A method and system for extracting weak fault features of high-speed rail bearings

Abstract

The present invention discloses a method and system for extracting weak fault features of high-speed rail bearings. The method comprises: obtaining a fault vibration signal of a high-speed rail bearing and performing dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal; determining adaptive Morlet wavelet parameters in a Morlet wavelet activation function according to a DPSO algorithm to obtain a target Morlet wavelet activation function, and setting an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder; extracting nonlinear mappings from the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibrator signal; performing a convolution operation on the target fault vibrator signal and a synchronous extraction operator, and extracting fault feature information from the target fault vibrator signal according to a preset multi-scale analysis method. By analyzing the extracted fault features, fault frequency information is obtained, which greatly improves the detection accuracy and robustness of weak fault features of high-speed rail bearings.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault feature extraction, and in particular relates to a method and system for extracting weak fault features of high-speed rail bearings. Background Art

[0002] Bearings are one of the key components of a train's running gear. The running gear consists of numerous mechanical structures, including gearboxes, wheelsets, and other mechanical components. These mechanical components also generate vibrations during train operation. These vibration signals are mixed with the vibration signals of the wheelset bearings. The acceleration sensor installed on the wheelset axle box collects mixed signals from multiple vibration sources, making it difficult to directly analyze and process the measurement signals. Summary of the Invention

[0003] The present invention provides a method and system for extracting characteristics of weak faults of high-speed rail bearings, which are used to solve the technical problem that it is difficult to directly analyze and process measurement signals.

[0004] In a first aspect, the present invention provides a method for extracting characteristics of weak faults in high-speed rail bearings, comprising:

[0005] Acquire a fault vibration signal of a high-speed rail bearing, and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal;

[0006] Determining adaptive Morlet wavelet parameters in a Morlet wavelet activation function according to a DPSO algorithm to obtain a target Morlet wavelet activation function, and setting an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder;

[0007] Extracting a nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal;

[0008] A convolution operation is performed on the target fault vibrator signal and the synchronization extraction operator, and fault feature information in the target fault vibrator signal is extracted according to a preset multi-scale analysis method.

[0009] In a second aspect, the present invention provides a high-speed rail bearing weak fault feature extraction system, comprising:

[0010] a processing module configured to obtain a fault vibration signal of a high-speed rail bearing and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal;

[0011] A setting module is configured to determine adaptive Morlet wavelet parameters in the Morlet wavelet activation function according to the DPSO algorithm to obtain a target Morlet wavelet activation function, and set an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder;

[0012] a first extraction module configured to extract a nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal;

[0013] The second extraction module is configured to perform a convolution operation on the target fault vibrator signal and a synchronous extraction operator, and extract fault feature information from the target fault vibrator signal according to a preset multi-scale analysis method.

[0014] In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the high-speed rail bearing weak fault feature extraction method of any embodiment of the present invention.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program instructions are executed by a processor, the processor executes the steps of the method for extracting weak fault features of high-speed rail bearings of any embodiment of the present invention.

[0016] This application's method and system for extracting subtle fault features from high-speed rail bearings takes into account the performance of the adaptive deep autoencoder (ADAE) in enhancing subtle fault features and the advantages of the multi-scale synchronized extraction transform (MS-SET) in time-frequency analysis. It uses multi-scale local linear slice analysis (LLTSA) for feature dimensionality reduction and combines this with signal reconstruction technology to ensure accurate feature preservation. By analyzing the extracted fault features, fault frequency information is obtained, significantly improving the accuracy and robustness of detecting subtle fault features in high-speed rail bearings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of a method for extracting weak fault features of high-speed rail bearings provided by one embodiment of the present invention;

[0019] Figure 2 This is a structural block diagram of a system for extracting weak fault features of high-speed rail bearings provided by one embodiment of the present invention;

[0020] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] See also Figure 1 , which shows a flow chart of a method for extracting weak fault features of high-speed rail bearings of the present application.

[0023] like Figure 1 As shown in FIG, the method for extracting the characteristics of weak faults of high-speed rail bearings specifically includes the following steps:

[0024] Step S101: Acquire a fault vibration signal of a high-speed railway bearing, and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal.

[0025] In this step, set is a high-dimensional matrix composed of fault vibration signals, where For the first sample, For the second sample, For the samples, and D are the number of samples and sample dimensions respectively, and each sample represents a data point in the high-dimensional feature space;

[0026] Determine the neighborhood of each sample and select k nearest neighbor samples based on the Euclidean distance between samples As the first samples The expression for calculating the Euclidean distance between samples is:

[0027] ,

[0028] Where, is the Euclidean distance between two samples, For the The first nearest neighbor sample of a sample, For the The second nearest neighbor sample of the sample, For the The kth nearest neighbor sample of a sample, For the The jth nearest neighbor sample of a sample;

[0029] For the samples , by minimizing the reconstruction error, we can get The local linear representation on , defines the objective function as:

[0030] ,

[0031] Where, is the approximation of the reconstructed sample by weighted sum of neighborhood samples;

[0032] By minimizing the reconstruction error, the weight of each sample can be obtained , such that:

[0033] ,

[0034] Where, is the approximation of the weighted and reconstructed samples, is the weight coefficient, For the The jth nearest neighbor sample of a sample;

[0035] By minimizing the objective function of reconstruction error, the transformation matrix is solved , which is used to map high-dimensional data to a low-dimensional space. Specifically, the goal is to optimize the global transformation so that each data point retains its local structure in the high-dimensional space after dimensionality reduction:

[0036] ,

[0037] Where, is a high-dimensional matrix, is the transpose symbol;

[0038] Finally, the high-dimensional matrix X is transformed by the matrix Map to low-dimensional space to obtain low-dimensional representation :

[0039] ,

[0040] Then, non-negative matrix factorization (NMF) is used to construct the reconstruction model. The goal of NMF is to represent the low-dimensional signal Decomposed into two non-negative matrices and :

[0041] ,

[0042] Where W is the basis matrix and H is the coefficient matrix;

[0043] The optimization goal is to minimize the reconstruction error, and the expression is:

[0044]

[0045] Where, is a low-dimensional signal, is the basis matrix, is the coefficient matrix, is the Frobenius norm;

[0046] Reconstruct the low-dimensional signal Y back to the high-dimensional space, the expression is:

[0047] ,

[0048] Where, is the reconstructed signal, for The pseudo-inverse matrix of is the transformation matrix.

[0049] Step S102: determining adaptive Morlet wavelet parameters in the Morlet wavelet activation function according to the DPSO algorithm to obtain a target Morlet wavelet activation function, and setting an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder.

[0050] In this step, the Morlet wavelet activation function is used to design a modified autoencoder to establish a reliable mapping hidden in this complex signal. The expression is:

[0051] ,

[0052] Where, is the amplitude, is the amplitude of the wavelet function at time t, For time, is the bandwidth, is the center frequency;

[0053] Final Output Calculated as:

[0054] ,

[0055] ,

[0056] Where, is the output of hidden node j, is the output value of the final output node i, is the activation function, is the connection weight coefficient, is the number of hidden layer nodes, is the amplitude adjustment coefficient of Morlet wavelet, is the number of input nodes, is the weight coefficient between input node k and hidden node j, is the input value of input node k, is the shift factor of hidden node j, is the scale factor of hidden node j, is the bandwidth parameter of the Morlet wavelet, is the center frequency of the Morlet wavelet;

[0057] Adding a sparse penalty to the cost function, the expression is:

[0058] ,

[0059] Where, is the cost function after introducing the sparse penalty term, The original cost function value is, is the sparse penalty factor, is the sparsity coefficient, is the actual average activation value of the jth neuron in the hidden layer;

[0060] The training of the autoencoder is to minimize the cost function by updating the weights, which is expressed as:

[0061] ,

[0062] Where, is the learning rate.

[0063] It should be noted that, assuming Indicates the current position of particle i represents the current velocity of particle i; represents the individual optimal position of particle i; Represents the global optimal position. Initially, the speed and position of each particle are randomly generated. The position is evenly distributed within the preset range, and the speed is randomly generated within the given range. At the same time, the individual optimal position of the particle is set as the initial position of the particle itself.

[0064] According to the adaptive inertia weight optimization strategy, in the early stage of the search, the particles conduct a wide global search. In the later stage of the search, the particles concentrate on the local optimal solution for a refined search. The expression of the adaptive inertia weight optimization strategy is:

[0065] ,

[0066] Where, is the initial inertia weight, is the inertia weight at convergence, is the maximum number of iterations, is the current iteration number;

[0067] In each generation, the expressions for updating the particle position and velocity are:

[0068] ,

[0069] ,

[0070] Where, is the velocity of particle i in dimension j at the t+1th iteration, is the position of particle i in dimension j at the t+1th iteration, is the velocity of particle i in dimension j at the tth iteration, is the position of particle i in dimension j at the tth iteration, is the individual optimal position of particle i in dimension j at the tth iteration, is the global optimal position of particle i in dimension j at the tth iteration, 、 are acceleration constants, 、 are all random numbers uniformly distributed in the interval [0,1];

[0071] In the later stage of iteration, simulated annealing is introduced as a local search strategy to further optimize the global optimal solution, where the probability P of accepting a new solution is expressed as:

[0072] ,

[0073] Where, is the current temperature parameter, is the fitness value of the current global optimal solution, is the newly generated fitness value;

[0074] If the fitness value of particle i in the current iteration is better than its historical optimal value, the individual optimal position of the particle is updated; if the current fitness value of particle i is better than the fitness value of the global optimal position, the global optimal position is updated;

[0075] When the number of iterations reaches the maximum value or the fitness value of the global optimal solution changes less than the set threshold, the iteration is terminated and the final optimal solution is returned, that is, the adaptive Morlet wavelet parameters in the Morlet wavelet activation function are determined.

[0076] Step S103 : extracting nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal.

[0077] In this step, a more accurate nonlinear mapping that captures the hidden time series signal is achieved by stacking several nonlinear regression layers. In particular, the input is fed into the first MAE to obtain the low-level weights W(1) and features h(1). Next, h(1) is treated as the input to train the second MAE, which then obtains the high-level weights W(2) and features h(2). This is repeated until the last MAE, and then a nonlinear regression layer needs to be added on top to generate the result. The expression is:

[0078] ,

[0079] ,

[0080] Where, is the input of the sample with time series step size m-1, is the highest level feature of the input, and are the weights and biases of the nonlinear regression layer, respectively.

[0081] Step S104 : performing a convolution operation on the target fault vibrator signal and a synchronization extraction operator, and extracting fault feature information from the target fault vibrator signal according to a preset multi-scale analysis method.

[0082] In this step, the scale factor of the multi-scale analysis is set , the expression is:

[0083] ,

[0084] Where, is the first scale factor in multi-scale analysis, is the second scale factor in multi-scale analysis, is the nth scale factor in the multi-scale analysis;

[0085] According to the set scale factor, construct the corresponding window function for each scale , is the scale factor The adjusted window function, To time according to Zoom in or out;

[0086] Perform STFT on the signal of each scale, and use the window function to perform convolution operation on the input signal to obtain the time-frequency domain , the expression is:

[0087] ,

[0088] Where, For movable windows, is the reconstructed signal, is the imaginary unit, To express the angular frequency, is the integral variable;

[0089] make , according to Parseval's theorem, rewrite the time-frequency domain The target expression is:

[0090] ,

[0091] Where, is the frequency variable, is the complex conjugate, for Fourier transform of

[0092] calculate Fourier transform of , the expression is:

[0093] ,

[0094] Assume an amplitude of A and a frequency of Single-component harmonic signal , the Fourier transform result of the single-component harmonic signal is ;

[0095] Substitute the Fourier transform result of the single-component harmonic signal into the target expression to obtain the STFT result of the single-component harmonic signal, which is expressed as:

[0096] ,

[0097] Where, is the center frequency, is the STFT result of the signal.

[0098] In summary, the result of the harmonic signal after STFT is still the frequency The harmonic signal composition of The window function has the characteristic of being very compact in the frequency domain, and the energy of the time-frequency image is concentrated in the frequency domain. In this frequency range, the amplitude of the time-frequency representation is the largest, and the value is ; and the time-frequency analysis results have the best noise robustness.

[0099] For any ,in , the two-dimensional instantaneous frequency of the STFT result for:

[0100]

[0101] Where, is the imaginary unit, for The time derivative of is calculated as:

[0102] ,

[0103] The new time-frequency expression is only composed of = The time-frequency coefficient of the instantaneous frequency can be calculated, which is SET, and the expression is:

[0104] ,

[0105] Where, That is SEO, For in time and frequency The time-frequency representation value below.

[0106] Will Substitution In the equation, we get:

[0107] ,

[0108] Where, is the frequency variable, is the Dirac δ function.

[0109] In summary, this method leverages the performance of the adaptive deep autoencoder (ADAE) in enhancing weak fault signatures and the advantages of the multi-scale synchronized extraction transform (MS-SET) in time-frequency analysis. It uses multi-scale local linear slice analysis (LLTSA) for feature dimensionality reduction and combines this with signal reconstruction techniques to ensure accurate feature preservation. By analyzing the extracted fault signatures, fault frequency information is obtained, significantly improving the accuracy and robustness of detecting weak fault signatures in high-speed rail bearings.

[0110] See also Figure 2, which shows a structural block diagram of a high-speed rail bearing weak fault feature extraction system of the present application.

[0111] like Figure 2 As shown, the high-speed rail bearing weak fault feature extraction system 200 includes a processing module 210, a setting module 220, a first extraction module 230 and a second extraction module 240.

[0112] Among them, the processing module 210 is configured to obtain the fault vibration signal of the high-speed rail bearing, and perform dimensionality reduction processing on the fault vibration signal to obtain the target fault vibration signal; the setting module 220 is configured to determine the adaptive Morlet wavelet parameters in the Morlet wavelet activation function according to the DPSO algorithm, obtain the target Morlet wavelet activation function, and set the autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder; the first extraction module 230 is configured to extract the nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain the target fault vibration sub-signal; the second extraction module 240 is configured to perform a convolution operation on the target fault vibration sub-signal and a synchronous extraction operator, and extract the fault feature information in the target fault vibration sub-signal according to a preset multi-scale analysis method.

[0113] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects also apply to Figure 2 The modules in it will not be described in detail here.

[0114] In other embodiments, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the method for extracting weak fault features of high-speed rail bearings in any of the above method embodiments;

[0115] As an embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0116] Acquire a fault vibration signal of a high-speed rail bearing, and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal;

[0117] Determining adaptive Morlet wavelet parameters in a Morlet wavelet activation function according to a DPSO algorithm to obtain a target Morlet wavelet activation function, and setting an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder;

[0118] Extracting a nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal;

[0119] A convolution operation is performed on the target fault vibrator signal and the synchronization extraction operator, and fault feature information in the target fault vibrator signal is extracted according to a preset multi-scale analysis method.

[0120] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the high-speed rail bearing weak fault feature extraction system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the high-speed rail bearing weak fault feature extraction system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0121] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 The example of the bus connection is taken. The memory 320 is the computer-readable storage medium mentioned above. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, realizes the high-speed rail bearing weak fault feature extraction method of the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal input related to the user settings and function control of the high-speed rail bearing weak fault feature extraction system. The output device 340 may include a display device such as a display screen.

[0122] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0123] As an embodiment, the electronic device is applied to a system for extracting weak fault features of high-speed rail bearings and is used for a client, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0124] Acquire a fault vibration signal of a high-speed rail bearing, and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal;

[0125] Determining adaptive Morlet wavelet parameters in a Morlet wavelet activation function according to a DPSO algorithm to obtain a target Morlet wavelet activation function, and setting an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder;

[0126] Extracting a nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal;

[0127] A convolution operation is performed on the target fault vibrator signal and the synchronization extraction operator, and fault feature information in the target fault vibrator signal is extracted according to a preset multi-scale analysis method.

[0128] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods of each embodiment or certain portions of the embodiments.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for extracting characteristics of weak faults of high-speed rail bearings, characterized in that: include: Acquire a fault vibration signal of a high-speed rail bearing, and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal; Determining adaptive Morlet wavelet parameters in a Morlet wavelet activation function according to a DPSO algorithm to obtain a target Morlet wavelet activation function, and setting an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder; Extracting a nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal; A convolution operation is performed on the target fault vibrator signal and the synchronization extraction operator, and fault feature information in the target fault vibrator signal is extracted according to a preset multi-scale analysis method.

2. The method for extracting characteristics of weak faults of high-speed rail bearings according to claim 1 is characterized in that: The performing dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal comprises: set up is a high-dimensional matrix composed of fault vibration signals, where For the first sample, For the second sample, For the samples, and D are the number of samples and sample dimensions respectively, and each sample represents a data point in the high-dimensional feature space; Determine the neighborhood of each sample and select k nearest neighbor samples based on the Euclidean distance between samples As the first samples The expression for calculating the Euclidean distance between samples is: ， Where, is the Euclidean distance between two samples, For the The first nearest neighbor sample of a sample, For the The second nearest neighbor sample of the sample, For the The kth nearest neighbor sample of a sample, For the The jth nearest neighbor sample of a sample; For the samples , by minimizing the reconstruction error, we can get The local linear representation on , defines the objective function as: ， Where, is the approximation of the reconstructed sample by weighted sum of neighborhood samples; The optimization goal is to minimize the reconstruction error, and the expression is: ， Where, is a low-dimensional signal, is the basis matrix, is the coefficient matrix, is the Frobenius norm; Reconstruct the low-dimensional signal Y back to the high-dimensional space, the expression is: ， Where, is the reconstructed signal, for The pseudo-inverse matrix of is the transformation matrix.

3. The method for extracting characteristics of weak faults of high-speed rail bearings according to claim 1 is characterized in that: The expression of the autoencoder is: ， Where, is the amplitude, is the amplitude of the wavelet function at time t, For time, is the bandwidth, is the center frequency; Determining the adaptive Morlet wavelet parameters in the Morlet wavelet activation function according to the DPSO algorithm to obtain the target Morlet wavelet activation function includes: Assumptions Indicates the current position of particle i represents the current velocity of particle i; represents the individual optimal position of particle i; Represents the global optimal position. Initially, the speed and position of each particle are randomly generated. The position is evenly distributed within the preset range, and the speed is randomly generated within the given range. At the same time, the individual optimal position of the particle is set as the initial position of the particle itself. According to the adaptive inertia weight optimization strategy, in the early stage of the search, the particles conduct a wide global search. In the later stage of the search, the particles concentrate on the local optimal solution for a refined search. The expression of the adaptive inertia weight optimization strategy is: ， Where, is the initial inertia weight, is the inertia weight at convergence, is the maximum number of iterations, is the current iteration number; In each generation, the expressions for updating the particle position and velocity are: ， ， Where, is the velocity of particle i in dimension j at the t+1th iteration, is the position of particle i in dimension j at the t+1th iteration, is the velocity of particle i in dimension j at the tth iteration, is the position of particle i in dimension j at the tth iteration, is the individual optimal position of particle i in dimension j at the tth iteration, is the global optimal position of particle i in dimension j at the tth iteration, 、 are acceleration constants, 、 are all random numbers uniformly distributed in the interval [0,1]; In the later stage of iteration, simulated annealing is introduced as a local search strategy to further optimize the global optimal solution, where the probability P of accepting a new solution is expressed as: ， Where, is the current temperature parameter, is the fitness value of the current global optimal solution, is the newly generated fitness value; If the fitness value of particle i in the current iteration is better than its historical optimal value, the individual optimal position of the particle is updated; if the current fitness value of particle i is better than the fitness value of the global optimal position, the global optimal position is updated; When the number of iterations reaches the maximum value or the fitness value of the global optimal solution changes less than the set threshold, the iteration is terminated and the final optimal solution is returned, that is, the adaptive Morlet wavelet parameters in the Morlet wavelet activation function are determined.

4. The method for extracting characteristics of weak faults of high-speed rail bearings according to claim 1 is characterized in that: The convolution operation of the target fault vibrator signal with a synchronization extraction operator and extracting fault feature information from the target fault vibrator signal according to a preset multi-scale analysis method includes: Setting the scale factor for multiscale analysis , the expression is: ， Where, is the first scale factor in multi-scale analysis, is the second scale factor in multi-scale analysis, is the nth scale factor in the multi-scale analysis; According to the set scale factor, construct the corresponding window function for each scale , is the scale factor The adjusted window function, To time according to Zoom in or out; Perform STFT on the signal of each scale, and use the window function to perform convolution operation on the input signal to obtain the time-frequency domain , the expression is: ， Where, For movable windows, is the reconstructed signal, is the imaginary unit, To express the angular frequency, is the integral variable; make , according to Parseval's theorem, rewrite the time-frequency domain The target expression is: ， Where, is the frequency variable, is the complex conjugate, for Fourier transform of calculate Fourier transform of , the expression is: ， Assume an amplitude of A and a frequency of Single-component harmonic signal , the Fourier transform result of the single-component harmonic signal is ; Substitute the Fourier transform result of the single-component harmonic signal into the target expression to obtain the STFT result of the single-component harmonic signal, which is expressed as: ， Where, is the center frequency, is the STFT result of the signal.

5. A high-speed rail bearing weak fault feature extraction system, characterized by: include: a processing module configured to obtain a fault vibration signal of a high-speed rail bearing and perform dimensionality reduction processing on the fault vibration signal to obtain a target fault vibration signal; A setting module is configured to determine adaptive Morlet wavelet parameters in the Morlet wavelet activation function according to the DPSO algorithm to obtain a target Morlet wavelet activation function, and set an autoencoder according to the target Morlet wavelet activation function to obtain an adaptive deep autoencoder; a first extraction module configured to extract a nonlinear mapping in the target fault vibration signal according to the adaptive deep autoencoder to obtain a target fault vibration sub-signal; The second extraction module is configured to perform a convolution operation on the target fault vibrator signal and a synchronous extraction operator, and extract fault feature information from the target fault vibrator signal according to a preset multi-scale analysis method.

6. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images