Passenger car four channel chassis component durability test device

Abstract

The application discloses a passenger car four-channel chassis component durability test device and relates to the field of durability tests, which comprises a test frame main body, a tractor one installed at the bottom of the test frame main body, a tractor two installed at the left side of the test frame main body, a tractor three installed at the right side of the test frame main body and a control module installed on the front of the test frame main body, wherein the tractor one, the tractor two and the tractor three are used for fixing the tested components and conducting horizontal, vertical and torsional fatigue tests; a prediction model is constructed, the test state of a future period is predicted and obtained based on the test data of the current test project, the mapping relationship between the initial period damage state of the test component and the future period fission and deformation state is analyzed, and then the long-term test performance of the tested object can be quickly obtained through short-term actual tests.

Description

Technical Field

[0001] This invention relates to the field of durability testing technology, specifically to a durability testing device for four-channel chassis components of passenger vehicles. Background Technology

[0002] With the development of the automotive industry and the increasing demands for safety, reliability and service life of passenger vehicles, modern automotive chassis technology is becoming increasingly complex, involving a variety of materials and components. Automakers need to conduct systematic and comprehensive testing on the fatigue, load-bearing capacity and damage evolution process of chassis components under various working conditions. Chassis components are subjected to multiple composite loads such as lateral, vertical and torsional loads during driving. Durability testing can help manufacturers develop more durable products, thereby reducing resource waste and environmental impact.

[0003] The rise of big data and machine learning has enabled the collection and analysis of large amounts of data during the testing process, thereby improving the accuracy and efficiency of testing. Through data analysis, manufacturers can better predict product performance and maintenance needs.

[0004] Traditional test benches often use single-channel or fixed-direction loading, which can only simulate single vertical or lateral fatigue loads. They are difficult to truly reflect the multi-directional composite stresses that chassis components bear in complex road conditions. In actual driving scenarios, the frequency and amplitude of the impact force they bear are not uniform in a short period of time. Traditional methods predict damage based on empirical formulas or simplified mechanical models, which are difficult to capture complex behaviors such as nonlinear degradation of materials and microcrack propagation. This results in large deviations in life prediction. They also require manual design and rely on a fixed sequence, such as static load before dynamic load, making it difficult to quickly respond to the testing requirements of new materials or design changes. Summary of the Invention

[0005] (a) Technical problem to be solved: In view of the above-mentioned shortcomings of the prior art, the present invention provides a four-channel chassis component durability testing device for passenger vehicles, which can effectively solve the problems of the prior art.

[0006] (II) Technical Solution: To achieve the above objectives, the present invention is implemented through the following technical solution:

[0007] This invention discloses a durability testing device for a four-channel chassis component of a passenger vehicle, comprising a test frame body. A first traction device is installed at the bottom of the test frame body, a second traction device is installed on the left side of the test frame body, a third traction device is installed on the right side of the test frame body, and a control module is installed on the front of the test frame body. Wherein:

[0008] The first, second, and third traction devices are used to fix the tested component and to pull it to perform lateral, vertical, and torsional fatigue tests.

[0009] The control module includes:

[0010] The test execution unit is used to register various combined test items, select and execute a certain combined test item, and obtain the test parameters of the tested component in the current cycle.

[0011] The analysis and prediction unit is used to perform model analysis on the test parameters obtained from the combined test items and predict the state data of damage evolution of test components in future cycles.

[0012] The data generation module is used to simulate and generate corresponding combinations of virtual test items based on the state data of damage evolution of test components in future cycles.

[0013] The project adjustment module is used to analyze the various test parameters in the current test combination based on the difference between the current test data and the predicted data, as well as the virtual test project combination, and to use the optimization algorithm to calculate the adjusted test parameter combination as the plan for the next round of testing.

[0014] The active verification module is used to generate control commands for traction device one, traction device two, and traction device three based on the adjusted combined test project plan, and to compare the verified data with the predicted data as the basis for updating the prediction model parameters.

[0015] Furthermore, the test execution unit has sub-modules deployed at its lower levels, including a project management module, a combination selection module, and a data acquisition module. The project management module and the combination selection module are interconnected via a wireless network, and the combination selection module and the data acquisition module are interconnected via a wireless network.

[0016] The project management module is used to record the combination of various test items corresponding to Tractor 1, Tractor 2 and Tractor 3, and to classify the entered combined test items.

[0017] The combination selection module is used to select the combination test items for the current period based on the current test status, component performance, and historical test trend data.

[0018] The data acquisition module is used to perform a complete cycle of durability testing on a specified test component based on the selected combination of test items, and to collect data on the status of the test equipment and the parameter data of the test component during the test process through sensors.

[0019] Furthermore, the process of the combined selection module selecting items is as follows:

[0020] Step 1: Obtain the estimated performance parameters of the current test component and the trend data of historical tests. The trend data includes the variation pattern of component performance parameters, damage accumulation rate and correlation characteristics of test interruption events in historical tests.

[0021] Step 2: Dynamically match the component performance parameters from historical tests with the pre-existing combined test items in the project management module, and extract candidate test item combinations that are associated with the current test component type, preset durability target, and damage sensitivity direction;

[0022] Step 3: Preset the scoring model, and score the candidate test item combination in multiple dimensions based on the scoring model. The scoring dimensions include test efficiency weight, damage feature coverage weight, and effectiveness feedback weight of historical similar test schemes.

[0023] Step 4: Filter candidate combinations with scores higher than the preset threshold, and determine the optimal combination of test items for the current period using a dynamic programming algorithm based on the real-time test resource usage status and optimization target constraints.

[0024] Step 5: Send the optimal combination test items to the data acquisition module to trigger the execution of the full cycle test, and record the currently selected logical parameters as the input for updating historical trend data.

[0025] Furthermore, the analysis and prediction unit is equipped with sub-modules, including a damage analysis module, a model building module, and a damage prediction module. The damage analysis module and the model building module are interconnected via a wireless network, and the model building module and the damage prediction module are also interconnected via a wireless network.

[0026] The damage analysis module is used to perform preliminary analysis on the collected data, identify various damage states of the test components during loading, quantify and record the damage state of each test cycle, and establish a corresponding damage state file by combining historical data, recording the time, location and damage degree of each test point.

[0027] The model building module is used to build a prediction model based on the damage state data obtained from single-cycle testing, using machine learning algorithms. The prediction model establishes a mapping relationship between the initial cycle damage state and the future cycle fission and deformation state, and filters key feature variables related to damage evolution.

[0028] The damage prediction module is used to predict the damage status over several future periods using a pre-built prediction model. The model takes into account various test combinations of data from the current period and outputs the state data of the damage evolution of the test components in future periods.

[0029] Furthermore, during the process of screening key feature variables, the model building module receives test combination data collected in real time by sensors within the current period, obtains the loading force value, displacement, torque parameters and component deformation feature data of each test component, normalizes the obtained feature data, and extracts preset damage feature variables, including: stress concentration factor, strain gradient value and material fatigue accumulation factor.

[0030] Furthermore, the prediction model constructed by the model building module establishes a multi-period time series correlation through an LSTM neural network, and outputs damage state prediction data containing several future test periods. The prediction data is decomposed into specific damage types, occurrence locations, damage degrees, and prediction time points. The damage types include at least two of the following: crack propagation rate, plastic deformation, and loose gaps in the connectors.

[0031] Furthermore, during operation, the project adjustment module establishes a quantitative model of the difference between the measured damage parameters and the predicted data for the current period, and extracts the deviation features of the test parameters.

[0032] Multi-objective correlation analysis is performed on the simulation data and deviation characteristics of the virtual test project combination to construct optimized constraints including load intensity, application frequency and test timing.

[0033] The particle swarm optimization algorithm is used to iteratively optimize the current combination of test parameters. Under the constraint conditions, the objective functions are to minimize the prediction residual and maximize the damage coverage, and the adjusted combination of test parameters is obtained by solving the problem.

[0034] The optimized parameter combination is verified with the virtual test results to determine the confidence level, and the scheme that meets the preset reliability threshold is selected as the test instruction set for the next cycle.

[0035] Furthermore, during the operation phase, when the deviation between the actual test data and the predicted data exceeds a preset threshold, the active verification module automatically triggers the retraining process of the prediction model in the model building module. It adopts a sliding time window algorithm to retain the test data in the most recent several periods as the training sample set, and adjusts the number of hidden layer nodes and activation function combination parameters of the neural network of the prediction model built by the model building module through cross-validation.

[0036] Furthermore, the test execution unit is interconnected with a repository module via a wireless network. The repository module is used to centrally control all collected and calculated data, perform categorized storage combining cloud and local storage, and provide online indexing interfaces for historical data in each category.

[0037] Furthermore, the project adjustment module is connected to an active adjustment module via an electrical medium. The active adjustment module is used to receive the next round of test plan output by the project adjustment module, provide a visual display, provide user authentication, provide the user who has passed the authentication with the right to modify the test plan, and after the modification is completed, feed the modified data back to the project adjustment module application.

[0038] (III) Beneficial Effects: Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects:

[0039] 1. By constructing a predictive model, the test status of a future period can be predicted based on the test data of the current test project. The mapping relationship between the initial period damage state of the test component and the future period fission and deformation state can be analyzed. This allows the long-term test performance of the test object to be quickly obtained through short-term actual tests, thereby reducing test time and ensuring accuracy, and effectively reducing errors caused by various factors in actual tests.

[0040] 2. By utilizing optimization algorithms, the device can adjust the combination of test parameters in real time based on the difference between the current test results and the predicted data, thereby adapting to different test requirements. By generating virtual test project combinations, simulations can be performed before actual testing, reducing test costs and risks. By combining historical data and real-time test data, a damage state archive can be established, enabling a better understanding of the performance evolution trend of components. By optimizing the test plan, unnecessary repeated testing and resource waste are reduced.

[0041] 3. Through actuators that are independently controlled in the horizontal, vertical and torsional directions, multi-degree-of-freedom dynamic coupling loading is achieved to simulate the multi-axis linkage effect of the actual force on the chassis components during vehicle operation. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0043] Figure 1 This is an overall structural diagram of the present invention;

[0044] Figure 2 This is a schematic diagram of the overall framework of the present invention;

[0045] Figure 3 This is a schematic diagram of the control module framework in this invention.

[0046] The labels in the diagram represent: 1. Test fixture body; 2. Traction device one; 3. Traction device two; 4. Traction device three; 5. Control module; 51. Test execution unit; 511. Project management module; 512. Combination selection module; 513. Data acquisition module; 52. Analysis and prediction unit; 521. Damage analysis module; 522. Model building module; 523. Damage prediction module; 53. Data generation module; 54. Project adjustment module; 55. Active verification module; 56. Active adjustment module; 57. Repository module. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0048] The present invention will be further described below with reference to embodiments.

[0049] ① Example 1: The passenger vehicle four-channel chassis component durability testing device of this example, such as Figures 1-3 As shown, the test frame includes a main body 1, a traction device 2 installed at the bottom inside the main body 1, a traction device 3 installed on the left side inside the main body 1, a traction device 4 installed on the right side inside the main body 1, and a control module 5 installed on the front of the main body 1.

[0050] Traction device 1 (2), traction device 2 (3), and traction device 3 (4) are used to fix the tested component and to pull it to perform lateral, vertical, and torsional fatigue tests.

[0051] Control module 5 includes: a test execution unit 51, used to register various combined test items, select and execute a certain combined test item, and obtain the test parameters of the tested component in the current cycle; the test execution unit 51 has sub-modules deployed below it, including: a project management module 511, a combination selection module 512, and a data acquisition module 513. The project management module 511 and the combination selection module 512 are interconnected via a wireless network, and the combination selection module 512 and the data acquisition module 513 are interconnected via a wireless network, wherein:

[0052] Project management module 511 is used to record the combination of various test items corresponding to traction device 1 2, traction device 2 3 and traction device 3 4, and to classify the entered combined test items.

[0053] The combination selection module 512 is used to select items based on the estimated performance of the current test component and its historical test trend data, and obtain the combination test items for the current period.

[0054] The data acquisition module 513 is used to perform a complete cycle of durability testing on a specified test component according to the selected combination of test items, and to collect data on the status of the test equipment and the parameter data of the test component during the test process through sensors.

[0055] The analysis and prediction unit 52 is used to perform model analysis on the test parameters obtained from the combined test items and predict the state data of damage evolution of test components in future cycles. The analysis and prediction unit 52 has sub-modules deployed below it, including: a damage analysis module 521, a model building module 522, and a damage prediction module 523. The damage analysis module 521 and the model building module 522 are interconnected via a wireless network, and the model building module 522 and the damage prediction module 523 are interconnected via a wireless network.

[0056] The damage analysis module 521 is used to perform preliminary analysis on the collected data, identify various damage states of the test component during loading, quantify and record the damage state of each test cycle, establish a corresponding damage state file by combining historical data, and record the time, location and damage degree of each detection point.

[0057] The model building module 522 is used to build a prediction model based on the damage state file obtained from single-cycle testing, using machine learning algorithms. The prediction model establishes a mapping relationship between the initial cycle damage state and the future cycle fission and deformation state, and filters key feature variables. In the process of filtering key feature variables, the module receives test combination data collected in real time by sensors during the current cycle, obtains the loading force value, displacement, torque parameters and component deformation feature data of each test component, normalizes the obtained feature data, and extracts preset damage feature variables, including: stress concentration factor, strain gradient value and material fatigue accumulation factor.

[0058] The prediction model establishes a multi-cycle time series correlation through an LSTM neural network and outputs damage state prediction data containing several future test cycles. The prediction data is decomposed into specific damage types, occurrence locations, damage degrees, and prediction time points. The damage types include at least two of the following: crack propagation rate, plastic deformation, and loose gaps in the connectors.

[0059] Damage prediction module 523 is used to obtain the prediction model built by model building module 522, input the key feature variables of various test data in the current period into the prediction model, and output the state data of damage evolution of test components in future periods.

[0060] Data generation module 53 is used to simulate and generate corresponding virtual test item combinations based on the state data of damage evolution of test components in future cycles.

[0061] The project adjustment module 54 is used to analyze the various test parameters in the current combined test project based on the difference between the current test data and the predicted data, as well as the virtual test project combination. It then uses an optimization algorithm to calculate the adjusted test parameter combination as the plan for the next round of testing. The project adjustment module 54 is electrically connected to the active adjustment module 56. The active adjustment module 56 receives the plan for the next round of testing output by the project adjustment module 54, provides a visual display, and provides user authentication. It grants the authenticated user the right to modify the test plan and, after modification, feeds the modified data back to the project adjustment module 54. A user authentication mechanism is designed to ensure that only authenticated users can modify the test plan, thus improving the system's security.

[0062] The active verification module 55 is used to generate control commands for traction device 1 2, traction device 2 3 and traction device 3 4 according to the adjusted combined test project plan, and to compare the verified data with the predicted data as the basis for updating the prediction model parameters.

[0063] As a preferred embodiment of this example, Figure 3 As shown, the test execution unit 51 is connected to the storage module 57 via a wireless network. The storage module 57 is used to centrally control all collected and calculated data, perform classified storage combining cloud and local storage, and provide online indexing interfaces for historical data of each category. Through the combination of cloud and local storage, classified storage and online indexing of data are realized, making it convenient to access historical data at any time and promoting data sharing and collaborative work.

[0064] Compared to existing technologies, this system can simultaneously perform lateral, vertical, and torsional fatigue tests, enabling more comprehensive durability testing of chassis components and better reflecting performance under real-world usage conditions. Through its modular design of test items and sub-modules, it can intelligently record, classify, and process test data. This design makes the testing process more efficient and allows for analysis of historical data to optimize subsequent testing strategies.

[0065] Multi-period prediction models built using LSTM neural networks can predict the future damage evolution of components in real time, helping engineers identify potential risks in advance and reduce the probability of failure. By analyzing the differences between current test data and predicted data, and using optimization algorithms to adjust the combination of test parameters, test plans can be continuously improved, increasing the accuracy and effectiveness of testing. Based on current test data and prediction results, virtual test projects can be generated, optimizing the test process, improving test efficiency, and reducing resource waste.

[0066] ② Example 2: At other levels, this example also provides another optimization mechanism based on Example 1, specifically a project selection process, as follows:

[0067] Step 1: Obtain the estimated performance parameters of the current test component and the trend data of historical tests. The trend data includes the variation pattern of component performance parameters, damage accumulation rate and correlation characteristics of test interruption events in historical tests.

[0068] Step 2: Dynamically match the component performance parameters from historical tests with the pre-existing combined test items in the project management module 511, and extract candidate test item combinations that are associated with the current test component type, preset durability target, and damage-sensitive direction;

[0069] Step 3: Preset the scoring model, and score the candidate test item combination in multiple dimensions based on the scoring model. The scoring dimensions include test efficiency weight, damage feature coverage weight, and effectiveness feedback weight of historical similar test schemes.

[0070] Step 4: Filter candidate combinations with scores higher than the preset threshold, and determine the optimal combination of test items for the current period using a dynamic programming algorithm based on the real-time test resource usage status and optimization target constraints.

[0071] Step 5: Send the optimal combination test items to the data acquisition module 513 to trigger the execution of the full cycle test, and record the currently selected logical parameters as the input for updating historical trend data.

[0072] Compared with existing technologies, this mechanism can perform dynamic matching by acquiring the estimated performance parameters of the current test component and historical test trend data. It is more scientific and accurate than static or experience-based matching methods and can quickly adapt to different test conditions and component characteristics.

[0073] Introducing a scoring model to perform multi-dimensional scoring on candidate test item combinations can comprehensively consider multiple influencing factors, making the selection of items more comprehensive and objective, reducing errors caused by subjective judgment. In the selected candidate combinations, the real-time test resource occupancy status and optimization target constraints can be considered. By optimizing the combination through dynamic programming algorithm, the best test results can be achieved under limited resources, improving resource utilization efficiency.

[0074] Recording the currently selected logical parameters as input for updating historical trend data helps optimize subsequent test plans and continuously improves the intelligence and adaptability of testing. By effectively screening and optimizing test items, it can effectively reduce invalid tests and resource waste, thereby shortening the overall test cycle time and reducing test costs.

[0075] ③ Example 3: This example provides a personalized adjustment strategy for the original test item, including the following process:

[0076] Establish a quantitative model of the difference between the measured damage parameters and the predicted data in the current period, and extract the deviation features of the test parameters;

[0077] Multi-objective correlation analysis is performed on the simulation data and deviation characteristics of the virtual test project combination to construct optimized constraints including load intensity, application frequency and test timing.

[0078] The particle swarm optimization algorithm is used to iteratively optimize the current combination of test parameters. Under the constraint conditions, the objective functions are to minimize the prediction residual and maximize the damage coverage, and the adjusted combination of test parameters is obtained by solving the problem.

[0079] The optimized parameter combination is verified with the virtual test results to determine the confidence level, and the scheme that meets the preset reliability threshold is selected as the test instruction set for the next cycle.

[0080] Compared with existing technologies, by establishing a quantitative model of the difference between the measured damage parameters and the predicted data in the current cycle, the difference between the actual test results and the predicted model can be accurately identified and quantified. This is more accurate than simple statistical analysis and helps to deeply understand the shortcomings of test performance. By performing correlation analysis between the simulation data of the virtual test project combination and the deviation characteristics, the interaction between different factors can be considered more comprehensively, helping to identify the factors that have the greatest impact on the test results, thus providing a more targeted basis for subsequent optimization.

[0081] The system constructs optimized constraints including load strength, operating frequency, and test timing, making the optimization process more flexible and precise. This allows for adjustments in more complex test environments, ensuring the practical feasibility of the selected solution. It emphasizes personalized adjustments to the original test items and enables flexible adjustments to test parameters based on actual test conditions and requirements. This allows the test process to better adapt to specific component characteristics and usage scenarios.

[0082] Working principle: During operation, the device fixes the test component by means of the bottom traction device 2, the left traction device 3, and the right traction device 4 inside the test frame body 1, and performs lateral or vertical tensile, compression, and torsional fatigue tests. The control module 5 is responsible for registering the combined test items, the project management module 511 records the combination of each test item, the combination selection module 512 selects the combined test items for the current cycle, and sends them to the data acquisition module 513 to execute the complete test cycle, ensuring comprehensive and reliable data acquisition.

[0083] Next, the analysis and prediction unit 52 analyzes the test data, uses machine learning algorithms to build a prediction model to identify the damage state and predict changes in future cycles, and selects key feature variables. The project adjustment module 54 adjusts the test parameters based on the difference between the real-time test results and the predicted data, forms the next round of test plan, and combines it with the virtual test project to verify the effectiveness of the plan. The active verification module 55 starts the retraining process when the deviation between the actual test data and the predicted data exceeds the threshold to ensure the accuracy of the model. At the same time, the storage module 57 summarizes and classifies the data and provides convenient online indexing. The entire workflow realizes efficient interaction and data sharing between the modules through a wireless network.

[0084] This device comprehensively evaluates the durability of components by combining lateral, vertical, and torsional fatigue tests. At the same time, by utilizing machine learning algorithms and optimization techniques, the device can analyze test data in real time, predict future damage states, and dynamically adjust test parameters to ensure the effectiveness and accuracy of the test plan. In addition, the modular design and wireless network connection improve the system's flexibility and data management efficiency, making the testing process more intelligent and automated.

[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A four-channel chassis component durability testing device for passenger vehicles, characterized in that, The test frame includes a main body, with a traction device one installed at the bottom inside the main body, a traction device two installed on the left side inside the main body, a traction device three installed on the right side inside the main body, and a control module installed on the front of the main body. The first, second, and third traction devices are used to fix the tested component and to pull it to perform lateral, vertical, and torsional fatigue tests. The control module includes: The test execution unit is used to register various combined test items, select and execute a certain combined test item, and obtain the test parameters of the tested component in the current cycle. The analysis and prediction unit is used to perform model analysis on the test combination data collected in real time by the sensors and predict the state data of damage evolution of test components in future cycles. The data generation module is used to simulate and generate corresponding combinations of virtual test items based on the state data of damage evolution of test components in future cycles. The project adjustment module is used to analyze the various test parameters in the current test combination based on the difference between the current test data and the predicted data, as well as the virtual test project combination, and to use the optimization algorithm to calculate the adjusted test parameter combination as the plan for the next round of testing. The active verification module is used to generate control commands for traction device one, traction device two, and traction device three based on the adjusted combined test project plan, and to compare the verified data with the predicted data as the basis for updating the prediction model parameters.

2. The passenger vehicle four-channel chassis component durability testing device according to claim 1, characterized in that, The test execution unit has sub-modules deployed below it, including: a project management module, a combination selection module, and a data acquisition module. The project management module and the combination selection module are interconnected via a wireless network, and the combination selection module and the data acquisition module are interconnected via a wireless network. The project management module is used to record the combination of various test items corresponding to Tractor 1, Tractor 2 and Tractor 3, and to classify the entered combined test items. The combination selection module is used to select items based on the estimated performance of the current test component and its historical test trend data, and obtain the combination test items for the current period. The data acquisition module is used to perform a complete cycle of durability testing on a specified test component based on the selected combination of test items, and to collect data on the status of the test equipment and the parameter data of the test component during the test process through sensors.

3. The passenger vehicle four-channel chassis component durability testing device according to claim 2, characterized in that, The process of the combined selection module in selecting items is as follows: Step 1: Obtain the estimated performance parameters of the current test component and the trend data of historical tests. The trend data includes the variation pattern of component performance parameters, damage accumulation rate and correlation characteristics of test interruption events in historical tests. Step 2: Dynamically match the component performance parameters from historical tests with the pre-existing combined test items in the project management module, and extract candidate test item combinations that are associated with the current test component type, preset durability target, and damage sensitivity direction; Step 3: Preset the scoring model, and score the candidate test item combination in multiple dimensions based on the scoring model. The scoring dimensions include test efficiency weight, damage feature coverage weight, and effectiveness feedback weight of historical similar test schemes. Step 4: Filter candidate combinations with scores higher than the preset threshold, and determine the optimal combination of test items for the current period using a dynamic programming algorithm based on the real-time test resource usage status and optimization target constraints. Step 5: Send the optimal combination test items to the data acquisition module to trigger the execution of the full cycle test, and record the currently selected logical parameters as the input for updating historical trend data.

4. The durability testing device for four-channel chassis components of passenger vehicles according to claim 1, characterized in that, The analysis and prediction unit has sub-modules deployed at its lower levels. These sub-modules include: a damage analysis module, a model building module, and a damage prediction module. The damage analysis module and the model building module are interconnected via a wireless network, and the model building module and the damage prediction module are also interconnected via a wireless network. The damage analysis module is used to perform preliminary analysis on the collected data, identify various damage states of the test components during loading, quantify and record the damage state of each test cycle, and establish a corresponding damage state file by combining historical data, recording the time, location and damage degree of each test point. The model building module is used to build a predictive model based on the damage state profile obtained from single-cycle testing, using machine learning algorithms. The predictive model establishes a mapping relationship between the initial cycle damage state and the future cycle fission and deformation state, and selects key feature variables. The damage prediction module is used to obtain the prediction model built by the model building module, input the key feature variables of various test data in the current period into the prediction model, and output the state data of damage evolution of test components in future periods.

5. The passenger vehicle four-channel chassis component durability testing device according to claim 4, characterized in that, During the process of selecting key feature variables, the model building module receives test combination data collected in real time by sensors within the current period, obtains the loading force value, displacement, torque parameters, and component deformation feature data of each test component, normalizes the obtained feature data, and extracts preset damage feature variables. Damage characteristic variables include: stress concentration factor, strain gradient value, and material fatigue accumulation factor.

6. The passenger vehicle four-channel chassis component durability testing device according to claim 4, characterized in that, The prediction model constructed by the model building module establishes a multi-period time series correlation through an LSTM neural network, and outputs damage state prediction data containing several future test periods. The prediction data is decomposed into specific damage types, occurrence locations, damage degrees, and prediction time points. The damage types include at least two of the following: crack propagation rate, plastic deformation, and loose gaps in the connectors.

7. The passenger vehicle four-channel chassis component durability testing device according to claim 1, characterized in that, During operation, the project adjustment module establishes a quantitative model of the difference between the measured damage parameters and the predicted data in the current period, and extracts the deviation features of the test parameters. Multi-objective correlation analysis is performed on the simulation data and deviation characteristics of the virtual test project combination to construct optimized constraints including load intensity, application frequency and test timing. The particle swarm optimization algorithm is used to iteratively optimize the current combination of test parameters. Under the constraint conditions, the objective functions are to minimize the prediction residual and maximize the damage coverage, and the adjusted combination of test parameters is obtained by solving the problem. The optimized parameter combination is verified with the virtual test results to determine the confidence level, and the scheme that meets the preset reliability threshold is selected as the test instruction set for the next cycle.

8. The durability testing device for four-channel chassis components of passenger vehicles according to claim 1, characterized in that, During the operation phase, when the deviation between the actual test data and the predicted data exceeds a preset threshold, the active verification module automatically triggers the retraining process of the prediction model in the model building module. It adopts a sliding time window algorithm to retain the test data in the most recent several periods as the training sample set, and adjusts the number of hidden layer nodes and activation function combination parameters of the neural network of the prediction model built by the model building module through cross-validation.

9. The durability testing device for four-channel chassis components of passenger vehicles according to claim 1, characterized in that, The test execution unit is interconnected with a repository module via a wireless network. The repository module is used to centrally control all collected and calculated data, perform categorized storage combining cloud and local storage, and provide online indexing interfaces for historical data in each category.

10. The passenger vehicle four-channel chassis component durability testing device according to claim 1, characterized in that, The project adjustment module is connected to the active adjustment module via an electrical medium. The active adjustment module is used to receive the next round of test plan output by the project adjustment module, provide visual display, provide user authentication, provide modification permissions for the test plan to verified users, and after modification, feed the modified data back to the project adjustment module application.

Images