CN117629616B - Rocker testing method and system - Google Patents

Abstract

The application relates to the technical field of rocker testing, and discloses a rocker testing method and system. The method comprises the following steps: creating a first rocker test parameter of the target rocker, and performing rocker test and data acquisition to obtain first rocker response data; performing thermal response factor combination, generating a second rocker test parameter, performing rocker test and data acquisition, and obtaining second rocker response data; performing rocker response change feature analysis to obtain a first rocker feature set and a second rocker feature set; performing thermal influence coefficient analysis and coding fusion to obtain a target rocker feature matrix; performing rocker thermal response anomaly analysis through a rocker anomaly analysis model to obtain a rocker thermal response anomaly index; through a hybrid topology optimization algorithm, the design parameters of the target rocker are optimized according to the abnormal thermal response indexes of the rocker, and the design parameters of the target rocker are obtained.

Description

Rocker testing method and system

Technical Field

The application relates to the technical field of rocker testing, in particular to a rocker testing method and system.

Background

In the field of modern engineering and science, rockers are widely used as a common mechanical element in control systems and mechanical devices. To ensure the performance and reliability of the rocker, the design and testing of the rocker becomes critical. Conventional testing methods typically rely on experience and trial and error, which limits the overall understanding and optimization of rocker performance. Thus, researchers are pressing to need an advanced, accurate method of testing rockers to better understand and optimize the design parameters of rockers, improving their performance and reliability.

However, there are problems and challenges that limit the further development of the rocker test method. Conventional testing methods generally provide limited information and have difficulty capturing complex features of the rocker response. Second, differences in the performance of rockers under different temperature conditions are often neglected, which leads to problems in practical applications. How to accurately evaluate the thermal response anomalies of the rocker and how to use this information for optimization of design parameters remains a challenging problem.

Disclosure of Invention

The application provides a rocker testing method and a system, which are used for improving the accuracy of the thermal response test analysis of a rocker.

In a first aspect, the present application provides a method for testing a rocker, the method comprising:

Creating a first rocker test parameter of a target rocker, and carrying out rocker test and data acquisition on the target rocker based on the first rocker test parameter to obtain first rocker response data;

performing thermal response factor combination on the first rocker test parameters to generate second rocker test parameters, and performing rocker test and data acquisition on the target rocker based on the second rocker test parameters to obtain second rocker response data;

Performing rocker response change feature analysis on the first rocker response data to obtain a first rocker feature set, and performing rocker response change feature analysis on the second rocker response data to obtain a second rocker feature set;

Performing thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and performing coding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix;

Inputting the target rocker characteristic matrix into a preset rocker abnormal analysis model to perform rocker thermal response abnormal analysis to obtain a rocker thermal response abnormal index;

And optimizing the design parameters of the target rocker according to the abnormal thermal response indexes of the rocker by a preset hybrid topology optimization algorithm to obtain the design parameters of the target rocker.

In a second aspect, the present application provides a rocker testing system comprising:

the first testing module is used for creating a first rocker testing parameter of the target rocker, and carrying out rocker testing and data acquisition on the target rocker based on the first rocker testing parameter to obtain first rocker response data;

The second testing module is used for carrying out thermal response factor combination on the first rocker testing parameters to generate second rocker testing parameters, and carrying out rocker testing and data acquisition on the target rocker based on the second rocker testing parameters to obtain second rocker response data;

The processing module is used for carrying out rocker response change characteristic analysis on the first rocker response data to obtain a first rocker characteristic set, and carrying out rocker response change characteristic analysis on the second rocker response data to obtain a second rocker characteristic set;

the fusion module is used for carrying out thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and carrying out coding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix;

the analysis module is used for inputting the target rocker characteristic matrix into a preset rocker abnormal analysis model to perform rocker thermal response abnormal analysis to obtain a rocker thermal response abnormal index;

And the optimization module is used for optimizing the design parameters of the target rocker according to the abnormal thermal response indexes of the rocker through a preset hybrid topology optimization algorithm to obtain the design parameters of the target rocker.

In the technical scheme provided by the application, a plurality of test parameters including a plurality of parameters such as test speed, test time, test mechanics and temperature are used to ensure comprehensive test of the performance of the target rocker. This helps capture various performance characteristics of the rocker. Through heat conduction and thermal expansion analysis, thermal response factors are combined, so that the test is closer to the actual use condition, and the accuracy and reliability of the test are improved. And generating a characteristic set of the rocker by characteristic analysis of the response data, and analyzing by using a thermal influence coefficient. This helps capture key features in rocker performance and provides a more comprehensive performance assessment. The rocker thermal response abnormality can be detected more accurately by introducing a rocker abnormality analysis model of a convolution long-short-term memory network and a full-connection layer. This improves the accuracy of fault detection and helps to discover potential problems in advance. Through a hybrid topology optimization algorithm, design parameters can be optimized according to abnormal thermal response indexes of the rocker, so that performance and reliability of the rocker are improved. Multiple technical characteristics are combined together, so that comprehensive target rocker performance evaluation can be provided, and further accuracy of rocker thermal response test analysis is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained based on these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an embodiment of a testing method for a joystick according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a testing system for a joystick according to an embodiment of the present application.

Detailed Description

The embodiment of the application provides a rocker testing method and a system. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, a specific flow of an embodiment of the present application is described below with reference to fig. 1, where an embodiment of a method for testing a rocker in an embodiment of the present application includes:

Step S101, creating first rocker test parameters of a target rocker, and carrying out rocker test and data acquisition on the target rocker based on the first rocker test parameters to obtain first rocker response data;

It will be appreciated that the execution body of the present application may be a rocker test system, and may also be a terminal or a server, which is not limited herein. The embodiment of the application is described by taking a server as an execution main body as an example.

Specifically, initial design parameters of the target rocker are obtained, including the size, shape, material properties, expected operating conditions, etc. of the rocker. Based on the initial design parameters, the target rocker is analyzed for testing speed and testing time, and the speed and the time length under which the test is carried out are determined, so that the performance of the rocker in actual use can be simulated most effectively, and the obtained testing speed parameters and testing time parameters can directly influence the implementation of the test and the accuracy of response data. And (3) carrying out mechanical analysis on the target rocker, and understanding and predicting the behavior and response of the rocker under stress. By the analysis, the mechanical parameters such as bending degree, vibration frequency, stability and the like of the rocker under the action of different forces and directions are obtained. These parameters help to simulate and evaluate the performance of the rocker in practical applications. A first rocker test parameter of the target rocker is created. The speed, time and mechanical analysis results are comprehensively considered, so that the test parameters can comprehensively and accurately reflect the design intention and expected performance of the rocker. And performing actual rocker testing on the target rocker based on the first rocker testing parameters. This test simulates not only the normal use of the rocker, but also possible extreme or abnormal conditions to evaluate its performance and stability comprehensively. And in the test process, response data acquisition is carried out on the target rocker. These data are direct evidence of the assessment of rocker performance and require accurate and comprehensive recording of the performance of the rocker under different test conditions. The raw response data often contains noise or missing values, which can affect the accuracy and reliability of subsequent analysis. Therefore, the data cleaning and missing value interpolation processing are performed on the initial remote sensing response data. The data cleaning can remove noise and abnormal values, so that the quality and consistency of the data are ensured, and the missing value interpolation is used for complementing the missing part of the data, so that the data set is more complete. By these processes, accurate, complete first rocker response data can be obtained.

Step S102, performing thermal response factor combination on the first rocker test parameters to generate second rocker test parameters, and performing rocker test and data acquisition on the target rocker based on the second rocker test parameters to obtain second rocker response data;

specifically, the target rocker is subjected to heat conduction analysis, so that heat transfer characteristics of the rocker under different temperature conditions are understood and predicted, and heat conduction parameters are obtained, wherein the parameters describe how heat propagates inside the rocker material, and the key indexes comprise heat conductivity, heat diffusivity and the like. And simultaneously, carrying out thermal expansion analysis on the target rocker, and evaluating the physical dimensional change of the rocker when the temperature changes. Thermal expansion analysis will provide detailed information about thermal expansion parameters such as expansion coefficient and temperature changes affecting rocker size. These two sets of parameters, namely the heat conduction parameter and the thermal expansion parameter, together constitute a comprehensive description of the behavior of the rocker in a thermal environment. And setting temperature test data of the rocker based on parameters obtained by thermal response analysis. These data will simulate the various temperature conditions encountered by a rocker in practical applications, including performance at normal temperature, stability at extreme high or low temperatures, and the effect of temperature change rates on rocker performance. The temperature test data is set to ensure that the second round of rocker testing is able to fully cover the thermal environment the rocker encounters in actual use. And carrying out parameter fusion on the temperature test data and the first rocker test parameters to generate second rocker test parameters. The process of parameter fusion not only needs to consider thermal response parameters, but also integrates speed, time and mechanical parameters obtained in the first round of testing. And performing a second round of rocker testing on the target rocker based on the generated second rocker testing parameters, and performing response data acquisition. This round of testing is more focused on the performance of rockers in thermal environments, including thermal stability, performance changes under thermal stress, and reliability over prolonged exposure to specific temperature conditions. During the data acquisition process, not only the response data of the rocker is recorded, but also data preprocessing is performed, which includes noise filtering, calibration data and necessary conversion and normalization processing of the data. These preprocessing steps ensure the accuracy and reliability of the resulting second rocker response data.

Step S103, performing rocker response change feature analysis on the first rocker response data to obtain a first rocker feature set, and performing rocker response change feature analysis on the second rocker response data to obtain a second rocker feature set;

Specifically, curve fitting is performed on the first rocker response data, and discrete data points are converted into a continuous response curve, so that the behavior characteristics of the rocker can be further analyzed. And similarly, performing curve fitting on the second rocker response data to obtain a corresponding second rocker response curve. And identifying characteristic points of the first rocker response curve, and finding out points representing key characteristics of rocker behaviors, such as extreme points, inflection points and the like, on the curve. These first candidate curve feature points can reveal the particular behavior and performance of the rocker under certain test conditions. And similarly, carrying out characteristic point identification processing on the second rocker response curve to obtain corresponding second candidate curve characteristic points, wherein the characteristic points reflect the performances of the rocker under different thermal response conditions. In order to further analyze and compare the curve feature points, a mean value calculation is performed on each response curve to obtain a first curve mean value and a second curve mean value. These two averages not only represent the average behavior of the respective curves, but also serve as screening criteria to help identify more representative feature points. And screening the first candidate curve characteristic points based on the first curve mean value, removing points which deviate from the mean value too far, and reserving first target curve characteristic points which can truly reflect the characteristics of the rocking bar. And similarly, screening the second candidate curve characteristic points according to the second curve average value to obtain second target curve characteristic points. And carrying out normalization processing on the characteristic points of the target curve. Normalization is a method of adjusting the range of values so that data from different sources or of different magnitudes can be compared and analyzed under the same criteria. And carrying out normalization processing on the characteristic points of the first target curve to obtain a first rocker characteristic set, wherein the characteristic set reflects the behavior characteristics of the rocker under the first round of test conditions in a standardized form. And similarly, carrying out normalization processing on the characteristic points of the second target curve to obtain a second rocker characteristic set, wherein the characteristic set shows the performances of the rocker under different thermal response conditions.

Step S104, carrying out thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and carrying out coding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix;

Specifically, a mean value calculation is performed on the first rocker feature set to obtain a mean value representing all features in the set, where the mean value reflects the mean behavior characteristics of the rocker under the first round of testing conditions. And similarly, carrying out average value calculation on the second rocker characteristic set to obtain a second rocker characteristic average value, wherein the average value represents the average behaviors of the rocker under different thermal response conditions. And calculating the standard deviation according to the mean value of the first rocker characteristic set, wherein the standard deviation is a statistic for measuring the data dispersion degree and reflects the fluctuation of the rocker characteristic value relative to the mean value. And similarly, calculating the standard deviation according to the mean value of the second rocker characteristic set. The two standard deviations provide variability conditions of the rocker characteristics under different test conditions, and data support is provided for understanding the consistency and stability of the rocker behavior. A correlation coefficient analysis is performed to determine a correlation between the first rocker feature set and the second rocker feature set. This analysis aims at assessing the variation pattern of the rocker characteristics under different test conditions, and by calculating the target thermal influence coefficient, the influence of the thermal environment on the rocker performance can be quantified. The first rocker feature set and the second rocker feature set are respectively encoded, and the features are converted into a series of encoding sequences, so that subsequent mathematical processing and analysis are facilitated. And after the first rocker characteristic coding sequence and the second rocker characteristic coding sequence are obtained, carrying out coding fusion according to the target thermal influence coefficient. The fusion process combines the rocker characteristics under two different test conditions to generate a target rocker characteristic matrix comprehensively considering the thermal influence. The feature matrix not only contains behavior information of the rocker in different environments, but also fuses quantitative analysis of the influence of the thermal environment on the performance of the rocker.

Step S105, inputting the target rocker feature matrix into a preset rocker abnormal analysis model to perform rocker thermal response abnormal analysis, so as to obtain a rocker thermal response abnormal index;

specifically, the target rocker feature matrix is input into a preset rocker anomaly analysis model. The model is a complex deep learning network, which includes two key components: a first convolutional long-duration memory network (ConvLSTM) and a second convolutional long-duration memory network, and two fully-connected layers. These networks combine the advantages of Convolutional Neural Networks (CNNs) and long-short-term memory networks (LSTM) to enable efficient processing and analysis of time-series data and extraction of complex spatial features. And processing the target rocker feature matrix through a first convolution long-short-time memory network, and extracting hidden features representing the rocker behaviors, wherein the features comprise important information in time sequence data. The resulting first rocker hidden feature includes the behavior pattern and characteristics of the rocker under certain conditions. And processing the target rocker feature matrix through a second convolution long-short-time memory network to obtain the hidden features of the intermediate rocker. And carrying out characteristic operation on the target thermal influence coefficient and the hidden characteristic of the intermediate rocker so as to ensure that the thermal influence is effectively integrated into model analysis, wherein the obtained hidden characteristic of the second rocker reflects the deep behavior of the rocker under the thermal response condition. And fusing the first rocker hidden feature and the second rocker hidden feature through a ReLU (RECTIFIED LINEAR Unit) activation function in the first full connection layer. The ReLU function is commonly used for increasing nonlinear characteristics of a network and solving the gradient disappearance problem in deep learning, and can help a model to capture more complex characteristic relations so as to obtain a fused rocker hidden characteristic, and the characteristic set integrates key information of the rocker under different test conditions and provides a basis for calculating abnormal indexes. And processing the hidden characteristics of the fusion rocker through a Softmax function in the second full-connection layer, and calculating the thermal response abnormal index of the rocker. The Softmax function is often used in multi-classification problems, which can transform a multi-element feature vector into a probability distribution, indicating the relatedness of each result. Through the function, the abnormal probabilities of the rocker under various thermal response conditions can be obtained, and the probabilities form a rocker thermal response abnormal index, so that a quantitative basis is provided for subsequent evaluation and decision.

And S106, optimizing the design parameters of the target rocker according to the abnormal thermal response indexes of the rocker by a preset hybrid topology optimization algorithm to obtain the design parameters of the target rocker.

Specifically, the optimization target and constraint conditions of the target rocker are defined according to the abnormal thermal response index of the rocker. These optimization objectives and constraints are based on the performance requirements and thermal response anomaly indicators of the rocker, ensuring that the rocker can meet the expected performance criteria in actual use and has good stability and reliability. The target design variables of the target rocker are selected, including the size, shape, material, or any other factor affecting the performance of the rocker. And carrying out design parameter analysis on the target design variable through a preset hybrid topology optimization algorithm. The algorithm combines various optimization techniques, such as gradient descent, genetic algorithm, simulated annealing and the like, and can find an optimal solution in a complex design space. By this algorithm, a plurality of candidate rocker design parameters may be generated, each representing a rocker design solution. Then, a rocker finite element model of the target rocker is constructed, which model is used to simulate and analyze the physical behavior of the rocker on a computer. And respectively carrying out rocker simulation test on the multiple candidate rocker design parameters based on the rocker finite element model to obtain rocker simulation test data of each candidate parameter. And respectively calculating the thermal response abnormal index of each candidate rocker design parameter through a rocker abnormal analysis model. The performance of each candidate design in terms of thermal response is evaluated using the previously defined anomaly analysis model, and the calculated anomaly metrics reflect the problems and risks encountered by each design in an actual thermal environment. And carrying out optimization iterative analysis on all candidate rocker design parameters according to the calculated rocker simulation abnormal indexes. And (3) by comparing the performance and stability of different design parameters, gradually iterating and adjusting the design, and finally generating the design parameters of the target rocker. This parameter is the design scheme with the best performance and lowest risk among all the candidate designs, and can ensure the best performance and the longest service life of the rocker in practical application. In the embodiment of the application, a plurality of test parameters including a plurality of parameters including test speed, test time, test mechanics and temperature are used to ensure the comprehensive test of the performance of the target rocker. This helps capture various performance characteristics of the rocker. Through heat conduction and thermal expansion analysis, thermal response factors are combined, so that the test is closer to the actual use condition, and the accuracy and reliability of the test are improved. And generating a characteristic set of the rocker by characteristic analysis of the response data, and analyzing by using a thermal influence coefficient. This helps capture key features in rocker performance and provides a more comprehensive performance assessment. The rocker thermal response abnormality can be detected more accurately by introducing a rocker abnormality analysis model of a convolution long-short-term memory network and a full-connection layer. This improves the accuracy of fault detection and helps to discover potential problems in advance. Through a hybrid topology optimization algorithm, design parameters can be optimized according to abnormal thermal response indexes of the rocker, so that performance and reliability of the rocker are improved. Multiple technical characteristics are combined together, so that comprehensive target rocker performance evaluation can be provided, and further accuracy of rocker thermal response test analysis is improved.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Acquiring initial rocker design parameters of a target rocker, and analyzing the test speed and the test time of the target rocker according to the initial rocker design parameters to obtain test speed parameters and test time parameters;

(2) Performing test mechanical analysis on the target rocker according to the initial rocker design parameters to obtain test mechanical parameters;

(3) Creating a first rocker test parameter of the target rocker according to the test speed parameter, the test time parameter and the test mechanical parameter;

(4) Performing rocker test on the target rocker based on the first rocker test parameter, and collecting response data of the target rocker to obtain initial rocker response data;

(5) And performing data cleaning and missing value interpolation processing on the initial remote sensing response data to obtain first rocker response data.

Specifically, initial design parameters of the target rocker are obtained. These parameters typically include the size, shape, material properties, and intended operating environment of the rocker, among others. Analysis of test speed and test time was performed. Determining at what speed and length of time the test is performed most effectively simulates the behavior of the rocker in actual use. For example, if the rocker is designed for a fast-reacting environment, the test speed will be set higher accordingly. By analyzing the design use and operating environment of the rocker, appropriate test speed parameters and test time parameters can be determined. And carrying out test mechanical analysis on the target rocker according to the initial rocker design parameters. The bending, vibration and other mechanical responses of the rocker when stressed are calculated. These test mechanical parameters reflect the various mechanical conditions encountered by the rocker in actual use. And creating a first rocker test parameter of the target rocker according to the test speed parameter, the test time parameter and the test mechanical parameter. The speed, time and mechanical analysis results are comprehensively considered, so that the test parameters can comprehensively and accurately reflect the design intention and expected performance of the rocker. And then, based on the first rocker test parameters, performing actual rocker test on the target rocker, and performing response data acquisition on the target rocker. These data are direct evidence of the assessment of rocker performance and require accurate and comprehensive recording of the performance of the rocker under different test conditions. The raw response data often contains noise or missing values, which can affect the accuracy and reliability of subsequent analysis. Therefore, data cleaning and missing value interpolation processing are required for the initial rocker response data. The data cleaning can remove noise and abnormal values, so that the quality and consistency of the data are ensured, and the missing value interpolation is used for complementing the missing part of the data, so that the data set is more complete. By these processes, accurate, complete first rocker response data can be obtained.

In a specific embodiment, the process of executing step S102 may specifically include the following steps:

(1) Performing thermal conduction analysis on the target rocker to obtain thermal conduction parameters, and performing thermal expansion analysis on the target rocker to obtain thermal expansion parameters;

(2) Setting temperature test data of the target rocker according to the heat conduction parameters and the heat expansion parameters;

(3) Carrying out parameter fusion on the temperature test data and the first rocker test parameters to generate second rocker test parameters;

(4) And performing rocker test on the target rocker based on the second rocker test parameters, and performing response data acquisition and data preprocessing on the target rocker to obtain second rocker response data.

In particular, conducting a thermal conduction analysis of a target rocker to determine the rate and manner in which heat is transferred in the rocker material typically involves calculating the thermal conductivity, a parameter that characterizes the ratio of heat flow per unit area to temperature gradient per unit time of the material. Whereas thermal expansion analysis focuses on how the size and shape of the rocker changes under the influence of temperature changes, this generally involves calculating the coefficient of thermal expansion of the material, a parameter that characterizes the rate of change of volume or length of the material over temperature changes. Temperature test data for the target rocker is set according to these parameters. These test data should cover the entire temperature range in which the rocker operates, including extreme high and low temperature conditions, by simulating the effects of different temperature conditions on the rocker in subsequent tests in order to evaluate the thermal environmental impact that the rocker encounters in practical use. And carrying out parameter fusion to generate a second rocker test parameter. This fusion process not only requires consideration of thermal response parameters, but also integrates the speed, time and mechanical parameters obtained in the first round of testing. Through this fusion process, the second rocker test parameters will be able to more accurately simulate the behavior of the rocker in an actual thermal environment. And carrying out a second round of rocker testing on the target rocker based on the generated second rocker testing parameters, and collecting response data. This round of testing is more focused on the performance of rockers in thermal environments, including thermal stability, performance changes under thermal stress, and reliability over prolonged exposure to specific temperature conditions. During the data acquisition process, not only the response data of the rocker is recorded, but also data preprocessing is performed, which includes noise filtering, calibration data and necessary conversion and normalization processing of the data. These preprocessing steps ensure the accuracy and reliability of the resulting second rocker response data. For example, when conducting thermal conductivity analysis, it is found that in a continuous operating state, some portion of the rocker may increase in temperature due to heat buildup, which may affect the performance or life of the rocker. By thermal expansion analysis, the rocker is found to deform slightly as the temperature changes significantly, which is not acceptable for a precision control system. Therefore, during testing, special attention is paid to the areas or conditions, so that the rocker design can effectively manage heat and keep the structure stable.

In a specific embodiment, the process of executing step S103 may specifically include the following steps:

(1) Performing curve fitting on the first rocker response data to obtain a first rocker response curve, and performing curve fitting on the second rocker response data to obtain a second rocker response curve;

(2) Performing curve characteristic point identification on the first rocker response curve to obtain a plurality of first candidate curve characteristic points, and performing curve characteristic point identification on the second rocker response curve to obtain a plurality of second candidate curve characteristic points;

(3) Calculating a curve average value of the first rocker response curve to obtain a first curve average value, and calculating a curve average value of the second rocker response curve to obtain a second curve average value;

(4) Performing curve characteristic point screening on the first candidate curve characteristic points according to the first curve mean value to obtain a plurality of first target curve characteristic points, and performing curve characteristic point screening on the second candidate curve characteristic points according to the second curve mean value to obtain a plurality of second target curve characteristic points;

(5) And carrying out feature normalization processing on the plurality of first target curve feature points to obtain a first rocker feature set, and carrying out feature normalization processing on the plurality of second target curve feature points to obtain a second rocker feature set.

Specifically, curve fitting is performed on the first rocker response data, and a first rocker response curve is obtained. A mathematical model that best represents the trend of the data is found using statistical or machine learning methods, such as least squares, polynomial fitting, or neural networks. Curve fitting not only helps understand the overall trend of the data, but also smoothes out the data noise present. And performing curve fitting on the second rocker response data to obtain a second rocker response curve. These two curves will represent the behavior patterns of the rocker under two different sets of test conditions, respectively. And (3) identifying curve characteristic points of the first rocker response curve, and finding out points such as maximum values, minimum values or inflection points and the like for describing key behaviors of the curve. These feature points represent a significant change or special behavior of the rocker response. And identifying curve characteristic points of the second rocker response curve to obtain second candidate curve characteristic points. Key information representing the behavior of the rocker is extracted from the two sets of response data. And calculating the curve mean value to obtain a standardized reference to evaluate and compare different curve characteristic points. The mean value of the first rocker response curve is calculated as a first curve mean value, and the mean value of the second rocker response curve is calculated as a second curve mean value. The two average values reflect the average response behaviors of the rocker under two groups of test conditions, and provide basis for subsequent feature point screening. And screening the first candidate curve characteristic points and the second candidate curve characteristic points according to the first curve mean value and the second curve mean value. And eliminating characteristic points which are not representative or deviate from the average action too far, and only retaining the characteristic points of the target curve which can truly reflect the characteristics of the rocker. For example, if the response value of a feature point is far above or below most data and there is no reasonable interpretation, then that point is due to noise or an abnormal situation and should be removed from the analysis. And carrying out feature normalization processing on the screened multiple first target curve feature points and the second target curve feature points. Normalization is a data preprocessing technique that is typically used to scale features to a uniform range or distribution so that a fair comparison between different features can be made while maintaining important relationships and structures in the data. By this process, a first and a second rocker feature set can be obtained that reflect, in a standardized form, the key behavior and characteristics of the rocker under two different sets of test conditions.

In a specific embodiment, the process of executing step S104 may specifically include the following steps:

(1) Performing average value calculation on the first rocker feature set to obtain a first rocker feature average value, and performing average value calculation on the second rocker feature set to obtain a second rocker feature average value;

(2) Performing standard deviation calculation on the first rocker feature set according to the first rocker feature mean value to obtain a first rocker feature standard deviation, and performing standard deviation calculation on the second rocker feature set according to the second rocker feature mean value to obtain a second rocker feature standard deviation;

(3) According to the first rocker characteristic mean value, the second rocker characteristic mean value, the first rocker characteristic standard deviation and the second rocker characteristic standard deviation, carrying out correlation coefficient analysis on the first rocker characteristic set and the second rocker characteristic set to obtain a target thermal influence coefficient;

(4) Encoding the first rocker feature set and the second rocker feature set respectively to obtain a first rocker feature encoding sequence and a second rocker feature encoding sequence;

(5) And carrying out coding fusion on the first rocker feature coding sequence and the second rocker feature coding sequence according to the target thermal influence coefficient to obtain a target rocker feature matrix.

Specifically, the average value of the first rocker feature set is calculated, and the first rocker feature average value is obtained. The mean provides a measure of the central tendency of the rocker to behave under a first set of test conditions. And similarly, carrying out mean value calculation on the second rocker characteristic set to obtain a second rocker characteristic mean value. These two averages represent the average behavior characteristics of the rocker under two different sets of test conditions, respectively. And carrying out standard deviation calculation on the first rocker characteristic set according to the first rocker characteristic mean value to obtain a first rocker characteristic standard deviation. The standard deviation is a statistic for measuring the dispersion degree of data, and reflects the fluctuation of the characteristic value of the rocker relative to the mean value. From this calculation, the variability of the rocker features under the first set of test conditions can be understood. And similarly, calculating the standard deviation of the second rocker characteristic set according to the second rocker characteristic mean value to obtain a second rocker characteristic standard deviation. The two standard deviations provide variability of the rocker characteristics under two sets of test conditions, and data support is provided for understanding the consistency and stability of rocker behavior. A correlation coefficient analysis is performed to determine a correlation between the first rocker feature set and the second rocker feature set. The change modes of the characteristics of the rocker under different test conditions are evaluated, and the influence of the thermal environment on the performance of the rocker can be quantified by calculating a target thermal influence coefficient, wherein the coefficient provides a measure of the behavior change of the rocker under different temperature conditions. And respectively encoding the first rocker feature set and the second rocker feature set, and converting the features into a series of encoding sequences to obtain a first rocker feature encoding sequence and a second rocker feature encoding sequence. And carrying out coding fusion according to the target thermal influence coefficient. And combining the rocker characteristics under two different test conditions to generate a target rocker characteristic matrix comprehensively considering the thermal influence. The feature matrix not only contains behavior information of the rocker in different environments, but also fuses quantitative analysis of the influence of the thermal environment on the performance of the rocker. For example, assuming a rocker for fine control, after conducting thermal conduction and thermal expansion analysis, the performance of the rocker was found to be significantly affected by heat over a range of temperatures. In the first set of tests, the rockers exhibited consistent response times and stable dynamic behavior at normal temperatures, while in the second set of tests, the rockers exhibited different response times and dynamic characteristics at higher temperatures. By performing curve fitting and feature point identification on the two groups of data, the variation trend of response time along with temperature and the variation situation of dynamic behavior can be found. The information is quantized through mean value and standard deviation calculation, and then through correlation coefficient analysis and coding fusion, a rocker characteristic matrix containing temperature influence information is finally formed.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Inputting a target rocker characteristic matrix into a preset rocker anomaly analysis model, wherein the rocker anomaly analysis model comprises a first convolution long-short time memory network, a second convolution long-short time memory network, a first full-connection layer and a second full-connection layer;

(2) Extracting hidden features of the target rocker feature matrix through a first convolution long-short-time memory network to obtain first rocker hidden features;

(3) Extracting hidden features of the target rocker feature matrix through a second convolution long-short-time memory network to obtain middle rocker hidden features, and carrying out feature operation on the target thermal influence coefficient and the middle rocker hidden features to obtain second rocker hidden features;

(4) Feature fusion is carried out on the first rocker hidden feature and the second rocker hidden feature through a ReLU function in the first full-connection layer, and fusion rocker hidden features are obtained;

(5) And calculating the rocker thermal response abnormal index by using a Softmax function in the second full-connection layer to fuse hidden characteristics of the rocker, so as to obtain the rocker thermal response abnormal index.

Specifically, the feature matrix of the target rocker is input into a preset rocker anomaly analysis model. The model is a deep learning network, and the rocker anomaly analysis model comprises a first convolution long-short time memory network, a second convolution long-short time memory network, a first full-connection layer and a second full-connection layer. These networks combine the advantages of Convolutional Neural Networks (CNNs) and long-short-term memory networks (LSTM) to enable efficient processing and analysis of time-series data and extraction of complex spatial features. And processing the target rocker characteristic matrix through a first convolution long-short-time memory network. The ConvLSTM structure is adapted to process spatial data with time series properties that can capture long-term dependencies in the time series while preserving spatial information. During processing, the first convolution long-short-duration memory network will extract hidden features representing the behavior of the rocker, which features contain important information in the time-series data. The resulting first rocker hidden feature includes the behavior pattern and characteristics of the rocker under certain conditions. The second convolution long-short time memory network further processes the target rocker feature matrix. The purpose of this layer is to extract deeper features and perform feature operations in combination with the target thermal influence coefficients. The target thermal influence coefficient is taken as an important input, reflects the influence of the thermal environment on the performance of the rocker, and can be combined with the hidden characteristic of the intermediate rocker, so that the thermal environment factors can be effectively integrated into the model analysis, and the obtained hidden characteristic of the second rocker reflects the deep behavior of the rocker under the thermal response condition. And fusing the first rocker hidden feature and the second rocker hidden feature through a ReLU (RECTIFIED LINEAR Unit) activation function in the first full connection layer. ReLU functions are commonly used in deep learning to increase the nonlinear characteristics of the network and solve the gradient vanishing problem, which can help the model capture more complex characteristic relationships. Through the processing of the step, the hidden characteristics of the fusion rocker are obtained, and the characteristic set integrates key information of the rocker under different testing conditions, so that a basis is provided for calculating abnormal indexes. And processing the hidden characteristics of the fusion rocker through a Softmax function in the second full-connection layer, and calculating the thermal response abnormal index of the rocker. The Softmax function is often used in multi-classification problems, which can transform a multi-element feature vector into a probability distribution, indicating the relatedness of each result. Through the function, the abnormal probabilities of the rocker under various thermal response conditions can be obtained, and the probabilities form a rocker thermal response abnormal index, so that a quantitative basis is provided for subsequent evaluation and decision. For example, assuming a rocker is tested under different temperature conditions, the characterization matrix includes data in multiple dimensions, such as response time, vibration frequency, etc. By processing the first and second convolution long and short time memory networks, complex patterns of these features over time and temperature can be extracted. These modes show a significant increase in response time of the rocker at certain specific temperatures, or an abnormal change in vibration frequency. Through fusion of the ReLU function and abnormal index calculation of the Softmax function, an index set which comprehensively reflects abnormal probability of the rocker under various thermal response conditions can be finally obtained. These indicators can help identify potential problems with the rocker under certain conditions, as well as provide important information for improving the rocker design and increasing its reliability.

In a specific embodiment, the process of executing step S106 may specifically include the following steps:

(1) Defining an optimization target and a constraint condition of a target rocker according to the abnormal thermal response index of the rocker, and selecting a target design variable of the target rocker;

(2) Carrying out design parameter analysis on target design variables according to an optimization target and constraint conditions by a preset hybrid topology optimization algorithm to generate a plurality of candidate rocker design parameters;

(3) Constructing a rocker finite element model of a target rocker, and respectively performing a rocker simulation test on a plurality of candidate rocker design parameters based on the rocker finite element model to obtain rocker simulation test data of each candidate rocker design parameter;

(4) Respectively calculating thermal response abnormal indexes of the rocker simulation test data through a rocker abnormal analysis model to obtain rocker simulation abnormal indexes of each candidate rocker design parameter;

(5) And carrying out optimization iterative analysis on the multiple candidate rocker design parameters according to the rocker simulation abnormal indexes to generate target rocker design parameters.

Specifically, the optimization target and constraint conditions of the target rocker are defined according to the abnormal thermal response index of the rocker. These indicators reflect the performance and reliability of the rocker under certain thermal conditions, and optimization objectives include reducing thermal response anomalies, improving stability and durability of the rocker, etc. Constraints include physical properties of the material, cost constraints, design specifications, or any other criteria that must be complied with. The target design variables of the target rockers are selected, which are parameters to be adjusted in the optimization process, such as the size, shape, material, or other relevant properties of the rockers. And carrying out design parameter analysis on the target design variable through a preset hybrid topology optimization algorithm. The algorithm combines a plurality of optimization techniques, and can find an optimal solution in a complex design space. The design variables are gradually improved in an iterative mode according to defined optimization targets and constraint conditions, and a plurality of candidate rocker design parameters are generated. These parameters represent a series of rocker design schemes, each of which meets to some extent optimization objectives and constraints. Then, a rocker finite element model of the target rocker is constructed. Finite Element Analysis (FEA) is a computer simulation technique used to predict the response of an object under the action of an external force. By building a finite element model of the rocker, the performance of the rocker can be predicted and analyzed without actually manufacturing and testing the rocker. And based on the model, performing rocker simulation test on each candidate rocker design parameter to obtain rocker simulation test data of each design parameter. These data provide detailed information about how the candidate design behaves in the actual application. And respectively calculating the thermal response abnormal index of each candidate rocker design parameter through a rocker abnormal analysis model. The performance of each candidate design in terms of thermal response is evaluated using the previously defined anomaly analysis model, and the calculated anomaly metrics reflect the problems and risks encountered by each design in an actual thermal environment. And carrying out optimization iterative analysis on all candidate rocker design parameters according to the calculated rocker simulation abnormal indexes. And (3) by comparing the performance and stability of different design parameters, gradually iterating and adjusting the design, and finally generating the design parameters of the target rocker. This parameter is the design scheme with the best performance and lowest risk among all the candidate designs, and can ensure the best performance and the longest service life of the rocker in practical application. For example, assuming a rocker is unstable in performance in a high temperature environment, the abnormal thermal response index is higher than expected. Through a hybrid topology optimization algorithm, a number of candidate designs are generated, some of which improve their thermal stability by changing the material or structure of the rockers. After simulation test and abnormal index calculation are carried out on the candidate designs, the performance of a certain design at high temperature is found to be greatly improved. Through optimization iterative analysis, the design is finally determined as a target rocker design parameter. Thus, not only the performance of the rocker is improved, but also the risk of abnormality in actual use is reduced.

The method for testing the rocker in the embodiment of the present application is described above, and the system for testing the rocker in the embodiment of the present application is described below, referring to fig. 2, where an embodiment of the system for testing the rocker in the embodiment of the present application includes:

the first test module 201 is configured to create a first rocker test parameter of a target rocker, and perform a rocker test and data acquisition on the target rocker based on the first rocker test parameter, so as to obtain first rocker response data;

The second testing module 202 is configured to perform thermal response factor combination on the first rocker testing parameter to generate a second rocker testing parameter, and perform rocker testing and data acquisition on the target rocker based on the second rocker testing parameter to obtain second rocker response data;

the processing module 203 is configured to perform a rocker response change feature analysis on the first rocker response data to obtain a first rocker feature set, and perform a rocker response change feature analysis on the second rocker response data to obtain a second rocker feature set;

The fusion module 204 is configured to perform thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and perform encoding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix;

the analysis module 205 is configured to input the target rocker feature matrix into a preset rocker anomaly analysis model to perform rocker thermal response anomaly analysis, so as to obtain a rocker thermal response anomaly index;

and the optimization module 206 is configured to optimize the design parameters of the target rocker according to the thermal response anomaly indexes of the rocker by using a preset hybrid topology optimization algorithm, so as to obtain the design parameters of the target rocker.

Through the cooperation of the above components, a plurality of test parameters including test speed, test time, test mechanics and temperature are used to ensure the comprehensive test of the performance of the target rocker. This helps capture various performance characteristics of the rocker. Through heat conduction and thermal expansion analysis, thermal response factors are combined, so that the test is closer to the actual use condition, and the accuracy and reliability of the test are improved. And generating a characteristic set of the rocker by characteristic analysis of the response data, and analyzing by using a thermal influence coefficient. This helps capture key features in rocker performance and provides a more comprehensive performance assessment. The rocker thermal response abnormality can be detected more accurately by introducing a rocker abnormality analysis model of a convolution long-short-term memory network and a full-connection layer. This improves the accuracy of fault detection and helps to discover potential problems in advance. Through a hybrid topology optimization algorithm, design parameters can be optimized according to abnormal thermal response indexes of the rocker, so that performance and reliability of the rocker are improved. Multiple technical characteristics are combined together, so that comprehensive target rocker performance evaluation can be provided, and further accuracy of rocker thermal response test analysis is improved.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, systems and units may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims (7)

1. The rocker testing method is characterized by comprising the following steps of:

Creating a first rocker test parameter of a target rocker, and carrying out rocker test and data acquisition on the target rocker based on the first rocker test parameter to obtain first rocker response data; the method specifically comprises the following steps: acquiring initial rocker design parameters of a target rocker, and analyzing the test speed and the test time of the target rocker according to the initial rocker design parameters to obtain test speed parameters and test time parameters; performing test mechanical analysis on the target rocker according to the initial rocker design parameters to obtain test mechanical parameters; creating a first rocker test parameter of the target rocker according to the test speed parameter, the test time parameter and the test mechanical parameter; performing rocker testing on the target rocker based on the first rocker testing parameters, and collecting response data of the target rocker to obtain initial rocker response data; performing data cleaning and missing value interpolation processing on the initial remote sensing response data to obtain first rocker response data;

performing thermal response factor combination on the first rocker test parameters to generate second rocker test parameters, and performing rocker test and data acquisition on the target rocker based on the second rocker test parameters to obtain second rocker response data;

Performing rocker response change feature analysis on the first rocker response data to obtain a first rocker feature set, and performing rocker response change feature analysis on the second rocker response data to obtain a second rocker feature set;

Performing thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and performing coding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix;

Inputting the target rocker characteristic matrix into a preset rocker abnormal analysis model to perform rocker thermal response abnormal analysis to obtain a rocker thermal response abnormal index;

And optimizing the design parameters of the target rocker according to the abnormal thermal response indexes of the rocker by a preset hybrid topology optimization algorithm to obtain the design parameters of the target rocker.

2. The rocker testing method of claim 1, wherein the performing thermal response factor combination on the first rocker testing parameter to generate a second rocker testing parameter, and performing rocker testing and data acquisition on the target rocker based on the second rocker testing parameter, to obtain second rocker response data, includes:

Performing thermal conduction analysis on the target rocker to obtain thermal conduction parameters, and performing thermal expansion analysis on the target rocker to obtain thermal expansion parameters;

setting temperature test data of the target rocker according to the heat conduction parameter and the thermal expansion parameter;

performing parameter fusion on the temperature test data and the first rocker test parameters to generate second rocker test parameters;

and performing rocker testing on the target rocker based on the second rocker testing parameters, and performing response data acquisition and data preprocessing on the target rocker to obtain second rocker response data.

3. The method of claim 2, wherein performing a rocker response change feature analysis on the first rocker response data to obtain a first rocker feature set, and performing a rocker response change feature analysis on the second rocker response data to obtain a second rocker feature set, comprises:

performing curve fitting on the first rocker response data to obtain a first rocker response curve, and performing curve fitting on the second rocker response data to obtain a second rocker response curve;

Performing curve characteristic point identification on the first rocker response curve to obtain a plurality of first candidate curve characteristic points, and performing curve characteristic point identification on the second rocker response curve to obtain a plurality of second candidate curve characteristic points;

Calculating a curve average value of the first rocker response curve to obtain a first curve average value, and calculating a curve average value of the second rocker response curve to obtain a second curve average value;

performing curve characteristic point screening on the first candidate curve characteristic points according to the first curve average value to obtain a plurality of first target curve characteristic points, and performing curve characteristic point screening on the second candidate curve characteristic points according to the second curve average value to obtain a plurality of second target curve characteristic points;

And carrying out feature normalization processing on the plurality of first target curve feature points to obtain a first rocker feature set, and carrying out feature normalization processing on the plurality of second target curve feature points to obtain a second rocker feature set.

4. The rocker testing method of claim 3, wherein the performing thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and performing encoding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix, includes:

performing average value calculation on the first rocker feature set to obtain a first rocker feature average value, and performing average value calculation on the second rocker feature set to obtain a second rocker feature average value;

Performing standard deviation calculation on the first rocker feature set according to the first rocker feature mean to obtain a first rocker feature standard deviation, and performing standard deviation calculation on the second rocker feature set according to the second rocker feature mean to obtain a second rocker feature standard deviation;

according to the first rocker characteristic mean value, the second rocker characteristic mean value, the first rocker characteristic standard deviation and the second rocker characteristic standard deviation, carrying out correlation coefficient analysis on the first rocker characteristic set and the second rocker characteristic set to obtain a target thermal influence coefficient;

Encoding the first rocker feature set and the second rocker feature set respectively to obtain a first rocker feature encoding sequence and a second rocker feature encoding sequence;

and carrying out coding fusion on the first rocker feature coding sequence and the second rocker feature coding sequence according to the target thermal influence coefficient to obtain a target rocker feature matrix.

5. The rocker testing method according to claim 4, wherein the step of inputting the target rocker feature matrix into a preset rocker anomaly analysis model to perform a rocker thermal response anomaly analysis to obtain a rocker thermal response anomaly index comprises the steps of:

Inputting the target rocker feature matrix into a preset rocker anomaly analysis model, wherein the rocker anomaly analysis model comprises a first convolution long-short time memory network, a second convolution long-short time memory network, a first full-connection layer and a second full-connection layer;

Extracting hidden features of the target rocker feature matrix through the first convolution long-short-time memory network to obtain first rocker hidden features;

Extracting hidden features of the target rocker feature matrix through the second convolution long short-time memory network to obtain middle rocker hidden features, and carrying out feature operation on the target thermal influence coefficient and the middle rocker hidden features to obtain second rocker hidden features;

Performing feature fusion on the first rocker hidden feature and the second rocker hidden feature through a ReLU function in the first full-connection layer to obtain a fused rocker hidden feature;

and calculating the rocker thermal response abnormal index of the fusion rocker hidden characteristic through a Softmax function in the second full-connection layer to obtain the rocker thermal response abnormal index.

6. The rocker testing method according to claim 5, wherein the optimizing the design parameters of the target rockers according to the abnormal thermal response indexes of the rockers by a preset hybrid topology optimization algorithm to obtain the design parameters of the target rockers comprises:

Defining an optimization target and a constraint condition of the target rocker according to the rocker thermal response abnormal index, and selecting a target design variable of the target rocker;

Carrying out design parameter analysis on the target design variable according to the optimization target and the constraint condition through a preset hybrid topology optimization algorithm to generate a plurality of candidate rocker design parameters;

constructing a rocker finite element model of the target rocker, and respectively carrying out rocker simulation test on the plurality of candidate rocker design parameters based on the rocker finite element model to obtain rocker simulation test data of each candidate rocker design parameter;

Respectively calculating thermal response abnormal indexes of the rocker simulation test data through the rocker abnormal analysis model to obtain rocker simulation abnormal indexes of each candidate rocker design parameter;

And carrying out optimization iterative analysis on the plurality of candidate rocker design parameters according to the rocker simulation abnormal indexes to generate target rocker design parameters.

7. A rocker testing system, the rocker testing system comprising:

The first testing module is used for creating a first rocker testing parameter of the target rocker, and carrying out rocker testing and data acquisition on the target rocker based on the first rocker testing parameter to obtain first rocker response data; the method specifically comprises the following steps: acquiring initial rocker design parameters of a target rocker, and analyzing the test speed and the test time of the target rocker according to the initial rocker design parameters to obtain test speed parameters and test time parameters; performing test mechanical analysis on the target rocker according to the initial rocker design parameters to obtain test mechanical parameters; creating a first rocker test parameter of the target rocker according to the test speed parameter, the test time parameter and the test mechanical parameter; performing rocker testing on the target rocker based on the first rocker testing parameters, and collecting response data of the target rocker to obtain initial rocker response data; performing data cleaning and missing value interpolation processing on the initial remote sensing response data to obtain first rocker response data;

The second testing module is used for carrying out thermal response factor combination on the first rocker testing parameters to generate second rocker testing parameters, and carrying out rocker testing and data acquisition on the target rocker based on the second rocker testing parameters to obtain second rocker response data;

The processing module is used for carrying out rocker response change characteristic analysis on the first rocker response data to obtain a first rocker characteristic set, and carrying out rocker response change characteristic analysis on the second rocker response data to obtain a second rocker characteristic set;

the fusion module is used for carrying out thermal influence coefficient analysis on the first rocker feature set and the second rocker feature set to obtain a target thermal influence coefficient, and carrying out coding fusion on the first rocker feature set and the second rocker feature set according to the target thermal influence coefficient to obtain a target rocker feature matrix;

the analysis module is used for inputting the target rocker characteristic matrix into a preset rocker abnormal analysis model to perform rocker thermal response abnormal analysis to obtain a rocker thermal response abnormal index;

And the optimization module is used for optimizing the design parameters of the target rocker according to the abnormal thermal response indexes of the rocker through a preset hybrid topology optimization algorithm to obtain the design parameters of the target rocker.