Intelligent optimization method and system for spline bending test
By combining intelligent optimization algorithm with finite element analysis technology, the optimal test parameter combination is generated, which solves the problem of difficult parameter identification and insufficient testing efficiency in spline bending test, and achieves more efficient testing accuracy and lower cost spline bending test.
Patent Information
- Application Number
- CN202411192572.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-17
AI Technical Summary
The difficulty of parameter identification, insufficient testing efficiency and stability in spline bending tests makes it difficult to meet the needs of rapid evaluation and optimization of design in large-scale engineering projects or complex material designs.
The intelligent optimization algorithm is combined with finite element analysis technology, and by determining optimization goals, identifying test parameters, establishing finite element analysis models, adjusting algorithms and models, generating the optimal test parameter combination, conducting spline bending tests, improving test accuracy and efficiency.
It effectively improves the accuracy and efficiency of spline bending tests, reduces the actual number of experiments and costs, and can better adapt to complex test conditions and application scenarios.
Smart Images
Figure CN119152996A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of bending testing, and in particular to an intelligent optimization method and system for spline bending testing. Background Art
[0002] The spline bending test is an experimental method widely used to evaluate the mechanical properties of materials, especially for determining the yield strength, flexural strength and elastic modulus of materials. By applying a bending load to the material spline and observing the stress distribution and deformation behavior of the spline during the bending process, the mechanical properties of the material can be obtained. This test method has important applications in the engineering field, especially in materials science, structural engineering and manufacturing, and is used to evaluate the reliability and durability of materials under actual working conditions.
[0003] With the increasing demands of modern engineering, the development of spline bending test is also advancing. Traditional spline bending test mainly relies on physical experiments in the laboratory. Although the accuracy is high, the experiment is time-consuming, costly, and can only test a limited combination of parameters, which makes it difficult to meet the needs of rapid evaluation and optimization design in large-scale engineering projects or complex material designs. Therefore, an intelligent optimization method for spline bending test has become one of the current development directions. Summary of the invention
[0004] The present invention provides an intelligent optimization method and system for a spline bending test, which can effectively solve the problems in the background technology.
[0005] In order to achieve the above object, the technical solution adopted by the present invention is: An intelligent optimization method for a spline bending test, the method comprising: Determining an optimization target for a spline bending test and identifying test parameters for the spline bending test; Based on the optimization goal, a suitable intelligent optimization algorithm is selected, and several test parameter combinations of the spline bending test are generated by the intelligent optimization algorithm; Establishing a finite element analysis model, inputting a plurality of test parameter combinations into the finite element analysis model for analysis, and obtaining finite element analysis results; Feeding back the finite element analysis results to the intelligent optimization algorithm, adjusting the intelligent optimization algorithm, and generating an optimal test parameter combination through the adjusted intelligent optimization algorithm; The spline bending test is performed using the optimal test parameter combination to obtain a spline bending test result.
[0006] Furthermore, after generating the optimal test parameter combination, corresponding finite element analysis results are obtained at the same time, and the intelligent optimization algorithm and the finite element analysis model are further adjusted according to the corresponding finite element analysis results.
[0007] Further, the identifying test parameters of the spline bending test includes: Select the parameters to be analyzed and define the sensitivity index; Design the parameter experiment plan, execute the experiment plan, and collect the experimental parameter settings and experimental output results during the experiment; The sensitivity index of each parameter is calculated according to the experimental parameter settings and the experimental output results, and key parameters are identified as the test parameters.
[0008] Furthermore, the finite element analysis model is established, and a plurality of test parameter combinations are input into the finite element analysis model for analysis to obtain finite element analysis results, including: Establishing a geometric model of the spline and defining material properties of the spline; Selecting a suitable unit type to mesh the spline; defining boundary conditions and load conditions for the spline bending test; The solution parameters are set, and the test parameter combination is input into the finite element analysis model to perform finite element analysis and obtain finite element analysis results.
[0009] Furthermore, meshing the spline includes: Analyze the geometric complexity and material properties of the geometric model and select mesh density for preliminary partitioning; Screening the stress concentration area of the geometric model, adjusting the mesh density of the stress concentration area to generate a final mesh; The final mesh was quality checked.
[0010] Furthermore, a convergence analysis is performed on the final mesh after quality inspection.
[0011] Furthermore, a termination condition is set for the iterative process of the intelligent optimization algorithm to generate the optimal test parameter combination. An intelligent optimization system for spline bending test, the system comprising: An optimization target determination module is used to determine the optimization target of the spline bending test and identify the test parameters of the spline bending test; A parameter combination generation module, which selects a suitable intelligent optimization algorithm based on the optimization target, and generates several test parameter combinations of the spline bending test through the intelligent optimization algorithm; A finite element model building module is used to build a finite element analysis model, and input a plurality of test parameter combinations into the finite element analysis model for analysis to obtain a finite element analysis result; An analysis result feedback module feeds back the finite element analysis result to the intelligent optimization algorithm, adjusts the intelligent optimization algorithm, and generates an optimal test parameter combination through the adjusted intelligent optimization algorithm; The spline bending test module performs the spline bending test by combining the optimal test parameters to obtain a spline bending test result.
[0012] Furthermore, the optimization target determination module includes: A sensitivity index definition unit selects the parameters to be analyzed and defines the sensitivity index; An experimental scheme design unit, which designs the parameter experimental scheme, executes the experimental scheme, and collects experimental parameter settings and experimental output results during the experiment; A test parameter identification unit calculates the sensitivity index of each parameter according to the experimental parameter setting and the experimental output result, and identifies key parameters as the test parameters.
[0013] Furthermore, the finite element model building module includes: A geometric model building unit is used to build a geometric model of the spline and define material properties of the spline; Meshing unit, selecting a suitable unit type, and meshing the spline; A condition definition unit, defining boundary conditions and load conditions of the spline bending test; The finite element analysis unit sets solution parameters, inputs the test parameter combination into the finite element analysis model to perform finite element analysis, and obtains finite element analysis results.
[0014] The technical solution of the present invention can achieve the following technical effects: The present invention effectively solves the problems of difficult parameter identification, insufficient test efficiency and stability in spline bending tests by combining intelligent optimization algorithms and finite element analysis technology, improves the accuracy and efficiency of spline bending tests, reduces the number and cost of actual experiments, and can better adapt to complex test conditions and application scenarios.
[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 A schematic diagram of a process flow of an intelligent optimization method for a spline bending test; Figure 2 Schematic diagram of the process to obtain finite element analysis results; Figure 3 Schematic diagram of the structure of an intelligent optimization system for spline bending test. DETAILED DESCRIPTION
[0018] 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 only part of the embodiments of the present invention, rather than all the embodiments.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.
[0020] Embodiment 1 like Figure 1 As shown, an intelligent optimization method for spline bending test, the method comprises: S1: Determine the optimization target of the spline bending test and identify the test parameters of the spline bending test; Specifically, in order to clarify the direction of optimization, the specific optimization goals can be determined, such as minimizing material usage, maximizing structural strength, reducing the number of tests, or improving test accuracy; in order to achieve more precise adjustment and feedback, the key parameters of the spline bending test can be identified, including material properties (such as elastic modulus, yield strength), geometry (such as thickness, radius of curvature) and load conditions (such as load position, speed of applying load), etc.
[0021] S2: Based on the optimization goal, select a suitable intelligent optimization algorithm, and generate several test parameter combinations for the spline bending test through the intelligent optimization algorithm; In this embodiment, different optimization algorithms have different search strategies, which can help find the global optimal solution or the local optimal solution. The most suitable algorithm can be selected according to the specific optimization goals and problem characteristics, such as genetic algorithm, particle swarm algorithm and simulated annealing algorithm. After selecting a suitable optimization algorithm, the initial parameters of the optimization algorithm are set, and a certain number of test parameter combinations are initialized according to the selected optimization algorithm.
[0022] S3: Establish a finite element analysis model, input a number of test parameter combinations into the finite element analysis model for analysis, and obtain finite element analysis results; S4: Feedback the finite element analysis results to the intelligent optimization algorithm, adjust the intelligent optimization algorithm, and generate the optimal test parameter combination through the adjusted intelligent optimization algorithm; In this step, a suitable finite element analysis model can be established according to the specific requirements of the spline bending test, and several pre-selected or generated test parameter combinations are input into the established finite element analysis model. Each parameter combination represents a possible condition setting for the spline bending test. Each parameter combination is analyzed in the finite element analysis model, and the finite element analysis results under each parameter combination are collected, including maximum stress, displacement field, strain distribution, etc. The collected finite element analysis results are fed back to the intelligent optimization algorithm to optimize the intelligent optimization algorithm to help it adjust the parameter combination generated in the next step, including adjusting the parameters of the intelligent optimization algorithm, adjusting the range of the search space, updating the search direction or adjusting the step size, etc.; this process can gradually optimize the parameter combination of the spline bending test.
[0023] S5: Perform a spline bending test using an optimal test parameter combination to obtain a spline bending test result.
[0024] By combining intelligent optimization algorithm with finite element analysis, the key parameters in spline bending test can be optimized, which can improve the accuracy and efficiency of the test. The combination of optimization algorithm and finite element analysis forms a closed-loop system. The optimization algorithm generates parameter combinations, and finite element analysis evaluates its performance. The evaluation results in turn affect the subsequent steps of the optimization algorithm. Through the above-mentioned feedback mechanism, the optimization algorithm and simulation process are iterated multiple times, and the test parameter combination is gradually adjusted, so that the system can gradually approach the optimal solution.
[0025] The present invention effectively solves the problems of difficult parameter identification, insufficient test efficiency and stability in spline bending tests by combining intelligent optimization algorithms and finite element analysis technology, improves the accuracy and efficiency of spline bending tests, reduces the number and cost of actual experiments, and can better adapt to complex test conditions and application scenarios.
[0026] In order to better explore the entire parameter space, after generating the optimal test parameter combination, the corresponding finite element analysis results are obtained at the same time, and the intelligent optimization algorithm and finite element analysis model are further adjusted according to the corresponding finite element analysis results.
[0027] On the basis of the above embodiments, in order to better explore the entire parameter space and find a better combination of test parameters, the intelligent optimization algorithm and the finite element analysis model can be further adjusted to discover the limitations or shortcomings of the model and adjust the model accordingly to improve its accuracy and predictive ability.
[0028] As a preferred embodiment of this invention, the test parameters of the spline bending test are identified, including: A1: Select the parameters to be analyzed and define the sensitivity index; Specifically, determine the parameters to be analyzed, such as the geometric parameters of the spline, material properties, loading conditions, etc. To ensure the rationality and reality of the parameters, you can set the range of each parameter, such as the minimum and maximum values of the parameters. In order to evaluate each parameter, you can select a suitable sensitivity index to quantify the impact of the parameter on the output result. The sensitivity index can be selected: (1) Influence coefficient: It represents the direct influence of each parameter on the objective function and can be calculated by partial derivatives or other methods.
[0029] (2) Coefficient of variation: It measures the variability of a parameter by calculating the ratio of the standard deviation of the parameter to its mean.
[0030] (3) Normalized sensitivity index: Normalize the influence coefficient to make it easier to compare.
[0031] A2: Design parameter experiment plan, execute the experiment plan, and collect the experimental parameter settings and experimental output results during the experiment; In order to collect experiments under different parameter settings, this step can design experimental plans according to the parameter range and test objectives, perform experiments under different parameter combinations, record the input parameter values and output results corresponding to each experiment, and organize the experimental data into a table or matrix form for subsequent analysis. The experimental design can be a full factorial design or a partial factorial design. The full factorial design can fully cover all parameter combinations, accurately estimate all main effects and interaction effects, and have a more comprehensive understanding of the sensitivity of the parameters; compared with the full factorial design, the partial factorial design significantly reduces the number of experiments, and only selects some parameters for experimentation, which can still capture the main effects and some important interaction effects.
[0032] A3: Calculate the sensitivity index of each parameter based on the experimental parameter settings and experimental output results, and identify the key parameters as test parameters.
[0033] In order to evaluate the influence of each parameter on the test results, the sensitivity index of all parameters can be ranked. The parameters with higher sensitivity values have a greater impact on the results. Parameters with higher sensitivity are selected as key parameters, which have a significant impact on the test results.
[0034] Based on the above embodiments, Figure 2 As shown, a finite element analysis model is established, and several test parameter combinations are input into the finite element analysis model for analysis to obtain finite element analysis results, including: B1: Establish the geometric model of the spline and define the material properties of the spline; In this embodiment, material properties are assigned to various parts in the model. These properties usually include Young's modulus, Poisson's ratio, density, etc. If the spline material exhibits nonlinear behavior, such as plastic deformation, a more complex material model needs to be defined, such as a stress-strain curve. In the finite element model, the key parameter combination generated by the intelligent optimization algorithm needs to be input into the model, such as the thickness, width, load size, support position, etc. of the spline. Therefore, in order to be able to handle different parameter combinations, the finite element model needs to have certain parametric characteristics, that is, the geometric dimensions, material properties or load conditions of the model can be quickly adjusted.
[0035] B2: Select the appropriate element type and mesh the spline; The degree of mesh refinement has a great influence on the accuracy of the analysis results, so the appropriate mesh density can be selected according to the complexity of the problem to divide the geometric model into finite element meshes. For the selection of unit type, the finite element unit type can be selected according to the problem type, such as one-dimensional, two-dimensional, three-dimensional units, linear or nonlinear units, etc.
[0036] B3: Define boundary conditions and load conditions for spline bending test; This step defines the boundary conditions of the spline bending test, such as fixing the two ends of the spline or applying constraints at certain locations. The load defines how and where the external force or torque acts on the spline. It is one of the most important inputs in finite element analysis and simulates the load conditions in actual tests, such as applying bending force, torque or pressure. Applying the load requires determining the direction and magnitude of the load and defining the direction in which the load is applied, such as perpendicular to the spline plane or along the spline axis. The load direction is usually directly related to the test target, while the load magnitude can be set according to the actual test situation or standard test specifications.
[0037] B4: Set the solution parameters, input the test parameter combination into the finite element analysis model for finite element analysis, and obtain the finite element analysis results.
[0038] After applying boundary conditions and loads, you need to set the solver parameters to control the finite element analysis solution process. The solution parameters include: (1) Solution type: You can choose static analysis, dynamic analysis, nonlinear analysis, etc.
[0039] (2) Convergence criteria: Define the convergence criteria, such as the tolerance range of force, displacement or energy.
[0040] (3) Time step: If you are performing time-dependent analysis, such as dynamic analysis or nonlinear analysis, you can set the time step and total time.
[0041] (4) Iteration parameters: Set the parameters in the iteration process, such as the maximum number of iterations, initial step size, etc.
[0042] After setting the solution parameters, you can run the finite element solver to start the actual analysis and calculation. During the solver analysis, monitor the convergence behavior and calculation progress of the solution process. If the solution does not converge, you can adjust the solution parameters, boundary conditions or mesh division.
[0043] As a preferred embodiment of this invention, meshing the spline includes: C1: Analyze the geometric complexity and material properties of the geometric model and select the mesh density for preliminary division; C2: Screen the stress concentration area of the geometric model and adjust the mesh density of the stress concentration area to generate the final mesh; Stress concentration areas refer to places in the structure where stress distribution is uneven and local stress is significantly higher than other areas. Stress concentration areas are usually key parts that affect the overall strength and performance of the structure. In order to improve analysis accuracy and control computing resources, the grid can be locally encrypted; the grid is refined in areas where stress is concentrated or changes greatly to ensure that the unit size is small enough to capture stress changes. The unit size can be adjusted according to the rate of change of the stress gradient. Progressive encryption is usually used, that is, gradually transitioning from the stress concentration area to a coarser grid outward. By increasing the grid density in the stress concentration area, the stress distribution in these areas can be more accurately reflected and calculation errors can be reduced.
[0044] C3: Perform a quality check on the final mesh.
[0045] In this step, in order to ensure that the geometric shape and structure of the mesh division can correctly reflect the actual physical behavior in the finite element analysis and avoid calculation errors or instability caused by poor mesh quality, a mesh quality check can be performed. The mesh quality check includes: graphical check, unit quality index check, unit shape, unit size consistency, unit quality index, mesh continuity, etc.
[0046] Furthermore, the final mesh after quality check is subjected to convergence analysis.
[0047] Mesh quality checks can detect and correct potential mesh problems, but this does not fully guarantee the accuracy of the results. Therefore, the next step is to verify whether the mesh density is fine enough to ensure the stability of the analysis results. By gradually refining the mesh and observing the changes in the results, it is determined whether the analysis results tend to stabilize with the increase in mesh density. If the results no longer change significantly, it means that the mesh is fine enough to obtain accurate results. Convergence analysis can be implemented by comparing the calculation results at different mesh densities, such as displacement or stress; if the result change is less than a predetermined threshold after several mesh refinements, the convergence is considered good.
[0048] Furthermore, a termination condition is set for the iterative process of generating the optimal test parameter combination by the intelligent optimization algorithm.
[0049] On the basis of the above embodiments, in order to ensure that the optimization process converges within a reasonable time and obtains the optimal test parameter combination, a maximum number of iterations can be set. When the number of iterations of the algorithm reaches this value, the optimization process is automatically stopped. Even if the optimal solution has not been reached, the current best parameter combination will be used as the result; a threshold for the rate of change of the objective function value can also be set. When the change amplitude of the objective function is less than the threshold in several consecutive iterations, the algorithm is considered to have converged and the iteration is stopped; by setting reasonable termination conditions, unnecessary computing time and resource consumption can be greatly reduced, and the overall efficiency of the optimization process can be improved. Since excessive iterations may cause the algorithm to fall into a local optimal solution or cause the result to be too complex and impractical, setting termination conditions can help avoid this situation and ensure that the solution obtained is both reasonable and practical.
[0050] Embodiment 2 like Figure 3 As shown, an intelligent optimization system for spline bending test, the system includes: An optimization target determination module is used to determine the optimization target of the spline bending test and identify the test parameters of the spline bending test; The parameter combination generation module selects a suitable intelligent optimization algorithm based on the optimization target and generates several test parameter combinations for the spline bending test through the intelligent optimization algorithm; The finite element model building module builds the finite element analysis model, inputs a number of test parameter combinations into the finite element analysis model for analysis, and obtains the finite element analysis results; The analysis result feedback module feeds back the finite element analysis results to the intelligent optimization algorithm, adjusts the intelligent optimization algorithm, and generates the optimal test parameter combination through the adjusted intelligent optimization algorithm; The spline bending test module performs spline bending test through the optimal test parameter combination to obtain the spline bending test result.
[0051] The above-mentioned adjustment system in the present invention can effectively realize the intelligent optimization method of spline bending test, and the technical effects that can be achieved are as described in the above-mentioned embodiments, which will not be repeated here.
[0052] Furthermore, the optimization target determination module includes: A sensitivity index definition unit selects the parameters to be analyzed and defines the sensitivity index; The experimental scheme design unit conducts parameter experimental scheme design, executes the experimental scheme, and collects experimental parameter settings and experimental output results during the experiment; The test parameter identification unit calculates the sensitivity index of each parameter according to the experimental parameter settings and the experimental output results, and identifies the key parameters as test parameters.
[0053] Furthermore, the finite element model building module includes: A geometric model building unit is used to build a geometric model of the spline and define the material properties of the spline; Meshing unit, select the appropriate unit type, and mesh the spline; Condition definition unit, which defines the boundary conditions and load conditions of the spline bending test; The finite element analysis unit sets the solution parameters, inputs the test parameter combination into the finite element analysis model for finite element analysis, and obtains the finite element analysis results.
[0054] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.
[0055] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.
Claims
1. An intelligent optimization method for spline bending test, characterized in that: The method comprises: Determining an optimization target for a spline bending test and identifying test parameters for the spline bending test; Based on the optimization goal, a suitable intelligent optimization algorithm is selected, and several test parameter combinations of the spline bending test are generated by the intelligent optimization algorithm; Establishing a finite element analysis model, inputting a plurality of test parameter combinations into the finite element analysis model for analysis, and obtaining finite element analysis results; Feeding back the finite element analysis result to the intelligent optimization algorithm, adjusting the intelligent optimization algorithm, and generating an optimal test parameter combination through the adjusted intelligent optimization algorithm; The spline bending test is performed using the optimal test parameter combination to obtain a spline bending test result.
2. The intelligent optimization method for spline bending test according to claim 1, characterized in that: After generating the optimal test parameter combination, the corresponding finite element analysis results are obtained at the same time, and the intelligent optimization algorithm and the finite element analysis model are further adjusted according to the corresponding finite element analysis results.
3. The intelligent optimization method for spline bending test according to claim 1, characterized in that: The identifying test parameters of the spline bending test comprises: Select the parameters to be analyzed and define the sensitivity index; Design the parameter experiment plan, execute the experiment plan, and collect the experimental parameter settings and experimental output results during the experiment; The sensitivity index of each parameter is calculated according to the experimental parameter settings and the experimental output results, and key parameters are identified as the test parameters.
4. The intelligent optimization method for spline bending test according to claim 1, characterized in that: The step of establishing a finite element analysis model, inputting a plurality of test parameter combinations into the finite element analysis model for analysis, and obtaining finite element analysis results includes: Establishing a geometric model of the spline and defining material properties of the spline; Selecting a suitable unit type to mesh the spline; defining boundary conditions and load conditions for the spline bending test; The solution parameters are set, and the test parameter combination is input into the finite element analysis model to perform finite element analysis and obtain finite element analysis results.
5. The intelligent optimization method for spline bending test according to claim 4, characterized in that: Meshing the spline includes: Analyze the geometric complexity and material properties of the geometric model and select mesh density for preliminary partitioning; Screening the stress concentration area of the geometric model, adjusting the mesh density of the stress concentration area to generate a final mesh; The final mesh was quality checked.
6. The intelligent optimization method for spline bending test according to claim 5, characterized in that: A convergence analysis is performed on the final mesh after quality checking.
7. The intelligent optimization method for spline bending test according to claim 1, characterized in that: A termination condition is set for the iterative process of the intelligent optimization algorithm to generate the optimal test parameter combination.
8. An intelligent optimization system for spline bending test, characterized in that: The system comprises: An optimization target determination module is used to determine the optimization target of the spline bending test and identify the test parameters of the spline bending test; A parameter combination generation module, which selects a suitable intelligent optimization algorithm based on the optimization target, and generates several test parameter combinations of the spline bending test through the intelligent optimization algorithm; A finite element model building module is used to build a finite element analysis model, and input a plurality of test parameter combinations into the finite element analysis model for analysis to obtain a finite element analysis result; An analysis result feedback module feeds back the finite element analysis result to the intelligent optimization algorithm, adjusts the intelligent optimization algorithm, and generates an optimal test parameter combination through the adjusted intelligent optimization algorithm; The spline bending test module performs the spline bending test by combining the optimal test parameters to obtain a spline bending test result.
9. The intelligent optimization system for spline bending test according to claim 8, characterized in that: The optimization target determination module includes: A sensitivity index definition unit selects the parameters to be analyzed and defines the sensitivity index; An experimental scheme design unit, which designs the parameter experimental scheme, executes the experimental scheme, and collects experimental parameter settings and experimental output results during the experiment; A test parameter identification unit calculates the sensitivity index of each parameter according to the experimental parameter setting and the experimental output result, and identifies key parameters as the test parameters.
10. The intelligent optimization system for spline bending test according to claim 1, characterized in that: The finite element model building module includes: A geometric model building unit is used to build a geometric model of the spline and define material properties of the spline; Meshing unit, selecting a suitable unit type, and meshing the spline; A condition definition unit, defining boundary conditions and load conditions of the spline bending test; The finite element analysis unit sets solution parameters, inputs the test parameter combination into the finite element analysis model to perform finite element analysis, and obtains finite element analysis results.