Heavy truck electric drive bridge fault diagnosis method based on data driving

Abstract

The invention discloses a data driving-based heavy truck electric drive bridge fault diagnosis method, which comprises the following steps of: firstly, acquiring operation state data of a heavy truck electric drive bridge in various use scenes, marking fault categories, and constructing an original data set; carrying out sample generation by adopting a generative adversarial network based on weight noise to realize data expansion, and merging the expanded data with the original data to form a training data set; selecting a self-encoder based on boundary smoothing as a feature dimension reduction model, and training the feature dimension reduction model by using the training data set; adopting a probabilistic neural network based on quantum probability guidance as a classifier model, and training the classifier model by using features output by the feature dimension reduction model; and finally, collecting original data of a to-be-evaluated heavy truck electric drive bridge, and inputting the original data into the trained feature dimension reduction model for feature processing. And inputting the processed features into the trained classifier model for classification to obtain a classification result. According to the invention, high precision and high robustness of electric drive bridge fault diagnosis can be realized.

Description

Technical Field

[0001] The present invention relates to the field of heavy truck electric drive axle fault diagnosis, and in particular to a data-driven heavy truck electric drive axle fault diagnosis method. Background Art

[0002] As an important power transmission device for heavy trucks, the stability and reliability of the operation of the electric drive axle are directly related to the safety and service life of the vehicle. However, in various scenarios such as high-speed driving, complex urban traffic, and bad weather, the electric drive axle of heavy trucks is prone to failures due to long-term load, environmental changes and component aging, such as bearing damage, motor failure, sensor failure, brake system problems and tire abnormalities. These problems not only affect vehicle performance, but may also cause serious economic losses and safety risks.

[0003] The current methods for solving heavy truck electric drive axle faults have the following shortcomings:

[0004] 1. In the electric drive axle fault diagnosis task, the traditional generative adversarial network lacks effective diversity control in data generation, and the generated data is prone to pattern collapse. When the training samples are insufficient, the generated data has poor adaptability to complex working conditions.

[0005] 2. In the electric drive axle fault diagnosis task, the existing feature dimensionality reduction model is difficult to take into account the compression of high-dimensional data and the processing of boundary anomalies, resulting in insufficient performance of the reduced-dimensional features in sparse areas, affecting the robustness and accuracy of the diagnosis.

[0006] 3. In the electric drive axle fault diagnosis task, the traditional probabilistic neural network has limited performance when faced with uncertain information, and the classification accuracy of complex fault modes is insufficient. The classifier has low processing ability for small amounts of data or abnormal data and cannot meet the fault diagnosis needs under complex working conditions. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention proposes a data-driven heavy truck electric drive axle fault diagnosis method, and the specific technical solution is as follows:

[0008] A data-driven method for diagnosing a heavy truck electric drive axle fault includes the following steps:

[0009] Step 1: Collect the operating status data of the heavy-duty truck electric drive axle in various usage scenarios, mark the fault categories, and build the original data set;

[0010] Step 2: Use a weighted noise-based generative adversarial network to generate samples and achieve data expansion; the generative adversarial network includes a generator and a discriminator, and noise is injected into the weight of the generator. The generator generates data based on the current weight and the injected noise; the discriminator evaluates the difference between the generated data and the real data, and feeds back to the generator. The generator dynamically adjusts the intensity of the noise injected into the weight of the generator according to the feedback, thereby training the weighted noise-based generative adversarial network to obtain the expanded samples output by the trained model; and the expanded samples are merged with the original data to form a training data set;

[0011] Step 3: Construct and train a feature dimensionality reduction model; the feature dimensionality reduction model is an autoencoder based on boundary smoothing, including an encoder and a decoder. The encoder compresses the input data to a low-dimensional representation, and smoothes the output of the encoder through a smoothing function for outliers and boundary effects in the dimensionality reduction process; the decoder reconstructs the low-dimensional representation into a feature vector that is as similar as possible to the input data; the data is processed by forward propagation, and then the autoencoder parameters are updated by gradient descent through error back propagation;

[0012] Step 4: construct a classifier model, and use the dimension-reduced data output from step 3 to train the classifier model; the classifier model is a probabilistic neural network guided by quantum probability, and the weights and activation function parameters in the probabilistic neural network are dynamically adjusted by using the quantum state estimation method, and the classification process is optimized by simulating quantum behavior, so that the network can better adapt to changes in data distribution in each step of training; the data is processed by forward propagation, and then the weights and quantum parameters of the probabilistic neural network are updated by error back propagation;

[0013] Step 5: Collect the original data of the heavy-duty truck electric drive axle to be evaluated, and input it into the trained feature dimension reduction model for feature processing; then input the processed features into the trained classifier model for classification to obtain the classification results.

[0014] Further, the fault categories include normal operation, bearing damage, motor failure, sensor failure, brake system problem, and tire abnormality.

[0015] Furthermore, the operating status data of the heavy-duty truck electric drive axle include bearing temperature Ra, wheel hub vibration amplitude Da, wheel axle torque Sa, brake temperature Ta, tire pressure Ca, speed sensor data Pa, GPS positioning data Qa, electric drive axle current Ka, electric drive axle voltage Ma and control unit feedback signal Na.

[0016] Furthermore, the training process of the weighted noise-based generative adversarial network in step 2 is as follows:

[0017] S201: Initialize generator G c Weight and the discriminator D c Weight The initialization method is expressed as:

[0018]

[0019] Where randn() represents a random number generated from a standard normal distribution; ← is a parameter update operation; d c represents the dimension of the input noise, m c Represents the dimension of the middle layer of the generator, n c Indicates the dimension of the output data;

[0020] S202: In each iteration, the weight of the generator is dynamically adjusted according to the feedback from the discriminator:

[0021]

[0022]

[0023] In the formula, z c is the input noise of the generator, is the loss function of the generative adversarial network, η c is the learning rate of the generative adversarial network, represents the gradient of the generator weight; G c () is a generator function; D c () is the discriminator function; is the weight update amount of the generator; is a real sample; represents the partial derivative of the generator output with respect to its weight, calculated by the back-propagation algorithm;

[0024] S203: The generator generates data based on the current weights and injected noise:

[0025]

[0026] In the formula, is the sample generated by the generator; σ c is a noise intensity parameter used to adjust the amplitude of noise injection so that the intensity of noise injection can be dynamically adjusted according to the performance of the discriminator, thereby more finely controlling the quality and diversity of generated data; represents the error rate of the discriminator on the current generated data, α c Is the first parameter that controls the decay rate; β c It is the second parameter that controls the decay speed;

[0027] S204: The discriminator evaluates the difference between the generated data and the real data and feeds it back to the generator; the parameter update increment calculation method of the discriminator is expressed as:

[0028]

[0029] In the formula, represents the gradient of the discriminator weight;

[0030] S205: Repeat iterative steps S202-S204 until the preset stop iteration condition is met and the model training is completed.

[0031] Furthermore, the training process of the feature dimensionality reduction model is as follows:

[0032] S301: Initialize the parameters of the boundary smoothing based autoencoder:

[0033]

[0034] In the formula, represents the weight of the encoder, Indicates the encoder bias; represents the weight of the decoder, represents the bias of the decoder; randn() represents the random function; d r,in is the dimension of the encoder input layer, d r,mid is the dimension of the encoder's intermediate layer, d r,out is the dimension of the encoder output layer; zeros() is a function that generates a vector of all zeros;

[0035] S302: During the training process of the autoencoder, the data is processed by forward propagation, and then the autoencoder parameters are updated by using the gradient descent method through error back propagation;

[0036] Among them, the loss function L of the autoencoder r The calculation method is expressed as:

[0037]

[0038] In the formula, x r is the input data of the autoencoder, is the output reconstructed by the decoder, Sig() is the Sigmoid activation function; ∥∥ is the L2 norm; is the output of the smoothed autoencoder; is the weight coefficient of the i-th dimension autoencoder; n r is the vector dimension corresponding to the samples of the current batch input to the autoencoder;

[0039] The update amount of the autoencoder parameters is calculated as follows:

[0040]

[0041] In the formula, is the update amount of the encoder's weight parameters; is the encoder bias parameter update amount; is the update amount of the decoder weight parameters; is the update amount of the bias parameter of the decoder; is the learning rate of the autoencoder at the tth iteration; is the learning rate of the initial autoencoder; is the learning rate of the autoencoder at the tth iteration; γ r is the learning rate decay factor of the autoencoder, is the average diameter of the convex hull in the tth iteration, is the diameter of the initial convex hull;

[0042] S303: Calculate the updated autoencoder parameters by the following formula:

[0043]

[0044] Where ← represents the parameter update operation.

[0045] S304: Repeat S302 to S303 until the preset stop iteration condition is met and the feature dimensionality reduction model training is completed.

[0046] Furthermore, the training process of the classifier model includes the following sub-steps:

[0047] S401: Initialize the weights and quantum state parameters of the probabilistic neural network:

[0048]

[0049] In the formula, represents the initial weight matrix, d u is the input dimension of the probabilistic neural network, h u is the hidden layer dimension of the probabilistic neural network, represents the initial parameters of the quantum state;

[0050] S402: Dynamically adjust the weights and activation function parameters in the probabilistic neural network using quantum state estimation methods; optimize the classification process by simulating quantum behavior so that the network can better adapt to changes in data distribution in each step of training;

[0051] Among them, the update increment of the quantum state parameter is expressed as:

[0052]

[0053] Where η u is the learning rate of the probabilistic neural network, Y u is the true label, is the model prediction, represents the partial derivative of the quantum state parameter, L u () is the loss function of the probabilistic neural network; represents the gradient of the loss function of the probabilistic neural network with respect to the quantum state parameters; is the partial derivative of the loss function with respect to the predicted output, represents the gradient of the predicted value with respect to the quantum state parameters; φ u (X uj ) is the activation function after weight normalization, ψ u (X uj ,θ u ) is the quantum state function, i * is an imaginary unit;

[0054] S403: In each iteration, the features input to the probabilistic neural network are forward propagated through the neural network guided by quantum probability. The neural network calculates the output according to the current parameter state. In this process, the network processes the input data through quantum probability methods and adjusts the activation state using quantum state estimation.

[0055] Among them, the model predicts the label The calculation method is expressed as:

[0056]

[0057] Where, X u is the feature input to the probabilistic neural network, b u is the bias term of the probabilistic neural network, f u () is the quantum probability guided activation function;

[0058] The calculation method of the quantum probability guided activation function is expressed as:

[0059]

[0060] In the formula, a u =W u ·X u +b u is the weighted input, α u is the dynamic adjustment coefficient, which is calculated as follows:

[0061]

[0062] In the formula, γ u is the first hyperparameter used to adjust the activation strength; β uis the second hyperparameter used to adjust the activation strength; C u Indicates the number of categories;

[0063] S404: Perform forward propagation of data according to S403 to obtain the output of the network, that is, the model prediction label, and calculate the loss function value in combination with the real label, and use the back propagation algorithm to update the network weights and quantum state parameters to minimize the loss function; the loss function L u The cross entropy loss is calculated as follows:

[0064]

[0065] Where Y uc is the true label of the cth category; is the probability of the model prediction label for the cth category;

[0066] Furthermore, the gradient of the loss function with respect to the weights When used to update weights, the calculation method of the updated increment is expressed as:

[0067]

[0068] In the formula, ΔW u is the weight update increment of the probabilistic neural network; η u is the learning rate of the probabilistic neural network;

[0069] S405: After each iteration, the weights and quantum state parameters of the probabilistic neural network are updated according to the results of back propagation, and after each parameter update, the quantum state parameter θ u Perform normalization to ensure the stability of quantum probability distribution;

[0070] Among them, the update method of the weights and quantum state parameters of the probabilistic neural network is expressed as:

[0071] W u ←W u +ΔW u

[0072] θ u ←θ u +Δθ u

[0073]

[0074] In the formula, ∥θ u ∥ is the L2 norm of the quantum state parameter, θ u,j is the jth element of the quantum state parameter.

[0075] S406: Repeat S402 to S405 until the preset stop iteration condition is met and the model training is completed.

[0076] The beneficial effects of the present invention are as follows:

[0077] 1. The present invention introduces noise into the generator weights of the traditional generative adversarial network and dynamically adjusts the noise intensity to improve the authenticity and diversity of the generated data, thereby solving the problem of poor model generalization ability caused by insufficient training samples and significantly improving the effectiveness of data expansion.

[0078] 2. The present invention dynamically handles boundary anomalies through boundary smoothing strategy, improves the adaptability to feature boundaries and noise in the dimensionality reduction process, and enhances the robustness of the model and its ability to process sparse area data.

[0079] 3. The present invention is based on quantum state estimation and neural network, and optimizes weights and activation functions through quantum probability, thereby enhancing the network's adaptability to uncertain data and effectively improving the classifier's recognition accuracy and stability for complex fault modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 The present invention is a flow chart of the data-driven heavy truck electric drive axle fault diagnosis method. DETAILED DESCRIPTION

[0081] The present invention will be described in detail below based on the accompanying drawings and preferred embodiments, and the purpose and effects of the present invention will become more clear. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0082] like Figure 1 As shown, the data-driven heavy truck electric drive axle fault diagnosis method of the present invention comprises the following steps:

[0083] Step 1: Collect the operating status data of heavy-duty truck electric drive axles in various usage scenarios, label the categories, and construct the original data set.

[0084] In one embodiment, the marked categories include normal operation, bearing damage, motor failure, sensor failure, brake system problem, and tire abnormality. The operating status data includes bearing temperature Ra, wheel hub vibration amplitude Da, axle torque Sa, brake temperature Ta, tire pressure Ca, speed sensor data Pa, GPS positioning data Qa, electric drive bridge current Ka, electric drive bridge voltage Ma, and control unit feedback signal Na.

[0085] In practical applications, the attributes of data are usually more than 10 attributes, and the number of attributes of data may reach dozens or even hundreds.

[0086] Step 2: Use a weighted noise-based generative adversarial network to generate samples and achieve data expansion; the generative adversarial network includes a generator and a discriminator. Noise is injected into the weights of the generator, and the generator generates data based on the current weights and the injected noise; the discriminator evaluates the difference between the generated data and the real data and feeds it back to the generator. The generator dynamically adjusts the intensity of the noise injected into the weights of the generator based on this feedback, thereby training the weighted noise-based generative adversarial network to obtain the expanded samples output by the trained model; and the expanded samples are merged with the original data to form a training data set.

[0087] It is understandable that in the task of the present invention, the collection, acquisition, labeling and preprocessing of training data are time-consuming and labor-intensive, and insufficient training samples are likely to lead to poor generalization ability of the model, while affecting the accuracy of the model. It is understandable that in the task of the present invention, the collection, acquisition, labeling and preprocessing of training data are time-consuming and labor-intensive, and insufficient training samples are likely to lead to poor generalization ability of the model, while affecting the accuracy of the model. In the traditional generative adversarial network, the generator and the discriminator compete with each other to improve the authenticity of the generated data. The present invention injects noise into the weights of the generator, which can not only increase the diversity of the data generated by the model, but also help the network avoid overfitting during the learning process and improve the generalization ability of the model.

[0088] Step 2 specifically includes the following sub-steps:

[0089] S201: Initialize generator G c Weight and the discriminator D c Weight The initialization method is expressed as:

[0090]

[0091] Where randn() represents a random number generated from a standard normal distribution; ← is a parameter update operation; d c represents the dimension of the input noise, m c Represents the dimension of the middle layer of the generator, n c Indicates the dimension of the output data.

[0092] S202: In each iteration, the noise injected into the generator weight is dynamically adjusted according to the feedback of the discriminator. Specifically, the weight of the generator is dynamically adjusted according to the feedback of the discriminator. The weight calculation method is expressed as:

[0093]

[0094] In the formula, z c is the input noise of the generator, is the loss function of the generative adversarial network, ηc is the learning rate of the generative adversarial network, represents the gradient of the generator weight; G c () is a generator function; D c () is the discriminator function; is the weight update amount of the generator; is a real sample; Represents the partial derivative of the generator output with respect to its weights, calculated by the back-propagation algorithm.

[0095] S203: The generator generates data based on the current weights and the injected noise; the generated data should cover the distribution of real data as much as possible in the feature space, while adding a certain diversity to simulate different fault conditions; the specific generation method is expressed as:

[0096]

[0097] In the formula, is the sample generated by the generator; σ c is a noise intensity parameter used to adjust the amplitude of noise injection so that the intensity of noise injection can be dynamically adjusted according to the performance of the discriminator, thereby more finely controlling the quality and diversity of generated data; represents the error rate of the discriminator on the current generated data, α c Is the first parameter that controls the decay rate; β c is the second parameter that controls the decay speed.

[0098] S204: The discriminator evaluates the difference between the generated data and the real data and feeds back to the generator. The generator adjusts its parameters based on this feedback to optimize the authenticity and diversity of the generated data. The parameter update increment calculation method of the discriminator is expressed as:

[0099]

[0100] In the formula, represents the gradient with respect to the discriminator weights.

[0101] S205: Repeat iterative steps S202-S204 until the preset stop iteration condition is met and the model training is completed.

[0102] In one embodiment, the preset condition for stopping iteration is reaching a preset maximum number of iterations. Preferably, the preset maximum number of iterations is set to 1000 times.

[0103] Step 3: Build and train a feature dimensionality reduction model; the feature dimensionality reduction model is an autoencoder based on boundary smoothing, including an encoder and a decoder. The encoder compresses the input data to a low-dimensional representation. For outliers and boundary effects in the dimensionality reduction process, the encoder output is smoothed by a smoothing function; the decoder reconstructs the low-dimensional representation into a feature vector that is as similar as possible to the input data; the data is processed by forward propagation, and then the autoencoder parameters are updated by gradient descent through error back propagation;

[0104] The training of the feature dimensionality reduction model specifically includes the following steps:

[0105] S301: Initialize the parameters of the boundary smoothing based autoencoder;

[0106] In one embodiment, the initialization method is expressed as:

[0107]

[0108]

[0109] In the formula, represents the weight of the encoder, Indicates the encoder bias; represents the weight of the decoder, represents the bias of the decoder; randn() represents the random function; d r,in is the dimension of the encoder input layer, d r,mid is the dimension of the middle layer of the encoder, d r,out is the dimension of the encoder output layer; zeros() is a function that generates a full 0 vector.

[0110] S302: During the training of the autoencoder, the data is processed by forward propagation, and then the autoencoder parameters are updated by the gradient descent method through error back propagation.

[0111] During the training process of the autoencoder, the loss function of the autoencoder is calculated as:

[0112]

[0113] Where, L r is the loss function of the autoencoder; x r is the input data of the autoencoder, is the output reconstructed by the decoder, Sig() is the Sigmoid activation function; ∥∥ is the L2 norm; is the output of the smoothed autoencoder; is the weight coefficient of the i-th dimension autoencoder; n rIt is the vector dimension corresponding to the samples of the current batch input to the autoencoder.

[0114] In one embodiment, the weight coefficients of the autoencoder are used to adjust the contribution of each dimension feature in the error; these weights are dynamically assigned according to the importance of the feature; the weight coefficients of the autoencoder The calculation method is expressed as:

[0115]

[0116] In the formula, is the characteristic variance of the input data of the i-th dimension autoencoder; is the feature of the input data of the i-th dimension autoencoder; ∈ re is a small constant to avoid division by zero; Var() is the variance function.

[0117] In order to deal with outliers and boundary effects in the dimensionality reduction process, an automatic boundary smoothing strategy is adopted to enhance the robustness of the model by dynamically adjusting the boundary value processing. Specifically, the output of the encoder is smoothed by a smoothing function. Therefore, the output of the smoothed autoencoder It is expressed as:

[0118]

[0119] In the formula, τ r () is a smooth function, δ r is the smoothing strength parameter; θ r It is an automatically adjusted threshold parameter used to control the degree of smoothing and improve adaptability to the boundaries of input data.

[0120] In one embodiment, the smoothing strength parameter is determined using an adaptive method based on the local density of data, and the calculation method is expressed as:

[0121]

[0122] In the formula, calculate In its neighborhood The kernel density estimation in can accurately process data in high-density and sparse areas, improving the robustness and adaptability of the overall model; represents the neighborhood; k r () is the kernel density estimation function; mean() is the average function; ∈ rea is a preset small constant. Preferably, ∈ rea Set to 0.001.

[0123] The training of the autoencoder is completed by continuously optimizing the loss function in the iterative process. The calculation method of the parameter update amount for each iteration is expressed as:

[0124]

[0125] In the formula, is the weight parameter update amount of the encoder; is the encoder bias parameter update amount; is the update amount of the decoder weight parameter; is the update amount of the bias parameter of the decoder; is the learning rate of the autoencoder at the tth iteration.

[0126] During the training process of the autoencoder, the convex hull convergence strategy is used to optimize the training process of the autoencoder. By adjusting the learning step size and weight update strategy, the network converges quickly. The learning rate is dynamically adjusted according to the data distribution characteristics in the current iteration as follows:

[0127]

[0128] In the formula, is the learning rate of the initial autoencoder; is the learning rate of the autoencoder at the tth iteration; γ r is the learning rate decay factor of the autoencoder, is the average diameter of the convex hull in the tth iteration, is the diameter of the initial convex hull. The learning rate decreases as the convex hull diameter decreases to prevent instability caused by too large a step size in the later stages of learning.

[0129] S303: Calculate the updated autoencoder parameters by the following formula:

[0130]

[0131]

[0132] Where ← represents the parameter update operation.

[0133] S304: Repeat S302 to S303 until the preset stop iteration condition is met and the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations. Preferably, the preset maximum number of iterations is set to 1000 times.

[0134] Step 4: Input the reduced-dimensional data into the classifier model for training; use a probabilistic neural network guided by quantum probability as the classifier model.

[0135] The classifier model of the present invention is based on the traditional probabilistic neural network, adopts quantum probability to enhance the performance of the network when processing uncertain information, and optimizes the weights and activation functions through quantum state estimation technology, thereby improving classification accuracy and stability.

[0136] Specifically, the training process of the probabilistic neural network algorithm guided by quantum probability is as follows:

[0137] S401: Initialize the weights and quantum state parameters of the probabilistic neural network. The initialization method is expressed as:

[0138]

[0139] In the formula, represents the initial weight matrix, d u is the input dimension of the probabilistic neural network, h u is the hidden layer dimension of the probabilistic neural network, represents the initial parameters of the quantum state.

[0140] S402: Use quantum state estimation methods to dynamically adjust the weights and activation function parameters in the probabilistic neural network, and optimize the classification process by simulating quantum behavior, so that the network can better adapt to changes in data distribution in each step of training.

[0141] The update increment of quantum state parameters is expressed as:

[0142]

[0143] Where η u is the learning rate of the probabilistic neural network, Y u is the true label, is the model prediction label, represents the partial derivative of the quantum state parameter, L u () is the loss function of the probabilistic neural network.

[0144] Gradient of the loss function of a probabilistic neural network with respect to the quantum state parameters The calculation method is expressed as:

[0145]

[0146] ψ u (X uj ,θ u )=cos(θ u X uj )+i * sin(θ u X uj )

[0147] In the formula, is the partial derivative of the loss function with respect to the predicted output, represents the gradient of the predicted value with respect to the quantum state parameters; φ u (X uj ) is the activation function after weight normalization, ψ u (X uj ,θ u ) is the quantum state function, i * Is an imaginary unit.

[0148] S403: In each iteration, the features input to the probabilistic neural network are forward propagated through the neural network guided by quantum probability. The neural network calculates the output based on the current parameter state. During this process, the network processes the input data through quantum probability methods and adjusts the activation state using quantum state estimation.

[0149] Model prediction labels The calculation method is expressed as:

[0150]

[0151] Where, X u is the feature input to the probabilistic neural network, b u is the bias term of the probabilistic neural network, f u () is the quantum probability guided activation function.

[0152] In one embodiment, the calculation method of the quantum probability guided activation function is expressed as:

[0153]

[0154] In the formula, a u =W u ·X u +b u is the weighted input, α u is the dynamic adjustment coefficient, which is calculated as follows:

[0155]

[0156] In the formula, γ u is the first hyperparameter used to adjust the activation strength; β u is the second hyperparameter used to adjust the activation strength; C u Indicates the number of categories.

[0157] S404. Calculate the loss function value based on the output of the probabilistic neural network and the true label, and use the back-propagation algorithm to update the weights and quantum state parameters of the network to minimize the loss function.

[0158] The calculation method of the loss function of the probabilistic neural network is expressed as:

[0159]

[0160] Where Y uc and are the true labels Y for the cth category respectively. u and the model predicts labels

[0161] The gradient of the loss function with respect to the weights When used to update weights, the calculation method of the updated increment is expressed as:

[0162]

[0163] In the formula, ΔW u is the weight update increment of the probabilistic neural network; η u is the learning rate of the probabilistic neural network. Preferably, η u Set to 0.01.

[0164] S405: After each iteration, the weights and quantum parameters of the network are updated according to the results of back propagation. The updating method is expressed as:

[0165] W u ←W u +ΔW u

[0166] θ u ←θ u +Δθ u

[0167] After each parameter update, the quantum state parameter θ u Normalization is performed to ensure the stability of quantum probability distribution, which is expressed as:

[0168]

[0169] In the formula, ∥θ u ∥ is the L2 norm of the quantum state parameter, and the calculation method is expressed as:

[0170]

[0171] In the formula, θ u,j is the jth element of the quantum state parameter.

[0172] S406, repeat the iteration until the preset stop iteration condition is met, and the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations, and preferably, the preset maximum number of iterations is set to 1000 times.

[0173] Step 5: Collect the original data of the heavy-duty truck electric drive axle to be evaluated, and input it into the trained feature dimension reduction model for feature processing; then input the processed features into the trained classifier model for classification to obtain the classification results.

[0174] Those skilled in the art can understand that the above are only preferred examples of the invention and are not intended to limit the invention. Although the invention is described in detail with reference to the above examples, those skilled in the art can still modify the technical solutions recorded in the above examples or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, etc. made within the spirit and principle of the invention shall be included in the protection scope of the invention.

Claims

1. A data-driven method for diagnosing faults in heavy truck electric drive axles, characterized in that: The steps include: Step 1: Collect the operating status data of the heavy-duty truck electric drive axle in various usage scenarios, mark the fault categories, and build the original data set; Step 2: Using a weighted noise-based generative adversarial network to generate samples and achieve data expansion; the generative adversarial network includes a generator and a discriminator, and noise is injected into the weight of the generator, and the generator generates data based on the current weight and the injected noise; The discriminator evaluates the difference between the generated data and the real data and feeds back to the generator. The generator dynamically adjusts the intensity of the noise injected into the weight of the generator according to the feedback, thereby training the weight noise-based generative adversarial network to obtain an expanded sample of the trained model output; The expanded samples and original data are merged to form a training data set; Step 3: Build and train the feature dimensionality reduction model; The feature dimensionality reduction model is an autoencoder based on boundary smoothing, including an encoder and a decoder. The encoder compresses the input data to a low-dimensional representation, and smoothes the output of the encoder through a smoothing function for outliers and boundary effects in the dimensionality reduction process. The decoder reconstructs the low-dimensional representation into a feature vector that is as similar as possible to the input data; the data is processed by forward propagation, and then the autoencoder parameters are updated using gradient descent by error backpropagation; Step 4: construct a classifier model, and use the dimension-reduced data output from step 3 to train the classifier model; the classifier model is a probabilistic neural network guided by quantum probability, and the weights and activation function parameters in the probabilistic neural network are dynamically adjusted by using the quantum state estimation method, and the classification process is optimized by simulating quantum behavior, so that the network can better adapt to changes in data distribution in each step of training; the data is processed by forward propagation, and then the weights and quantum parameters of the probabilistic neural network are updated by error back propagation; Step 5: Collect the original data of the heavy-duty truck electric drive axle to be evaluated, and input it into the trained feature dimension reduction model for feature processing; then input the processed features into the trained classifier model for classification to obtain the classification results.

2. The data-driven heavy truck electric drive axle fault diagnosis method according to claim 1 is characterized in that: Fault categories include normal operation, bearing damage, motor failure, sensor failure, brake system problems and tire abnormalities.

3. The data-driven heavy truck electric drive axle fault diagnosis method according to claim 1 is characterized in that: The operating status data of the heavy-duty truck electric drive axle include bearing temperature Ra, wheel hub vibration amplitude Da, wheel axle torque Sa, brake temperature Ta, tire pressure Ca, speed sensor data Pa, GPS positioning data Qa, electric drive axle current Ka, electric drive axle voltage Ma and control unit feedback signal Na.

4. The data-driven heavy truck electric drive axle fault diagnosis method according to claim 1 is characterized in that: The training process of the weighted noise-based generative adversarial network in step 2 is as follows: S201: Initialize generator G c Weight and the discriminator D c Weight The initialization method is expressed as: Where randn() represents a random number generated from a standard normal distribution; ← is a parameter update operation; d c represents the dimension of the input noise, m c Represents the dimension of the middle layer of the generator, n c Indicates the dimension of the output data; S202: In each iteration, the weight of the generator is dynamically adjusted according to the feedback from the discriminator: In the formula, z c is the input noise of the generator, is the loss function of the generative adversarial network, η c is the learning rate of the generative adversarial network, represents the gradient of the generator weight; G c () is a generator function; D c () is the discriminator function; is the weight update amount of the generator; is a real sample; represents the partial derivative of the generator output with respect to its weight, calculated by the back-propagation algorithm; S203: The generator generates data based on the current weights and injected noise: In the formula, is the sample generated by the generator; σ c is a noise intensity parameter used to adjust the amplitude of noise injection so that the intensity of noise injection can be dynamically adjusted according to the performance of the discriminator, thereby more finely controlling the quality and diversity of generated data; represents the error rate of the discriminator on the current generated data, α c It is the first parameter that controls the decay speed; β c It is the second parameter that controls the decay speed; S204: The discriminator evaluates the difference between the generated data and the real data and feeds it back to the generator; the parameter update increment calculation method of the discriminator is expressed as: In the formula, represents the gradient of the discriminator weight; S205: Repeat iterative steps S202-S204 until the preset stop iteration condition is met and the model training is completed.

5. The data-driven heavy truck electric drive axle fault diagnosis method according to claim 4 is characterized in that: The training process of the feature dimensionality reduction model is as follows: S301: Initialize the parameters of the boundary smoothing based autoencoder: In the formula, represents the weight of the encoder, Indicates the encoder bias; represents the weight of the decoder, represents the bias of the decoder; randn() represents the random function; d r,in is the dimension of the encoder input layer, d r,mid is the dimension of the middle layer of the encoder, d r,out is the dimension of the encoder output layer; zeros() is a function that generates a vector of all zeros; S302: During the training process of the autoencoder, the data is processed by forward propagation, and then the autoencoder parameters are updated by using the gradient descent method through error back propagation; Among them, the loss function L of the autoencoder r The calculation method is expressed as: In the formula, x r is the input data of the autoencoder, is the output reconstructed by the decoder, Sig() is the Sigmoid activation function; ∥∥ is the L2 norm; is the output of the smoothed autoencoder; is the weight coefficient of the i-th dimension autoencoder; n r is the vector dimension corresponding to the samples of the current batch input to the autoencoder; The update amount of the autoencoder parameters is calculated as follows: In the formula, is the update amount of the encoder's weight parameters; is the encoder bias parameter update amount; is the update amount of the decoder weight parameter; is the update amount of the bias parameter of the decoder; is the learning rate of the autoencoder at the tth iteration; is the learning rate of the initial autoencoder; is the learning rate of the autoencoder at the tth iteration; γ r is the learning rate decay factor of the autoencoder, is the average diameter of the convex hull in the tth iteration, is the diameter of the initial convex hull; S303: Calculate the updated autoencoder parameters by the following formula: Where ← represents the parameter update operation. S304: Repeat S302 to S303 until the preset stop iteration condition is met and the feature dimensionality reduction model training is completed.

6. The data-driven heavy truck electric drive axle fault diagnosis method according to claim 4 is characterized in that: The training process of the classifier model includes the following sub-steps: S401: Initialize the weights and quantum state parameters of the probabilistic neural network: In the formula, represents the initial weight matrix, d u is the input dimension of the probabilistic neural network, h u is the hidden layer dimension of the probabilistic neural network, represents the initial parameters of the quantum state; S402: Dynamically adjust the weights and activation function parameters in the probabilistic neural network using quantum state estimation methods; optimize the classification process by simulating quantum behavior so that the network can better adapt to changes in data distribution in each step of training; Among them, the update increment of the quantum state parameter is expressed as: Where η u is the learning rate of the probabilistic neural network, Y u is the true label, is the model prediction, represents the partial derivative of the quantum state parameter, L u () is the loss function of the probabilistic neural network; represents the gradient of the loss function of the probabilistic neural network with respect to the quantum state parameters; is the partial derivative of the loss function with respect to the predicted output, represents the gradient of the predicted value with respect to the quantum state parameters; φ u (X uj ) is the activation function after weight normalization, ψ u (X uj ,θ u ) is the quantum state function, i * is an imaginary unit; S403: In each iteration, the features input to the probabilistic neural network are forward propagated through the neural network guided by quantum probability. The neural network calculates the output according to the current parameter state. In this process, the network processes the input data through quantum probability methods and adjusts the activation state using quantum state estimation. Among them, the model predicts the label The calculation method is expressed as: Where, X u is the feature input to the probabilistic neural network, b u is the bias term of the probabilistic neural network, f u () is the quantum probability guided activation function; The calculation method of the quantum probability guided activation function is expressed as: In the formula, a u =W u ·X u +b u is the weighted input, α u is the dynamic adjustment coefficient, which is calculated as follows: In the formula, γ u is the first hyperparameter used to adjust the activation strength; β u is the second hyperparameter used to adjust the activation strength; C u Indicates the number of categories; S404: Perform forward propagation of data according to S403 to obtain the output of the network, that is, the model prediction label, and calculate the loss function value in combination with the real label, and use the back propagation algorithm to update the network weights and quantum state parameters to minimize the loss function; the loss function L u The cross entropy loss is calculated as follows: Where Y uc is the true label of the cth category; is the probability of the model prediction label for the cth category; The gradient of the loss function with respect to the weights When used to update weights, the calculation method of the updated increment is expressed as: In the formula, ΔW u is the weight update increment of the probabilistic neural network; η u is the learning rate of the probabilistic neural network; S405: After each iteration, the weights and quantum state parameters of the probabilistic neural network are updated according to the results of back propagation, and after each parameter update, the quantum state parameter θ u Perform normalization to ensure the stability of quantum probability distribution; Among them, the update method of the weights and quantum state parameters of the probabilistic neural network is expressed as: IN u ←In u +ΔW u i u ←θ u +Δθ u In the formula, ∥θ u ∥ is the L2 norm of the quantum state parameter, θ u,j is the jth element of the quantum state parameter; S406: Repeat S402 to S405 until the preset stop iteration condition is met and the model training is completed.

Images