A method, system, storage medium and device for extracting fault characteristics of machine tool bearings

Abstract

The present invention belongs to the technical field of rotating machinery fault diagnosis, and provides a method, a system, a storage medium and a device for extracting fault features of machine tool bearings. The present invention respectively establishes dictionaries for the fault impact components, harmonic components and modal components of the vibration signals of machine tool bearings; based on the original vibration signals and each constructed dictionary, a physical information multi-dictionary sparse decomposition framework is established, and the physical information multi-dictionary sparse decomposition framework is solved until it converges to the global optimal solution; according to the solution result, the modal components and harmonic components in the vibration signals are removed, and the fault impact components are extracted for fault diagnosis. The present invention solves the problems of low accuracy of feature extraction and more interference in the existing methods, and can effectively extract the fault impact components, separate the modal and harmonic components, and suppress noise, thereby improving the accuracy and reliability of fault diagnosis.

Description

Technical Field

[0001] The present invention belongs to the technical field of rotating machinery fault diagnosis, and particularly relates to a method, system, storage medium and device for extracting fault features of machine tool bearings. Background Art

[0002] The statements in this part only provide background technical information related to the present invention, and do not necessarily constitute prior art.

[0003] In the fault diagnosis of machine tool bearings, vibration signals usually contain various components, such as fault impact components, harmonic components, modal components and noise. The traditional sparse decomposition methods have the following problems when dealing with complex vibration signals:

[0004] (1) The matching degree between the dictionary design and the actual fault impact waveform is insufficient, resulting in inaccurate extraction of fault features;

[0005] (2) The modal components and harmonic components have a large interference on the extraction of fault features and are difficult to effectively separate;

[0006] (3) The L1 norm of the traditional sparse decomposition method may over-punish small amplitude coefficients, thus losing important fault information. Summary of the Invention

[0007] In order to solve the above problems, the present invention proposes a method, system, storage medium and device for extracting fault features of machine tool bearings. The present invention is based on physical information multi-dictionary sparse decomposition, can effectively extract fault impact components, separate modal and harmonic components, and suppress noise, thereby improving the accuracy and reliability of fault diagnosis.

[0008] According to some embodiments, the present invention adopts the following technical solutions:

[0009] A method for extracting fault features of machine tool bearings, comprising the following steps:

[0010] Obtain the vibration signal of the machine tool bearing;

[0011] Utilize the physical characteristics of fault impacts to establish a generalized double-pulse response wavelet dictionary for representing the fault impact components in the vibration signal, and construct a harmonic dictionary using the discrete Fourier transform for representing the harmonic components in the vibration signal; perform operational modal analysis using the cepstrum-based stochastic subspace method to obtain modal parameters, and then construct a modal dictionary for representing the modal components in the vibration signal;

[0012] Based on the original vibration signal and the constructed dictionaries, and introducing a weighted L1 norm, establish a physical information multi-dictionary sparse decomposition framework, and solve the physical information multi-dictionary sparse decomposition framework until it converges to the global optimal solution;

[0013] Based on the solution results of the physical information multi-dictionary sparse decomposition framework, the modal components and harmonic components in the vibration signal are removed, and the fault impact components are extracted for fault diagnosis.

[0014] As an alternative implementation, the process of establishing the generalized double impulse response wavelet dictionary by utilizing the physical characteristics of the fault impact includes: establishing the time-domain expression of the generalized double impulse response wavelet, parameterizing the size of the spallation zone therein, determining the size of the spallation zone through the pulse duration, and introducing it into the construction of the double impulse response wavelet dictionary.

[0015] As a further defined implementation, the generalized double impulse response wavelet dictionary is constructed as:

[0016] ;

[0017] wherein, the pulse appearing in the spallation zone is , represents the convolution operation, is the initial time indicating the occurrence of the pulse, and the time-domain expression of the generalized double impulse response wavelet is:

[0018] ;

[0019] wherein, A i is the amplitude parameter, i = 1, 2, 3, 4, , and are the damping ratio, undamped natural frequency, and damped natural frequency respectively, is the interval time between two pulses, and , is the inner diameter of the bearing, is the rotational frequency, is the diameter of the spallation zone.

[0020] As an alternative implementation, based on the original vibration signal and each constructed dictionary, and introducing the weighted L1 norm, the process of establishing the objective function of the physical information multi-dictionary sparse decomposition framework includes: integrating the weighted L1 norm into the sparse regularization decomposition, and establishing the physical information multi-dictionary sparse decomposition framework as:

[0021] ;

[0022] wherein, Di is the dictionary corresponding to the i th component or excitation source, and this framework is a unified form of sparse decomposition, decomposing the vibration signal into multiple components and the corresponding dictionaries, is the i th trade-off parameter, is the sparse coefficient of the i th excitation source, is the weight distribution coefficient, which consists of p matrices, namely , represents the diagonal matrix , and the weight coefficient distribution model is defined as:

[0023] ;

[0024] where is the stability parameter.

[0025] As a further limited implementation manner, the physical information multi-dictionary sparse decomposition framework can be used for single-dictionary sparse decomposition, double-dictionary sparse decomposition or multi-dictionary decomposition, and can be used for fault diagnosis of single excitation source and / or multiple excitation sources.

[0026] As an alternative implementation manner, the process of solving the physical information multi-dictionary sparse decomposition framework until converging to the global optimal solution includes: dividing the physical information multi-dictionary sparse decomposition framework into the sum of two functions, performing variable splitting, introducing auxiliary variables, transforming the unconstrained optimization problem into a constrained problem, using the alternating minimization method to handle the constrained problem, using the augmented Lagrangian method to rewrite the constrained problem, and performing the minimization process until converging to the global minimum.

[0027] As an alternative implementation manner, during the minimization process, the matrix inversion lemma is used to simplify the solution process.

[0028] A machine tool bearing fault feature extraction system includes:

[0029] A signal acquisition module, configured to acquire the vibration signal of the machine tool bearing;

[0030] A multi-dictionary construction module, configured to utilize the physical characteristics of the fault impact to establish a generalized double impulse response wavelet dictionary for representing the fault impact components in the vibration signal, and utilize the discrete Fourier transform to construct a harmonic dictionary for representing the harmonic components in the vibration signal; perform operational modal analysis using the cepstrum-based stochastic subspace method to obtain modal parameters, and further construct a modal dictionary for representing the modal components in the vibration signal;

[0031] A multi-dictionary sparse decomposition module, configured to establish a physical information multi-dictionary sparse decomposition framework based on the original vibration signal and each constructed dictionary, and introduce a weighted L1 norm, and solve the physical information multi-dictionary sparse decomposition framework until converging to the global optimal solution;

[0032] The fault feature extraction module is configured to remove the modal components and harmonic components from the vibration signal according to the solution result of the physical information multi-dictionary sparse decomposition framework, and extract the fault impact components for fault diagnosis.

[0033] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the steps in the above method are completed.

[0034] An electronic device includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps in the above method are completed.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] The generalized double impulse response wavelet function constructed by the present invention has better morphological similarity with the fault impact components, and the proposed generalized double impulse response wavelet dictionary has better sparse representation performance. The present invention identifies modal parameters and constructs a modal dictionary through the cepstrum-based stochastic subspace operational modal analysis method, and can consider the influence of modes during sparse representation. (3) The present invention constructs a physical information multi-dictionary sparse decomposition framework, which can remove the interference of modal components and harmonic components while extracting fault components, and overcomes the deficiencies of traditional L1 norm regularization by using a weighted strategy. While suppressing noise, it can better retain the fault impact components.

[0037] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given in conjunction with the accompanying drawings and are described in detail as follows. Description of the Drawings

[0038] The specification drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0039] Figure 1 It is a schematic flow chart of a method for extracting the fault features of a machine tool bearing by physical information multi-dictionary sparse decomposition of an embodiment. Detailed Embodiments

[0040] The present invention will be further described below in conjunction with the drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanations of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. In addition, it should also be understood that when the terms "comprising" and / or "including" are used in this specification, they specify the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0043] In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0044] Embodiment 1

[0045] A method for extracting fault features of machine tool bearings by multi-dictionary sparse decomposition of physical information, as Figure 1 shown, includes the following steps:

[0046] Step 1: Obtain the vibration signal of the machine tool bearing.

[0047] In this step, the vibration signal of the machine tool bearing can be collected by a sensor, or the vibration signal of the machine tool bearing uploaded by the collection terminal can be obtained.

[0048] Step 2: Construct dictionaries for different components in the vibration signal.

[0049] Specifically, design a generalized double-pulse response wavelet according to the physical characteristics of the fault impact, adjust the parameters to generate a group of generalized double-pulse response wavelet functions with different morphologies, and combine them into a generalized double-pulse response wavelet dictionary to represent the fault components;

[0050] Construct a harmonic dictionary using the discrete Fourier transform to represent the harmonic components in the vibration signal;

[0051] Use the cepstrum-based stochastic subspace method for operational modal analysis to identify modal parameters, and construct a modal dictionary according to these parameters to represent the modal components in the vibration signal.

[0052] Step 3: Establish a physical information multi-dictionary sparse decomposition framework with the original signal and the dictionaries constructed in Step 2, introduce the weighted L1 norm, and then use the split augmented Lagrangian shrinkage algorithm to solve this optimization problem to ensure convergence to the global optimal solution.

[0053] Step 4: For the solution result, remove the modal components and harmonic components in the signal, and extract the fault impact components for subsequent fault diagnosis work.

[0054] The following describes each step in detail.

[0055] First, in step two, according to morphological component analysis (MCA), the vibration signal can be regarded as a linear combination of multiple components with different morphologies, and the performance of signal sparse decomposition depends on the similarity between the constructed dictionary and the decomposed components. Therefore, in order to accurately represent the waveform of the impact component, a generalized double impulse response wavelet dictionary is designed in this embodiment.

[0056] The time-domain expression of the generalized double impulse response wavelet is:

[0057] ;

[0058] where , , and are amplitude parameters, , and are the damping ratio, undamped natural frequency, and damped natural frequency respectively, is the time interval between two pulses.

[0059] By appropriate parameter settings, the constructed dictionary can generate different waveforms, including single impulse response wavelets, unilateral decaying wavelets, bilateral symmetric decaying wavelets, and bilateral asymmetric decaying wavelets, etc.

[0060] The generalized double impulse response wavelet of this embodiment can be used to represent multiple components due to its flexible form, such as the components of faulty transient bearings and gears, unbalance components, and friction components. The performance of fault feature extraction is related to the structure of the constructed double impulse response wavelet basis function. Therefore, the double impulse response wavelet basis function with higher morphological similarity can better express the process of two collisions.

[0061] In addition, in order to further improve the accuracy of the sparse signal decomposition model, the size of the spalling area is parameterized in this embodiment and introduced into the construction of the double impulse response wavelet dictionary. The size of the spalling area of a rolling bearing can be estimated by the pulse duration , and the specific relationship is:

[0062] ;

[0063] where is the inner diameter of the bearing. is the rotational frequency. is the diameter of the spalling area. The pulse appearing in the spalling area can be expressed as:

[0064] ;

[0065] Therefore, the final generalized double impulse response wavelet dictionary is constructed as:

[0066] ;

[0067] wherein represents a convolution operation, is the initial time when the pulse appears.

[0068] By introducing parameters related to the size of the spalling zone, a series of over-complete dictionaries of double-pulse response wavelet bases with different parameters can be generated to ensure that the generated waveform has better morphological similarity with the impulse response. In previous studies, the size of the spalling zone was not considered in the dictionary design process, resulting in a mismatch between the dictionary and the vibration data, thus reducing the signal-to-noise ratio of the extracted fault features. In this embodiment, the size of the spalling zone is considered in the dictionary design process to extract accurate fault features, so the designed generalized double impulse response wavelet dictionary has better performance.

[0069] To improve the signal-to-noise ratio of the extracted fault features, when performing fault feature extraction, the modal components can be separated from the vibration signal. In this embodiment, the cepstrum-based stochastic subspace operational modal analysis method (SSI-OMA) and the stabilization diagram are used to identify the modal parameters with the modal assurance criterion. The identified parameters are used to construct a modal dictionary to sparsely represent the modal components and separate them from the original signal.

[0070] In step three, a physical information multi-dictionary sparse decomposition framework is constructed. By accurately representing each component of the vibration signal through the designed dictionary, the fault components are extracted and the interference of harmonic components and modal components is removed, realizing high-precision fault feature extraction.

[0071] The generalized double pulse response wavelet dictionary proposed in this embodiment can be used as a transient impact dictionary because it has better morphological similarity. The proposed modal dictionary can represent modal components. The harmonic components are represented by a harmonic dictionary obtained by discrete Fourier transform (DFT).

[0072] According to the weighting mechanism, a series of weighting coefficients can be used to emphasize the important information of the target and suppress some irrelevant details. To improve the performance of sparse decomposition and overcome the deficiency of the L1 norm, the weighted L1 norm is integrated into the sparse regularization decomposition, thus constructing a physical information multi-dictionary sparse decomposition framework as follows:

[0073] ;

[0074] wherein is the dictionary corresponding to the i th component or excitation source. This framework is a unified form of sparse decomposition, which can decompose a signal into several components and the corresponding dictionaries. is the iA trade-off parameter. is the i sparse coefficient of the th excitation source. p is the weight allocation coefficient, which consists of matrices, namely representing the diagonal matrix , and the weight coefficient allocation model is defined as:

[0075] ;

[0076] where is the stability parameter, which is set to 0.3 in this embodiment.

[0077] The weighted coefficient allocation realizes the selection and retention of the fault impact components, thereby improving the performance of fault impact extraction. The proposed physical information multi-dictionary sparse decomposition framework can perform single-dictionary sparse decomposition, double-dictionary sparse decomposition, and multi-dictionary (i.e., more than two dictionaries) decomposition, so it can be used for single-excitation source and multi-excitation source fault diagnosis.

[0078] In this embodiment, the split augmented Lagrangian shrinkage algorithm is used to obtain the optimal solution of the framework. For the convenience of solution, the physical information multi-dictionary sparse decomposition framework can be rewritten as the sum of two sub-functions, namely:

[0079] ;

[0080] ;

[0081] ;

[0082] Since the two sub-functions are strictly convex functions, the physical information multi-dictionary sparse decomposition framework is also a strictly convex function. To simplify the derivation process, the following symbols are introduced:

[0083] , , , ;

[0084] After variable splitting, the unconstrained optimization problem can be transformed into the following constrained problem, namely:

[0085] ;

[0086] After introducing the auxiliary variable z , the constrained problem can be processed by the alternating minimization method. Using the augmented Lagrangian method, this problem can be rewritten as:

[0087] ;

[0088] ;

[0089] wherein, μ is the penalty parameter, is the k th auxiliary variable in the z th iteration, is the k th sparse coefficient in the x th iteration, is the k th Lagrange multiplier in the

[0090] The minimization of the above problem alternates between x and z, and the algorithm can converge to the global minimum. During the x and z alternating minimization, the following steps can be obtained:

[0091] ;

[0092] ;

[0093] ;

[0094] The alternating minimization problem is converted into a sub-problem. The sub-problem is the L1-norm regularized basis pursuit denoising problem, which can be solved by soft thresholding, i.e.:

[0095] ;

[0096] is the k +1th auxiliary variable in the z th iteration;

[0097] The sub-problem is a strictly convex quadratic function, belonging to the constrained least squares problem, and its minimization process can be expressed as:

[0098] ;

[0099] When the dictionary is a tight frame, the matrix inverse lemma can be used to simplify the solution process, so the minimization process is:

[0100] ;

[0101] To further simplify the iteration process, the iteration process is slightly adjusted, i.e.:

[0102] ;

[0103] Through the above steps, the variables x and z are updated alternately. When applying this algorithm, the amplitude parameter of the wavelet dictionary is set according to the amplitude of the analyzed signal, because providing an approximation helps to accelerate convergence. The value of the trade-off parameter is set in the range of (0, 1]. A too small value will make the processed result retain some redundant components, while a too large value will cause the loss of waveform details.

[0104] The computational complexity of the proposed physics-informed multi-dictionary sparse decomposition framework is as follows: This algorithm involves some simple computational steps, namely the operators , , , , , and the soft threshold operator.

[0105] Among them, the harmonic dictionary D1 is a discrete Fourier transform dictionary, and its computational complexity is O(NlogN) . The generalized double-pulse response wavelet dictionary D2 and the mode dictionary D3 involve wavelet transforms, and their computational complexity is O(NlogN) . The computational complexity of the soft threshold operator is O(N) . Therefore, the total computational complexity of the proposed physics-informed multi-dictionary sparse decomposition framework is O (kNlogN+N) , where k is the number of iterations. The computational complexity is not high, and less computational resources are used, which can improve efficiency.

[0106] As a typical application example, the modular test bench consists of a motor, a bearing test module, a flywheel module, and a load motor. The damage to the outer raceway of the bearing is caused by electrical discharge machining (EDM). The sampling frequency of the vibration signal is 64000 Hz, the rotational speed is 1500 r / min, and the theoretical fault characteristic frequency of the outer race of the bearing is 79.6 Hz. When an outer race fault occurs in the bearing, a spectral peak appears at the fault characteristic frequency in the frequency domain. If the spectral peak can be extracted in the frequency domain, the outer race fault of the bearing can be diagnosed.

[0107] In this example, the proposed physics-informed multi-dictionary sparse decomposition framework is applied to the fault feature extraction of this vibration signal. The parameters of the double-pulse response wavelet are set as follows: , , , , , , and the trade-off parameter is set as follows: , , (Parameters are optimized by exhaustive grid search of peak signal-to-noise ratio.) A random subspace operating modal analysis method based on cepstrum is used to identify modal parameters.

[0108] In this example, the first four modes of the system and their parameters are identified, and then these parameters are used to construct four elements and form a modal dictionary. Considering that the size of the spalling zone is unknown, the generalized double impulse response wavelet dictionary and the modal dictionary are The value range is 0 to 0.1 (the interval is 0.01), and then they are combined into a redundant dictionary. Through the sparse representation learning process, the most matching sub-dictionary is selected to extract the fault features. The experimental results show that the proposed physical information multi-dictionary sparse decomposition framework can effectively extract the fault impact component. The amplitude of the extracted fault impact component in the time domain and frequency domain is retained, and the spectrum peak is obvious in the frequency domain. The method provided in this embodiment provides an effective solution for rolling bearing fault diagnosis.

[0109] Of course, in other embodiments, the number of modes identified in the system can be changed according to specific circumstances and requirements, and is not limited to the above values.

[0110] Embodiment 2

[0111] A machine tool bearing fault feature extraction system, comprising:

[0112] A signal acquisition module is configured to acquire a vibration signal of a machine tool bearing;

[0113] The multi-dictionary construction module is configured to use the physical characteristics of the fault impulse to establish a generalized double-pulse response wavelet dictionary for representing the fault impulse component in the vibration signal, and to use discrete Fourier transform to construct a harmonic dictionary for representing the harmonic component in the vibration signal; use the random subspace method based on the cepstrum to perform working modal analysis to obtain modal parameters, and then construct a modal dictionary for representing the modal components in the vibration signal;

[0114] A multi-dictionary sparse decomposition module is configured to establish a physical information multi-dictionary sparse decomposition framework based on the original vibration signal and each constructed dictionary, and introduce a weighted L1 norm, and solve the physical information multi-dictionary sparse decomposition framework until it converges to a global optimal solution;

[0115] The fault feature extraction module is configured to remove the modal components and harmonic components in the vibration signal according to the solution results of the physical information multi-dictionary sparse decomposition framework, and extract the fault impact component for fault diagnosis.

[0116] Embodiment 3

[0117] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the steps in the method provided in embodiment 1 are completed.

[0118] Example 4

[0119] An electronic device includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps in the method provided in Example 1 are completed.

[0120] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD - ROM , optical memories, etc.).

[0121] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0122] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0124] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made by those skilled in the art without creative efforts within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for extracting machine tool bearing fault features, characterized in that: The following steps are involved: Obtain vibration signals of machine tool bearings; By using the physical characteristics of fault impulse, a generalized double-pulse response wavelet dictionary is established to represent the fault impulse component in the vibration signal. A harmonic dictionary is constructed using discrete Fourier transform to represent the harmonic component in the vibration signal. The random subspace method based on the cepstrum is used to perform working modal analysis to obtain modal parameters, and then a modal dictionary is constructed to represent the modal components in the vibration signal. Based on the original vibration signal and the constructed dictionaries, and introducing the weighted L1 norm, a physical information multi-dictionary sparse decomposition framework is established, and the physical information multi-dictionary sparse decomposition framework is solved until it converges to a global optimal solution; According to the solution results of the physical information multi-dictionary sparse decomposition framework, the modal components and harmonic components in the vibration signal are removed, and the fault impulse components are extracted for fault diagnosis; The process of establishing the generalized double-pulse response wavelet dictionary includes: establishing the time domain expression of the generalized double-pulse response wavelet, parameterizing the size of the peeling zone therein, determining the size of the peeling zone by the pulse duration, and introducing it into the construction of the double-pulse response wavelet dictionary; The generalized double impulse response wavelet dictionary is constructed as: ； Among them, the pulse appearing in the spalling zone is , represents the convolution operation, To express the initial time of the pulse, the time domain expression of the generalized double pulse response wavelet is: ； in, A i is the amplitude parameter, i=1, 2, 3, 4, , and are the damping ratio, undamped natural frequency and damped natural frequency respectively, is the time interval between two pulses, and , is the inner diameter of the bearing, is the rotation frequency, is the diameter of the spalling zone.

2. A method for extracting machine tool bearing fault features as claimed in claim 1, characterized in that: Based on the original vibration signal and the constructed dictionaries, and introducing the weighted L1 norm, the process of establishing the objective function of the physical information multi-dictionary sparse decomposition framework includes: integrating the weighted L1 norm into the sparse regularization decomposition, and establishing the physical information multi-dictionary sparse decomposition framework as follows: ； in, Di It is with i The framework is a unified form of sparse decomposition, which decomposes the vibration signal into multiple components and corresponding dictionaries. It is i trade-off parameters, It is i The sparse coefficients of the excitation sources, is the weight distribution coefficient, given by p The matrix is ​​composed of , Represents a diagonal matrix , weight coefficient allocation model Defined as: ； in is the stability parameter.

3. A method for extracting machine tool bearing fault features as claimed in claim 2, characterized in that: The physical information multi-dictionary sparse decomposition framework performs single-dictionary sparse decomposition, dual-dictionary sparse decomposition or multi-dictionary decomposition, which can be used for fault diagnosis of single excitation source and / or multiple excitation sources.

4. A method for extracting machine tool bearing fault features as claimed in claim 1, characterized in that: The process of solving the physical information multi-dictionary sparse decomposition framework until converging to the global optimal solution includes: dividing the physical information multi-dictionary sparse decomposition framework into the sum of two functions, performing variable splitting, introducing auxiliary variables, converting the unconstrained optimization problem into a constrained problem, using the alternating minimization method to handle the constraint problem, using the enhanced Lagrangian method to rewrite the constraint problem, and performing a minimization process until converging to the global minimum.

5. A method for extracting machine tool bearing fault features as claimed in claim 4, characterized in that: During the minimization process, the matrix inverse lemma is used to simplify the solution process.

6. A machine tool bearing fault feature extraction system, characterized in that: include: A signal acquisition module is configured to acquire a vibration signal of a machine tool bearing; The multi-dictionary construction module is configured to use the physical characteristics of the fault impulse to establish a generalized double-pulse response wavelet dictionary for representing the fault impulse component in the vibration signal, and to use discrete Fourier transform to construct a harmonic dictionary for representing the harmonic component in the vibration signal; use the random subspace method based on the cepstrum to perform working modal analysis to obtain modal parameters, and then construct a modal dictionary for representing the modal components in the vibration signal; A multi-dictionary sparse decomposition module is configured to establish a physical information multi-dictionary sparse decomposition framework based on the original vibration signal and each constructed dictionary, and introduce a weighted L1 norm, and solve the physical information multi-dictionary sparse decomposition framework until it converges to a global optimal solution; A fault feature extraction module is configured to remove modal components and harmonic components in the vibration signal according to the solution results of the physical information multi-dictionary sparse decomposition framework, and extract fault impact components for fault diagnosis; The process of establishing the generalized double-pulse response wavelet dictionary includes: establishing the time domain expression of the generalized double-pulse response wavelet, parameterizing the size of the peeling zone therein, determining the size of the peeling zone by the pulse duration, and introducing it into the construction of the double-pulse response wavelet dictionary; The generalized double impulse response wavelet dictionary is constructed as: ； Among them, the pulse appearing in the spalling zone is , represents the convolution operation, To express the initial time of the pulse, the time domain expression of the generalized double pulse response wavelet is: ； in, A i is the amplitude parameter, i=1, 2, 3, 4, , and are the damping ratio, undamped natural frequency and damped natural frequency respectively, is the time interval between two pulses, and , is the inner diameter of the bearing, is the rotation frequency, is the diameter of the spalling zone.

7. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of the method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps in the method according to any one of claims 1 to 5 are completed.

Images