Design method and system for generating non-standard petrochemical equipment based on deep learning

Abstract

The present invention provides a design method and system for generating non-standard petrochemical equipment based on deep learning, which relates to the technical field of non-standard pressure vessel design. In order to solve the problem that the automatically generated design method has poor interactivity with users, the design method includes the following steps: S1, obtaining process parameters and standard calculation formulas in the process of pressure vessel production; S2, constructing a process parameter database; S3, training a pressure vessel design model according to the process parameter database; S4, taking the product performance requirements of the target pressure vessel as input parameters and inputting them into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software; S5, receiving and identifying the content adjustment of the module parameters by the user on the simulation software, and feeding back the content adjustment to the pressure vessel design model to obtain new module parameters, which can enhance the interactivity between the user and the pressure vessel design model and have a better experience.

Description

Technical Field

[0001] The present invention relates to the technical field of non-standard pressure vessel design, and particularly to a design method and system for petrochemical non-standard equipment generated based on deep learning. Background Art

[0002] Due to the need to meet special working conditions, complex structures or customized requirements, the design of non-standard pressure vessels often involves the coupling optimization between multiple parameters, the compatibility between new materials, and high-strength safety verification. Traditional design methods rely on manual experience and continuous trial and error, resulting in low efficiency and difficulty in balancing multiple objectives. Therefore, at present, a method of using deep learning to learn a large number of parameters of pressure vessels has been proposed, which can automatically generate non-standard pressure vessels. However, this automatic generation method requires a large amount of training to obtain the non-standard pressure vessels desired by users. After each automatic generation, it is relatively inconvenient for users to adjust the model results, resulting in poor user experience and interactivity. Summary of the Invention

[0003] The object of the present invention is to provide a design method for petrochemical non-standard equipment generated based on deep learning, which uses deep learning to conduct a large amount of analysis on process parameters in the pressure vessel production process, can quickly integrate pressure vessel standards and real-time process parameters, greatly shorten the design cycle, and reduce the dependence on manual labor.

[0004] To solve the above technical problems, the present invention adopts the following solutions:

[0005] A design method for petrochemical non-standard equipment generated based on deep learning, comprising the following steps:

[0006] S1. Obtain the process parameters in the pressure vessel production process and their related standard calculation formulas;

[0007] S2. Structurally store the process parameters according to the process parameters and their data types, and associate the corresponding process parameters through the related standard calculation formulas to obtain a process parameter database;

[0008] S3. Construct an initial deep learning model, input the process parameters in the process parameter database as input parameters into the initial deep learning model according to the association relationship, and perform iterative training with the related standard calculation formulas as constraint conditions to obtain a pressure vessel design model;

[0009] S4. Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software;

[0010] S5. Receive and recognize the content adjustment of module parameters by the user on the simulation software, feedback the content adjustment to the pressure vessel design model, update the pressure vessel design model, and obtain new module parameters.

[0011] Further, in S1, the process of obtaining the process parameters and their related standard calculation formulas in the pressure vessel production process is specifically as follows: Obtain the process form file recorded in the pressure vessel production process, perform content recognition processing on the process form file, extract the process parameters, and obtain the related standard calculation formulas according to the process rules corresponding to the process parameters.

[0012] Further, the step S2 includes the following steps:

[0013] S21. According to the data types of the process parameters in the pressure vessel production process, mark all the process parameters with types, and one data type corresponds to several process parameters.

[0014] S22. Build a process parameter database, use the data type as the library name of the sub-library in the process parameter database, store the corresponding process parameters in the sub-library, and isolate and store the process parameters of each process form file in the sub-library, number the process parameters of the same process form file, and associate the process parameters with the same number through the relevant standard calculation formulas to obtain the process parameter database.

[0015] Further, the data types include container geometry, head geometry, interface design, and material type. The container geometry includes cylindrical, spherical, and irregular shapes. The head geometry includes elliptical, spherical, and flat shapes. The interface design includes inlet and outlet pipe diameters, flange sizes, and connection methods. The material type includes carbon steel, stainless steel, titanium alloy, and composite materials.

[0016] Further, in S22, the process of associating the process parameters with the same number through the relevant standard calculation formulas is specifically as follows:

[0017] Number the sub-libraries in the process parameter database in sequence, obtain the position information of each process parameter through the numbers of the sub-library and the process parameter. The position information refers to the coordinate position formed by the sub-library where the process parameter is located and the internal position information of the sub-library. Then, associate the coordinate positions of each process parameter according to the relevant standard calculation formulas to form a coordinate association table.

[0018] Further, in S3, the process of building an initial deep learning model, inputting the process parameters in the process parameter database as input parameters into the initial deep learning model according to the association relationship, and performing iterative training with the relevant standard calculation formulas as constraint conditions to obtain the pressure vessel design model is as follows:

[0019] Construct an initial deep learning model, find the corresponding process parameters according to the correlation relationship, obtain multiple training data sets with the process parameters and the corresponding historical design requirement data, input the multiple training data sets into the initial deep learning model for iterative training, and perform constraint verification on the generated process parameters through relevant standard calculation formulas in each iteration, so that the trained deep learning model serves as a pressure vessel design model.

[0020] Furthermore, the deep learning model includes a generative adversarial network, a convolutional neural network, and multi-objective optimization. The generative adversarial network generates non-standard container geometries that meet the design requirements. The convolutional neural network predicts material properties based on the process parameter database. Through multi-objective optimization, multiple training data sets are input into the initial deep learning model for optimization at the same time, and the optimal deep learning model is obtained as the pressure vessel design model.

[0021] Furthermore, in S4, the process of taking the product performance requirements of the target pressure vessel as input parameters and inputting them into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software is as follows:

[0022] Take the product performance requirements of the target pressure vessel as input parameters and input them into the pressure vessel design model. Match relevant standard calculation formulas according to the product performance requirements. Obtain the process parameters of the target pressure vessel through the relevant standard calculation formulas. Input the process parameters into the simulation software for simulation to obtain the target pressure vessel and its module parameters displayed on the simulation software. The module parameters are obtained through the simulation software and include cylinder module parameters, head module parameters, and flange module parameters.

[0023] A design system for petrochemical non-standard equipment generated based on deep learning, applying the described design method for petrochemical non-standard equipment generated based on deep learning, includes:

[0024] Data acquisition module: Obtain the process parameters and their relevant standard calculation formulas in the pressure vessel production process;

[0025] Model construction module: Construct an initial deep learning model, input the process parameters in the process parameter database as input parameters into the initial deep learning model according to the correlation relationship, and perform iterative training with the relevant standard calculation formulas as constraint conditions to obtain a pressure vessel design model;

[0026] Pressure vessel design module: Take the product performance requirements of the target pressure vessel as input parameters and input them into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software;

[0027] Pressure vessel feedback module: Receives and identifies the content adjustment of module parameters by the user on the simulation software, and feeds back the content adjustment to the pressure vessel design model to update the pressure vessel design model and obtain new module parameters.

[0028] Advantages of the present invention:

[0029] The present invention provides a design method and system for petrochemical non-standard equipment based on deep learning, which changes the traditional design method relying on manual experience to a design method automatically generated by a deep learning model. In this design method, process parameters and relevant standard calculation formulas are structurally stored first. Through the structural storage, there is an association relationship between each process parameter. Through the association relationship, the optimal design method of the target pressure vessel can be quickly determined. Moreover, based on deep learning, a large amount of analysis is carried out on the process parameters in the pressure vessel production process, and the pressure vessel standards and real-time process parameters can be quickly integrated, greatly shortening the design cycle, reducing the dependence on manual labor, and at the same time, promoting the development of high-performance and high-safety non-standard equipment, meeting the stringent requirements of fields such as petrochemical and aerospace.

[0030] This system not only includes a pressure vessel design module, but also includes a pressure vessel feedback module. The pressure vessel design module is used to perform a large amount of analysis on the process parameters in the pressure vessel production process based on deep learning. The pressure vessel feedback module is used to receive and identify the content adjustment of the module parameters by the user and output it to the pressure vessel design module, so that the pressure vessel design module can be retrained. Through the combination of the pressure vessel design module and the pressure vessel feedback module, the interactivity between the user and the pressure vessel design model can be realized, facilitating the user to accurately generate the required non-standard pressure vessels and improving the user experience. Description of the drawings

[0031] Figure 1 It is a schematic flow chart of the design method in Embodiment 1 of the present invention;

[0032] Figure 2 It is a schematic structural diagram of the process parameter database in Embodiment 1 of the present invention. Detailed implementation manners

[0033] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. The description of at least one exemplary embodiment below is actually only illustrative and in no way restrictive of the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0034] Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention.

[0035] Meanwhile, it should be understood that, for the sake of convenience in description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship.

[0036] In addition, for the sake of clarity and conciseness, descriptions of well-known structures, functions, and configurations may be omitted. Those of ordinary skill in the art will recognize that various changes and modifications can be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0037] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be regarded as part of the authorization specification.

[0038] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0039] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments:

[0040] Embodiment 1

[0041] Since non-standard pressure vessels need to meet special working conditions, complex structures, or customized requirements, their design often involves the coupled optimization between multiple parameters, the compatibility between new materials, and high-strength safety verification. Currently, the design methods for non-standard pressure vessels generally rely on manual experience and continuous trial and error, with low efficiency and difficulty in taking into account the balance between multiple objectives. Therefore, it has been proposed to use deep learning methods to learn a large number of parameters of pressure vessels, which can automatically generate non-standard pressure vessels. However, this automatic generation method requires a large amount of training to obtain the non-standard pressure vessels desired by users. After each automatic generation, it is relatively inconvenient for users to adjust the model results, resulting in poor user experience and interactivity.

[0042] To solve the above problems, a design method for generating non-standard petrochemical equipment based on deep learning is proposed in this embodiment, as Figure 1 shown, including the following steps:

[0043] S1. Obtain the process parameters in the production process of the pressure vessel and their related standard calculation formulas;

[0044] S2. Structurally store according to the process parameters and their data types, and correlate the corresponding process parameters through relevant standard calculation formulas to obtain a process parameter database;

[0045] S3. Construct an initial deep learning model, input the process parameters in the process parameter database as input parameters into the initial deep learning model according to the correlation relationship, and perform iterative training with the relevant standard calculation formulas as constraint conditions to obtain a pressure vessel design model;

[0046] S4. Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software;

[0047] S5. Receive and recognize the content adjustment of the module parameters by the user on the simulation software, feedback the content adjustment to the pressure vessel design model, and update the pressure vessel design model to obtain new module parameters.

[0048] In actual situations, the design of non-standard pressure vessels often involves multiple parameters such as geometric parameters, operating conditions parameters, material parameters, load parameters, safety parameters, manufacturing parameters, economic parameters, environmental parameters, and functional parameters. Moreover, during the production process of pressure vessels, relevant parameters are usually recorded in the form of a table and stored as a process table file.

[0049] And the above parameters have different values for different components of non-standard pressure vessels. For example, geometric parameters not only include parameters representing the geometric shape of the vessel but also parameters representing the geometric shape of the head, and each parameter contains multiple content values. For example, the geometric shape of the vessel includes cylindrical, spherical, and irregular shapes.

[0050] Therefore, in this embodiment, the parameters are grouped by data type for different components and different types of non-standard pressure vessels to obtain multiple data types. Specifically, the data types include the geometric shape of the vessel, the geometric shape of the head, interface design, the highest temperature the vessel needs to withstand, the lowest temperature the vessel needs to withstand, working pressure, working temperature, material type, etc.

[0051] Then, isolate the process parameters in the data type according to the parameter content. Specifically, the container geometry includes cylindrical, spherical, and irregular shapes, the head geometry includes elliptical, spherical, and flat shapes, the interface design includes the inlet and outlet pipe diameters, flange sizes, and connection methods, and the material types include carbon steel, stainless steel, titanium alloy, and composite materials. Then, one data type corresponds to several process parameters, and the process parameters of the same data type recorded in different pressure vessel production processes will be different. Therefore, in this embodiment, the process parameters in different pressure vessel production processes can be obtained according to their historical design requirements, increasing the diversity of the database and facilitating the massive analysis of the process parameters in the pressure vessel production process by deep learning.

[0052] In one embodiment, in S1, the process of obtaining the process parameters and their related standard calculation formulas in the pressure vessel production process is specifically as follows: Obtain the process form file recorded in the pressure vessel production process, perform content recognition processing on the process form file, extract the process parameters, and obtain the related standard calculation formulas according to the process rules corresponding to the process parameters.

[0053] In one embodiment, the step S2 includes the following steps:

[0054] S21. Mark the types of all process parameters according to the data types of the process parameters in the pressure vessel production process. One data type corresponds to several process parameters;

[0055] S22. Construct a process parameter database. Use the data type as the name of the sub-database in the process parameter database, store the corresponding process parameters in the sub-database, and isolate and store the process parameters of each process form file in the sub-database. Number the process parameters of the same process form file, and associate the process parameters with the same number through the relevant standard calculation formulas to obtain the process parameter database.

[0056] In one embodiment, in S22, the process of associating the process parameters with the same number through the relevant standard calculation formulas is specifically as follows:

[0057] Number the sub-databases in the process parameter database in sequence. Obtain the position information of each process parameter through the numbers of the sub-database and the process parameter. The position information refers to the coordinate position formed by the sub-database where the process parameter is located and the internal position information of the sub-database. Then, associate the coordinate positions of each process parameter according to the relevant standard calculation formulas to form a coordinate association table.

[0058] Specifically, such as Figure 2As shown, in the process parameter database, the data type is used as the library name of the sub-library in the process parameter database. Each sub-library is isolated from each other, including two sub-libraries such as data type 1 and data type 2. Each sub-library contains its corresponding process parameters, and the process parameters are stored separately according to the process form file within the sub-library. For example, in data type 1, there are process parameter 1 with number A and process parameter 2 with number B. At this time, if in data type 2, there are process parameter 1 with number A and process parameter 2 with number C, and the relevant standard calculation formula includes data type 1 and data type 2, then the process parameter 1 in data type 1 with the same number and the process parameter 1 in data type 2 are associated. Before association, the sub-libraries can be numbered. For example, data type 1 is numbered a and data type 2 is numbered b. Through the numbering of the sub-library and the process parameters within the sub-library, the position information of each process parameter can be located. For example, the position information of process parameter 1 in data type 1 is (a, A), and the position information of process parameter 1 in data type 2 is (b, A). Associating with the position information can form a coordinate association table and store it in the process parameter database. Through structured storage, there is an association relationship between each process parameter. Through the association relationship, the optimal design method of the target pressure vessel can be quickly determined.

[0059] In one embodiment, in S3, the process of constructing the initial deep learning model, taking the process parameters in the process parameter database as input parameters according to the association relationship and inputting them into the initial deep learning model, and using the relevant standard calculation formula as the constraint condition for iterative training to obtain the pressure vessel design model is as follows:

[0060] Construct the initial deep learning model, find the corresponding process parameters according to the association relationship, obtain multiple training data sets with the process parameters and the corresponding historical design requirement data, input the multiple training data sets into the initial deep learning model for iterative training, and in each iteration, perform constraint verification on the generated process parameters through the relevant standard calculation formula, so that the trained deep learning model is used as the pressure vessel design model.

[0061] In one embodiment, the deep learning model includes a generative adversarial network, a convolutional neural network, and multi-objective optimization. The generative adversarial network generates a non-standardized container geometry that meets the design requirements. The convolutional neural network predicts the material properties based on the process parameter database. The multi-objective optimization simultaneously optimizes the input of multiple training data sets into the initial deep learning model to obtain the optimal deep learning model as the pressure vessel design model.

[0062] Specifically, when constructing the initial deep learning model, the initial deep learning model includes an input layer, a hidden layer, an output layer, and a loss function. The input layer uses the process parameters in the process parameter database as input parameters. The hidden layer uses a multi-layer neural network to extract features. The output layer can output the process parameters of the target pressure vessel. The loss function can ensure that the output process parameters of the target pressure vessel conform to the relevant standard calculation formula, realizing the constraint verification of the generated process parameters.

[0063] In one embodiment, the process of inputting the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model and obtaining the module parameters of the target pressure vessel displayed on the simulation software is as follows:

[0064] Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model. Match the relevant standard calculation formula according to the product performance requirements. Obtain the process parameters of the target pressure vessel through the relevant standard calculation formula. Input the process parameters into the simulation software for simulation to obtain the target pressure vessel and its module parameters displayed on the simulation software. The module parameters are obtained through the simulation software and include cylinder module parameters, head module parameters, and flange module parameters.

[0065] Specifically, the module parameters refer to the parameters that can be obtained on the simulation software. For example, the cylinder module parameters include the length, width, etc. of the cylinder. The user can obtain the corresponding cylinder module parameters by clicking on the cylinder on the simulation software. Since the parameters automatically generated by the model have strong randomness, the cylinder module parameters obtained through the pressure vessel design model may not be exactly what the user really needs. Therefore, in this embodiment, a pressure feedback module is designed based on the pressure vessel design model. There can be multiple pressure feedback modules, and each pressure feedback module corresponds to a module parameter. The pressure feedback module refers to the cylinder simulation model, head simulation model, flange simulation model, etc. on the simulation software. The user can accurately obtain the parameters on the cylinder simulation model, head simulation model, and flange simulation model by clicking and adjust the parameters. When the pressure feedback module receives and recognizes the adjustment of the module parameter content by the user, it will output it to the pressure vessel design module, causing the pressure vessel design model to be retrained. Through the pressure vessel design model plus the pressure vessel feedback module, the interactivity between the user and the pressure vessel design model can be realized, facilitating the user to accurately generate the required non-standard pressure vessels and improving the user experience.

[0066] In summary, the present invention provides a design method and system for generating non-standard petrochemical equipment based on deep learning, which changes the traditional design method relying on manual experience to a design method automatically generated by a deep learning model. In this design method, process parameters and related standard calculation formulas are structurally stored first. Through the structural storage, there is an association relationship between each process parameter. Through the association relationship, the optimal design method of the target pressure vessel can be quickly determined. Moreover, based on deep learning, a large amount of analysis is carried out on the process parameters in the production process of the pressure vessel, and the pressure vessel standards and real-time process parameters can be quickly integrated, greatly shortening the design cycle, reducing the dependence on manual labor, and at the same time promoting the development of high-performance and high-safety non-standard equipment, meeting the stringent requirements of fields such as petrochemical and aerospace.

[0067] Embodiment 2

[0068] A design system for generating non-standard petrochemical equipment based on deep learning, applying the design method for generating non-standard petrochemical equipment based on deep learning as described above, includes:

[0069] Data acquisition module: Obtain the process parameters and their related standard calculation formulas in the production process of the pressure vessel;

[0070] Model construction module: Construct an initial deep learning model, input the process parameters in the process parameter database as input parameters into the initial deep learning model according to the association relationship, and perform iterative training with the related standard calculation formulas as constraint conditions to obtain a pressure vessel design model;

[0071] Pressure vessel design module: Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software;

[0072] Pressure vessel feedback module: Receive and recognize the content adjustment of the module parameters by the user on the simulation software, feedback the content adjustment to the pressure vessel design model, update the pressure vessel design model, and obtain new module parameters.

[0073] The above is only a preferred embodiment of the present invention, and does not impose any form of limitation on the present invention. Based on the technical essence of the present invention, any simple modification, equivalent replacement, and improvement made to the above embodiments within the spirit and principle of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A design method for generating non-standard petrochemical equipment based on deep learning, characterized in that, The described design method includes the following steps: S1. Obtain the process parameters in the production process of the pressure vessel and their related standard calculation formulas; S2. Structurally store the process parameters according to the process parameters and their data types, and associate the corresponding process parameters through the related standard calculation formulas to obtain a process parameter database; S3. Construct an initial deep learning model, input the process parameters in the process parameter database as input parameters into the initial deep learning model according to the association relationship, and perform iterative training with the related standard calculation formulas as constraint conditions to obtain a pressure vessel design model; The specific process is as follows: Construct an initial deep learning model, find the corresponding process parameters according to the association relationship, obtain multiple training data sets with the process parameters and the corresponding historical design requirement data, input the multiple training data sets into the initial deep learning model for iterative training, and perform constraint verification on the generated process parameters through the related standard calculation formulas in each iteration, so that the trained deep learning model is used as the pressure vessel design model; The deep learning model includes a generative adversarial network, a convolutional neural network, and multi-objective optimization. The generative adversarial network generates a non-standardized container geometry that meets the design requirements. The convolutional neural network predicts the material properties based on the process parameter database. The multi-objective optimization simultaneously optimizes the input of multiple training data sets into the initial deep learning model to obtain the optimal deep learning model as the pressure vessel design model; S4. Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software; S5. Receive and identify the content adjustment of the module parameters by the user on the simulation software, feedback the content adjustment to the pressure vessel design model, update the pressure vessel design model, and obtain new module parameters.

2. The design method of a non-standard petrochemical equipment generated based on deep learning according to claim 1, wherein In S1, the process of obtaining the process parameters in the production process of the pressure vessel and their related standard calculation formulas is specifically as follows: Obtain the process form file recorded in the production process of the pressure vessel, perform content recognition processing on the process form file, extract the process parameters, and obtain the related standard calculation formulas according to the process rules corresponding to the process parameters.

3. The design method of a non-standard petrochemical equipment generated based on deep learning according to claim 2, characterized in that, The steps in S2 include the following steps: S21. According to the data types of the process parameters in the production process of the pressure vessel, mark all the process parameters with types, and one data type corresponds to several process parameters; S22. Construct a process parameter database, use the data type as the library name of the sub-library in the process parameter database, store the corresponding process parameters in the sub-library, and isolate and store the process parameters of each process form file in the sub-library, number the process parameters of the same process form file, and associate the process parameters with the same number through the related standard calculation formulas to obtain a process parameter database.

4. The design method of a non-standard petrochemical equipment generated based on deep learning according to claim 3, characterized in that, The data types include container geometry, head geometry, interface design, and material type. The container geometry includes cylindrical, spherical, and irregular shapes. The head geometry includes elliptical, spherical, and flat shapes. The interface design includes inlet / outlet pipe diameter, flange size, and connection method. The material type includes carbon steel, stainless steel, titanium alloy, and composite materials.

5. The design method of a non-standard petrochemical equipment generated based on deep learning according to claim 3, characterized in that, In S22, the process of correlating process parameters with the same number through relevant standard calculation formulas is specifically as follows: In the process parameter database, the sub-libraries are numbered in sequence. The position information of each process parameter is obtained through the numbers of the sub-library and the process parameter. The position information refers to the coordinate position formed by the sub-library where the process parameter is located and the internal position information of the sub-library. Then, according to the relevant standard calculation formulas, the coordinate positions of each process parameter are correlated to form a coordinate correlation table.

6. The design method of a non-standard petrochemical equipment generated based on deep learning according to claim 1, characterized in that, In S4, the process of inputting the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model and obtaining the module parameters of the target pressure vessel displayed on the simulation software is as follows: Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model. Match the relevant standard calculation formulas according to the product performance requirements. Obtain the process parameters of the target pressure vessel through the relevant standard calculation formulas. Input the process parameters into the simulation software for simulation to obtain the target pressure vessel and its module parameters displayed on the simulation software. The module parameters are obtained through the simulation software and include cylinder module parameters, head module parameters, and flange module parameters.

7. A design system for generating non-standard petrochemical equipment based on deep learning, characterized in that, Applying a design method for petrochemical non-standard equipment generated based on deep learning as described in any one of claims 1-6, includes: Data acquisition module: Obtain the process parameters and their relevant standard calculation formulas during the production process of the pressure vessel. Process parameter database construction module: Structurally store according to the process parameters and their data types, and correlate the corresponding process parameters through relevant standard calculation formulas to obtain a process parameter database. Model construction module: Construct an initial deep learning model. Input the process parameters in the process parameter database as input parameters into the initial deep learning model according to the correlation relationship, and use the relevant standard calculation formulas as constraint conditions for iterative training to obtain a pressure vessel design model. Pressure vessel design module: Input the product performance requirements of the target pressure vessel as input parameters into the pressure vessel design model to obtain the module parameters of the target pressure vessel displayed on the simulation software. Pressure vessel feedback module: Receive and identify the content adjustment of the module parameters by the user on the simulation software, feedback the content adjustment to the pressure vessel design model, update the pressure vessel design model, and obtain new module parameters.

Images