Electric drive system motor spatial-temporal characteristic neural network fault diagnosis method and system

Abstract

The invention discloses an electric drive system motor spatial-temporal characteristic neural network fault diagnosis method and system, and is suitable for a motor system under various complex working conditions. According to the method, vibration signals under various fault motors are collected to serve as original signals, the original signals are preprocessed to form a data sample set, multi-scale decomposition is conducted on data in the sample set to obtain spatio-temporal characteristics to be output, population coding is conducted on the spatio-temporal characteristics to form time pulses, and the time pulses are output. And finally, the constructed pulse convolutional network model is utilized to train input, a gradient descent method is introduced into the training model, and convolution and batch standardization time layer strategies are combined, so that the stability and classification precision of the network are effectively improved. Wherein the local features of the signals are extracted through multi-scale decomposition, and the local features of the signals are matched with the motor fault features in terms of local properties, so that the motor fault diagnosis accuracy is remarkably improved, and reliable operation of the electric drive system of the electric power carrying equipment is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of motor fault detection, and in particular to a method and system for diagnosing motor faults in an electric drive system using a spatiotemporal characteristic neural network. Background Art

[0002] As the key and core component of the electromechanical transmission system of electric transport equipment, the electric drive system has been widely used in electric transport equipment such as heavy-duty mining trucks, new energy special vehicles, and transportation-type heavy-duty automatic elevators. Its operating performance, reliability, and environmental applicability are the key factors restricting its development. With the continuous expansion of the application fields of electric transport equipment, new requirements are put forward for electric drive systems, especially in some special applications. The long-term service of electric drive systems in extreme natural environments has become the new normal, so new requirements are put forward for the fault diagnosis of electric drive system motors, especially in rail transit, aerospace, military equipment and other applications with high reliability requirements.

[0003] Existing motor fault diagnosis methods are divided into two categories: data-driven and model-based. At present, the motor fault diagnosis methods based on model construction mainly rely on prior knowledge. However, the structure and function of the electric drive system are extremely complex, and it is very difficult to build an accurate mathematical model to simulate its motor system and its components. Artificial neural networks, as a widely used tool, successfully construct the mapping relationship between fault symptoms and fault categories through inter-layer learning mechanisms. Therefore, data-driven fault classification methods based on deep learning of neural networks and other forms have been widely studied and applied.

[0004] However, since the signals analyzed in motor fault diagnosis are usually in the form of one-dimensional time series, convolutional neural networks are very inadequate in extracting time features. The spiking neural network, which has biologically reasonable neuron modeling, adds the concept of time series to the model and can obtain richer spatiotemporal dynamic features. However, the information of the spiking neural network's neural morphology is limited and it is difficult to accurately represent the data. The simplified spiking neuron model limits its expressive power and dynamic diversity, which makes it difficult for spiking neural networks to achieve high classification accuracy in classification tasks.

[0005] Therefore, how to effectively improve the accuracy of motor fault diagnosis in electric drive systems is still a hot topic in this field and is a key issue in ensuring the reliable operation of electric drive systems for electric transportation equipment. Summary of the invention

[0006] The purpose of the present invention is to solve the technical problem that the accuracy of motor fault diagnosis in electric drive systems needs to be improved, and further provide a method and system for motor fault diagnosis in electric drive systems based on spatiotemporal characteristics of neural networks. The method of the present invention combines the respective advantages of convolutional neural networks and pulse neural networks, and creatively proposes a new pulse convolutional neural network for motor fault diagnosis, that is, batch normalization time layer BNTT and integral-release model LIF are sequentially inserted after the convolutional layer and the fully connected layer in the convolutional module and the fully connected layer module.

[0007] To this end, the present invention provides the following technical solutions:

[0008] On the one hand, the present invention provides a method for diagnosing motor faults in an electric drive system based on a spatiotemporal characteristic neural network, comprising the following steps:

[0009] Step 1: Collect motor vibration signals under normal and multiple fault conditions to form an original data set, and then perform at least sample slicing and sample labeling on the samples of the original data set to obtain sample sets under different fault states and normal states;

[0010] Step 2: Convert the motor vibration signal of each sample into a pulse signal of each sample encoded in a pulse mode, and divide the sample set into a training set and a test set;

[0011] Step 3: construct a fault diagnosis model based on a pulse convolutional neural network, and input the pulse signal of the sample into the pulse convolutional neural network for model training;

[0012] The network architecture of the pulse convolutional neural network is as follows: a convolution module, a pooling layer and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integration-discharge model LIF are sequentially inserted after at least one convolution layer in the convolution module and after one fully connected layer in the fully connected layer module;

[0013] Step 4: Collect the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis.

[0014] Preferably, in the convolution module and the fully connected module, the data processing models of the network layer including the convolution layer / fully connected layer, the batch normalization time layer BNTT and the integration-disbursement model LIF are as follows:

[0015]

[0016] In the formula, are the output membrane potentials of neuron i at time step t and time step t-1, respectively. Corresponding to the output of the network layer, neuron i is regarded as an output neuron / output channel and as the input of a network layer; is the pulse input of neuron j at time step t, that is, the input of the corresponding network layer, and neuron j is regarded as the input neuron / input channel; ω ij is the connection weight connecting neurons j and i; t is the learnable parameter at time step t, v is the voltage threshold, λ is the leakage factor, which is used to simulate the leakage behavior of the LIF model. Represents the output of the batch normalization time layer BNTT;

[0017] Unnormalized membrane potential is the input of the batch normalization time layer BNTT, and the data processing of the batch normalization time layer BNTT is expressed as:

[0018]

[0019] In the formula, represents the normalized membrane potential, and They are the mean and variance of the sample input of the batch normalization time layer BNTT corresponding to neuron i at time step t, and ε is a pre-given minimum value.

[0020] Preferably, the learnable parameter γ at the next time step is t+1 The learnable parameter γ from the previous time step t Update, the update formula is: γ t+1 =γ t -ηΔγ t , η is the preset coefficient;

[0021] Among them, the update difference Δγ t The calculation of is as follows:

[0022]

[0023] In the formula, m represents the total number of samples in a batch of model training, b is the sample index in the corresponding batch, and u t is the network output of the convolutional / fully connected module corresponding to time step t, is the network output membrane potential corresponding to sample b at time step t, which is the output membrane potential of all neurons i corresponding to sample b. constitute; is the output of the batch normalization time layer BNTT corresponding to sample b at time step t, which is composed of all neurons i corresponding to sample b. Composition; L is the loss function, θ is the symbol of partial derivative.

[0024] The mean of all neurons i and variance Construct the mean vector μ t and the variance vector σ t , the calculation formula is:

[0025]

[0026] In the formula, is the input of the batch normalization time layer BNTT corresponding to sample b at time step t, that is, the input of all neurons i corresponding to sample b Composition, m represents the total number of samples in a batch of model training, and b is the sample index in the corresponding batch.

[0027] Preferably, the model training process uses the time back propagation method to perform network training;

[0028] Among them, the weight gradient formula of the connected neurons in the network layer without the batch normalization time layer BNTT is:

[0029]

[0030] The weight gradient formula of the connected neurons in the network layer containing the batch normalization time layer BNTT is:

[0031]

[0032] In the formula, Δω ij is the connection weight ω connecting neurons j and i ij The weight gradient is used to update the connection weight ω ij ; T is the total number of time steps set, L is the loss function, is the corresponding network layer output of neuron i at time step t, is the output membrane potential of the network layer of neuron i at time step t; It is the input of the batch normalization time layer BNTT corresponding to sample b at time step t; represents the output of the batch normalization time layer BNTT corresponding to sample b and sample k; m represents the total number of samples in a batch in model training, b and k are the sample indexes in the corresponding batch, ε is a pre-given minimum value, and σ t It is the variance of the sample input of the batch normalization time layer BNTT at time step t, where T and t represent the total number of time steps and time step index respectively.

[0033] Preferably, there are:

[0034]

[0035] Among them, the piecewise linear approximation proxy gradient descent method is used to solve as follows:

[0036]

[0037] Where the hyperparameter ξ is the attenuation factor of the back-propagation gradient, and v is the set threshold.

[0038] Preferably, in step 2, the process of converting the motor vibration signal of each sample into a pulse signal of each sample encoded in a pulse mode is as follows:

[0039] The motor vibration signal of each sample is extracted by using a low-pass filter and a high-pass filter, and the approximation coefficient of the wavelet decomposition of the sample data and the bi-norm of all detail coefficients are combined into a one-dimensional array as the fault feature output of the sample;

[0040] The Gaussian function is used to perform population encoding on the fault feature output of each sample to obtain the pulse signal of each sample.

[0041] Among them, the technical solution of the present invention uses Gaussian population coding to encode input features into discrete pulses for communication, laying the foundation for the subsequent discretized pulse neuron model, so that the neuron is activated only when the pulse signal received by the neuron reaches the threshold. This is an accurate imitation of the biological brain and is more energy-efficient.

[0042] Preferably, the fault type includes any combination of an eccentricity fault, a single-phase fault, a broken bar fault, a bearing fault and a short circuit fault.

[0043] In another aspect, the present invention further provides a diagnostic system based on the above fault diagnosis method, comprising at least:

[0044] The data acquisition and processing module is used to collect the vibration signals of the motor under normal and multiple fault conditions to form an original data set, and then perform sample slicing and sample labeling on the samples of the original data set to obtain sample sets under different fault conditions and normal conditions;

[0045] An encoding module, used for converting the motor vibration signal of each sample into a pulse signal of each sample in a pulse mode, and dividing the sample set into a training set and a test set;

[0046] A model building and training module is used to build a fault diagnosis model based on a pulse convolutional neural network, and input the pulse signal of the sample into the pulse convolutional neural network for model training;

[0047] The network architecture of the pulse convolutional neural network is as follows: a convolution module, a pooling layer and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integration-discharge model LIF are sequentially inserted after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module;

[0048] The diagnostic module is used to collect the motor vibration signal of the motor to be monitored, convert it into a pulse signal, and then input it into the trained fault diagnosis model for fault diagnosis.

[0049] In a third aspect, the present invention provides a computer terminal, comprising at least:

[0050] one or more processors and a memory storing one or more computer programs;

[0051] The processor calls the computer program to implement:

[0052] Load a pre-trained fault diagnosis model or build and train a fault diagnosis model;

[0053] Obtain the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis;

[0054] The fault diagnosis model is constructed based on a pulse convolutional neural network, and the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer, and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integral-discharge model LIF are inserted after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module;

[0055] The input of the fault diagnosis model is the pulse signal, and the output is the fault diagnosis result.

[0056] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is called by a processor to implement:

[0057] Load a pre-trained fault diagnosis model or build and train a fault diagnosis model;

[0058] Obtain the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis;

[0059] The fault diagnosis model is constructed based on a pulse convolutional neural network, and the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer, and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integral-discharge model LIF are inserted after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module;

[0060] The input of the fault diagnosis model is the pulse signal, and the output is the fault diagnosis result.

[0061] Beneficial Effects

[0062] Compared with the existing method, the advantages of the present invention are:

[0063] The technical solution of the present invention creatively proposes a new pulse convolutional neural network for realizing motor fault diagnosis, that is, the batch normalization time layer BNTT and the integral-release model LIF are inserted in sequence after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module, integrating the respective advantages of the convolutional neural network and the pulse neural network, converting the motor vibration signal of the motor into a pulse signal and integrating it into the pulse neural network, making full use of the spatiotemporal dynamic characteristics of the original motor vibration signal, effectively solving the problems of insufficient local feature extraction of the motor vibration signal and slow processing of large-scale data, and effectively improving the stability and classification accuracy of the neural network. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0065] Figure 2 Schematic diagram of a method for diagnosing motor faults in an electric drive system based on spatiotemporal characteristics of a neural network according to an embodiment of the present invention.

[0066] Figure 3 A schematic diagram of the “drain-integrate-discharge” behavior of the LIF provided in an embodiment of the present invention.

[0067] Figure 4 This is a training flow chart of a pulse convolutional neural network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The electric drive system motor spatiotemporal characteristic neural network fault diagnosis method and system provided by the present invention are applied to the fault diagnosis of the electric drive system motor. The core of the method is to propose a pulse convolutional neural network that integrates a convolutional neural network and a pulse neural network, and introduce a batch normalization time layer BNTT.

[0069] The present invention will be further described below with reference to the embodiments.

[0070] Embodiment 1:

[0071] like Figure 1 As shown, the present embodiment provides a method for diagnosing motor faults in an electric drive system using a spatiotemporal characteristic neural network, comprising the following steps:

[0072] Step 1: Collect motor vibration signals under normal and multiple fault conditions to form an original data set, and then perform at least sample slicing, sample labeling and sample shuffling on the samples of the original data set to obtain sample sets under different fault states and normal states.

[0073] In this embodiment, normal and five different motor fault vibration signals collected on a motor fault experimental platform are used, and the selected working conditions include variable speed working conditions and variable load working conditions. Figure 3 Schematic diagram of faulty motor, the faults set in this embodiment are eccentricity fault, single-phase fault, broken bar fault, bearing fault and short circuit fault, and each fault uses sensors to collect four groups of vibration signals at different positions. In other feasible embodiments, it is not limited to the above fault types.

[0074] The collected vibration signal is a one-dimensional time series, which is sliced ​​into samples. Then the samples with the same fault are labeled with the same label and randomly shuffled into a sample set.

[0075] Step 2: Convert the motor vibration signal of each sample into a pulse signal of each sample encoded in a pulse mode, and divide the sample set into a training set and a test set.

[0076] This embodiment preferably adopts the following method to convert the encoding:

[0077] S2-1: Use low-pass filter and high-pass filter to extract features of the motor vibration signal of each sample, and combine the approximation coefficient of the wavelet decomposition of the sample data and the bi-norm of all detail coefficients into a one-dimensional array as the fault feature output of the sample.

[0078] Among them, feature extraction is performed on the sample set data under various motor states, and the features of each fault are output at different frequencies and time scales. In order to extract frequency features and time scale features, low-pass filters and high-pass filters are used to obtain multi-level approximation coefficients and detail coefficients, as follows:

[0079]

[0080] Then, the approximation coefficient and the bi-norm of all detail coefficients are combined into a one-dimensional array as the fault feature output Y of the sample: Y = [a j [k j ],b j [k j ],b j-1 [k j-1 ]...,b1[k1]]

[0081] In the formula, A j [n] is the approximation coefficient of the jth layer, A0[n] is the input data, b j [n] is the detail coefficient of the jth layer, h[n] is the low-pass filter, g[n] is the high-pass filter, n represents the sampling point index, k j+1 Indicates the number of decomposition coefficients of this layer. In this embodiment, it is preferred that the number k of each decomposition layer is not consistent. The present invention obtains the characteristics of the data at different frequencies and time scales through the above multi-level decomposition.

[0082] S2-2: Use Gaussian function to perform population encoding on the fault feature output of each sample to obtain the pulse signal of each sample.

[0083] In this embodiment, the extracted fault features are first simply normalized, and then the input normalized features are reasonably encoded using multiple overlapping Gaussian functions, and each input variable is mapped to the pulse time of multiple input neurons. Preferably, each input feature is encoded by a set of Gaussian receptive fields containing M Gaussian functions, and the mean C of the i-th Gaussian function is i and standard deviation σ i The formula definition is as follows:

[0084]

[0085] In the above formula, I max and I min are the maximum and minimum values ​​of the input features corresponding to each sample, and N is an adjustable constant of the standard deviation σ, and M is the number of Gaussian functions. The above encoding process of this embodiment can be immediately as follows: calculating the activation values ​​of the M neurons of the encoding variable x, highly activated neurons will discharge in advance, while neurons with lower activation levels will delay discharge or not discharge. Among them, the encoding variable x is the normalized feature.

[0086] It should be understood that, in this embodiment, after encoding using the Gaussian receptive fields of M Gaussian functions, the normalized fault feature output is encoded as a discrete pulse signal, and each feature variable corresponds to a set of M encoding values. In other feasible embodiments, the feasible method of encoding the fault feature output as a pulse signal in other ways also falls within the protection scope of the present invention.

[0087] Among them, the processed sample set is divided into a training set and a test set, and a suitable batch size is selected for training; in this embodiment, each pulsed fault sample is concentrated, and then randomly divided into a training set and a test set according to a certain ratio, and then a parameter comparison is performed to select a suitable batch size for training.

[0088] Step 3: Construct a fault diagnosis model based on a pulse convolutional neural network, and input the pulse signal of the sample into the pulse convolutional neural network for model training.

[0089] like Figure 4 As shown in the figure, the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer and a fully connected module are provided in sequence, and a batch normalization time layer (Batch Normalization Through Time, BNTT) and an integral-disbursement model LIF are inserted in sequence after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module.

[0090] The above-mentioned spiking convolutional neural network is constructed based on the fusion of spiking neural network and convolutional neural network, that is, the LIF model is combined with the convolutional layer and the fully connected layer respectively. In each time step cycle, membrane potential leakage, pulse emission and membrane potential reset operations are added after each convolutional layer and fully connected layer. Figure 3 Shown is the “drain-integrate-discharge” behavior of the LIF model.

[0091] The batch normalization time layer BNTT introduced in the present invention is used to optimize the time-related learnable parameter γ to capture the input distribution that changes over time, thereby stabilizing the reverse gradient during the training process and ensuring better deep learning of SNN.

[0092] Based on the above structure, the data processing models of the network layers including the convolutional layer / fully connected layer, the batch normalization time layer BNTT and the integration-disbursement model LIF in the convolutional module and the fully connected module are as follows:

[0093]

[0094] In the formula, are the output membrane potentials of neuron i at time step t and time step t-1, respectively. Corresponding to the output of the network layer, neuron i is regarded as the output neuron / output channel; is the pulse input of neuron j at time step t, that is, the input of the corresponding network layer, and neuron j is regarded as the input neuron / input channel; ω ij is the connection weight connecting neurons j and i; t is the learnable parameter at time step t, v is the voltage threshold, λ is the leakage factor, which is used to simulate the leakage behavior of the LIF model. Represents the output of the batch normalization time layer BNTT;

[0095] Unnormalized membrane potential is the input of the batch normalization time layer BNTT, and the data processing of the batch normalization time layer BNTT is expressed as:

[0096]

[0097] In the formula, represents the normalized membrane potential, and They are the mean and variance of the sample input of the batch normalization time layer BNTT corresponding to neuron i at time step t, and ε is a pre-given minimum value.

[0098] Among them, the mean of all neurons i and variance Construct the mean vector μ t and the variance vector σt , the calculation formula is:

[0099]

[0100] In the formula, is the input of the batch normalization time layer BNTT corresponding to sample b at time step t, that is, the input of all neurons i corresponding to sample b Composition, m represents the total number of samples in a batch of model training, and b is the sample index in the corresponding batch.

[0101] Use different γ at all time steps t Value, γ t Find the optimal value at each time step to achieve efficient reasoning. That is, the learnable parameter γ at the next time step t+1 The learnable parameter γ from the previous time step t Update, Update | t For γ t+1 =γ t -ηΔγ t , where Δγ t The calculation of is as follows:

[0102]

[0103] In the formula, u t is the network output membrane potential of the convolutional / fully connected module corresponding to time step t, is the network output membrane potential corresponding to sample b at time step t, which is the output membrane potential of all neurons i corresponding to sample b. constitute; is the output of the batch normalization time layer BNTT corresponding to sample b at time step t, which is composed of all neurons i corresponding to sample b. constitute.

[0104] It should be understood that formulas (3)-(6) are all applicable to the operations of the convolutional module and the fully connected module that integrate BNTT and the integral-disbursement model LIF, and the data of the fully connected module is the classification result of the fault diagnosis module after the Softmax layer.

[0105] The model training of this embodiment adopts the time back propagation method to perform network training. Therefore, the operation of the pulse neurons in the pulse convolution model can be carried out along the time dimension, and the state of the neurons will be updated at each time step. Therefore, the weight gradient connecting the neurons is calculated as the accumulation at each time step.

[0106] Among them, the weight gradient formula of the connected neurons in the local network part that does not contain the batch normalization time layer BNTT is:

[0107]

[0108] Adding a BNTT layer to a LIF neuron changes the gradient calculation. is the sample input signal of the BNTT layer, then the gradient value of the BNTT layer through the next layer can be calculated. Therefore, the weight gradient formula of the connected neurons in the local network part containing the batch normalization time layer BNTT is:

[0109]

[0110] And there exists:

[0111] The above formula omits a neuron index i, where Δω ij is the connection weight ω connecting neurons j and i ij The weight gradient is used to update the connection weight ω ij ; T is the total number of time steps set, L is the loss function, and this embodiment selects the classification cross entropy loss function; is the corresponding network output of neuron i at time step t, is the network output membrane potential of neuron i at time step t; It is the input of the batch normalization time layer BNTT corresponding to sample b at time step t; represents the output of the batch normalization time layer BNTT corresponding to sample b and sample k; L is the loss function, m represents the total number of samples in a batch in model training, b and k are the sample indexes in the corresponding batch, ε is a pre-given minimum value, σ t It is the variance of the sample input of the batch normalization time layer BNTT at time step t, where T and t represent the total number of time steps and time step index respectively.

[0112] Since the threshold function o i The derivative of is a Diklak function, which is undefined at the peak of the pulse and is 0 elsewhere, so the gradient Δω ij It is difficult to calculate. The proxy gradient descent method using piecewise linear approximation is as follows:

[0113]

[0114] In the above formula, the hyperparameter ξ is the attenuation factor of the back-propagation gradient, and v is the threshold. The hyperparameter ξ should be set according to the size of the time step T, because each time step has gradient accumulation, so a smaller ξ is used for a larger T to avoid gradient explosion.

[0115] It should be noted that the technical solution of the present invention effectively solves the application problem of the standard back-propagation algorithm in pulse neural networks by introducing the proxy gradient method. That is, due to the particularity of the output mode of the pulse neural network and its dependence on time, it is necessary to process pulse signals in practical applications. Therefore, it cannot directly apply the gradient descent back-propagation algorithm based on differential calculation. In other feasible embodiments, other technical means can be adopted to solve this problem.

[0116] Based on the above theoretical analysis, it can be seen that the network model of the present invention is as follows:

[0117] Set a time step parameter T, for each time step t = 0, 1, ... T-1 and each layer of neurons l = 1, 2, ... L-1, have their own connection weight tensor W l , BNTT parameter γ l and the voltage threshold v of the lth network layer l . Update the membrane potential set by forward propagation When the membrane potential exceeds the threshold v l When the output peak The specific implementation method is as follows:

[0118]

[0119] In the above formula, capital letters represent vectors and lowercase letters represent scalar values. Formula (10) corresponds to the network layer with BNTT, and formula (11) corresponds to the network layer without BNTT. and are the membrane potential and output pulse set of all neurons in the first layer with time step t, W l is the weight w of all neurons connecting the lth layer and the l-1th layer ij The set of λ is the constant leakage factor of the membrane potential. The membrane potential of the last layer is accumulated without the leakage factor and no threshold function is used. This keeps the output value continuous and finally passes through the Softmax layer for diagnosis and identification of fault types.

[0120] Iterate the dataset by formula (10) to calculate the model gradient by back-propagating the loss L through the unfolded neural network. Here, the loss L is the loss of the last layer. The categorical cross entropy function between the cumulative membrane potential and the ground truth label Y (the score for each class of faults) is defined as:

[0121]

[0122] Based on the above theoretical statements, the present invention uses sample data to train the model, updates the weight parameters, obtains the data classification model of the network through continuous iteration, inputs the test set into the data classification model, and obtains the classification accuracy of the test set.

[0123] Step 4: Collect the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis.

[0124] In summary, the technical solution of the present invention fully extracts the spatiotemporal features of the original signal, effectively solving the problems of insufficient local feature extraction of motor vibration signals and slow processing of large-scale data. Gaussian population coding is used to encode input features into discrete pulses for communication. Neurons are activated only when the pulse signal received by the neuron reaches the threshold. This is an accurate imitation of the biological brain and is more energy-efficient. The convolutional pooling layer with BNTT is combined with SNN and the alternative gradient method is used in back propagation, which effectively improves the stability and classification accuracy of the pulse neural network. In addition, in order to test its performance, relevant comparative experiments were carried out in feature extraction and model training, and it was finally found that not only higher accuracy can be obtained in two different data sets, but also the computational cost is low.

[0125] Embodiment 2:

[0126] The present embodiment provides a diagnostic system based on the above-mentioned fault diagnosis method, which at least comprises: a data acquisition and processing module, a coding module, a model building and training module, and a diagnostic module which are interconnected / connected in sequence for communication.

[0127] Among them, the data acquisition and processing module is used to collect motor vibration signals under normal and multiple types of fault conditions to form an original data set, and then the samples of the original data set are at least sliced ​​and labeled to obtain sample sets under different fault states and normal states. The encoding module is used to convert the motor vibration signal of each sample into a pulse signal of each sample in a pulse mode, and divide the sample set into a training set and a test set. The model construction and training module is used to construct a fault diagnosis model based on a pulse convolutional neural network, and input the pulse signal of the sample into the pulse convolutional neural network for model training; the diagnosis module is used to collect the motor vibration signal of the motor to be monitored, convert it into a pulse signal, and then input it into the trained fault diagnosis model for fault diagnosis.

[0128] Among them, the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer and a fully connected module are arranged in sequence, and a batch normalization time layer BNTT and an integration-discharge model LIF are inserted in sequence at least after a convolution layer in the convolution module and after a fully connected layer in the fully connected layer module.

[0129] Please refer to the above method content for the specific implementation process of each module. The present invention will not be repeated here, and the division of the above functional modules is only for example. In some embodiments, some functional modules can be merged, and some functional modules can be split. Each functional module can be implemented in software or hardware or a combination of software and hardware. Among them, the hardware and software equipment includes but is not limited to general-purpose computer equipment, programmable gate arrays, digital signal processors, microprocessors and their corresponding programming or burning software.

[0130] Embodiment 3:

[0131] A computer terminal provided in this embodiment at least comprises: one or more processors and a memory storing one or more computer programs. The processor calls the computer program to implement: loading a pre-trained fault diagnosis model or building and training a fault diagnosis model; obtaining the motor vibration signal of the motor to be monitored and converting the code into a pulse signal, and then inputting the trained fault diagnosis model for fault diagnosis;

[0132] Among them, the fault diagnosis model is constructed based on a pulse convolutional neural network, and the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer and a fully connected module are arranged in sequence, and a batch normalization time layer BNTT and an integration-release model LIF are inserted in sequence at least after a convolution layer in the convolution module and after a fully connected layer in the fully connected layer module; the input of the fault diagnosis model is a pulse signal, and the output is a fault diagnosis result.

[0133] For the specific implementation process of each step, please refer to the description of the above method.

[0134] It should be understood that in the embodiments of the present invention, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the type of device.

[0135] Embodiment 4:

[0136] The present embodiment provides a computer-readable storage medium storing a computer program, which is called by a processor to implement: loading a pre-trained fault diagnosis model or building and training a fault diagnosis model; obtaining a motor vibration signal of a motor to be monitored and converting the signal into a pulse signal, and then inputting the trained fault diagnosis model to perform fault diagnosis;

[0137] Among them, the fault diagnosis model is constructed based on a pulse convolutional neural network, and the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer and a fully connected module are arranged in sequence, and a batch normalization time layer BNTT and an integration-release model LIF are inserted in sequence at least after a convolution layer in the convolution module and after a fully connected layer in the fully connected layer module; the input of the fault diagnosis model is a pulse signal, and the output is a fault diagnosis result.

[0138] For the specific implementation process of each step, please refer to the description of the above method.

[0139] The readable storage medium is a computer-readable storage medium, which may be an internal storage unit of the software and hardware device described in any of the aforementioned embodiments, such as a hard disk or memory of a controller. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the controller. Furthermore, the readable storage medium may also include both an internal storage unit of the controller and an external storage device. The readable storage medium is used to store the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0140] Based on this understanding, the technical solution of the present invention, in essence or in other words, the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., various media that can store program codes.

[0141] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is a device for realizing the function specified in one flow or multiple flows of the flow chart and / or one or multiple blocks of the block diagram with reference to the instructions executed by the processor according to the method, device (system) and computer program product of the embodiment of the present application. These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which realizes the function specified in one flow or multiple flows of the flow chart and / or one or multiple blocks of the block diagram. These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0142] It should be emphasized that the examples described in the present invention are illustrative rather than restrictive, and therefore the present invention is not limited to the examples described in the specific embodiments. Any other embodiments derived by those skilled in the art based on the technical solution of the present invention that do not depart from the purpose and scope of the present invention, whether modified or replaced, also fall within the scope of protection of the present invention.

Claims

1. A method for fault diagnosis of electric drive system motor based on spatiotemporal characteristics neural network, characterized by: The following steps are involved: Step 1: Collect motor vibration signals under normal and multiple fault conditions to form an original data set, and then perform at least sample slicing and sample labeling on the samples of the original data set to obtain sample sets under different fault states and normal states; Step 2: Convert the motor vibration signal of each sample into a pulse signal of each sample encoded in a pulse mode, and divide the sample set into a training set and a test set; Step 3: construct a fault diagnosis model based on a pulse convolutional neural network, and input the pulse signal of the sample into the pulse convolutional neural network for model training; The network architecture of the pulse convolutional neural network is as follows: a convolution module, a pooling layer and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integration-discharge model LIF are sequentially inserted after at least one convolution layer in the convolution module and after one fully connected layer in the fully connected layer module; Step 4: Collect the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis.

2. The method according to claim 1, characterized in that: In the convolution module and the fully connected module, the data processing models of the network layer including the convolution layer / fully connected layer, the batch normalization time layer BNTT and the integration-disbursement model LIF are as follows: In the formula, are the output membrane potentials of neuron i at time step t and time step t-1, respectively. Corresponding to the output of the network layer, neuron i is regarded as the output neuron / output channel; is the pulse input of neuron j at time step t, that is, the input of the corresponding network layer, and neuron j is regarded as the input neuron / input channel; ω ij is the connection weight connecting neurons j and i; t is the learnable parameter at time step t, v is the voltage threshold, λ is the leakage factor, which is used to simulate the leakage behavior of the integration-release model LIF. Represents the output of the batch normalization time layer BNTT; Unnormalized membrane potential is the input of the batch normalization time layer BNTT, and the data processing of the batch normalization time layer BNTT is expressed as: In the formula, represents the normalized membrane potential, and They are the mean and variance of the sample input of the batch normalization time layer BNTT corresponding to neuron i at time step t, and ε is a pre-given minimum value.

3. The method according to claim 2, characterized in that: The learnable parameter γ at the next time step t+1 The learnable parameter γ from the previous time step t Update, the update formula is: γ t+1 =γ t -ηΔγ t , η is the preset coefficient; Among them, the update difference Δγ t The calculation of is as follows: In the formula, m represents the total number of samples in a batch of model training, b is the sample index in the corresponding batch, and u t is the network output membrane potential of the convolutional / fully connected module corresponding to time step t, is the output membrane potential of the network layer corresponding to sample b at time step t, which is composed of all neurons i corresponding to sample b. constitute; is the output of the batch normalization time layer BNTT corresponding to sample b at time step t, which is composed of all neurons i corresponding to sample b. Composition; L is the loss function, is the symbol of partial derivative.

4. The method according to claim 2, characterized in that: The mean of all neurons i and variance Construct the mean vector μ t and the variance vector σ t , the calculation formula is: In the formula, is the input of the batch normalization time layer BNTT corresponding to sample b at time step t, that is, the input of all neurons i corresponding to sample b Composition, m represents the total number of samples in a batch of model training, and b is the sample index in the corresponding batch.

5. The method according to claim 1, characterized in that: The model training process uses the time back propagation method to train the network; Among them, the weight gradient formula of the connected neurons in the network layer without the batch normalization time layer BNTT is: The weight gradient formula of the connected neurons in the network layer containing the batch normalization time layer BNTT is: In the formula, Δω ij is the connection weight ω connecting neurons j and i ij The weight gradient is used to update the connection weight ω ij ; T is the total number of time steps set, L is the loss function, is the corresponding network layer output of neuron i at time step t, is the output membrane potential of the network layer of neuron i at time step t; It is the input of the batch normalization time layer BNTT corresponding to sample b at time step t; represents the output of the batch normalization time layer BNTT corresponding to sample b and sample k; m represents the total number of samples in a batch in model training, b and k are the sample indexes in the corresponding batch, ε is a pre-given minimum value, and σ t It is the variance of the sample input of the batch normalization time layer BNTT at time step t, where T and t represent the total number of time steps and time step index respectively.

6. The method according to claim 5, characterized in that: exist: Among them, the piecewise linear approximation proxy gradient descent method is used to solve as follows: Where the hyperparameter ξ is the attenuation factor of the back-propagation gradient, and v is the set threshold.

7. The method according to claim 1, characterized in that: The process of converting the motor vibration signal of each sample into a pulse signal of each sample encoded in a pulse mode in step 2 is as follows: The motor vibration signal of each sample is extracted by using a low-pass filter and a high-pass filter, and the approximation coefficient of the wavelet decomposition of the sample data and the bi-norm of all detail coefficients are combined into a one-dimensional array as the fault feature output of the sample; The Gaussian function is used to perform population encoding on the fault feature output of each sample to obtain the pulse signal of each sample.

8. A diagnostic system based on the method according to any one of claims 1 to 7, characterized in that: At least: The data acquisition and processing module is used to collect the vibration signals of the motor under normal and multiple fault conditions to form an original data set, and then perform sample slicing and sample labeling on the samples of the original data set to obtain sample sets under different fault conditions and normal conditions; An encoding module, used for converting the motor vibration signal of each sample into a pulse signal of each sample in a pulse mode, and dividing the sample set into a training set and a test set; A model building and training module is used to build a fault diagnosis model based on a pulse convolutional neural network, and input the pulse signal of the sample into the pulse convolutional neural network for model training; The network architecture of the pulse convolutional neural network is as follows: a convolution module, a pooling layer and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integration-discharge model LIF are sequentially inserted after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module; The diagnostic module is used to collect the motor vibration signal of the motor to be monitored, convert it into a pulse signal, and then input it into the trained fault diagnosis model for fault diagnosis.

9. A computer terminal, characterized in that: At least: one or more processors and a memory storing one or more computer programs; The processor calls the computer program to implement: Load a pre-trained fault diagnosis model or build and train a fault diagnosis model; Obtain the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis; The fault diagnosis model is constructed based on a pulse convolutional neural network, and the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer, and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integral-discharge model LIF are inserted after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module; The input of the fault diagnosis model is the pulse signal, and the output is the fault diagnosis result.

10. A computer-readable storage medium, characterized in that: A computer program is stored, which is called by a processor to implement: Load a pre-trained fault diagnosis model or build and train a fault diagnosis model; Obtain the motor vibration signal of the motor to be monitored and convert it into a pulse signal, which is then input into the trained fault diagnosis model for fault diagnosis; The fault diagnosis model is constructed based on a pulse convolutional neural network, and the network architecture of the pulse convolutional neural network is: a convolution module, a pooling layer, and a fully connected module are sequentially provided, and a batch normalization time layer BNTT and an integral-discharge model LIF are inserted after the convolution layer and the fully connected layer in the convolution module and the fully connected layer module; The input of the fault diagnosis model is the pulse signal, and the output is the fault diagnosis result.

Images