Automatic test method and system for air suspension

Abstract

The invention belongs to the technical field of testing, and discloses an automatic testing method and system for an air suspension, and the method comprises the steps: obtaining a vibration testing signal of the air suspension; performing multi-mode decomposition on the vibration test signal based on an empirical mode decomposition algorithm to obtain a plurality of intrinsic mode components; performing screening processing on the plurality of intrinsic mode components to obtain a plurality of processed intrinsic mode components; constructing key features based on the plurality of processed intrinsic mode components; the key features are input into a suspension fault test model for fault test, a test result is obtained, and the test result comprises the probability that the air suspension breaks down and the corresponding fault type; wherein the suspension fault test model is constructed based on transfer learning. The method has the advantages that the real-time performance is high, early hidden faults can be positioned, and the model is high in generalization ability, high in test efficiency, high in fault test accuracy and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of testing, and in particular relates to an automatic testing method and system for an air suspension. Background Art

[0002] As the automotive industry rapidly evolves toward intelligent, electrified, and high-end features, air suspension systems, owing to their superior dynamic adjustment capabilities (adaptive adjustment of vehicle height and stiffness), have become a core feature of high-end passenger cars and commercial vehicles. This system replaces traditional steel springs with air springs, integrating an electronic control unit (ECU) with continuously adjustable dampers (CDC), significantly improving ride comfort, handling stability, and vehicle handling. However, its complex mechatronic structure (including air circuits, valve bodies, rubber airbags, sensors, etc.) also introduces a higher risk of failure. For example, air spring leakage / rupture can lead to loss of vehicle height control; shock absorber damping failure can cause abnormal vehicle body shaking; guide mechanism bushing wear can cause unusual noise and misalignment; and air circuit blockage or solenoid valve failure can lead to loss of adjustment function.

[0003] Such faults not only directly impact driving safety and comfort but can also trigger cascading damage to the chassis system, significantly increasing repair costs. Traditional fault diagnosis methods rely primarily on manual experience-based troubleshooting, static air pressure testing, or dedicated test bench disassembly. These methods suffer from low efficiency, poor real-time performance, and difficulty locating early, hidden faults. This is particularly true for slowly developing chronic faults (such as minor air leaks or gradual aging of bushings), as traditional methods often only identify them after the problem has significantly worsened. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic testing method and system for an air suspension, so as to solve the problems of low efficiency, poor real-time performance and difficulty in locating early hidden faults in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides an automatic testing method for an air suspension, the method comprising: Obtain vibration test signals for air suspension; Perform multimodal decomposition of the vibration test signal based on the empirical mode decomposition algorithm to obtain multiple eigenmode components; Performing screening processing on multiple eigenmode components to obtain several processed eigenmode components; Construct key features based on several processed intrinsic mode components; Key features are input into a suspension fault test model for fault testing to obtain test results, including the probability of air suspension failure and the corresponding fault type; wherein the suspension fault test model is constructed based on transfer learning.

[0006] Preferably, the method further comprises: constructing a suspension fault test model, comprising: Obtaining a first sample data set and a second sample data set, wherein the first sample data set includes a plurality of suspension vibration signals with known labels, and the second sample data set is a suspension vibration signal to be tested, wherein the suspension vibration signal to be tested includes a normal vibration signal or a vibration signal of an unknown fault type; Using the first sample data set to train the deep learning model to obtain a trained deep learning model; Based on the transfer learning algorithm, the model parameters of the trained deep learning model are transferred to the learning model to be trained to obtain the transferred model; The model parameters of the migrated model are updated based on the second sample data set to obtain a suspension fault test model.

[0007] Preferably, the deep learning model is a convolutional neural network or a recurrent neural network.

[0008] Preferably, before performing multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm, the method further includes: dividing the vibration test signal into multiple segment signals; after performing multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm, each segment signal corresponds to at least one intrinsic mode component.

[0009] Preferably, the vibration test signal is subjected to multimodal decomposition based on an empirical mode decomposition algorithm to obtain multiple eigenmodal components, including: For any segment signal, the segment signal is expanded into two groups to obtain a first segment test signal and a second segment test signal; Adding positive random white noise to the first segment test signal to obtain a first signal; Adding negative random white noise to the second segment test signal to obtain a second signal; Decomposing the first signal and the second signal based on an empirical mode decomposition algorithm to obtain a plurality of first components and a plurality of second components; The kth first component and the kth second component are averaged to obtain the kth intrinsic mode component of the segment signal; where k=1,2,…,K, and K is the total order of the empirical mode decomposition algorithm.

[0010] Preferably, the plurality of eigenmode components are screened to obtain a plurality of processed eigenmode components, including: Determining a screening coefficient between each segment signal and each eigenmode component corresponding to the segment signal; The eigenmode components corresponding to the segment signal are screened based on the screening coefficient to screen out unnecessary eigenmode components, and the necessary eigenmode components corresponding to each segment signal are obtained, and the necessary eigenmode components are used as the processed eigenmode components.

[0011] Preferably, determining the screening coefficient between each segment signal and each eigenmode component corresponding to the segment signal includes: Extracting a first feature corresponding to each segment signal at each sampling moment in a sampling period and a second feature of each intrinsic mode component corresponding to each segment signal; Based on the first eigenvalue and the second eigenvalue, a similarity algorithm is used to calculate the similarity distance between the first feature and the second feature at each sampling moment; Determining a sum of distances corresponding to each eigenmode component in the sampling period based on the number of sampling moments in the sampling period and the similarity distance between the first feature and the second feature at each sampling moment; Based on the distance sum value, a screening coefficient is determined.

[0012] Preferably, the similarity algorithm is a cosine similarity algorithm.

[0013] In a second aspect, the present invention provides an automatic testing system for an air suspension, for implementing the above-mentioned automatic testing method for an air suspension, the system comprising: A signal acquisition module, used to obtain vibration test signals of the air suspension; A signal decomposition module is used to perform multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm to obtain multiple eigenmode components; A component screening module is used to screen multiple eigenmode components to obtain several processed eigenmode components; A feature construction module, used to construct key features based on several processed intrinsic mode components; A fault testing module is used to input key features into a suspension fault testing model for fault testing to obtain test results, wherein the test results include the probability of air suspension failure and the corresponding fault type; wherein the suspension fault testing model is constructed based on transfer learning.

[0014] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned automatic testing method for the air suspension when executing the computer program.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned automatic testing method for the air suspension when executed by a processor.

[0016] Beneficial effects: 1. The present invention collects vibration test signals from the air suspension, constructs key features based on the vibration test signals, and then inputs the key features into the suspension fault test model. This allows rapid determination of whether the air suspension will fail and the type of failure. This method has the advantages of strong real-time performance and the ability to locate early hidden faults. 2. The suspension fault test model of the present invention is constructed using transfer learning, which has high generalization ability and test efficiency; 3. After the vibration test signal of the present invention is decomposed by the empirical mode decomposition algorithm, multiple intrinsic mode components are screened and processed to extract intrinsic mode components useful for fault testing, reduce noise interference, and improve the accuracy of the suspension fault test model for fault testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings: Figure 1 is a flow chart of an automatic testing method for an air suspension provided by one embodiment of the present invention; Figure 2 The figure is a block diagram of an automatic test system for an air suspension provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly introduced below in conjunction with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0019] Example 1 Figure 1This is a flow chart of an automatic test method for an air suspension provided by an embodiment of the present invention. This method can be, but is not limited to, executed by a computer device with certain computing resources, such as a cloud server, a personal computer (PC, a multi-purpose computer with a size, price, and performance suitable for personal use; desktops, laptops, small laptops, tablets, and ultrabooks are all personal computers), a smart phone, a personal digital assistant (PDA), or a wearable device. Figure 1 As shown, this embodiment provides an automatic testing method for an air suspension, the method comprising: Step S10: Acquire a vibration test signal of the air suspension.

[0020] In this embodiment, any failure (e.g., air leakage, damping failure, wear, looseness, blockage, or rupture) of any air suspension component (air springs, shock absorbers, guide bushings, connectors, air circuits, compressor, etc.) will alter the mass, stiffness, and damping characteristics of the entire suspension system. These changes directly impact the system's vibration transmission characteristics and natural frequency. The vibration response (amplitude, frequency content, energy distribution, and time-domain characteristics) in a faulty state will inevitably show detectable differences compared to a healthy state.

[0021] This embodiment uses accelerometers to collect vibration test signals from the air suspension. The accelerometers are installed at the following locations: 1. Unsprung mass (near the wheel center / control arm), 2. Sprung mass (on the vehicle body side, near the suspension mounting point), 3. Air spring body / shock absorber barrel, and 4. Guide mechanism (such as the control arm).

[0022] This embodiment can be tested through road tests, bench tests, and pulse excitation / hammer impact tests. Road tests involve driving on different road spectra (such as rough roads, Belgian roads, and speed bumps) on a real vehicle or in a test field to collect vibration test signals. This method is closest to actual working conditions. Bench tests involve simulating various road surface spectrum inputs on a four-column vibration table or a multi-axis vibration table, precisely controlling the excitation conditions and achieving good repeatability. Pulse excitation / hammer impact tests involve obtaining the system's frequency response function (FRF) and identifying changes in the natural frequency and damping ratio.

[0023] Step S20: performing multimodal decomposition on the vibration test signal based on an empirical mode decomposition algorithm to obtain multiple eigenmode components.

[0024] As a further optimization of this embodiment, before performing multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm, the method further includes: dividing the vibration test signal into a plurality of segment signals.

[0025] Regarding step S20, the specific steps of performing multi-modal decomposition on the vibration test signal based on the empirical mode decomposition algorithm are as follows: Step S201: For any segment signal, expand the segment signal into two groups to obtain a first segment test signal and a second segment test signal; wherein, one segment signal can be copied to obtain two groups of identical segment signals to serve as the first segment test signal and the second segment test signal, or another segment signal that is most similar to the segment signal can be found from all segment signals to serve as the first segment test signal and the second segment test signal respectively.

[0026] Step S202: Add positive random white noise to the first test signal to obtain a first signal; wherein the function expression of the first signal is: ; Where, is the first segment test signal, t is the sampling time, For the first signal, is the positive random white noise added for the i-th time, is the noise amplitude.

[0027] Step S203: Add negative random white noise to the second test signal to obtain a second signal; wherein the function expression of the second signal is: ; Where, is the second signal, For the second segment test signal, is the negative random white noise added for the i-th time, is the noise amplitude.

[0028] Step S204: Decompose the first signal and the second signal based on an empirical mode decomposition algorithm to obtain a plurality of first components and a plurality of second components.

[0029] Among them, the functional relationship of the first component is: ; Where, is the kth first component of the i-th time, is the first residual wave after decomposition by the empirical mode decomposition algorithm for the i-th time; Among them, the functional relationship of the second component is: ; Where, is the kth second component of the i-th order, is the second residual wave after decomposition by the empirical mode decomposition algorithm for the i-th time.

[0030] Step S205: performing an average process on the kth first component and the kth second component to obtain the kth intrinsic mode component of the segment signal; wherein k=1, 2, ..., K, and K is the total order of the empirical mode decomposition algorithm.

[0031] Among them, the function expression of the kth eigenmode component is: ; Where, is the kth eigenmode component, and I is the total number of times the noise is added.

[0032] In this embodiment, negative random white noise and positive random white noise are added to the two groups of segment signals. After the averaging process in step S205 , the noise in the original signal can be eliminated, thereby reducing noise interference to the subsequent fault test.

[0033] Step S30: screening the plurality of eigenmode components to obtain a plurality of processed eigenmode components.

[0034] In this embodiment, after the vibration test signal is subjected to multimodal decomposition based on the empirical mode decomposition algorithm, each segment signal corresponds to at least one eigenmode component. Since at least one eigenmode component of each segment signal contains components that are helpful for fault testing and also contains components that are useless for fault testing, it is necessary to perform screening processing on the multiple eigenmode components to screen out components that are useless for fault testing.

[0035] Specifically, the steps of screening multiple eigenmode components are as follows: Step S301: determining a filtering coefficient between each segment signal and each eigenmode component corresponding to the segment signal.

[0036] In this embodiment, determining the screening coefficient between each segment signal and each eigenmode component corresponding to the segment signal includes the following steps: Step a1: Extract the first feature corresponding to each segment signal at each sampling moment in the sampling period and the second feature of each intrinsic mode component corresponding to each segment signal; wherein the first feature and the second feature can be amplitude, frequency component, energy distribution, time domain feature, etc.

[0037] Step a2: Based on the first eigenvalue and the second eigenvalue, a similarity algorithm is used to calculate the similarity distance between the first feature and the second feature at each sampling moment. The similarity algorithm in this embodiment can be a cosine similarity algorithm. The function expression of the similarity distance between the first feature and the second feature at each sampling moment is: ; Where, is the similarity distance between the first feature and the second feature at the jth sampling moment, is the cosine similarity function, is the nth eigenvalue of the first feature corresponding to the jth sampling moment, N is the total number of eigenvalues of the first feature, is the mth eigenvalue of the second feature corresponding to the jth sampling moment, and M is the total number of eigenvalues of the second feature.

[0038] Step a3: Based on the number of sampling moments in the sampling period and the similarity distance between the first feature and the second feature at each sampling moment, determine the sum of distances corresponding to the eigenmode components in the sampling period.

[0039] The function expression of the distance sum value in this embodiment is: ; Where D is the total distance value and J is the number of sampling moments.

[0040] Step a4: Determine the screening coefficient based on the distance sum value.

[0041] The function expression of the screening coefficient of this embodiment is: ; Where, is the screening coefficient.

[0042] Step S302: Filter the eigenmode components corresponding to the segment signal based on the filtering coefficient to filter out unnecessary eigenmode components, obtain necessary eigenmode components corresponding to each segment signal, and use the necessary eigenmode components as processed eigenmode components.

[0043] In this embodiment, when the screening coefficient of a certain intrinsic mode component in the segment signal is lower than a preset value, the intrinsic mode component is a non-essential intrinsic mode component and needs to be screened out; when the screening coefficient of a certain intrinsic mode component is greater than or equal to the preset value, the intrinsic mode component is a necessary intrinsic mode component and needs to be retained; this processing method can reduce the impact of noise and at the same time reduce the complexity of vibration test signal processing, and multiple intrinsic mode components have good stability and linearity characteristics.

[0044] Step S40: constructing key features based on the processed eigenmode components. The key features of this embodiment may be one or more of amplitude, frequency component, energy distribution, time domain features, etc.

[0045] Step S50: Inputting the key features into a suspension fault test model to perform fault testing and obtain test results, wherein the test results include the probability of air suspension failure and the corresponding fault type; wherein the suspension fault test model is constructed based on transfer learning.

[0046] As a further optimization of this embodiment, the method further includes: constructing a suspension fault test model, including: Step B10: Obtain a first sample data set and a second sample data set, where the first sample data set contains several suspension vibration signals with known labels, and the second sample data set is the suspension vibration signal to be tested, which contains normal vibration signals or vibration signals of unknown fault types; therefore, the first sample data set is used as the source domain data set for transfer learning, and the second sample data set is used as the target domain data set for transfer learning.

[0047] Step B20: Using the first sample data set to train the deep learning model to obtain a trained deep learning model; in this embodiment, the deep learning model is a convolutional neural network or a recurrent neural network; the trained deep learning model is a source domain model; Step B30: Based on the transfer learning algorithm, the model parameters of the trained deep learning model are transferred to the learning model to be trained to obtain the transferred model; the model parameters of this embodiment can be the weights and biases of the convolutional layer.

[0048] Step B40: Update the model parameters of the migrated model based on the second sample data set to obtain a suspension fault test model. After migrating the model parameters from the source domain to the target domain, fine-tune the model using the target domain data set to obtain the final suspension fault test model.

[0049] In this embodiment, the steps of training the deep learning model using the first sample data set are as follows: Using the first sample data set as the input parameter of the deep learning model, perform forward propagation and calculate the output of the model; Calculate the loss function, which can be cross entropy loss or mean square error loss. The loss function is used to measure the error between the model's predicted results and the actual results; Perform backpropagation to calculate the gradient of the loss function with respect to the model parameters, and use an optimization algorithm (such as gradient descent or Adam algorithm) to update the model parameters based on the gradient; Use the validation dataset to evaluate the performance of the model, such as calculating indicators such as accuracy, recall, and F1 value. Adjust the model structure and parameters based on the evaluation results, such as adding or reducing convolutional layers and adjusting the learning rate, to obtain a trained deep learning model.

[0050] The present invention collects the vibration test signal of the air suspension, constructs key features based on the vibration test signal, and then inputs the key features into the suspension fault test model. It can quickly determine whether the air suspension will fail and the type of fault. It has the advantages of strong real-time performance and the ability to locate early hidden faults. In addition, the suspension fault test model is constructed using transfer learning, which has high generalization ability and test efficiency. Secondly, after the vibration test signal is decomposed by the empirical mode decomposition algorithm, multiple intrinsic mode components are screened and processed to extract intrinsic mode components useful for fault testing, reduce noise interference, and improve the accuracy of the suspension fault test model for fault testing.

[0051] Example 2 Figure 2 FIG. 1 is a block diagram of an automatic test system for an air suspension provided by an embodiment of the present invention. Figure 2 As shown, this embodiment provides an automatic testing system for an air suspension, which is used to implement the automatic testing method for an air suspension in Example 1. The system includes: A signal acquisition module, used to obtain vibration test signals of the air suspension; A signal decomposition module is used to perform multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm to obtain multiple eigenmode components; A component screening module is used to screen multiple eigenmode components to obtain several processed eigenmode components; A feature construction module, for constructing key features based on several processed intrinsic mode components; A fault testing module is used to input key features into a suspension fault testing model for fault testing to obtain test results, wherein the test results include the probability of air suspension failure and the corresponding fault type; wherein the suspension fault testing model is constructed based on transfer learning.

[0052] This embodiment further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the automatic testing method for the air suspension in the first embodiment is implemented.

[0053] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the automatic testing method for the air suspension in the first embodiment is implemented.

[0054] The present invention collects the vibration test signal of the air suspension, constructs key features based on the vibration test signal, and then inputs the key features into the suspension fault test model. It can quickly determine whether the air suspension will fail and the type of fault. It has the advantages of strong real-time performance and the ability to locate early hidden faults. In addition, the suspension fault test model is constructed using transfer learning, which has high generalization ability and test efficiency. Secondly, after the vibration test signal is decomposed by the empirical mode decomposition algorithm, multiple intrinsic mode components are screened and processed to extract intrinsic mode components useful for fault testing, reduce noise interference, and improve the accuracy of the suspension fault test model for fault testing.

[0055] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0057] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. An automatic testing method for an air suspension, characterized in that: The method comprises: Obtain vibration test signals for air suspension; Perform multimodal decomposition of the vibration test signal based on the empirical mode decomposition algorithm to obtain multiple eigenmode components; Performing screening processing on multiple eigenmode components to obtain several processed eigenmode components; Construct key features based on several processed intrinsic mode components; Key features are input into a suspension fault test model for fault testing to obtain test results, including the probability of air suspension failure and the corresponding fault type; wherein the suspension fault test model is constructed based on transfer learning.

2. The automatic testing method of air suspension according to claim 1, characterized in that: The method further includes: constructing a suspension fault test model, including: Obtaining a first sample data set and a second sample data set, wherein the first sample data set includes a plurality of suspension vibration signals with known labels, and the second sample data set is a suspension vibration signal to be tested, wherein the suspension vibration signal to be tested includes a normal vibration signal or a vibration signal of an unknown fault type; Using the first sample data set to train the deep learning model to obtain a trained deep learning model; Based on the transfer learning algorithm, the model parameters of the trained deep learning model are transferred to the learning model to be trained to obtain the transferred model; The model parameters of the migrated model are updated based on the second sample data set to obtain a suspension fault test model.

3. The automatic testing method of air suspension according to claim 2, characterized in that: The deep learning model is a convolutional neural network or a recurrent neural network.

4. The automatic testing method of air suspension according to claim 1, characterized in that: Before performing multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm, the method further includes: dividing the vibration test signal into multiple segment signals; after performing multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm, each segment signal corresponds to at least one intrinsic mode component.

5. The automatic testing method of air suspension according to claim 4, characterized in that: The vibration test signal is decomposed into multiple modes based on the empirical mode decomposition algorithm to obtain multiple eigenmode components, including: For any segment signal, the segment signal is expanded into two groups to obtain a first segment test signal and a second segment test signal; Adding positive random white noise to the first segment test signal to obtain a first signal; Adding negative random white noise to the second segment test signal to obtain a second signal; Decomposing the first signal and the second signal based on an empirical mode decomposition algorithm to obtain a plurality of first components and a plurality of second components; The kth first component and the kth second component are averaged to obtain the kth intrinsic mode component of the segment signal; where k=1,2,…,K, and K is the total order of the empirical mode decomposition algorithm.

6. The automatic testing method for air suspension according to claim 4 or 5, characterized in that: Multiple eigenmode components are screened and processed to obtain several processed eigenmode components, including: Determining a screening coefficient between each segment signal and each eigenmode component corresponding to the segment signal; The eigenmode components corresponding to the segment signal are screened based on the screening coefficient to screen out unnecessary eigenmode components, and the necessary eigenmode components corresponding to each segment signal are obtained, and the necessary eigenmode components are used as the processed eigenmode components.

7. The automatic testing method of air suspension according to claim 6, characterized in that: Determining a screening coefficient between each segment signal and each eigenmode component corresponding to the segment signal includes: Extracting a first feature corresponding to each segment signal at each sampling moment in a sampling period and a second feature of each intrinsic mode component corresponding to each segment signal; Based on the first eigenvalue and the second eigenvalue, a similarity algorithm is used to calculate the similarity distance between the first feature and the second feature at each sampling moment; Determining a sum of distances corresponding to each eigenmode component in the sampling period based on the number of sampling moments in the sampling period and the similarity distance between the first feature and the second feature at each sampling moment; Based on the distance sum value, a screening coefficient is determined.

8. The automatic testing method of air suspension according to claim 7, characterized in that: The similarity algorithm is a cosine similarity algorithm.

9. An automatic test system for an air suspension, used to implement the automatic test method for an air suspension according to any one of claims 1 to 8, characterized in that: The system comprises: A signal acquisition module, used to obtain vibration test signals of the air suspension; A signal decomposition module is used to perform multimodal decomposition on the vibration test signal based on the empirical mode decomposition algorithm to obtain multiple eigenmode components; A component screening module is used to screen multiple eigenmode components to obtain several processed eigenmode components; A feature construction module, for constructing key features based on several processed intrinsic mode components; A fault testing module is used to input key features into a suspension fault testing model for fault testing to obtain test results, wherein the test results include the probability of air suspension failure and the corresponding fault type; wherein the suspension fault testing model is constructed based on transfer learning.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the automatic testing method for the air suspension according to any one of claims 1 to 8 is implemented.

Images