Vehicle steering system hydraulic internal leakage fault diagnosis method and system based on Bo-Transform-LSTM

Abstract

The invention provides a vehicle steering system hydraulic internal leakage fault diagnosis method and system based on Bo-Transform-LSTM, and relates to the technical field of fault detection, and the method comprises the steps: S1, obtaining leakage fault data of a multi-axis special vehicle hydraulic steering system under a preset fault degree; s2, normalizing the fault data, and dividing the normalized fault data into a training set and a test set according to a preset proportion; and S3, segmenting the input fault data, inputting the segmented fault data into the Bo-Transform-LSTM model, optimizing hyper-parameters of the Bo-Transform-LSTM model by using a Bayesian algorithm to obtain an optimal parameter combination, and storing the trained Bo-Transform-LSTM model. According to the method, the problem that accurate positioning is difficult when a fault occurs due to the fact that the hydraulic system has multiple components and high nonlinearity can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a method and system for diagnosing hydraulic internal leakage fault of a vehicle steering system based on Bo-Transformer-LSTM. Background Art

[0002] Multi-axle special vehicles have the characteristics of heavy load, many axles and long body, and they mostly use hydraulic power front wheel steering and independent rear axle hydraulic steering system. Due to the complex and harsh driving environment of multi-axle special vehicles and the strong nonlinearity of the hydraulic system, it is difficult to accurately locate the specific location of the fault when a fault occurs, which makes the maintenance of the vehicle more difficult and the cost increases.

[0003] In the intelligent fault diagnosis method of vehicle steering system, H.Xiong, Z.Wang, G.Wu, Y.Pan, Z.Yang, and Z.Long, "Steering Actuator Fault Diagnosis for Autonomous Vehicle With anAdaptive Denoising Residual Network," IEEE Trans.Instrum.Meas., 71, pp.1-13, (2022) proposed an adaptive denoising residual network for steering actuator fault diagnosis, reducing noise interference. S.He, X.Xu, J.Xie, F.Wang, Z.Liu, and F.Zhao, "Fault detection and fault-tolerantcontrol of autonomous steering system for intelligent vehicles combining Bi-LSTM and SPRT," Measurement, 212, p.112708, (2023) designed a fault detection and fault-tolerant control strategy based on bidirectional long short-term memory rack displacement estimator combined with sequence probability ratio test to deal with displacement sensor faults. Although deep learning can solve the fault diagnosis problem of nonlinear systems, a large amount of data is required to ensure the diagnostic accuracy of neural networks. At the same time, actual vehicle experiments under hydraulic steering system fault conditions cannot guarantee vehicle safety, making it difficult to collect sufficient fault data and unable to effectively solve the problem of difficulty in accurately locating faults in hydraulic system components. Summary of the invention

[0004] The problem solved by the invention is how to solve the problem that the hydraulic system has many components and strong nonlinearity, and it is difficult to accurately locate the fault when it occurs.

[0005] In order to solve the above problems, the present invention provides a vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM, comprising the steps of:

[0006] S1: Obtaining fault data of leakage of a hydraulic steering system of a multi-axle special vehicle under a preset fault degree;

[0007] S2: normalize the fault data, and divide the normalized fault data into a training set and a test set according to a preset ratio;

[0008] S3: Segment the input fault data and input it into the Bo-Transformer-LSTM model. Use the Bayesian algorithm to optimize the hyperparameters of the Bo-Transformer-LSTM model to obtain the optimal parameter combination, and save the trained Bo-Transformer-LSTM model.

[0009] S4: The data of the test set is split and input into the trained Bo-Transformer-LSTM model for prediction. The output of the prediction result is denormalized to obtain the actual prediction result. The actual prediction result is compared with the data in the test set to evaluate the prediction accuracy of the Bo-Transformer-LSTM model.

[0010] Furthermore, the acquisition of the fault data includes:

[0011] S11: Use a steering force angle tester to measure the steering wheel input angle and the steering torque fed back to the steering wheel by the steering system, and collect the vehicle's steering wheel steering angle, steering wheel steering torque and travel speed at the same time;

[0012] S12: testing the vehicle at different speeds, and recording the steering angle and steering torque input by the steering wheel during the test according to step S11. When the vehicle returns to its original position after one circle, the experiment is considered completed.

[0013] S13: The steering angle, steering torque, and steering cylinder inlet and outlet pressures are collected respectively, and a fault data set is generated in combination with the position information of the fault occurring during the test.

[0014] Furthermore, the step S2 comprises:

[0015] S21: Set the ratio of training set to test set, as well as the optimization range of LSTM unit number, learning rate, L2 regularization parameter, and set the maximum number of iterations and maximum number of training times of the Bayesian network.

[0016] Furthermore, the composition of the Bo-Transformer-LSTM model in step S3 includes:

[0017] Transformer encoding layer: provides data with attention to the Transformer-LSTM network. The data processed by the Transformer encoding layer provides data features for fault diagnosis. The mechanisms of the Transformer encoding layer include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization.

[0018] LSTM decoding layer: It consists of input gate, forget gate, output gate and cell state. LSTM takes Transformer encoding layer data, hidden layer data at the previous moment and cell state output at the previous moment as common input, and processes data serially through the gating mechanism;

[0019] Bayesian optimization is used to find the best hyperparameter configuration of the model, and the algorithm is optimized by optimizing the parameters of learning rate, L2 regularization, and the number of LSTM units.

[0020] Furthermore, the step S4 comprises:

[0021] S41: The prediction accuracy of the model was evaluated based on the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value as algorithm evaluation indicators;

[0022] S42: Based on the evaluation index, the collected fault data set is diagnosed through the Bo-Transformer-LSTM algorithm to obtain a prediction result.

[0023] Furthermore, the calculation formulas for the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value in step S41 are:

[0024]

[0025] Among them, TP represents the number of samples correctly identified as faulty; TN represents the number of samples correctly identified as non-faulty; FN represents the number of samples incorrectly identified as faulty; FP represents the number of samples incorrectly identified as non-faulty; f(x) represents the receiver operating characteristic curve.

[0026] A vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM, comprising:

[0027] Acquisition module: used to acquire fault data of leakage of hydraulic steering system of multi-axle special vehicle under preset fault degree;

[0028] Processing module: used to normalize the fault data and divide the normalized fault data into a training set and a test set according to a preset ratio;

[0029] Segmentation module: used to segment the input fault data and input it into the Bo-Transformer-LSTM model, optimize the hyperparameters of the Bo-Transformer-LSTM model using the Bayesian algorithm, obtain the optimal parameter combination, and save the trained Bo-Transformer-LSTM model;

[0030] Fault prediction module: It is used to segment the test set data and input it into the trained Bo-Transformer-LSTM model for prediction. The output of the prediction result is denormalized to obtain the actual prediction result. The actual prediction result is compared with the data in the test set to evaluate the prediction accuracy of the Bo-Transformer-LSTM model.

[0031] Furthermore, the acquisition of the fault data includes:

[0032] Acquisition unit: used to measure the steering wheel input angle and the steering torque fed back to the steering wheel by the steering system through a steering force angle tester, and to collect the vehicle's steering wheel steering angle, steering wheel steering torque and travel speed at the same time;

[0033] Testing unit: used to test the vehicle at different speeds, and record the steering angle and steering torque input by the steering wheel during the test according to step S11. When the vehicle returns to its original position after driving one circle, it is recorded as completing one experiment;

[0034] Generation unit: collects steering angle, steering torque and steering cylinder inlet and outlet pressure respectively, and generates a fault data set based on the location information of the fault that occurred during the test.

[0035] Furthermore, the processing module includes:

[0036] Setting unit: used to set the ratio of training set to test set, as well as the optimization range of LSTM unit number, learning rate, L2 regularization parameter, and set the maximum number of iterations and maximum number of training times of the Bayesian network.

[0037] Furthermore, the composition of the Bo-Transformer-LSTM model in the segmentation module includes:

[0038] Transformer encoding layer: provides data with attention to the Transformer-LSTM network. The data processed by the Transformer encoding layer provides data features for fault diagnosis. The mechanisms of the Transformer encoding layer include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization.

[0039] LSTM decoding layer: It consists of input gate, forget gate, output gate and cell state. LSTM takes Transformer encoding layer data, hidden layer data at the previous moment and cell state output at the previous moment as common input, and processes data serially through the gating mechanism;

[0040] Bayesian optimization is used to find the best hyperparameter configuration of the model, and the algorithm is optimized by optimizing the parameters of learning rate, L2 regularization, and the number of LSTM units.

[0041] Furthermore, the fault prediction module includes:

[0042] Evaluation unit: Based on the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value as algorithm evaluation indicators, the prediction accuracy of the model is evaluated;

[0043] Fault diagnosis unit: Based on the evaluation index, the collected fault data set is diagnosed through the Bo-Transformer-LSTM algorithm to obtain the prediction results.

[0044] Furthermore, the calculation formulas for the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value in the evaluation unit are as follows:

[0045]

[0046] Among them, TP represents the number of samples correctly identified as faulty; TN represents the number of samples correctly identified as non-faulty; FN represents the number of samples incorrectly identified as faulty; FP represents the number of samples incorrectly identified as non-faulty; f(x) represents the receiver operating characteristic curve.

[0047] The present invention adopts the above technical solution to achieve the following beneficial effects:

[0048] The present invention uses a Bo-Transformer-LSTM neural network. The Transformer decoding layer is reconstructed and integrated with the long short-term memory time series neural network structure. At the same time, the various parameters of the Bayesian optimization network are used to realize the identification and processing of different types of faults. The Bo-Transformer-LSTM neural network can accurately identify different types of faults and effectively reduce the maintenance difficulty of the hydraulic steering system of multi-axis special vehicles. The real vehicle experimental data of the multi-axis special vehicle under normal driving state is collected, and the model accuracy is verified by comparing with the AMESim simulation model of the hydraulic steering system. The fault data set of the hydraulic steering system is generated by the simulation model; at the same time, the Bo-Transformer-LSTM algorithm is proposed to perform fault diagnosis on the hydraulic steering system of the multi-axis special vehicle. The network realizes data feature extraction by combining data serial and parallel. In the Bo-Transformer-LSTM network, the Transformer is responsible for data parallel processing and focuses on the specific part of the data. When analyzing specific faults, it can ensure that the features are not forgotten and improve the accuracy of fault diagnosis. LSTM is responsible for data serial processing and focuses on the overall trend of the data. When analyzing multiple types of faults, it can ensure sufficient data features and improve the accuracy of fault classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The process of the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention Figure 1 ;

[0050] Figure 2 The process of the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention Figure 2 ;

[0051] Figure 3 A schematic diagram of the LSTM algorithm structure in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention;

[0052] Figure 4 A flow chart of a method for diagnosing hydraulic internal leakage in a vehicle steering system based on Bo-Transformer-LSTM provided in the first embodiment of the present invention;

[0053] Figure 5 A line graph of steering wheel angle data in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention;

[0054] Figure 6A line graph of steering wheel torque data in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention;

[0055] Figure 7 A schematic diagram of a simulation model of fault categories in a vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention;

[0056] Figure 8a , Figure 8b , Figure 8c and Figure 8d A comparison chart of prediction results of four different algorithm test sets in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in Example 1 of the present invention;

[0057] Figure 9a , Figure 9b , Fig.9c and Figure 9d A comparison diagram of confusion matrices of four different algorithms in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in Example 1 of the present invention;

[0058] Fig.10a , Fig.10b , Fig.10c and Fig.10d A comparison chart of the areas under the curves of four different algorithms in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in the first embodiment of the present invention;

[0059] Fig.11 A comparison chart of evaluation indicators of four different algorithms in the vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in Example 1 of the present invention;

[0060] Fig.12a and Figure 12b A schematic diagram of the network structure in a Transformer-LSTM unit in a vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM provided in Embodiment 1 of the present invention;

[0061] Fig.13 The structure of the vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM provided in the second embodiment of the present invention Figure 1 ;

[0062] Fig.14The structure of the vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM provided in the second embodiment of the present invention Figure 2 . DETAILED DESCRIPTION

[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0064] The following are specific embodiments of the present invention and the accompanying drawings to further describe the technical solution of the present invention, but the present invention is not limited to these embodiments.

[0065] Embodiment 1: This embodiment provides a method for diagnosing hydraulic internal leakage faults in a vehicle steering system based on Bo-Transformer-LSTM. Figure 1 and Figure 2 As shown, the method comprises the steps of:

[0066] S1: Obtaining fault data of leakage of a hydraulic steering system of a multi-axle special vehicle under a preset fault degree;

[0067] S2: normalize the fault data, and divide the normalized fault data into a training set and a test set according to a preset ratio;

[0068] S3: Segment the input fault data and input it into the Bo-Transformer-LSTM model. Use the Bayesian algorithm to optimize the hyperparameters of the Bo-Transformer-LSTM model to obtain the optimal parameter combination, and save the trained Bo-Transformer-LSTM model.

[0069] S4: The data of the test set is split and input into the trained Bo-Transformer-LSTM model for prediction. The output of the prediction result is denormalized to obtain the actual prediction result. The actual prediction result is compared with the data in the test set to evaluate the prediction accuracy of the Bo-Transformer-LSTM model.

[0070] Specifically, the real vehicle experimental data of the multi-axle special vehicle under normal driving state is collected, and the model accuracy is verified by comparing with the AMESim simulation model of the hydraulic steering system. The fault data set of the hydraulic steering system is generated by the simulation model; the Bo-Transformer-LSTM algorithm is proposed to diagnose the fault of the hydraulic steering system of the multi-axle special vehicle. The network realizes data feature extraction by combining data serial and parallel. In the Bo-Transformer-LSTM network, the Transformer is responsible for data parallel processing and focuses on the specific part of the data. When analyzing specific faults, it can ensure that the features are not forgotten and improve the accuracy of fault diagnosis. LSTM is responsible for data serial processing and focuses on the overall trend of the data. When analyzing multiple types of faults, it can ensure sufficient data features and improve the accuracy of fault classification. Bayes optimization is responsible for optimizing network hyperparameters, dynamically adjusting the processing method of input data during network training, and optimizing the performance of the model.

[0071] The acquisition of fault data includes:

[0072] S11: Use a steering force angle tester to measure the steering wheel input angle and the steering torque fed back to the steering wheel by the steering system, and collect the vehicle's steering wheel steering angle, steering wheel steering torque and travel speed at the same time;

[0073] S12: testing the vehicle at different speeds, and recording the steering angle and steering torque input by the steering wheel during the test according to step S11. When the vehicle returns to its original position after one circle, the experiment is considered completed.

[0074] S13: The steering angle, steering torque, and steering cylinder inlet and outlet pressures are collected respectively, and a fault data set is generated in combination with the position information of the fault occurring during the test.

[0075] Wherein, step S2 comprises:

[0076] S21: Set the ratio of training set to test set, as well as the optimization range of LSTM unit number, learning rate, L2 regularization parameter, and set the maximum number of iterations and maximum number of training times of the Bayesian network.

[0077] The structure of the Bo-Transformer-LSTM model in step S3 includes:

[0078] Transformer encoding layer: provides data with attention to the Transformer-LSTM network. The data processed by the Transformer encoding layer provides data features for fault diagnosis. The mechanisms of the Transformer encoding layer include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization.

[0079] LSTM decoding layer: It consists of input gate, forget gate, output gate and cell state. LSTM takes Transformer encoding layer data, hidden layer data at the previous moment and cell state output at the previous moment as common input, and processes data serially through the gating mechanism;

[0080] Bayesian optimization is used to find the best hyperparameter configuration of the model, and the algorithm is optimized by optimizing the parameters of learning rate, L2 regularization, and the number of LSTM units.

[0081] See also Fig.12a and Figure 12b , modify the Decoder layer in the Transformer model to a fully connected layer, and replace the original attention layer with the LSTM layer.

[0082] Specifically, the self-attention mechanism is a key feature of the Transformer model, which enables the model to perform weighted aggregation on parts of the input sequence. By calculating the attention score between the query Q, key K and value V, d K Represents the number of dimensions of K. The model can determine the importance of each position to other positions. After the attention score is scaled, it is fused into the value matrix by weighted summation to produce the final output. The calculation formula is shown in formula (1):

[0083]

[0084] Specifically, the Transformer model uses multiple parallel self-attention mechanisms to capture different types of relationships. Each head learns different weights to capture information in different representation subspaces. In this case, W A represents the learning parameters, and the calculation formula of the multi-head attention mechanism is shown in formula (2):

[0085]

[0086] Specifically, since Transformer has no built-in sequence order information, position encoding is used to add some information to each position in the input sequence so that the model can distinguish tokens at different positions. The calculation formulas are shown in formulas (3) and (4):

[0087]

[0088] Among them, pos represents the sequence position, i represents the dimension, and d represents the size of the embedding space dimension.

[0089] Specifically, the LSTM decoding layer consists of an input gate, a forget gate, an output gate, and a cell state. LSTM needs to transform the Transformer encoding layer data and the previous hidden layer data h t The cell state output C at the previous moment t As a common input, the data is processed serially through the gating mechanism to achieve data processing. The LSTM network structure is as follows Figure 3 As shown in the figure, σ represents the sigmoid activation function, h represents the hidden state, x represents the input, and C represents the cell state.

[0090] Specifically, in the application of the Transformer-LSTM model, Bayesian optimization can be used to automatically find the optimal hyperparameter configuration of the model and optimize the algorithm by optimizing the following parameters:

[0091] Learning rate: controls the step size of the model's weight update in each iteration, which has a significant impact on the model's convergence speed and final performance;

[0092] L2 regularization: A regularization technique used to prevent overfitting, which improves the generalization ability of the model by randomly discarding a portion of neurons during training;

[0093] Number of LSTM units: The number of neurons in the LSTM layer determines the capacity and complexity of the model.

[0094] Through Bayesian optimization, the way input data is processed can be dynamically adjusted during the training process to optimize the performance of the model.

[0095] See also Figure 4 The fault diagnosis process of hydraulic internal leakage of multi-axis special vehicle steering system based on Bo-Transformer-LSTM network is as follows: obtain fault data of different degrees of internal leakage of multi-axis special vehicle hydraulic steering system; normalize the processed data and divide the training set and test set according to the proportion; segment the input data, input the segmented data into the model, and optimize the hyperparameters through the Bayesian algorithm to obtain the optimal parameter combination and save the trained model; segment the test set data and input it into the model for prediction, denormalize the output to obtain the prediction result, compare it with the prediction set data, and evaluate the model accuracy.

[0096] Wherein, step S4 comprises:

[0097] S41: The prediction accuracy of the model was evaluated based on the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value as algorithm evaluation indicators;

[0098] S42: Based on the evaluation index, the collected fault data set is diagnosed through the Bo-Transformer-LSTM algorithm to obtain a prediction result.

[0099] Specifically, the fault data set is constructed as follows:

[0100] The AM-2012 steering force angle tester is used to measure the steering wheel input angle θ and the steering torque T fed back to the steering wheel by the steering system. At the same time, the vehicle's steering wheel angle θ, steering wheel steering torque T and travel speed are collected.

[0101] Before the experiment, the driver drove the vehicle several times along the preset experimental path similar to the letter "∞" to reach the state of preparing to start the experiment. When the experiment officially begins, the steering wheel of the experimental vehicle is first returned to the center, and the vehicle starts driving with the symmetry center of the experimental path of the letter "∞" as the starting point. After driving along the preset experimental path, the vehicle is stopped in place after one circle is completed and restored to the state before departure. After the vehicle stops, the steering wheel is returned to the initial return position.

[0102] During the experiment, the experimental vehicle travels along the preset "∞" experimental path at speeds of 10km / h, 20km / h and 30km / h respectively. When the vehicle speed is stable, the AM-2012 tester will start working and record the steering wheel angle θ and steering torque T in real time. When the vehicle starts from the symmetric center of the experimental path and returns to the original position, it is recorded as completing a complete experiment. After completing three complete experiments at each speed, the actual vehicle verification experiment is completed.

[0103] The experiment obtained 9 data under three different vehicle speeds, using the representative experimental data at 20km / h, a total of 1800 groups. The experimental screened data was plotted into a line graph. The results are as follows Figure 5 and Figure 6 As shown in the figure. By comparing the simulation results of the total model of the all-wheel steering system with the actual experimental data, the correctness of the model establishment can be verified. Figure 5 and Figure 6 shown.

[0104] Figure 5 By comparing the model input angle signal with the experimental angle data, it is found that the change of the model input angle signal can roughly fit the change trend of the input angle data image during the experiment; Figure 6 The model spring steering torque is compared with the experimental steering torque data, and it is also found that the image change trend can be roughly fitted. The comparison results show that when the input angle is roughly fitted, the parameter curve of the steering torque can also be roughly fitted. The simulation is basically consistent with the experiment, and the experimental purpose is basically achieved, verifying the correctness of the overall model.

[0105] Specific, hydraulic steering system failure classification:

[0106] For special vehicles, leakage faults in the steering hydraulic system usually occur in the rotary valve, front axle hydraulic steering, 4-axis hydraulic steering and 5-axis hydraulic steering, a total of 4 fault locations. According to the location and number of faults, they are divided into 15 categories, as shown in Table 1, where 1 represents the location where the fault occurs.

[0107] Table 1

[0108]

[0109] According to the different degrees of internal leakage, the preset fault levels are divided into three levels of faults:

[0110] Slight internal leakage, which means that the vehicle can complete the expected steering performance, but there is a certain delay in steering;

[0111] Moderate internal leakage, which means that the vehicle still has the steering function, but cannot reach the expected steering angle;

[0112] Severe internal leakage, manifested in the complete loss of the vehicle's steering function.

[0113] Therefore, according to the location of the fault and the severity of the internal leakage, combined with the loss of vehicle steering function when serious internal leakage occurs in engineering practice, it is impossible to accurately determine the location of the serious internal leakage, and it is divided into 30 types.

[0114] Specifically, according to the classification of internal leakage faults in the hydraulic steering system in Table 1, the fault data set is collected through the following simulation model. Taking the category 15 fault model as an example, the remaining 14 categories are permutations and combinations of the four fault locations. Category 15 is as follows: Figure 7 shown.

[0115] Figure 5 The data shown is the data generated by the fault model under steering conditions. The fault data set is generated according to the above 15 fault categories. The throttle diameter is set from 0 to the corresponding pipeline diameter with a diameter change of 0.1 mm. The steering angle, steering torque, front axle steering cylinder inlet and outlet pressure, 4-axis and 5-axis steering cylinder inlet and outlet pressure, a total of 7 types of data are collected to generate the fault data set.

[0116] Specifically, the data set is set up to collect 30 types of data for slight internal leakage and moderate internal leakage corresponding to 15 types of faults, and 500 groups of data are selected from each type of data to generate a fault data set.

[0117] Model parameter settings: In terms of model, the ratio of training set to test set is 7:3, the optimization range of LSTM unit number parameter is 10-50, and the optimization range of learning rate parameter is 10 -3-1; L2 regularization parameter optimization interval is 10 -10 -10 -2 ; The maximum number of iterations of the Bayesian network is 30, and the maximum number of training times is 200.

[0118] Evaluation index A method called polygon area measurement is used to evaluate the performance of the classifier. In PAM, classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index JI, and F value FM are used as evaluation indicators of the algorithm. The mathematical definitions are given as shown in formula (5) to formula (10).

[0119]

[0120] Where TP is the number of true positives, i.e., the number of samples correctly identified as faulty. TN is the number of true negatives, i.e., the number of samples correctly identified as non-faulty. FN is the number of false negatives, i.e., the number of samples incorrectly identified as faulty as non-faulty. FP is the number of false positives, i.e., the number of samples incorrectly identified as non-faulty as faulty. f(x) is the receiver operating characteristic curve, where the true positive rate SE is a function of the false positive rate 1-SP at different cutoff points.

[0121] PAM is calculated using the area of ​​the polygon created by the points CA, SE, SP, AUC, JI, and FM in a regular hexagon. The regular hexagon is composed of 6 equilateral triangles, and the length of each side is equal to 1. Represent the values ​​of CA, SE, SP, AUC, JI, and FM respectively. The calculation formula of PAM is as shown in formula (11):

[0122]

[0123] Where PA is the area of ​​the polygon. To normalize PAM to the interval [0,1], the PA value is divided by 2.59807.

[0124] This experiment uses multiple sets of data to verify the performance of the network. Four algorithms, LSTM, Transformer, Transformer-LSTM, and Bo-Transformer-LSTM, are used to diagnose the collected fault data sets. The results are shown in Figures 8 to 9. Fig.11 result.

[0125] Figure 8a , Figure 8b , Figure 8c and Figure 8d Represents the prediction results of 4 different algorithm test sets, Figure 9a , Figure 9b , Fig.9c and Figure 9d Represents the confusion matrix of 4 different algorithms; Fig.10a , Fig.10b , Fig.10c and Fig.10d Represents the area under the curve of 4 different algorithms; Fig.11 Represents 4 different algorithm evaluation indicators.

[0126] Table 2

[0127]

[0128] Specifically, the comparison results of the four algorithms are shown in Figures 8 to Fig.11 As shown in Table 2, among the four algorithms, the Bo-Transformer-LSTM algorithm has obvious advantages over the other three algorithms. Its classification accuracy reaches 98.0556%, indicating that the algorithm can effectively complete fault classification; the sensitivity reaches 1, indicating that the algorithm has a strong ability to detect faults; the specificity reaches 1, indicating that the algorithm can reduce unnecessary maintenance and inspection; the area under the curve reaches 0.9997, indicating that the overall performance of the algorithm is good under all possible classification thresholds; its value is between 0 and 1, where 1 represents a perfect classifier, 0.5 represents an invalid classifier, which is equivalent to random guessing, and a value lower than 0.5 means worse than random guessing, which means that the performance of the classifier is reversed. The Jaccard index reaches 1, indicating that the algorithm has high consistency; the F value reaches 1, indicating that the performance of the algorithm has achieved a good balance between precision and recall, and the proportion of false positives and false negatives is low. The PAM value obtained by combining various data is 0.99, which has the best effect among the four fault diagnosis algorithms.

[0129] Specifically, by building a simulation model of the hydraulic steering system and comparing it with the actual vehicle experiment, the correctness of the simulation model is verified, and a fault data set is generated using the simulation model of the internal leakage fault of the hydraulic steering system. The generated fault data set is used to perform fault diagnosis and analysis on the hydraulic steering system of special vehicles, and a multi-axis special vehicle hydraulic steering system fault diagnosis algorithm based on Bo-Transformer-LSTM is adopted. The classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI, and F value are used as algorithm evaluation indicators to verify the effectiveness of the algorithm.

[0130] This method uses the Bo-Transformer-LSTM neural network. The Transformer decoding layer is reconstructed and integrated with the long short-term memory time series neural network structure. At the same time, the parameters of the network are optimized by Bayesian to realize the identification and processing of different types of faults. The Bo-Transformer-LSTM neural network can accurately identify different types of faults and effectively reduce the maintenance difficulty of the hydraulic steering system of multi-axle special vehicles. The real vehicle experimental data of the multi-axle special vehicle under normal driving state is collected, and the model accuracy is verified by comparing with the AMESim simulation model of the hydraulic steering system. The fault data set of the hydraulic steering system is generated by the simulation model; at the same time, the Bo-Transformer-LSTM algorithm is proposed to diagnose the fault of the hydraulic steering system of the multi-axle special vehicle. The network realizes data feature extraction by combining data serial and parallel. In the Bo-Transformer-LSTM network, the Transformer is responsible for data parallel processing and focuses on the specific part of the data. When analyzing specific faults, it can ensure that the features are not forgotten and improve the accuracy of fault diagnosis. LSTM is responsible for data serial processing and focuses on the overall trend of the data. When analyzing multiple types of faults, it can ensure sufficient data features and improve the accuracy of fault classification.

[0131] Embodiment 2: This embodiment provides a vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM, such as Fig.13 and Fig.14 As shown, the system includes:

[0132] Acquisition module: used to acquire fault data of leakage of hydraulic steering system of multi-axle special vehicle under preset fault degree;

[0133] Processing module: used to normalize the fault data and divide the normalized fault data into a training set and a test set according to a preset ratio;

[0134] Segmentation module: used to segment the input fault data and input it into the Bo-Transformer-LSTM model, optimize the hyperparameters of the Bo-Transformer-LSTM model using the Bayesian algorithm, obtain the optimal parameter combination, and save the trained Bo-Transformer-LSTM model;

[0135] Fault prediction module: It is used to segment the test set data and input it into the trained Bo-Transformer-LSTM model for prediction. The output of the prediction result is denormalized to obtain the actual prediction result. The actual prediction result is compared with the data in the test set to evaluate the prediction accuracy of the Bo-Transformer-LSTM model.

[0136] See also Fig.14 , where the acquisition of fault data includes:

[0137] Acquisition unit: used to measure the steering wheel input angle and the steering torque fed back to the steering wheel by the steering system through a steering force angle tester, and to collect the vehicle's steering wheel steering angle, steering wheel steering torque and travel speed at the same time;

[0138] Testing unit: used to test the vehicle at different speeds, and record the steering angle and steering torque input by the steering wheel during the test according to step S11. When the vehicle returns to its original position after driving one circle, it is recorded as completing one experiment;

[0139] Generation unit: collects steering angle, steering torque and steering cylinder inlet and outlet pressure respectively, and generates a fault data set based on the location information of the fault that occurred during the test.

[0140] The processing module includes:

[0141] Setting unit: used to set the ratio of training set to test set, as well as the optimization range of LSTM unit number, learning rate, L2 regularization parameter, and set the maximum number of iterations and maximum number of training times of the Bayesian network.

[0142] Among them, the composition of the Bo-Transformer-LSTM model in the segmentation module includes:

[0143] Transformer encoding layer: provides data with attention to the Transformer-LSTM network. The data processed by the Transformer encoding layer provides data features for fault diagnosis. The mechanisms of the Transformer encoding layer include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization.

[0144] LSTM decoding layer: It consists of input gate, forget gate, output gate and cell state. LSTM takes Transformer encoding layer data, hidden layer data at the previous moment and cell state output at the previous moment as common input, and processes data serially through the gating mechanism;

[0145] Bayesian optimization is used to find the best hyperparameter configuration of the model, and the algorithm is optimized by optimizing the parameters of learning rate, L2 regularization, and the number of LSTM units.

[0146] Among them, the fault prediction module includes:

[0147] Evaluation unit: Based on the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value as algorithm evaluation indicators, the prediction accuracy of the model is evaluated;

[0148] Fault diagnosis unit: Based on the evaluation index, the collected fault data set is diagnosed through the Bo-Transformer-LSTM algorithm to obtain the prediction results.

[0149] Among them, the calculation formulas for classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value in the evaluation unit are:

[0150]

[0151] Among them, TP represents the number of samples correctly identified as faulty; TN represents the number of samples correctly identified as non-faulty; FN represents the number of samples incorrectly identified as faulty; FP represents the number of samples incorrectly identified as non-faulty; f(x) represents the receiver operating characteristic curve.

[0152] This system uses the Bo-Transformer-LSTM neural network. The Transformer decoding layer is reconstructed and integrated with the long short-term memory time series neural network structure. At the same time, the various parameters of the Bayesian optimization network are used to realize the identification and processing of different types of faults. The Bo-Transformer-LSTM neural network can accurately identify different types of faults and effectively reduce the maintenance difficulty of the hydraulic steering system of multi-axle special vehicles. The real vehicle experimental data of the multi-axle special vehicle under normal driving state is collected, and the model accuracy is verified by comparing with the AMESim simulation model of the hydraulic steering system. The fault data set of the hydraulic steering system is generated by the simulation model; at the same time, the Bo-Transformer-LSTM algorithm is proposed to diagnose the fault of the hydraulic steering system of the multi-axle special vehicle. The network realizes data feature extraction by combining data serial and parallel. In the Bo-Transformer-LSTM network, the Transformer is responsible for data parallel processing and focuses on the specific part of the data. When analyzing specific faults, it can ensure that the features are not forgotten and improve the accuracy of fault diagnosis. LSTM is responsible for data serial processing and focuses on the overall trend of the data. When analyzing multiple types of faults, it can ensure sufficient data features and improve the accuracy of fault classification.

[0153] Although the disclosure is disclosed as above, the protection scope of the disclosure is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the disclosure, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM, characterized in that: Includes steps: S1: Obtaining fault data of leakage of a hydraulic steering system of a multi-axle special vehicle under a preset fault degree; S2: normalize the fault data, and divide the normalized fault data into a training set and a test set according to a preset ratio; The step S2 comprises: S21: Set the ratio of training set to test set, as well as the optimization range of LSTM unit number, learning rate, L2 regularization parameter, and set the maximum number of iterations and maximum number of training times of the Bayesian network; S3: Segment the input fault data and input it into the Bo-Transformer-LSTM model. Use the Bayesian algorithm to optimize the hyperparameters of the Bo-Transformer-LSTM model to obtain the optimal parameter combination, and save the trained Bo-Transformer-LSTM model. The structure of the Bo-Transformer-LSTM model in step S3 includes: Transformer encoding layer: provides data with attention to the Transformer-LSTM network. The data processed by the Transformer encoding layer provides data features for fault diagnosis. The mechanisms of the Transformer encoding layer include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization. LSTM decoding layer: It consists of input gate, forget gate, output gate and cell state. LSTM takes Transformer encoding layer data, hidden layer data at the previous moment and cell state output at the previous moment as common input, and processes data serially through the gating mechanism; Bayesian optimization is used to find the best hyperparameter configuration of the model, and the algorithm is optimized by optimizing the parameters of learning rate, L2 regularization and number of LSTM units; S4: The data of the test set is split and input into the trained Bo-Transformer-LSTM model for prediction. The output of the prediction result is denormalized to obtain the actual prediction result. The actual prediction result is compared with the data in the test set to evaluate the prediction accuracy of the Bo-Transformer-LSTM model.

2. The vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM according to claim 1 is characterized in that: The acquisition of the fault data includes: S11: Use a steering force angle tester to measure the steering wheel input angle and the steering torque fed back to the steering wheel by the steering system, and collect the vehicle's steering wheel steering angle, steering wheel steering torque and travel speed at the same time; S12: testing the vehicle at different speeds, and recording the steering angle and steering torque input by the steering wheel during the test according to step S11. When the vehicle returns to its original position after one circle, the experiment is considered completed. S13: The steering angle, steering torque, and steering cylinder inlet and outlet pressures are collected respectively, and a fault data set is generated in combination with the position information of the fault occurring during the test.

3. The vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM according to claim 1 is characterized in that: The step S4 comprises: S41: The prediction accuracy of the model was evaluated based on the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value as algorithm evaluation indicators; S42: Based on the evaluation index, the collected fault data set is diagnosed through the Bo-Transformer-LSTM algorithm to obtain a prediction result.

4. The vehicle steering system hydraulic internal leakage fault diagnosis method based on Bo-Transformer-LSTM according to claim 3 is characterized in that: The calculation formulas for the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value in step S41 are: Among them, TP represents the number of samples correctly identified as faulty; TN represents the number of samples correctly identified as non-faulty; FN represents the number of samples incorrectly identified as faulty; FP represents the number of samples incorrectly identified as non-faulty; f(x) represents the receiver operating characteristic curve.

5. A vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM, characterized in that: include: Acquisition module: used to acquire fault data of leakage of hydraulic steering system of multi-axle special vehicle under preset fault degree; Processing module: used to normalize the fault data and divide the normalized fault data into a training set and a test set according to a preset ratio; The processing module comprises: Setting unit: used to set the ratio of training set to test set, as well as the optimization range of LSTM unit number, learning rate, L2 regularization parameter, and set the maximum number of iterations and maximum number of training of Bayesian network; Segmentation module: used to segment the input fault data and input it into the Bo-Transformer-LSTM model, optimize the hyperparameters of the Bo-Transformer-LSTM model using the Bayesian algorithm, obtain the optimal parameter combination, and save the trained Bo-Transformer-LSTM model; The composition of the Bo-Transformer-LSTM model in the segmentation module includes: Transformer encoding layer: provides data with attention to the Transformer-LSTM network. The data processed by the Transformer encoding layer provides data features for fault diagnosis. The mechanisms of the Transformer encoding layer include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization. LSTM decoding layer: It consists of input gate, forget gate, output gate and cell state. LSTM takes Transformer encoding layer data, hidden layer data at the previous moment and cell state output at the previous moment as common input, and processes data serially through the gating mechanism; Bayesian optimization is used to find the best hyperparameter configuration of the model, and the algorithm is optimized by optimizing the parameters of learning rate, L2 regularization and number of LSTM units; Fault prediction module: It is used to segment the test set data and input it into the trained Bo-Transformer-LSTM model for prediction. The output of the prediction result is denormalized to obtain the actual prediction result. The actual prediction result is compared with the data in the test set to evaluate the prediction accuracy of the Bo-Transformer-LSTM model.

6. The vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM according to claim 5 is characterized in that: The acquisition of the fault data includes: Acquisition unit: used to measure the steering wheel input angle and the steering torque fed back to the steering wheel by the steering system through a steering force angle tester, and to collect the vehicle's steering wheel steering angle, steering wheel steering torque and travel speed at the same time; Testing unit: used to test the vehicle at different speeds, and record the steering angle and steering torque input by the steering wheel during the test according to step S11. When the vehicle returns to its original position after driving one circle, it is recorded as completing one experiment; Generation unit: collects steering angle, steering torque and steering cylinder inlet and outlet pressure respectively, and generates a fault data set based on the location information of the fault that occurred during the test.

7. The vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM according to claim 5 is characterized in that: The fault prediction module comprises: Evaluation unit: Based on the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value as algorithm evaluation indicators, the prediction accuracy of the model is evaluated; Fault diagnosis unit: Based on the evaluation index, the collected fault data set is diagnosed through the Bo-Transformer-LSTM algorithm to obtain the prediction results.

8. The vehicle steering system hydraulic internal leakage fault diagnosis system based on Bo-Transformer-LSTM according to claim 7 is characterized in that: The calculation formulas for the classification accuracy CA, sensitivity SE, specificity SP, area under the ROC curve AUC, Jaccard index TI and F value in the evaluation unit are as follows: Among them, TP represents the number of samples correctly identified as faulty; TN represents the number of samples correctly identified as non-faulty; FN represents the number of samples incorrectly identified as faulty; FP represents the number of samples incorrectly identified as non-faulty. f(x) represents the receiver operating characteristic curve.

Images