Rolling bearing fault feature extraction method, system and device and storage medium

Abstract

The invention discloses a rolling bearing fault feature extraction method, system and device and a storage medium, and relates to the technical field of rotating machinery fault diagnosis, and the method comprises the steps: constructing a sparse coefficient matrix and a dictionary for a vibration signal of a rolling bearing; constructing a robust reconstruction error function based on # imgabs0 # divergence and constructing a structured sparse double regularization constraint which simultaneously considers intra-group sparsity and inter-group sparsity in a sparse coefficient matrix; constructing a robust structured sparse representation learning model based on the robust reconstruction error function and the structured sparse double regularization constraint, and alternately optimizing and updating the sparse coefficient matrix and the dictionary to obtain an optimal dictionary and an optimal sparse coefficient matrix; and reconstructing a fault pulse signal according to the optimal dictionary and the optimal sparse coefficient matrix, and extracting frequency spectrum features of the fault pulse signal for fault diagnosis. And the robustness and the accuracy of fault feature extraction are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical fault diagnosis, and in particular to a rolling bearing fault feature extraction method, system, equipment and storage medium. Background Art

[0002] In the early stages of rolling bearing faults, weak fault transient features are easily overwhelmed by background noise, outliers and abnormal conditions, making fault feature extraction and diagnosis difficult.

[0003] Existing sparse fault feature extraction methods cannot take into account both robustness to outliers and structural sparsity. The norm fidelity term is sensitive to outliers and abnormal conditions, and the analysis results are not sparse enough, which causes the fault characteristics to be interfered by other components, thereby increasing the false alarm rate. There is still room for improvement in improving the peak signal-to-noise ratio and eliminating outliers and abnormal conditions.

[0004] However, the existing robust sparse representation learning methods fail to fully consider the inherent structural characteristics of the data, resulting in poor results in extracting weak fault features. When the transient pulse is weak, the fault features are easily ignored, affecting the accuracy of fault diagnosis. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a rolling bearing fault feature extraction method, system, device and storage medium. By designing a robust reconstruction error function and a structured sparse dual regularization constraint, and constructing a robust structured sparse representation learning model, the robustness and accuracy of fault feature extraction are significantly improved.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a rolling bearing fault feature extraction method, comprising: Construct sparse coefficient matrix and dictionary for the vibration signal of rolling bearing respectively; The residual signal is defined based on the vibration signal, the sparse coefficient matrix and the dictionary to determine Divergence, by minimizing Divergence combined with residual signal is constructed based on The robust reconstruction error function of the divergence is constructed, and a structured sparse dual regularization constraint is constructed that simultaneously considers the intra-group sparsity and inter-group sparsity in the sparse coefficient matrix, where is any value not equal to 0; A robust structured sparse representation learning model is constructed based on the robust reconstruction error function and structured sparse dual regularization constraints, so as to alternately optimize and update the sparse coefficient matrix and dictionary until the set termination conditions are met, and then the optimal dictionary and the optimal sparse coefficient matrix are obtained. The fault pulse signal is reconstructed according to the optimal dictionary and the optimal sparse coefficient matrix, and the frequency spectrum characteristics of the fault pulse signal are extracted for fault diagnosis.

[0007] As an optional implementation, based on the probability density function of the residual signal and The estimated probability density function is , sure The divergence is: ; in, is the residual signal, , y is the segmented vibration signal, A is the dictionary, and x is the sparse coefficient; is the parameter in the conditional probability distribution function; for Approximate value of .

[0008] As an alternative implementation, minimize The divergence is: ; Combined residual signal , the robust reconstruction error function constructed for: ; in, is the conditional probability distribution function parameter The estimation of; K is the number of segments of the vibration signal; is the signal matrix after the vibration signal is segmented; The signal matrix Middle i Signal segment The jth data of Segment the i-th signal The residual of is the probability density function; is an intermediate parameter used to simplify the formula; is the noise standard deviation; A is the dictionary; is a sparse coefficient matrix Middle i List The jth data of is the number of points in each signal segment; is the F-norm; is the 2-norm.

[0009] As an optional implementation, the structured sparse dual regularization constraint is: ; ; in, is a regularization constraint controlling the sparsity within a group, is a regularization constraint that controls the sparsity between groups; is a sparse coefficient matrix No. i Column; K is the number of segments of the vibration signal; express Norm p Power, yes Norm.

[0010] As an optional implementation, the robust structured sparse representation learning model is: ; in, is the residual matrix No. i List; is the i-th column of dictionary A; is a sparse coefficient matrix The jth row in the middle; and is the sparsity tuning parameter.

[0011] As an optional implementation, the dictionary update process includes: ; Diagonal weight matrix The element in the i-th column and j-th row of It is expressed as: ; in, is the j-th column atom of dictionary A; K is the number of segments of the vibration signal; is the residual matrix No. i List; is a sparse coefficient matrix Middle i List The jth data of is the intermediate parameter; is the noise variance.

[0012] As an optional implementation, the sparse coefficient matrix update process includes: ; ; ; ; in, is a sparse coefficient matrix Middle i List The jth data of is the weighted residual projection; and are all regularization threshold parameters; sign is the sign function; is the diagonal weight matrix The i-th column of is the Tth element in the jth column of dictionary A; is the number of points in each signal segment; is the residual matrix No. i List; is the j-th column atom of dictionary A; and is the sparsity adjustment parameter; is the noise standard deviation.

[0013] In a second aspect, the present invention provides a rolling bearing fault feature extraction system, comprising: A preprocessing module is configured to construct a sparse coefficient matrix and a dictionary for the vibration signal of the rolling bearing respectively; The objective function building module is configured to define a residual signal based on the vibration signal, the sparse coefficient matrix and the dictionary to determine Divergence, by minimizing Divergence combined with residual signal is constructed based on The robust reconstruction error function of the divergence is constructed, and a structured sparse dual regularization constraint is constructed that simultaneously considers the intra-group sparsity and inter-group sparsity in the sparse coefficient matrix, where is any value not equal to 0; An optimization module is configured to construct a robust structured sparse representation learning model based on a robust reconstruction error function and a structured sparse dual regularization constraint, so as to alternately optimize and update the sparse coefficient matrix and the dictionary until a set termination condition is met, thereby obtaining an optimal dictionary and an optimal sparse coefficient matrix; The feature extraction module is configured to reconstruct the fault pulse signal according to the optimal dictionary and the optimal sparse coefficient matrix, and extract the frequency spectrum features of the fault pulse signal for fault diagnosis.

[0014] In a third aspect, the present invention provides an electronic device comprising 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 method described in the first aspect is performed.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0016] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method described in the first aspect.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a rolling bearing fault feature extraction method, system, device and storage medium, which is designed based on The robust reconstruction error function of the divergence can effectively reduce the influence of outliers and abnormal conditions in the signal and improve the accuracy of fault feature extraction.

[0018] The present invention proposes a rolling bearing fault feature extraction method, system, device and storage medium, designs structured sparse dual regularization constraints, considers intra-group sparsity and inter-group sparsity at the same time, and has stronger sparse representation capability.

[0019] The present invention proposes a rolling bearing fault feature extraction method, system, device and storage medium, combines a robust reconstruction error function and a structured sparse dual regularization constraint to construct a robust structured sparse representation learning model, has excellent performance in suppressing noise and outliers, enhancing sparsity and improving peak signal-to-noise ratio, and can effectively identify weak fault features in signals.

[0020] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0022] Figure 1 This is a flow chart of the rolling bearing fault feature extraction method provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "comprise" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0027] Example 1 This embodiment provides a rolling bearing fault feature extraction method, which significantly improves the robustness and accuracy of fault feature extraction by designing a robust reconstruction error function and a structured sparse dual regularization constraint and constructing a robust structured sparse representation learning model. It includes: Construct sparse coefficient matrix and dictionary for the vibration signal of rolling bearing respectively; The residual signal is defined based on the vibration signal, the sparse coefficient matrix and the dictionary to determine Divergence, by minimizing Divergence combined with residual signal is constructed based on The robust reconstruction error function of the divergence is constructed, and a structured sparse dual regularization constraint is constructed that simultaneously considers the intra-group sparsity and inter-group sparsity in the sparse coefficient matrix, where is any value not equal to 0; A robust structured sparse representation learning model is constructed based on the robust reconstruction error function and structured sparse dual regularization constraints, so as to alternately optimize and update the sparse coefficient matrix and dictionary until the set termination conditions are met, and then the optimal dictionary and the optimal sparse coefficient matrix are obtained. The fault pulse signal is reconstructed according to the optimal dictionary and the optimal sparse coefficient matrix, and the frequency spectrum characteristics of the fault pulse signal are extracted for fault diagnosis.

[0028] Combine the following Figure 1 The method of this embodiment is described in detail.

[0029] In this embodiment, the vibration signal of the rolling bearing is collected, and the one-dimensional vibration signal is segmented according to the sparse representation learning framework to construct a signal matrix; The number of signal segments is ,in, is the number of points in the original one-dimensional vibration signal, is the number of points in each signal segment, Indicates i The vibration signal is segmented.

[0030] Therefore, the signal matrix is ​​expressed as: (1).

[0031] According to the segmented vibration signal, the signal matrix is ​​expressed as: (2).

[0032] Since the representation capability of the analysis dictionary is limited and the signal cannot be adaptively represented, dictionary learning is used in this embodiment. The design of the initial dictionary has a great influence on the accuracy of fault feature extraction. The initial dictionary must be overcomplete, that is, the number of columns in the dictionary should be greater than the number of rows. In order to obtain satisfactory representation results and meet the requirements of the robust structured sparse representation learning algorithm, the initial dictionary is constructed based on the characteristics of the fault transient signal. The fault pulse of the bearing is transient, periodic, and has time-shift invariance.

[0033] Therefore, dictionary atoms are designed by using the time domain synchronous averaging method and the cyclic shift operator. The time domain synchronous averaging method can effectively eliminate the interference of random noise and non-periodic components while retaining the periodic components in the signal. Then, the processed vibration signal is segmented by the cyclic shift operator to construct an atomic matrix, which is composed of periodic fault pulses.

[0034] Thus, the initial dictionary is represented as: (3); Among them, N is the number of points in each segment, which is used as the number of rows of the initial dictionary here, M is the number of columns of the initial dictionary, and M>N.

[0035] Based on the signal matrix and initial fault pulse dictionary constructed above, the initial input of the robust structured sparse representation learning model is obtained.

[0036] In this embodiment, a robust structured sparse representation learning model is designed, and the objective function of the model consists of a robust reconstruction error function and a structured sparse dual regularization constraint.

[0037] First, a robust reconstruction error function is designed; the Frobenius norm and The data fidelity term of the norm is widely used as the reconstruction error term, but the traditional cost function is sensitive to outliers, and the accuracy of fault feature extraction will be affected by the anomaly. The robust reconstruction error function of the divergence suppresses outliers and abnormal signals; where is any value not equal to 0, and when When is 1, The divergence is KL divergence (Kulback-Leibler).

[0038] According to the morphological component analysis method, the residual signal is defined as , the residual signal , the residual of the ith signal segment is the conditional probability distribution function The conditional probability distribution function is the true probability distribution of the residual signal. is an unknown parameter, given by Parameterized estimated conditional probability distribution As Approximation of, where y is the segmented vibration signal in the signal matrix; A is the dictionary; x is the sparse coefficient in the sparse coefficient matrix; is the parameter that controls the probability distribution in the conditional probability distribution function; for The approximate value of .

[0039] Probability density function based on residual signal and The estimated probability density function is , The divergence is defined as: (4); It is determined by the parameters A generalized framework for defining the Kullback-Leibler divergence. Divergence provides a form of loss function suitable for enhancing robustness to Gaussian noise corruption.

[0040] By using the log-likelihood function ,Will Divergence This breaks down into: (5).

[0041] in: (6); (7); (8).

[0042] By minimizing Divergence , instead of maximum likelihood estimation, we get the parameters Since the first term in formula (5) is related to irrelevant, so it is The minimization has no effect. Minimizing the divergence, that is The estimate is rewritten as: (9).

[0043] In the traditional Frobenius norm and In the norm data fidelity term, the residual signal is a zero-mean, with a variance of Gaussian white noise. Under this assumption, the model is very sensitive to outliers and abnormal situations. The purpose of this example is to introduce Divergence is used to minimize the impact of noise, thereby enhancing the robustness of the model.

[0044] Probability density function for: (10); in, yes Elements of is the element of the i-th signal segment in the signal matrix; is an element of dictionary A; are the elements of the sparse coefficient matrix; is the noise standard deviation.

[0045] Combining equation (8) and equation (9), The estimate is rewritten as: (11); in, is an intermediate parameter used to simplify the formula.

[0046] Therefore, according to the parameters Based on the estimation derivation, this embodiment defines a robust reconstruction error function (robust fidelity): (12); in, , is the normalized residual signal.

[0047] based on Divergence robust reconstruction error function Reduce the sensitivity of the model to outliers and abnormal situations. In order to be consistent with the traditional reconstruction error term, this embodiment performs the following derivation.

[0048] when and hour, Rewritten as: (13).

[0049] Therefore, based on the residual signal , The function is written as: (14); in, For the i Signal segment The jth data in ; is a sparse coefficient matrix Middle i List The jth data of is the F-norm; is the 2-norm.

[0050] From the perspective of probability distribution, the robust fidelity term uses the statistical distribution of outliers and abnormal situations to gradually eliminate the impact on the sparse representation learning results. Therefore, the proposed fidelity term is robust to outliers and abnormal situations.

[0051] Secondly, a structured sparse dual regularization constraint is designed. The traditional sparse representation model only considers the sparsity within the group, but not the sparsity between groups, that is, the norm regularization term lacks structured information. Specifically, since the fault pulse is transient, the non-zero coefficients related to the fault characteristics are sparse in each column of the sparse coefficient matrix; at the inter-group level (the rows of the sparse coefficient matrix), since the pulse is time-invariant and periodic, there is a self-similar structure between the groups, and therefore, the coefficients related to the fault characteristics are also sparse at the inter-group level. In order to encode this structured sparsity, this embodiment designs a structured regularization to penalize unnecessary components, so that the extracted signal is sparse.

[0052] This embodiment defines a sparse coefficient matrix of norm to introduce sparsity both within and between groups, which is described as follows: (15); in, is a sparse coefficient matrix No. i List, express Norm pPower, yes Norm.

[0053] In this embodiment, the sparse coefficient matrix is ​​first initialized, and then the sparse coefficient matrix is ​​obtained by solving equation (27). Most elements of the sparse coefficient matrix are zero, and only a few non-zero values ​​correspond to the positions of the fault pulses.

[0054] according to The definition of the norm, the structured sparse dual regularization constraint is expressed as: (16); (17); in, is a regularization constraint controlling the sparsity within a group, is a regularization constraint that controls the sparsity between groups.

[0055] Therefore, in this embodiment, based on robust fidelity and structured sparse constraints, a robust structured sparse representation learning model is proposed, and its formula is as follows: (18); in, is the robust reconstruction error function, and is a structured sparse dual regularization constraint, is the sparsity adjustment parameter; The data to be processed.

[0056] Therefore, the robust structured sparse representation learning model is expressed as: (19).

[0057] The above robust structured sparse representation learning model is optimized using the Exact Block Coordinate Descent (EBCD) algorithm. It is expressed as a linear weighted combination, that is, Therefore, the robust structured sparse representation learning model is rewritten as: (20); The first term on the right side of the equation is the robust data fidelity, the second and third terms are structured dual regularization; is the residual matrix No. i List, , is a sparse coefficient matrix In the i-th row, is the i-th column atom of dictionary A; is the j-th column atom of dictionary A; is a sparse coefficient matrix The j-th row element in .

[0058] In this embodiment, according to the robust structured sparse representation learning model, an alternating optimization strategy is adopted to update the sparse coefficient matrix and the dictionary, specifically including: (1) Dictionary update; fixed coefficient , the optimal dictionary atom This is approximated by solving the following problem: (twenty one).

[0059] For formula (21), Derivative, expressed as: (twenty two).

[0060] Therefore, the dictionary atom It is expressed as: (twenty three).

[0061] To simplify the dictionary elements The expression of , introduces the diagonal weight matrix in the solution , so the updated atomic representation is: (twenty four).

[0062] The diagonal weight matrix is ​​expressed as: (25).

[0063] The elements of the diagonal weight matrix are expressed as: (26).

[0064] It can be seen that when and When the difference between is large, there are outliers and abnormal situations, and it cannot be With proper fitting, the weight of outliers and abnormal cases is almost zero, so their influence can be eliminated.

[0065] In addition, in formula (26) The value will also affect the weight. In practical applications, The value of is the noise variance) cannot be determined in advance. In this embodiment, the threshold is set estimate The value of . Given the residual and threshold , if satisfied , then the actual weight satisfies , we can get ,in is the weight value at the threshold.

[0066] For convenience, Fixed to 0.5, to search , and then obtain the best experimental results. The value of should be the residual set In order to determine the maximum value of The value of , assuming the set Middle q The value of the large element is the selected ,in ( Indicates rounding), parameter is the ratio of outliers to abnormal cases. The most important property of this weight is that it can effectively assign the smallest weight coefficient to outliers and abnormal cases. Since the weights of outliers and abnormal cases are small, their impact on the final estimation is also small, so the proposed model is robust.

[0067] (2) Sparse coefficient update: Fixed dictionary elements ,coefficient It is approximated by solving the following problem: (27).

[0068] For formula (27), Derivative, expressed as: (28).

[0069] The solution is obtained from the following formula: (29); (30); (31); (32); in, is the weighted residual projection; and are all regularization threshold parameters; sign is the sign function; is the diagonal weight matrix The i-th column of It is the Tth element in the jth column of dictionary A.

[0070] In summary, the dictionary and sparse coefficient matrix are updated through the above two alternating steps, and the termination condition is met. When To tolerate errors, the final optimal dictionary and optimal sparse coefficient matrix are output.

[0071] In this embodiment, according to the optimal dictionary and the optimal sparse coefficient matrix , and get the pulse signal matrix , and then reconstruct the one-dimensional estimated fault pulse signal , using the squared envelope spectrum (SES) analysis to process the estimated fault pulse signal , to obtain the spectrum characteristics. Fault diagnosis is performed based on the analyzed spectrum characteristics and theoretical fault characteristic frequencies.

[0072] The method proposed in this embodiment includes four main steps: weight calculation, residual calculation, sparse coefficient update and dictionary atom update. In order to illustrate the performance of the proposed method, the calculation of its complexity includes: exist K During the iteration, the weight The calculation needs Operations, residuals The calculation needs operations. In the sparse coefficient update phase, , and The calculations require operations, so the sparse coefficient update phase requires operations. In the dictionary atomic update phase, and Need and operations, each atom The calculation needs Operations, M The complexity of atomic updates is Therefore, the total complexity of the proposed algorithm is The computational complexity is not high, and fewer computing resources are used, which can improve efficiency.

[0073] In this embodiment, the experimental equipment includes a motor, an acceleration sensor, a thermocouple and a bearing. During the experiment, the motor speed is maintained at 2000RPM. The fault characteristic frequency of the outer ring raceway Calculated to be 236.4 Hz.

[0074] The proposed robust structured sparse representation learning model contains trade-off parameters and , scale parameters And the number of dictionary atoms M, in order to study the influence of these parameters in the bearing fault feature extraction experiment, this embodiment adopts different and The peak signal-to-noise ratio is compared by combining the parameters, and the results show that the trade-off parameters and The ranges are , Then fix the trade-off parameter , , study the scale parameter Due to the influence of Residual The ratio of outliers and abnormal situations in the range is [0, 1], and the specific value cannot be determined in advance. In order to obtain the best experimental performance, Parameter search was performed (the step size was set to 0.01). The results show that when When M is set to 0.19 and 0.30 respectively, the proposed method achieves the best results. The number of dictionary atoms M needs to be selected in a trade-off between computational cost and the required optimal peak signal-to-noise ratio.

[0075] In this embodiment, the proposed robust structured sparse representation learning method is used to extract bearing fault features. In order to obtain better performance, the number of initial dictionary atoms is set to M =40. According to the parameter search results, the trade-off regularization parameter is set to , . Parameters for rolling bearing fault feature extraction is set to 0.19 to further improve the performance. The experimental results show that the proposed robust structured sparse representation learning method can effectively extract fault pulses from time domain signals. In the frequency domain, , , , , and The spectral peak at the fault characteristic frequency is clearly visible, and the clear spectral peak at the fault characteristic frequency can provide an effective indicator for judging the outer ring fault of the bearing. The invention shows excellent performance in suppressing noise and outliers, while improving sparsity, and provides an effective solution for rolling bearing fault diagnosis. Example 2 This embodiment provides a rolling bearing fault feature extraction system, including: A preprocessing module is configured to construct a sparse coefficient matrix and a dictionary for the vibration signal of the rolling bearing respectively; The objective function building module is configured to define a residual signal based on the vibration signal, the sparse coefficient matrix and the dictionary to determine Divergence, by minimizing Divergence combined with residual signal is constructed based on The robust reconstruction error function of the divergence is constructed, and a structured sparse dual regularization constraint is constructed that simultaneously considers the intra-group sparsity and inter-group sparsity in the sparse coefficient matrix, where is any value not equal to 0; An optimization module is configured to construct a robust structured sparse representation learning model based on a robust reconstruction error function and a structured sparse dual regularization constraint, so as to alternately optimize and update the sparse coefficient matrix and the dictionary until a set termination condition is met, thereby obtaining an optimal dictionary and an optimal sparse coefficient matrix; The feature extraction module is configured to reconstruct the fault pulse signal according to the optimal dictionary and the optimal sparse coefficient matrix, and extract the frequency spectrum features of the fault pulse signal for fault diagnosis.

[0076] It should be noted that the above modules correspond to the steps described in Example 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Example 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer executable instructions.

[0077] In further embodiments, there is also provided: An electronic device includes 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 method described in Embodiment 1 is performed. For the sake of brevity, it will not be described in detail here.

[0078] It should be understood that in this embodiment, 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, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0079] 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 device type.

[0080] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is completed.

[0081] The method in Example 1 can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it is not described in detail here.

[0082] A computer program product includes a computer program, and when the computer program is executed by a processor, the method described in embodiment 1 is implemented.

[0083] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer executable instructions, such as instructions included in a program module, which are executed in a device on a real or virtual processor of the target to perform the process / method as described above. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or divided between program modules as needed. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0084] The computer program code for implementing the method of the present invention can be written in one or more programming languages. These computer program codes can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the computer or other programmable data processing device, causes the function / operation specified in the flow chart and / or block diagram to be implemented. The program code can be executed completely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer or completely on a remote computer or server.

[0085] In the context of the present invention, computer program codes or related data may be carried by any appropriate carrier to enable a device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, etc. Examples of signals may include electrical, optical, radio, acoustic or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0086] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0087] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A rolling bearing fault feature extraction method, characterized in that: include: Construct sparse coefficient matrix and dictionary for the vibration signal of rolling bearing respectively; The residual signal is defined based on the vibration signal, the sparse coefficient matrix and the dictionary to determine Divergence, by minimizing Divergence combined with residual signal is constructed based on The robust reconstruction error function of the divergence is constructed, and a structured sparse dual regularization constraint is constructed that simultaneously considers the intra-group sparsity and inter-group sparsity in the sparse coefficient matrix, where is any value not equal to 0; A robust structured sparse representation learning model is constructed based on the robust reconstruction error function and structured sparse dual regularization constraints, so as to alternately optimize and update the sparse coefficient matrix and dictionary until the set termination conditions are met, and then the optimal dictionary and the optimal sparse coefficient matrix are obtained. The fault pulse signal is reconstructed according to the optimal dictionary and the optimal sparse coefficient matrix, and the frequency spectrum characteristics of the fault pulse signal are extracted for fault diagnosis.

2. A rolling bearing fault feature extraction method as claimed in claim 1, characterized in that: Probability density function based on residual signal and The estimated probability density function is , sure The divergence is: ； in, is the residual signal, , y is the segmented vibration signal, A is the dictionary, and x is the sparse coefficient; is the parameter in the conditional probability distribution function; for Approximate value of .

3. A rolling bearing fault feature extraction method as claimed in claim 1, characterized in that: minimize The divergence is: ； Combined residual signal , the robust reconstruction error function constructed for: ； in, is the conditional probability distribution function parameter The estimation of; K is the number of segments of the vibration signal; is the signal matrix after the vibration signal is segmented; The signal matrix Middle i Signal segment The jth data of Segment the i-th signal The residual of is the probability density function; is an intermediate parameter used to simplify the formula; is the noise standard deviation; A is the dictionary; is a sparse coefficient matrix Middle i List The jth data of is the number of points in each signal segment; is the F-norm; is the 2-norm.

4. A rolling bearing fault feature extraction method as claimed in claim 1, characterized in that: The structured sparse dual regularization constraint is: ； ； in, is a regularization constraint controlling the sparsity within a group, is a regularization constraint that controls the sparsity between groups; is a sparse coefficient matrix No. i Column; K is the number of segments of the vibration signal; express Norm p Power, yes Norm.

5. A rolling bearing fault feature extraction method as claimed in claim 3 or 4, characterized in that: The robust structured sparse representation learning model is: ； in, is the residual matrix No. i List; is the i-th column of dictionary A; is a sparse coefficient matrix The jth row in the middle; and is the sparsity tuning parameter.

6. A rolling bearing fault feature extraction method as claimed in claim 1, characterized in that: The dictionary update process includes: ； Diagonal weight matrix The element in the i-th column and j-th row of It is expressed as: ； in, is the j-th column atom of dictionary A; K is the number of segments of the vibration signal; is the residual matrix No. i List; is a sparse coefficient matrix Middle i List The jth data of is the intermediate parameter; is the noise variance.

7. A rolling bearing fault feature extraction method as claimed in claim 1, characterized in that: The sparse coefficient matrix update process includes: ； ； ； ； in, is a sparse coefficient matrix Middle i List The jth data of is the weighted residual projection; and are all regularization threshold parameters; sign is the sign function; is the diagonal weight matrix The i-th column of is the Tth element in the jth column of dictionary A; is the number of points in each signal segment; is the residual matrix No. i List; is the j-th column atom of dictionary A; and is the sparsity adjustment parameter; is the noise standard deviation.

8. A rolling bearing fault feature extraction system, characterized in that: include: A preprocessing module is configured to construct a sparse coefficient matrix and a dictionary for the vibration signal of the rolling bearing respectively; The objective function building module is configured to define a residual signal based on the vibration signal, the sparse coefficient matrix and the dictionary to determine Divergence, by minimizing Divergence combined with residual signal is constructed based on The robust reconstruction error function of the divergence is constructed, and a structured sparse dual regularization constraint is constructed that simultaneously considers the intra-group sparsity and inter-group sparsity in the sparse coefficient matrix, where is any value not equal to 0; An optimization module is configured to construct a robust structured sparse representation learning model based on a robust reconstruction error function and a structured sparse dual regularization constraint, so as to alternately optimize and update the sparse coefficient matrix and the dictionary until a set termination condition is met, thereby obtaining an optimal dictionary and an optimal sparse coefficient matrix; The feature extraction module is configured to reconstruct the fault pulse signal according to the optimal dictionary and the optimal sparse coefficient matrix, and extract the frequency spectrum features of the fault pulse signal for fault diagnosis.

9. 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 method according to any one of claims 1 to 7 is completed.

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

Images