the target molecular-level reaction rate is performed, the method further comprises: Based on the target molecular-level reaction rate, the self-tuning result is verified.

8. A molecular level model self-tuning system for a petrochemical reactor device, characterized in that: include: A first acquisition module is configured to acquire field operating data and assay components, and determine simulation data of a target component in the bottom oil of the re-contact tank based on the field operating data and the assay components; a second acquisition module configured to acquire assay data of the target component and determine whether self-tuning is required based on the assay data and the simulation data; The optimization module is configured to optimize the reaction rate in the molecular-level reactor model based on the test data, the field operating data and the test components, if necessary, to obtain a target molecular-level reaction rate, and perform self-tuning based on the target molecular-level reaction rate.

9. 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 molecular-level model self-tuning method for a petrochemical reactor device as described in any one of claims 1 to 7 is implemented.

10. 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 method for self-tuning a molecular-level model of a petrochemical reactor device as claimed in any one of claims 1 to 7 is implemented.

Images