Data evaluation method in use process of reheating door valve casing
By establishing geometric models and machine learning methods of rehot valve shells, evaluating their stress, strain and deformation, the problems of high cost and long calculation time in the existing technology are solved, providing efficient data evaluation methods, and obtaining rehot valves The service characteristics of the shell.
Patent Information
- Application Number
- CN202411033948.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art is costly and difficult to obtain ultimate stress, strain and deformation parameters when evaluating the stress state of the re-popular valve housing, or requires professional knowledge and software operation capabilities for a long time.
By establishing a geometric model of the repopular valve shell, meshing and inputting external load condition conditions, compute stress, strain and deformation data, and fit the data using machine learning methods to obtain the mapping of the calculation results and known conditions. Relationship, obtain the service characteristics of the re-popular valve shell.
The data evaluation based on the simulation of F195 re-hot valve shell is realized. Combined with on-site test data, it provides a mapping relationship between the use pressure of F195 re-hot valve shell and the stress, strain and deformation of the valve body, reducing the calculation cost. and time, improve evaluation efficiency.
Smart Images

Figure CN119066800A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of data acquisition of a reheating valve housing, and in particular relates to a data evaluation method during the use of a reheating valve housing. Background Art
[0002] The reheat valve (reheat steam valve) is used to control the flow of reheat steam into the intermediate pressure cylinder of the steam turbine, and can automatically and quickly close and cut off the inlet steam flow when needed. It is an important part of the reheat stage in thermal power generation. The reheat valve housing, as a component of the reheat steam valve, mainly plays the role of protecting and supporting the internal mechanism of the valve body. Since the reheat valve housing is subjected to high pressure (about 25MPa) during use, its safety and reliability need to be highly concerned in design and use.
[0003] In daily production, the reheating valve shell mainly focuses on the stress, strain and deformation under the action of steam pressure, so as to obtain the stress state of the reheating valve shell during use. There are generally two existing methods. One is to install sensors on the outer shell of the reheating valve shell, and evaluate the stress state of the reheating valve shell through the data collected by the sensors in real time. This method is accurate and reliable, but the cost is high, and it is difficult to obtain its parameters such as ultimate stress, strain and deformation; another method is to obtain relevant parameters through simulation by finite element method, but this method takes a long time to calculate and requires strong professional knowledge and software operation ability. This patent is based on finite element simulation method and machine learning theory. On the basis of simulating the F195 reheating valve shell, it combines the actual test data on site to form a database of theoretical calculation and actual test, and regresses through machine learning methods to obtain the mapping relationship between the use pressure and valve body stress, strain and deformation (including maximum, minimum and average values) for the F195 reheating valve shell, and expresses it in the form of a formula.
[0004] The reheat valve (reheat steam valve) is used to control the flow of reheat steam into the intermediate pressure cylinder of the steam turbine, and can automatically and quickly close and cut off the inlet steam flow when needed. It is an important part of the reheat stage in thermal power generation. The reheat valve housing, as a component of the reheat steam valve, mainly plays the role of protecting and supporting the internal mechanism of the valve body. Since the reheat valve housing is subjected to high pressure (about 25MPa) during use, its safety and reliability need to be highly concerned in design and use.
[0005] In daily production, the reheating valve shell mainly focuses on the stress, strain and deformation under the action of steam pressure, so as to obtain the stress state of the reheating valve shell during use. There are generally two existing methods. One is to install sensors on the outer shell of the reheating valve shell, and evaluate the stress state of the reheating valve shell through the data collected by the sensors in real time. This method is accurate and reliable, but the cost is high, and it is difficult to obtain its ultimate stress, strain and deformation parameters; another method is to simulate and simulate through the finite element method to obtain relevant parameters, but this method takes a long time to calculate and requires strong professional knowledge and software operation capabilities. Summary of the invention
[0006] The present invention provides a method for evaluating data during the use of a reheating valve housing, which solves the problem that the reheating valve housing has high cost and is difficult to obtain data.
[0007] To achieve the above object, the present invention provides the following technical solutions:
[0008] A method for evaluating data during the use of a reheating valve housing, comprising:
[0009] Establish the geometric model of the reheating valve housing;
[0010] Mesh the geometric model of the reheating valve housing;
[0011] Enter external load conditions in the meshed reheating valve housing;
[0012] Calculate stress, strain and deformation data according to working conditions and perform data extraction;
[0013] The machine learning method is used to fit the extracted data, obtain the mapping relationship between the calculation results and the known conditions, and obtain the service characteristics of the reheating valve housing.
[0014] Preferably, the stress data calculated according to the working conditions is specifically:
[0015] y=C 0 +C 1 x 1 +C 2 x 2 +...+C i x i +...+C k x k
[0016] Among them, y is the stress, strain or deformation data of the reheating valve shell; x is the working condition parameter; C i is the weight coefficient of the i-th operating condition parameter, i∈[0,k]; k is the total number of operating condition parameters.
[0017] Preferably, the extracted data is fitted using a machine learning method, and the steps of obtaining a mapping relationship between the calculation results and the known conditions are specifically as follows:
[0018] First, the weight coefficient of each extracted data is obtained, and whether the mapping relationship is appropriate is determined based on the weight coefficient and the extracted data. If it is not appropriate, the weight coefficient is retrained until the requirements are met.
[0019] Preferably, the weight coefficient of each extracted data is obtained as follows:
[0020]
[0021] Where β is the calculation rate; n is the number of experimental samples; the superscript j represents the jth data in the experimental sample data, j∈[1,n]; and Y is the data of stress, strain or deformation of the reheating valve housing during the experiment.
[0022] Preferably, the method of retraining the weight coefficient is specifically:
[0023]
[0024] In the formula, ε is the judgment result.
[0025] Preferably, the data types of the data extracted include maximum stress, average stress, maximum strain, average strain, maximum deformation and average deformation.
[0026] Preferably, the reheating valve housing is meshed, and the mesh density of the curved portion of the reheating valve housing is greater than that of other portions.
[0027] A data evaluation system for a reheating valve housing during use, comprising:
[0028] Model building module: used to build the geometric model of the reheating valve housing;
[0029] Meshing module: used to mesh the geometric model of the reheating valve housing;
[0030] Data input module: used to input external load conditions in the reheat valve housing after meshing;
[0031] Data extraction module: used to calculate stress, strain and deformation data according to working conditions and perform data extraction;
[0032] Actual posture acquisition module: It is used to fit the extracted data using machine learning methods, obtain the mapping relationship between the calculation results and the known conditions, and obtain the service characteristics of the reheating valve housing.
[0033] Preferably, the stress data calculated according to the working conditions is specifically:
[0034] y=C 0 +C 1 x 1 +C 2 x 2 +...+C i x i +...+C k x k
[0035] Where y is the stress, strain or deformation data of the reheating valve housing; x is the operating parameter; C i is the weight coefficient of the i-th operating condition parameter, i∈[0,k]; k is the total number of operating condition parameters.
[0036] Preferably, the extracted data is fitted using a machine learning method, and the steps of obtaining a mapping relationship between the calculation results and the known conditions are specifically as follows:
[0037] First, the weight coefficient of each extracted data is obtained, and whether the mapping relationship is appropriate is determined based on the weight coefficient and the extracted data. If it is not appropriate, the weight coefficient is retrained until the requirements are met.
[0038] Preferably, the weight coefficient of each extracted data is obtained as follows:
[0039]
[0040] Where β is the calculation rate; n is the number of experimental samples; the superscript j represents the jth data in the experimental sample data, j∈[1,n]; and Y is the data of stress, strain or deformation of the reheating valve housing during the experimental test.
[0041] Preferably, the method of retraining the weight coefficient is specifically:
[0042]
[0043] In the formula, ε is the judgment result.
[0044] Preferably, the data types of the data extracted include maximum stress, average stress, maximum strain, average strain, maximum deformation and average deformation.
[0045] Preferably, the reheating valve housing is meshed, and the mesh density of the curved portion of the reheating valve housing is greater than that of other portions.
[0046] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a method for evaluating data during the use of a reheating valve housing are implemented.
[0047] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for evaluating data during the use of a reheating valve housing.
[0048] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides a data evaluation method during the use of a reheating valve housing, by establishing a geometric model of the reheating valve housing, meshing the geometric model of the reheating valve housing, inputting external load working conditions into the meshed reheating valve housing, calculating and obtaining stress, strain and deformation data according to the working conditions, and extracting data, fitting the extracted data using a machine learning method, obtaining a mapping relationship between the calculation results and known conditions, and obtaining service characteristic parameters such as stress / strain / deformation of the actual reheating valve housing. On the basis of simulating the F195 reheating valve housing, combining the actual test data on site to form a database of theoretical calculation and actual test, regressing through a machine learning method, obtaining a mapping relationship between the use pressure of the F195 reheating valve housing and the valve body stress, strain and deformation (including maximum value, minimum value and average value), and embodying it in the form of a formula. This patent can solve the shortcomings of the above method in use and provide a basis for evaluating the stress condition of the F195 reheating valve housing during use. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1 A flow chart of a method for evaluating data during use of a reheating valve housing according to the present invention;
[0050] Figure 2 The present invention is a block diagram of a data evaluation system during the use of a reheating valve housing. DETAILED DESCRIPTION
[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.
[0052] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.
[0053] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0054] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.
[0055] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.
[0056] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0057] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.
[0058] An embodiment of the present invention provides a method for evaluating data during the use of a reheating valve housing, comprising:
[0059] S101 Establish the geometric model of the reheating valve housing;
[0060] S102 meshes the geometric model of the reheating valve housing;
[0061] S103 inputting external load conditions in the reheating valve housing after meshing;
[0062] The reheating valve housing is meshed, and the mesh density of the curved part of the reheating valve housing is greater than that of other parts;
[0063] S104 calculates and obtains stress, strain and deformation data according to working conditions, and performs data extraction;
[0064] S105 uses machine learning methods to fit the extracted data, obtain the mapping relationship between the calculation results and the known conditions, and obtain the service characteristics of the reheating valve housing.
[0065] The extracted data are fitted using machine learning methods to obtain the mapping relationship between the calculation results and the known conditions. The specific steps for obtaining the service characteristics of the reheating valve housing are as follows:
[0066] Assume that the multivariate mapping relationship between the multivariate working condition parameters and the stress, strain or deformation service characteristic parameters of the reheating valve housing is as follows:
[0067] y=C 0 +C 1 x 1 +C 2 x 2 +...+C i x i +...+C k x k (1)
[0068] In formula (1), y is the stress, strain or deformation data of the reheating valve housing; x is the operating parameter; C i is the weight coefficient of the i-th operating condition parameter, i∈[0,k]; k is the total number of operating condition parameters.
[0069] make Each undetermined weight coefficient C is obtained according to the following formula i ,
[0070] In formula (2), β is the calculation rate; n is the number of experimental samples; the superscript j represents the jth data in the experimental sample data, j∈[1,n]; and Y is the stress, strain or deformation data of the reheating valve housing during the experimental test.
[0071] Calculate the weight coefficient C i After that, the mapping relationship can be judged whether it is appropriate by comparing the calculated result y of formula (1) with the actual test result Y during the experiment. If it is not appropriate, the weight coefficient C can be retrained using formula (2) i , until the requirements are met. The judgment result can be obtained by the following formula:
[0072]
[0073] In formula (3), ε is the judgment result.
[0074] If there are too many operating parameters that affect the stress, strain or deformation service characteristic parameters of the reheating valve housing, and formula (1) is difficult to effectively characterize them, then on the basis of formula (1), it can be changed into a multivariate quadratic equation, and the above steps are repeated until the multivariate mapping relationship expression between the corrected operating parameters and the stress, strain or deformation parameters of the reheating valve housing meets the requirements.
[0075] The relationship between the inner cavity pressure and stress, strain and deformation is shown in the following table:
[0076] Table 1 Relationship between inner cavity pressure and stress, strain and deformation
[0077]
[0078]
[0079] The fitting relationship finally obtained by the above method is as follows:
[0080] Maximum stress
[0081] y=125x 5 +499x 4 +623x 3 +871x 2 +1013x+1211
[0082] Mean stress
[0083] y=87x 5 +315x 4 +411x 3 +536x 2 +654x+874
[0084] Maximum strain
[0085] y=0.0009x 5 +0.0018x 4 +0.0021x 3 +0.0039x 2 +0.0045x+0.006
[0086] Average strain
[0087] y=0.0004x 5 +0.0009x 4 +0.0015x 3 +0.0024x 2 +0.0033x+0.0045
[0088] Maximum deformation
[0089] y=8x 5+11x 4 +19x 3 +24x 2 +38x+47
[0090] Average deformation
[0091] y=6x 5 +7x 4 +11x 3 +13x 2 +20x+25
[0092] According to the above expression, the relationship between the inner cavity pressure and the stress, strain and deformation can be directly obtained. The relevant results can be directly obtained without calculation, which greatly improves the calculation efficiency. Compared with the existing technology, this method can directly obtain the mapping relationship between input and output. The word calculation takes at least 1 hour, and the formula regression greatly improves the calculation efficiency. Compared with the experiment, the experimental cost is reduced, especially the temperature and pressure of the pipeline itself is extremely high, so it is not easy to do experiments. The use of this method can better obtain data results.
[0093] The embodiment of the present invention further provides a data evaluation system during the use of a reheating valve housing, comprising:
[0094] Model building module: used to build the geometric model of the reheating valve housing;
[0095] Meshing module: used to mesh the geometric model of the reheating valve housing;
[0096] Data input module: used to input external load conditions in the reheat valve housing after meshing;
[0097] Data extraction module: used to calculate stress, strain and deformation data according to working conditions and perform data extraction;
[0098] Actual posture acquisition module: It is used to fit the extracted data using machine learning methods, obtain the mapping relationship between the calculation results and the known conditions, and obtain the service characteristics of the reheating valve housing.
[0099] The stress data calculated according to the working conditions are as follows:
[0100] y=C 0 +C 1 x 1 +C 2 x 2 +...+C i x i +...+C k x k
[0101] Where y is the stress, strain or deformation data of the reheating valve housing; x is the operating parameter; C i is the weight coefficient of the i-th operating condition parameter, i∈[0,k]; k is the total number of operating condition parameters.
[0102] The steps of fitting the extracted data using machine learning methods and obtaining the mapping relationship between the calculation results and the known conditions are as follows:
[0103] First, the weight coefficient of each extracted data is obtained, and whether the mapping relationship is appropriate is determined based on the weight coefficient and the extracted data. If it is not appropriate, the weight coefficient is retrained until the requirements are met.
[0104] The weight coefficient of each extracted data is obtained as follows:
[0105]
[0106] Where β is the calculation rate; n is the number of experimental samples; the superscript j represents the jth data in the experimental sample data, j∈[1,n]; and Y is the data of stress, strain or deformation of the reheating valve housing during the experimental test.
[0107] The method for retraining weight coefficients is as follows:
[0108]
[0109] In the formula, ε is the judgment result.
[0110] The data types extracted include maximum stress, average stress, maximum strain, average strain, maximum deformation and average deformation. The reheating valve shell is meshed, and the mesh density of the curved part of the reheating valve shell is greater than that of other parts.
[0111] A terminal device is provided in one embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.
[0112] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.
[0113] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.
[0114] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0115] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.
[0116] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0117] Although the embodiments of the present invention are described above in conjunction with the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments and application fields, and the above-mentioned specific embodiments are only illustrative and instructive, rather than restrictive. Under the guidance of the specification, a person skilled in the art can also make many forms without departing from the scope of protection of the claims of the present invention, all of which belong to the scope of protection of the present invention.
Claims
1. A method for evaluating data during the use of a reheating valve housing, characterized in that: include: Establish the geometric model of the reheating valve housing; Mesh the geometric model of the reheating valve housing; Enter external load conditions in the meshed reheating valve housing; Calculate stress, strain and deformation data according to working conditions and perform data extraction; The machine learning method is used to fit the extracted data, obtain the mapping relationship between the calculation results and the known conditions, and obtain the service characteristics of the reheating valve housing.
2. The method for evaluating data during the use of a reheating valve housing according to claim 1, characterized in that: The stress, strain and deformation data calculated according to the working conditions are as follows: y=C0+C1x1+C2x2+...+C i x i +...+C k x k Where y is the stress, strain or deformation data of the reheating valve housing; x is the operating parameter; C i is the weight coefficient of the i-th operating condition parameter, i∈[0,k]; k is the total number of operating condition parameters.
3. The method for evaluating data during use of a reheating valve housing according to claim 1, characterized in that: The steps of fitting the extracted data using machine learning methods and obtaining the mapping relationship between the calculation results and the known conditions are as follows: First, the weight coefficient of each extracted data is obtained, and whether the mapping relationship is appropriate is determined based on the weight coefficient and the extracted data. If it is not appropriate, the weight coefficient is retrained until the requirements are met.
4. The method for evaluating data during use of a reheating valve housing according to claim 3, characterized in that: The weight coefficient of each extracted data is obtained as follows: In the formula, β is the calculation rate; n is the number of experimental samples; The superscript j represents the jth data in the experimental sample data, j∈[1,n]; Y is the data of stress, strain or deformation of the reheating valve housing during the experimental test.
5. The method for evaluating data during use of a reheating valve housing according to claim 4, characterized in that: The method for retraining weight coefficients is as follows: In the formula, ε is the judgment result.
6. The method for evaluating data during use of a reheating valve housing according to claim 1, characterized in that: The data types extracted include maximum stress, mean stress, maximum strain, mean strain, maximum deformation, and mean deformation.
7. The method for evaluating data during use of a reheating valve housing according to claim 1, characterized in that: The reheating valve housing is meshed, and the mesh density of the curved part of the reheating valve housing is greater than that of other parts.
8. A data evaluation system for a reheating valve housing during use, characterized in that: include: Model building module: used to build the geometric model of the reheating valve housing; Meshing module: used to mesh the geometric model of the reheating valve housing; Data input module: used to input external load conditions in the reheat valve housing after meshing; Data extraction module: used to calculate stress, strain and deformation data according to working conditions and perform data extraction; Actual posture acquisition module: It is used to fit the extracted data using machine learning methods, obtain the mapping relationship between the calculation results and the known conditions, and obtain the actual service posture of the reheating valve housing.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for evaluating data during use of a reheating valve housing as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for evaluating data during use of a reheating valve housing as described in any one of claims 1 to 7 are implemented.
