Butterfly valve plate sealing parameter optimization method based on NSGA-II algorithm
By optimizing the sealing parameters of the butterfly valve plate using the NSGA-II algorithm and response surface regression model, the problems of low efficiency and poor accuracy in the sealing design of the butterfly valve plate are solved, and efficient collaborative optimization of sealing performance is achieved.
Patent Information
- Application Number
- CN202611455574.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-18
- Publication Date
- 2026-11-10
AI Technical Summary
Existing technologies for butterfly valve plate sealing design suffer from low efficiency, poor precision, and difficulty in coordinated optimization, especially when dealing with the nonlinear coupling relationship of multiple parameters, resulting in poor sealing performance.
The NSGA-II algorithm, combined with finite element simulation and response surface regression model, is used to generate test sample data and construct a second-order response surface model by defining the contact stress of the sealing surface and the equivalent stress of the sealing ring as optimization objectives. Iterative optimization is then performed to obtain the Pareto optimal solution and optimize the sealing parameters of the butterfly valve plate.
It effectively reduces the amount of calculation, improves the accuracy of sealing parameter solution, realizes the synchronous optimization of sealing performance indicators, and outputs sealing parameters that are adapted to actual working conditions.
Smart Images

Figure CN123069587A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of valve design technology, and in particular to a method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm. Background Technology
[0002] Butterfly valves are widely used in pipeline systems under high-pressure conditions, such as those in deep-sea equipment, due to their simple structure and low fluid resistance. Sealing performance is a core indicator of butterfly valve quality, primarily dependent on the contact stress of the sealing surface. However, excessive contact stress can lead to excessive equivalent stress within the sealing ring, potentially causing material fatigue or extrusion failure. Therefore, balancing the contact stress of the sealing surface with the equivalent stress of the sealing ring is of significant research importance.
[0003] Traditional butterfly valve plate sealing design typically employs empirical formulas or single-factor trial-and-error methods. With the development of computer simulation technology, finite element simulation technology has been introduced into the design and sealing performance verification process of butterfly valves. By constructing a simulation model of the sealing structure, multi-objective optimization under a given combination of parameters can be achieved. Some design methods also introduce intelligent optimization algorithms to optimize sealing parameters.
[0004] However, when using empirical formulas or single-factor trial-and-error methods, it is difficult to handle the nonlinear coupling relationship of multiple parameters such as compression ratio, medium pressure difference, and structural inner diameter; directly using the finite element method is extremely time-consuming; the optimization results of existing intelligent optimization algorithms are prone to getting trapped in local optima, resulting in insufficient accuracy; therefore, existing technologies have technical problems such as low efficiency, poor accuracy, and difficulty in co-optimization. Summary of the Invention
[0005] To address the shortcomings of existing technologies, this invention provides a method for optimizing the sealing parameters of butterfly valve plates based on the NSGA-II algorithm, which solves the technical problems of low efficiency, poor accuracy, and difficulty in co-optimization in existing technologies.
[0006] The technical means employed in this invention are as follows: In a first aspect, the present invention provides a method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm, including: Define material properties and contact nonlinearity algorithms, and set external water pressure boundary conditions to construct a finite element simulation benchmark model of the butterfly valve sealing structure; Compression ratio, pressure difference between the inside and outside of the sealing ring, and hollow inner diameter of the sealing ring are used as design variables. Contact stress of the sealing surface and equivalent stress of the sealing ring are used as optimization objectives. The Box-Behnken experimental design method is adopted to generate multiple sets of test sample combinations within the range of the design variables. The contact stress value of the sealing surface and the equivalent stress value of the sealing ring corresponding to each set of test sample combinations are calculated through the finite element simulation benchmark model to obtain test sample data. Based on the experimental sample data, a second-order response surface regression model is constructed regarding the contact stress of the sealing surface and the equivalent stress of the sealing ring. With the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring, the NSGA-II algorithm is used to iteratively optimize the second-order response surface regression model. When the preset number of iterations is met, the Pareto optimal solution set is obtained. The optimal parameter combination is determined based on the Pareto optimal solution set, and the optimal parameter combination is input into the finite element simulation benchmark model for verification to obtain the verified butterfly valve plate sealing parameters.
[0007] Furthermore, the expression for the second-order response surface regression model is:
[0008] in, This represents the response value of the contact stress on the sealing surface or the equivalent stress of the sealing ring; Represents the i-th design variable; Represents the j-th design variable; Indicates the coefficient of the constant term; Represents the coefficient of the quadratic term; This represents the coefficient of the interaction term.
[0009] Furthermore, the NSGA-II algorithm is configured as follows: population size is set to 100, maximum number of generations is 200, crossover probability is 0.9, and mutation probability is 0.1.
[0010] Furthermore, the expression for the dual optimization objective is:
[0011]
[0012] in, This represents the maximization operation; Indicates the contact stress of the sealing surface; This represents the contact stress function of the sealing surface; This represents the minimization operation; This indicates the equivalent stress of the sealing ring; The equivalent stress function of the sealing ring is represented by A, B, and C, which represent the compression ratio, the pressure difference between the inside and outside of the sealing ring, and the hollow inner diameter of the sealing ring, respectively.
[0013] Further, determining the optimal parameter combination based on the Pareto optimal solution set includes: Calculate the Euclidean distance between each optimal solution in the Pareto optimal solution set and the ideal point, and determine the optimal parameter combination corresponding to the optimal solution with the shortest Euclidean distance; the ideal point is the point where the contact stress of the sealing surface is the maximum and the equivalent stress of the sealing ring is the minimum.
[0014] Furthermore, the finite element simulation benchmark model is a two-dimensional axisymmetric plane strain model, which uses the augmented Lagrange multiplier method to handle contact nonlinearity. The loading process includes three load steps: pre-tightening compression, applying external water pressure, and applying internal water pressure.
[0015] Furthermore, the butterfly valve is a double eccentric butterfly valve with a hollow rubber sealing ring, and the sealing ring is made of hydrogenated nitrile rubber.
[0016] Secondly, this invention also provides a butterfly valve plate sealing parameter optimization system based on the NSGA-II algorithm, comprising: The simulation model building module is used to define material properties and contact nonlinear algorithms, and set external water pressure boundary conditions to build a finite element simulation benchmark model of the butterfly valve sealing structure. The sample generation and calculation module is used to take the compression ratio, the pressure difference between the inside and outside of the sealing ring and the hollow inner diameter of the sealing ring as design variables, and the contact stress of the sealing surface and the equivalent stress of the sealing ring as optimization objectives. Using the Box-Behnken experimental design method, multiple sets of test sample combinations are generated within the range of the design variables. The sealing surface contact stress value and the equivalent stress value of the sealing ring corresponding to each set of test sample combinations are calculated through the finite element simulation benchmark model to obtain the test sample data. The regression model construction module is used to construct a second-order response surface regression model on the contact stress of the sealing surface and the equivalent stress of the sealing ring based on the test sample data. The multi-objective optimization processing module is used to perform iterative optimization on the second-order response surface regression model with the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring. When the preset number of iterations is met, the Pareto optimal solution set is obtained. The parameter determination and verification module is used to determine the optimal parameter combination based on the Pareto optimal solution set, input the optimal parameter combination into the finite element simulation benchmark model for verification, and obtain the verified butterfly valve plate sealing parameters.
[0017] Thirdly, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the butterfly valve plate sealing parameter optimization method based on the NSGA-II algorithm according to any one of the first aspects.
[0018] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the butterfly valve plate sealing parameter optimization method based on the NSGA-II algorithm according to any one of the first aspects.
[0019] Compared with the prior art, the present invention has the following advantages: This invention constructs a finite element simulation benchmark model of the butterfly valve sealing structure, generates sample combinations using the Box-Behnken experimental design method, and calculates experimental sample data using the simulation model. Based on this sample data, a second-order response surface regression model is established to replace a large amount of direct simulation calculations. With maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring as dual optimization objectives, the NSGA-II algorithm is used to iteratively optimize the regression model to obtain the Pareto optimal solution set. After selecting the optimal parameter combination, the sealing parameters of the butterfly valve plate are obtained through simulation model verification. This effectively reduces the overall calculation workload and improves the accuracy of parameter solution. At the same time, it can simultaneously optimize the parameters of two mutually restrictive sealing performance indicators and output sealing parameters adapted to actual working conditions. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a flowchart illustrating the butterfly valve plate sealing parameter optimization method based on the NSGA-II algorithm in an embodiment of the present invention. Figure 2 This is a three-dimensional response surface diagram of the sealing surface contact stress to compressibility, pressure difference between the inside and outside of the sealing ring, and hollow inner diameter of the sealing ring in an embodiment of the present invention. Figure 3 This is a three-dimensional response surface diagram of the equivalent stress of the sealing ring to the compressibility, the pressure difference between the inside and outside of the sealing ring, and the hollow inner diameter of the sealing ring in an embodiment of the present invention. Figure 4 This is a flowchart of the Pareto optimal solution set generated by the NSGA-II algorithm in an embodiment of the present invention. Detailed Implementation
[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0023] It should be noted that the terms "comprising" and "having" and any variations thereof in this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.
[0024] The embodiments of the present invention will now be described with reference to the accompanying drawings.
[0025] Please see Figure 1 This invention provides a method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm, including the following steps: Step 101: Define material properties and contact nonlinear algorithm, set external water pressure boundary conditions, and construct a finite element simulation benchmark model of the butterfly valve sealing structure to obtain a simulation calculation model that can be used to calculate the contact stress of the decryption surface and the equivalent stress of the sealing ring.
[0026] In some embodiments, the butterfly valve is a double eccentric butterfly valve with a hollow rubber sealing ring made of hydrogenated nitrile rubber. The finite element simulation baseline model is a two-dimensional axisymmetric plane strain model, which uses the augmented Lagrange multiplier method to handle contact nonlinearity. The loading process includes three load steps: pre-compression, application of external water pressure, and application of internal water pressure.
[0027] A two-dimensional axisymmetric finite element model was constructed, including the valve body, valve plate, valve seat cover, and hollow sealing ring as model objects. The metal material was titanium alloy, so that the two-dimensional axisymmetric plane strain model could reproduce the structural and material properties of each component of the butterfly valve.
[0028] Step 102: Using the compression ratio, the pressure difference between the inside and outside of the sealing ring, and the hollow inner diameter of the sealing ring as design variables, and the contact stress of the sealing surface and the equivalent stress of the sealing ring as optimization objectives, the Box-Behnken experimental design method is used to generate multiple sets of test sample combinations within the design variable range. The contact stress value of the sealing surface and the equivalent stress value of the sealing ring corresponding to each set of test sample combinations are calculated through the finite element simulation benchmark model to obtain the test sample data.
[0029] By using the Box-Behnken experimental design method to generate multiple sets of experimental sample combinations within the design variable range, the variable space can be covered with fewer sample points, and second-order interactions can be estimated to obtain experimental sample data for the appropriate compression ratio, pressure difference between the inside and outside of the sealing ring, and hollow inner diameter of the sealing ring.
[0030] Step 103: Based on the experimental sample data, construct a second-order response surface regression model for the contact stress of the sealing surface and the equivalent stress of the sealing ring.
[0031] Based on experimental sample data, a second-order response surface regression model is fitted using the least squares method. The goodness of fit of the model is verified by analysis of variance (Radj2 > 0.85 is required), which replaces the finite element simulation baseline model and significantly reduces the computational cost.
[0032] In some implementations, the expression for the second-order response surface regression model is:
[0033] in, This represents the response value of the contact stress on the sealing surface or the equivalent stress of the sealing ring; Represents the i-th design variable; Represents the j-th design variable; Indicates the coefficient of the constant term; Represents the coefficient of the quadratic term; This represents the coefficient of the interaction term.
[0034] Step 104: With the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring, the NSGA-II algorithm is used to iteratively optimize the second-order response surface regression model. When the preset number of iterations is met, the Pareto optimal solution set is obtained.
[0035] The second-order response surface regression model is embedded into the NSGA-II algorithm framework. Parameters such as population size and number of iterations are set, and a global search is performed with the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring to obtain the Pareto optimal solution set.
[0036] In some implementations, the expression for the dual optimization objective is:
[0037]
[0038] in, This represents the maximization operation; Indicates the contact stress of the sealing surface; This represents the contact stress function of the sealing surface; This represents the minimization operation; This indicates the equivalent stress of the sealing ring; The equivalent stress function of the sealing ring is represented by A, B, and C, which represent the compression ratio, the pressure difference between the inside and outside of the sealing ring, and the hollow inner diameter of the sealing ring, respectively.
[0039] In some implementations, the NSGA-II algorithm is configured with a population size of 100, a maximum number of generations of 200, a crossover probability of 0.9, and a mutation probability of 0.1.
[0040] Step 105: Determine the optimal parameter combination based on the Pareto optimal solution set, input the optimal parameter combination into the finite element simulation benchmark model for verification, and obtain the verified butterfly valve plate sealing parameters.
[0041] In some implementations, the optimal parameter combination is determined based on the Pareto optimal solution set, including: calculating the Euclidean distance between each optimal solution in the Pareto optimal solution set and the ideal point, and determining the optimal parameter combination corresponding to the shortest Euclidean distance as the optimal parameter combination; the ideal point is the point where the contact stress of the sealing surface is the maximum and the equivalent stress of the sealing ring is the minimum. This allows for the selection of the optimal parameter combination from the Pareto optimal solution set that meets the dual optimization objectives of the contact stress of the sealing surface and the equivalent stress of the sealing ring.
[0042] This invention also provides a butterfly valve plate sealing parameter optimization system based on the NSGA-II algorithm, including: a simulation model construction module for defining material properties and contact nonlinearity algorithms, setting external water pressure boundary conditions to construct a finite element simulation benchmark model of the butterfly valve sealing structure; and a sample generation and calculation module for using compressibility, pressure difference between the inside and outside of the sealing ring, and the hollow inner diameter of the sealing ring as design variables, and the contact stress of the sealing surface and the equivalent stress of the sealing ring as optimization objectives. Using the Box-Behnken experimental design method, multiple sets of test sample combinations are generated within the design variable range, and the contact stress value of the sealing surface and the sealing ring equivalent stress corresponding to each set of test sample combinations are calculated through the finite element simulation benchmark model. The test sample data includes: a sealing ring equivalent stress value; a regression model construction module for constructing a second-order response surface regression model based on the test sample data, which constructs a model for the contact stress of the sealing surface and the equivalent stress of the sealing ring; a multi-objective optimization module for iteratively optimizing the second-order response surface regression model using the NSGA-II algorithm with the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring, obtaining the Pareto optimal solution set when the preset number of iterations is met; and a parameter determination and verification module for determining the optimal parameter combination based on the Pareto optimal solution set, inputting the optimal parameter combination into the finite element simulation benchmark model for verification, and obtaining the verified sealing parameters of the butterfly valve plate.
[0043] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for optimizing the sealing parameters of a butterfly valve based on the NSGA-II algorithm.
[0044] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing the sealing parameters of a butterfly valve based on the NSGA-II algorithm.
[0045] The same or similar parts among the various embodiments in this specification can be referred to mutually, and will not be repeated here.
[0046] This invention constructs a finite element simulation benchmark model of the butterfly valve sealing structure, generates sample combinations using the Box-Behnken experimental design method, and calculates experimental sample data using the simulation model. Based on this sample data, a second-order response surface regression model is established to replace a large amount of direct simulation calculations. With maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring as dual optimization objectives, the NSGA-II algorithm is used to iteratively optimize the regression model to obtain the Pareto optimal solution set. After selecting the optimal parameter combination, the sealing parameters of the butterfly valve plate are obtained through simulation model verification. This effectively reduces the overall calculation workload and improves the accuracy of parameter solution. At the same time, it can simultaneously optimize the parameters of two mutually restrictive sealing performance indicators and output sealing parameters adapted to actual working conditions.
[0047] The technical solution of the present invention will be described below with reference to specific embodiments.
[0048] Example 1 Please see Figures 2-4 Step 1: Construct a finite element simulation baseline model A two-dimensional axisymmetric model of a DN150 double eccentric butterfly valve was established in the ANSYS Workbench environment; the metal material was TC4 titanium alloy; the sealing ring material was hydrogenated nitrile butadiene rubber (HNBR), and the Mooney-Rivlin constitutive model was adopted; the augmented Lagrange multiplier method was selected for the contact algorithm, and the friction coefficient was set to 0.2; the loading was set as follows: three-step loading: valve plate lowering (pre-tightening); applying external water pressure; applying internal water pressure.
[0049] Step 2: Experimental Design and Data Acquisition Sample points were generated using Box-Behnken Design, and APDL scripts were written for batch solving to extract the contact stress of the sealing surface and the equivalent stress of the sealing ring for each sample group.
[0050] Step 3: Construction and Validation of Response Surface Model The experimental sample data were processed using Design Expert software, and a second-order response surface regression model was fitted. Analysis of variance was performed: Radj2=0.8783 for the contact stress model and Radj2=0.9537 for the equivalent stress model. The p-values of both models were less than 0.0001, indicating that the models were extremely significant and the fitting accuracy met the engineering requirements, and could be used for subsequent optimization calculations.
[0051] Step 4: NSGA-II multi-objective genetic algorithm for optimization Write the NSGA-II algorithm program in the MATLAB environment and substitute the second-order response surface regression model obtained in step 3 as the objective function.
[0052] Algorithm parameters: Population size N=100, maximum number of generations G=200, crossover probability Pc=0.9, mutation probability Pm=0.1.
[0053] Objective function: , .
[0054] Constraints: 10%≤A≤20%, 0≤B≤1MPa, 6≤C≤8mm Optimization results: The algorithm converges after 200 generations, outputting the Pareto optimal front. All solutions on the front are non-dominated, meaning no single solution is superior to another solution across all objectives.
[0055] Step 5: Selection and Verification of the Optimal Solution The point closest to the ideal point in the Pareto optimal solution set is selected as the optimal solution.
[0056] Verification: The above parameters were substituted into the original finite element model for accurate calculation. The results show that the error between the predicted and simulated values is minimal, proving the effectiveness of the optimization process.
[0057] Example 2: Optimized application of different groove structures This embodiment demonstrates the versatility of the optimization method across different structures (groove structures).
[0058] Repeat the steps of Example 1, only changing the geometric model of the sealing groove to a rectangular groove.
[0059] Optimization results: The error between the predicted and simulated values is minimal, proving the effectiveness of the optimization process.
[0060] Conclusion: This method can quickly adapt to different geometric structures and automatically find the optimal parameter combination for each, demonstrating the robustness and universality of the method.
[0061] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0062] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm, characterized in that, include: Define material properties and contact nonlinearity algorithms, and set external water pressure boundary conditions to construct a finite element simulation benchmark model of the butterfly valve sealing structure; Compression ratio, pressure difference between the inside and outside of the sealing ring, and hollow inner diameter of the sealing ring are used as design variables. Contact stress of the sealing surface and equivalent stress of the sealing ring are used as optimization objectives. The Box-Behnken experimental design method is adopted to generate multiple sets of test sample combinations within the range of the design variables. The contact stress value of the sealing surface and the equivalent stress value of the sealing ring corresponding to each set of test sample combinations are calculated through the finite element simulation benchmark model to obtain test sample data. Based on the experimental sample data, a second-order response surface regression model is constructed regarding the contact stress of the sealing surface and the equivalent stress of the sealing ring. With the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring, the NSGA-II algorithm is used to iteratively optimize the second-order response surface regression model. When the preset number of iterations is met, the Pareto optimal solution set is obtained. The optimal parameter combination is determined based on the Pareto optimal solution set, and the optimal parameter combination is input into the finite element simulation benchmark model for verification to obtain the verified butterfly valve plate sealing parameters.
2. The method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm according to claim 1, characterized in that, The expression for the second-order response surface regression model is: in, This represents the response value of the contact stress on the sealing surface or the equivalent stress of the sealing ring; Represents the i-th design variable; Represents the j-th design variable; Indicates the coefficient of the constant term; Represents the coefficient of the quadratic term; This represents the coefficient of the interaction term.
3. The method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm according to claim 1, characterized in that, The NSGA-II algorithm is configured as follows: population size is set to 100, maximum number of generations is 200, crossover probability is 0.9, and mutation probability is 0.
1.
4. The method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm according to claim 1, characterized in that, The expression for the dual optimization objective is: in, This represents the maximization operation; Indicates the contact stress of the sealing surface; This represents the contact stress function of the sealing surface; This represents the minimization operation; This indicates the equivalent stress of the sealing ring; The equivalent stress function of the sealing ring is represented by A, B, and C, which represent the compression ratio, the pressure difference between the inside and outside of the sealing ring, and the hollow inner diameter of the sealing ring, respectively.
5. The method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm according to claim 1, characterized in that, Determining the optimal parameter combination based on the Pareto optimal solution set includes: Calculate the Euclidean distance between each optimal solution in the Pareto optimal solution set and the ideal point, and determine the optimal parameter combination corresponding to the optimal solution with the shortest Euclidean distance; the ideal point is the point where the contact stress of the sealing surface is the maximum and the equivalent stress of the sealing ring is the minimum.
6. The method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm according to claim 1, characterized in that, The finite element simulation benchmark model is a two-dimensional axisymmetric plane strain model. The augmented Lagrange multiplier method is used to handle contact nonlinearity. The loading process includes three load steps: pre-tightening compression, application of external water pressure, and application of internal water pressure.
7. The method for optimizing the sealing parameters of a butterfly valve plate based on the NSGA-II algorithm according to claim 1, characterized in that, The butterfly valve is a double eccentric butterfly valve with a hollow rubber sealing ring, and the sealing ring is made of hydrogenated nitrile rubber.
8. A butterfly valve plate sealing parameter optimization system based on NSGA-II algorithm, characterized in that, include: The simulation model building module is used to define material properties and contact nonlinear algorithms, and set external water pressure boundary conditions to build a finite element simulation benchmark model of the butterfly valve sealing structure. The sample generation and calculation module is used to take the compression ratio, the pressure difference between the inside and outside of the sealing ring and the hollow inner diameter of the sealing ring as design variables, and the contact stress of the sealing surface and the equivalent stress of the sealing ring as optimization objectives. Using the Box-Behnken experimental design method, multiple sets of test sample combinations are generated within the range of the design variables. The sealing surface contact stress value and the equivalent stress value of the sealing ring corresponding to each set of test sample combinations are calculated through the finite element simulation benchmark model to obtain the test sample data. The regression model construction module is used to construct a second-order response surface regression model on the contact stress of the sealing surface and the equivalent stress of the sealing ring based on the test sample data. The multi-objective optimization processing module is used to perform iterative optimization on the second-order response surface regression model with the dual optimization objectives of maximizing the contact stress of the sealing surface and minimizing the equivalent stress of the sealing ring. When the preset number of iterations is met, the Pareto optimal solution set is obtained. The parameter determination and verification module is used to determine the optimal parameter combination based on the Pareto optimal solution set, input the optimal parameter combination into the finite element simulation benchmark model for verification, and obtain the verified butterfly valve plate sealing parameters.
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, it implements the butterfly valve plate sealing parameter optimization method based on the NSGA-II algorithm according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the butterfly valve plate sealing parameter optimization method based on the NSGA-II algorithm according to any one of claims 1 to 7.
