Motor Bearing Fault Diagnosis Method and Device Based on Weighted Sparse Subspace Clustering

Abstract

The present application discloses a motor bearing fault diagnosis method and device based on weighted sparse subspace clustering. The motor bearing fault diagnosis method based on weighted sparse subspace clustering includes: obtaining a sample set, where the sample set includes vibration signals of bearings under different fault types; obtaining the vibration acceleration signal of the bearing to be diagnosed; performing feature extraction on the vibration acceleration signal of the bearing to be diagnosed, so as to obtain a feature vector to be diagnosed; obtaining a weighting term according to the vibration acceleration signal of the bearing to be diagnosed and the sample set; performing clustering through the weighted sparse subspace clustering method according to the weighting term, the feature vector to be diagnosed and the sample set, and obtaining a clustering result. In the algorithm of the present application, the similarity degree between data is introduced as the weighting term, which is beneficial to accurately diagnosing bearing faults.

Description

Technical Field

[0001] The present application relates to the technical field of motor bearing fault diagnosis, and specifically relates to a motor bearing fault diagnosis method based on weighted sparse subspace clustering and a motor bearing fault diagnosis device based on weighted sparse subspace clustering. Background Art

[0002] With the continuous improvement of the degree of industrial production automation, as a core power device, the safe and stable operation of the motor is of great significance to the entire production process. As an important supporting component of the motor, the bearing operates under high load for a long time, and its health status is easily threatened. Therefore, researching the fault diagnosis technology of motor bearings is of great significance to ensure the normal operation of the motor.

[0003] The fault diagnosis of bearings usually detects information such as the sound, temperature, smell, vibration, etc. of the bearings under different working conditions. When the bearing fault is relatively minor, it is difficult to judge based on signals such as its temperature and sound. However, the vibration signal of the bearing contains rich fault information and can reflect the motion state of the bearing changing over time. Therefore, the effective analysis of the vibration signal is an important method for diagnosing bearing faults at present. This analysis process is generally divided into several links: signal acquisition, signal processing, feature extraction, and decision diagnosis. Among them, time-frequency domain methods are generally selected for signal processing and feature extraction to extract the hidden features of the signal, and decision diagnosis generally needs to solve pattern recognition or clustering problems.

[0004] In recent years, algorithms such as sparse subspace clustering have been widely applied to the fault diagnosis of bearings. Although the traditional sparse subspace clustering algorithm can divide high-dimensional data features into different low-dimensional subspaces, its solution process is based on the global expression between data, which makes the algorithm vulnerable to noise, resulting in a low diagnostic accuracy for faults and being unsuitable for engineering applications under strong noise backgrounds. Summary of the Invention

[0005] The purpose of the present invention is to provide a motor bearing fault diagnosis method based on weighted sparse subspace clustering to at least solve one of the above technical problems.

[0006] In one aspect of the present invention, there is provided a motor bearing fault diagnosis method based on weighted sparse subspace clustering, and the motor bearing fault diagnosis method based on weighted sparse subspace clustering includes:

[0007] Obtain a sample set, where the sample set includes the vibration signals of the bearings under different fault types;

[0008] Obtain the vibration acceleration signal of the bearing to be diagnosed;

[0009] Extract features from the vibration acceleration signal of the bearing to be diagnosed, so as to obtain a feature vector to be diagnosed;

[0010] Obtain a weighting term based on the vibration acceleration signal of the bearing to be diagnosed and the sample set;

[0011] Perform clustering using the weighted sparse subspace clustering method based on the weighting term, the feature vector to be diagnosed, and the sample set, and obtain a clustering result.

[0012] Optionally, the feature extraction of the vibration acceleration signal of the bearing to be diagnosed to obtain a feature vector to be diagnosed includes:

[0013] Perform three-layer wavelet packet decomposition and reconstruction on the vibration acceleration signal;

[0014] Perform singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain a feature vector to be diagnosed.

[0015] Optionally, the performing singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain a feature vector to be diagnosed includes:

[0016] Select the low-frequency signals among the decomposed and reconstructed signals to form an initial feature matrix;

[0017] Perform singular value decomposition on the initial feature matrix to obtain a feature vector to be diagnosed.

[0018] Optionally, the selecting the low-frequency signals among the decomposed and reconstructed signals to form an initial feature matrix includes:

[0019] Select the first 5 low-frequency node signals among the signals of each node of the third-layer wavelet packet transform;

[0020] Merge the 5 low-frequency node signals to form an initial feature matrix.

[0021] Optionally, the performing clustering using the weighted sparse subspace clustering method based on the weighting term, the feature vector to be diagnosed, and the sample set, and obtaining a clustering result includes:

[0022] Construct a Gaussian similarity matrix between signals based on the feature vector to be diagnosed and the sample set;

[0023] Solve the weighted sparse representation model based on the Gaussian similarity matrix to obtain a representation coefficient matrix;

[0024] Calculate a similarity matrix based on the obtained representation coefficient matrix;

[0025] Apply a spectral clustering algorithm to the similarity matrix to obtain a clustering result.

[0026] Optionally, the applying a spectral clustering algorithm to the similarity matrix to obtain a clustering result includes:

[0027] Apply the normalized cut method to the similarity matrix for spectral clustering;

[0028] Obtain the clustering result of the vibration acceleration signal of the bearing to be diagnosed according to the spectral clustering result.

[0029] Optionally, the vibration signals of the bearing under different fault types include bearing healthy vibration signals, rolling element fault vibration signals, inner race fault vibration signals, and outer race fault vibration signals.

[0030] This application also provides a motor bearing fault diagnosis device based on weighted sparse subspace clustering, characterized in that the motor bearing fault diagnosis device based on weighted sparse subspace clustering includes:

[0031] A sample set acquisition module, which is used to acquire a sample set, and the sample set includes the vibration signals of the bearing under different fault types;

[0032] A vibration acceleration signal acquisition module, which is used to acquire the vibration acceleration signal of the bearing to be diagnosed;

[0033] A to-be-diagnosed feature vector acquisition module, which is used to extract features from the vibration acceleration signal of the bearing to be diagnosed, so as to obtain a to-be-diagnosed feature vector;

[0034] A sample set acquisition weighted term acquisition module, which is used to acquire a weighted term according to the vibration acceleration signal of the bearing to be diagnosed and the sample set;

[0035] A clustering result acquisition module, which is used to perform clustering according to the weighted term, the to-be-diagnosed feature vector and the sample set by using the weighted sparse subspace clustering method and obtain the clustering result.

[0036] Beneficial effects:

[0037] The motor bearing fault diagnosis method based on weighted sparse subspace clustering proposed in this application extracts signal features by performing wavelet packet transform and singular value decomposition on the vibration acceleration signal of the bearing to be diagnosed, establishes a weighted sparse subspace by using the characteristic parameters of the vibration acceleration signal of the bearing to be diagnosed and the sample set, and uses the method of clustering the representation coefficients for clustering, thereby constructing a dynamic depth model, and finally realizing the identification of the fault type of the test set. Compared with the traditional sparse subspace clustering diagnosis method, the present invention introduces the similarity degree between data as a weighted term in the algorithm, which is beneficial to accurately diagnose bearing faults. Description of the Drawings

[0038] Figure 1It is the flowchart of the motor bearing fault diagnosis method based on weighted sparse subspace clustering in an embodiment of the present invention;

[0039] Figure 2 It is the schematic diagram of the three - layer wavelet packet decomposition process in an embodiment of the present invention;

[0040] Figure 3 It is the algorithm flowchart of weighted sparse subspace clustering in an embodiment of the present invention;

[0041] Figure 4 It is the vibration signal waveform diagram collected in an embodiment of the present invention;

[0042] Figure 5 It is the three - dimensional effect diagram after clustering the fault features of the vibration signal in an embodiment of the present invention;

[0043] Figure 6 It is the exemplary structural diagram of an electronic device capable of implementing the motor bearing fault diagnosis method based on weighted sparse subspace clustering provided in an embodiment of the present application. Detailed implementation manners

[0044] To make the purpose, technical solutions and advantages of the implementation of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The described embodiments are some, but not all, of the embodiments of the present application. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application. The embodiments of the present application will be described in detail below with reference to the drawings.

[0045] As Figure 1 shown, the motor bearing fault diagnosis method based on weighted sparse subspace clustering includes:

[0046] Step 1: Obtain a sample set, where the sample set includes the vibration signals of bearings under different fault types;

[0047] Step 2: Obtain the vibration acceleration signal of the bearing to be diagnosed;

[0048] Step 3: Extract features from the vibration acceleration signal of the bearing to be diagnosed, so as to obtain the feature vector to be diagnosed;

[0049] Step 4: Obtain a weighting term according to the vibration acceleration signal of the bearing to be diagnosed and the sample set;

[0050] Step 5: According to the weighted terms, the feature vector to be diagnosed, and the sample set, perform clustering through the weighted sparse subspace clustering method and obtain the clustering result.

[0051] The motor bearing fault diagnosis method based on weighted sparse subspace clustering proposed in this application extracts signal features by performing wavelet packet transform and singular value decomposition on the vibration acceleration signal of the bearing to be diagnosed, establishes a weighted sparse subspace using the feature parameters of the vibration acceleration signal of the bearing to be diagnosed and the sample set, and performs clustering in the form of clustering of representation coefficients, thereby constructing a dynamic depth model and finally realizing the identification of the fault type of the test set. Compared with the traditional sparse subspace clustering diagnosis method, the present invention introduces the similarity degree between data as a weighted term in the algorithm, which is beneficial to accurately diagnose bearing faults.

[0052] In this embodiment, the feature extraction of the vibration acceleration signal of the bearing to be diagnosed to obtain the feature vector to be diagnosed includes:

[0053] Perform three-layer wavelet packet decomposition and reconstruction on the vibration acceleration signal;

[0054] Perform singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain the feature vector to be diagnosed.

[0055] In this embodiment, the performing singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain the feature vector to be diagnosed includes:

[0056] Select the low-frequency signals among the decomposed and reconstructed signals to form an initial feature matrix;

[0057] Perform singular value decomposition on the initial feature matrix to obtain the feature vector to be diagnosed.

[0058] In this embodiment, the selecting the low-frequency signals among the decomposed and reconstructed signals to form an initial feature matrix includes:

[0059] Select the first 5 low-frequency node signals among the signals of each node of the third-layer wavelet packet transform;

[0060] Merge the 5 low-frequency node signals to form an initial feature matrix.

[0061] In this embodiment, the performing clustering through the weighted sparse subspace clustering method according to the weighted terms, the feature vector to be diagnosed, and the sample set and obtaining the clustering result includes:

[0062] Construct a Gaussian similarity matrix between signals according to the feature vector to be diagnosed and the sample set;

[0063] Solve the weighted sparse representation model according to the Gaussian similarity matrix to obtain a representation coefficient matrix;

[0064] Calculate the similarity matrix according to the obtained representation coefficient matrix;

[0065] Apply the spectral clustering algorithm to the similarity matrix to obtain the clustering result.

[0066] In this embodiment, the applying the spectral clustering algorithm to the similarity matrix to obtain the clustering result includes:

[0067] Apply the normalized cut method to the similarity matrix for spectral clustering;

[0068] Obtain the clustering result of the vibration acceleration signal of the bearing to be diagnosed according to the spectral clustering result.

[0069] In this embodiment, the vibration signals of the bearing under different fault types include the vibration signal of the healthy bearing, the vibration signal of the rolling element fault, the vibration signal of the inner race fault, and the vibration signal of the outer race fault.

[0070] In this embodiment, the similarity matrix is calculated using the following formula:

[0071] ,

[0072] where the matrix U is the representation coefficient matrix of the weighted sparse representation model, and are the norms of the matrices U and , W is the similarity matrix, represents the transposed matrix.

[0073] In this embodiment, the wavelet packet decomposition algorithm includes:

[0074] ,

[0075] where d i,j,m is the j th coefficient of the i th sub-frequency band of the i th layer of wavelet packet decomposition ( j represents the index number of a certain frequency band, h(k) and g(k) are the wavelet packet filter coefficients, represents the summation of the k variable, represents adjusting the signal position).

[0076] In this embodiment, the wavelet packet reconstruction algorithm includes:

[0077] ,

[0078] Among them, d i,j,m is the j th sub-band coefficient of the m th layer of wavelet packet decomposition; i th coefficient; h(k) and g(k) are wavelet packet filter coefficients.

[0079] In this embodiment, the singular value decomposition formula is:

[0080] ,

[0081] Among them, the matrix A is the m×n -dimensional initial feature matrix, the matrix U is the m×m -dimensional left singular value matrix, the matrix is the n×n right singular value matrix, and the matrix is the m×n -dimensional diagonal matrix, and the elements on its main diagonal are the singular values of matrix A.

[0082] In this embodiment, the signal feature vector is:

[0083] ,

[0084] Among them, is the signal feature vector, are the element values on the main diagonal of the matrix arranged from large to small, and represents transpose.

[0085] In this embodiment, the Gaussian similarity function formula is:

[0086] ,

[0087] Among them, represents the Gaussian similarity of two signals d i and d j ; exp represents the natural exponential function; d i and d j are the feature vectors of different groups of signals, and represents the signals d i and d jThe squared Euclidean distance between is the standard deviation of the Gaussian distribution. The distance is mapped to similarity through the Gaussian function. The smaller the distance, the higher the similarity, and the closer it is to 1.

[0088] In this embodiment, the Gaussian similarity matrix between the signals is:

[0089] ,

[0090] where is the Gaussian similarity matrix, is the element in the matrix, representing the Gaussian similarity between the signals d i and d j .

[0091] In this embodiment, the weighted sparse representation model is:

[0092] ,

[0093] where is the norm of the sparse vector, s.t. represents being restricted to, that is, the constraint condition, d represents the signal feature vector, D is the data set processed by the algorithm, u is the representation coefficient. The condition that the model obeys is the self - representation of the data set and it cannot be represented only by itself, .

[0094] In this embodiment, the present application first extracts the signal features of the collected vibration signals of the test set through wavelet packet transform and singular value decomposition, then calculates the similarity between all the data of the test set and the sample set through the Gaussian similarity function as the weighting term, introduces the weighting term into the sparse subspace clustering algorithm, and finally completes the fault diagnosis of the bearing through the clustering result of the algorithm.

[0095] Thus, it can strengthen the connection between data with higher similarity according to the similarity degree between signal features, which is beneficial to the clustering of signal features under the same fault type. Compared with the traditional sparse subspace clustering diagnosis method, the present invention introduces the similarity degree between data as the weighting term in the algorithm, which is beneficial to the accurate diagnosis of bearing faults.

[0096] In this embodiment, in order to refine the frequency segmentation and improve the signal analysis effect, the vibration acceleration signal of the bearing to be diagnosed collected is subjected to three-layer wavelet packet decomposition and reconstruction. That is, first use the wavelet packet decomposition algorithm to divide the original signal into 2^3 = 8 frequency bands, and then use the wavelet packet reconstruction algorithm to reconstruct the stray signals in each frequency band, so as to complete the refinement of the 8 frequency bands of the original signal.

[0097] Wavelet packet decomposition has a strong ability of spectrum refinement analysis. k-layer wavelet packet decomposition can divide the original frequency band into k 2^k sub-frequency bands, and each frequency band does not overlap and there is no omission. Therefore, wavelet packet decomposition can be regarded as a filter bank. The schematic diagram of three-layer wavelet packet decomposition is as Figure 2 shown, where A represents the low-frequency part, D represents the high-frequency part, and the original signal is divided into 8 frequency bands.

[0098] In this embodiment, it is also necessary to screen the reconstructed signals in each frequency band to facilitate the extraction of the signal eigenvalues. Select the first 5 low-frequency node signals with rich fault information among the 8 node signals to form an initial feature matrix for singular value decomposition.

[0099] Through the above method, the tiny fault features that are easily submerged in noise can be effectively extracted. And it is very difficult to achieve such an extraction effect by directly performing time-domain or frequency-domain analysis on the vibration fault impact signal of the bearing. Therefore, the method proposed in the embodiment of the present invention can effectively extract the fault features of the signal, which is beneficial to improving the overall diagnosis accuracy.

[0100] In this embodiment, the sample set can be obtained by the following method:

[0101] Select several groups of vibration signals of the bearing under different fault types from the database, including several groups of vibration acceleration signals under the conditions of bearing health, rolling element fault, inner ring fault, and outer ring fault to form a sample set. Calculate the Gaussian similarity function values between all the data of the test set and the sample set. The Gaussian similarity function formula is:

[0102] ,

[0103] where, represents the Gaussian similarity of two signals d i and d j ; exp represents the natural exponential function; d i and d j are the feature vectors of different groups of signals, represents the signal d i and dj The squared Euclidean distance between is the standard deviation of the Gaussian distribution. The distance is mapped to a similarity through the Gaussian function. The smaller the distance, the higher the similarity, and the closer it is to 1.

[0104] After that, the calculation results are combined into a Gaussian similarity matrix :

[0105] ,

[0106] where is the Gaussian similarity matrix, is the element in the matrix, representing the signal d i and d j 's Gaussian similarity.

[0107] Solve the weighted sparse representation model to obtain the solution matrix U :

[0108] ,

[0109] where is the norm of the sparse vector, s.t. represents being restricted to, i.e., the constraint condition, d represents the signal feature vector, D is the dataset processed by the algorithm, u is the representation coefficient. The condition that the model obeys is the self - representation of the dataset and it cannot be represented only by itself, .

[0110] Use the obtained representation coefficient matrix U to solve the similarity matrix W :

[0111] ,

[0112] where the matrix U is the representation coefficient matrix of the weighted sparse representation model, and are the norms of the matrices U and , W is the similarity matrix, represents the transpose matrix.

[0113] Applying the spectral clustering algorithm to the obtained similarity matrix W can get the clustering result of the data.

[0114] Figure 3 is the algorithm flow chart of the above - mentioned method.

[0115] The weighted sparse subspace clustering algorithm proposed in this application can establish a strong connection between data with a high degree of similarity based on the similarity degree between data, thereby increasing the representation coefficients between similar data, which is beneficial to improving the clustering of similar data by the algorithm.

[0116] The following further elaborates on this application by way of example. It can be understood that this example does not constitute any limitation to this application.

[0117] Acceleration sensor model for collecting vibration acceleration signals: HK8100, output sensitivity: 50 mV / g. Use a data acquisition card to collect vibration signals and store them in a computer, with a sampling frequency of 10 kHz. In the experiment, an inner ring fault bearing with pitting or spalling was used for testing. This bearing is a cylindrical roller bearing of model BC1B326441A / HB1 produced by SKF. Control the motor speed to run at 18 Hz for a period of time and collect vibration signals. Figure 4 It is the waveform diagram of the vibration signal of the inner ring fault bearing collected. Use Matlab software to program and run the method proposed in this application.

[0118] In order to verify the effectiveness of the method proposed in this application, first perform three-layer wavelet packet transform on the collected vibration signals using db4 wavelet. Then select the first 5 nodes among the 8 nodes in the third layer to form the initial fault feature matrix of the bearing, and perform singular value decomposition on this initial feature matrix to extract the feature vectors to be diagnosed for this group of vibration acceleration signals as follows:

[0119] ,

[0120] Similarly, select several groups of data in the database to form a sample set. The sample set includes 5 groups of vibration signals under bearing health, rolling element fault, inner ring fault, and outer ring fault, a total of 20 groups. Perform wavelet packet transform and singular value decomposition on the 20 groups of vibration signals in this sample set to extract the fault feature vectors of the signals, and form the fault feature matrix of the sample set as follows. The matrix has 20 rows, and each row represents the feature vector extracted from a group of vibration signals.

[0121]

[0122] Calculate the Gaussian similarity function between all data, and and Perform weighted sparse subspace clustering together. Figure 5Shows the three-dimensional clustering results of weighted sparse subspace clustering. In the figure, the red circles represent the clustering results of healthy bearings in the sample set, the green triangles represent the clustering results of rolling element fault bearings in the sample set, the blue stars represent the clustering results of inner ring fault bearings in the sample set, the black diamonds represent the clustering results of outer ring fault bearings in the sample set, and the purple rectangles represent the clustering results of the test set. Since the final step of the weighted sparse subspace clustering algorithm is to perform K-means clustering, the three axes Vector 1, Vector 2, and Vector 3 of the three-dimensional graph respectively represent the first three elements of the eigenvectors calculated before the final K-means clustering of each data, that is, the coordinates of the points in the graph are the magnitudes of the first three values in the eigenvectors extracted before K-means clustering for each data point. The relative spatial positions of the points in the three-dimensional graph show the clustering effect of the algorithm. Although the three-dimensional graph cannot show all the clustering information, it can, to a certain extent, reflect the data processing ability and clustering effect of the weighted sparse subspace clustering algorithm. In Figure 5 it can be observed that the data in the test set is clustered into the category of inner ring fault bearings, which is consistent with the actual situation, successfully verifying the effectiveness of the method proposed in the present invention. And Figure 5 presents an ideal classification effect, that is, the distances between data of the same fault type are close, while the distances between data of different fault types are far.

[0123] This application also provides a motor bearing fault diagnosis device based on weighted sparse subspace clustering. The motor bearing fault diagnosis device based on weighted sparse subspace clustering includes a sample set acquisition module, a vibration acceleration signal acquisition module, a to-be-diagnosed eigenvector acquisition module, a sample set acquisition weighted term acquisition module, and a clustering result acquisition module. Among them,

[0124] The sample set acquisition module is used to acquire a sample set, and the sample set includes the vibration signals of bearings under different fault types;

[0125] The vibration acceleration signal acquisition module is used to acquire the vibration acceleration signal of the bearing to be diagnosed;

[0126] The to-be-diagnosed eigenvector acquisition module is used to extract features from the vibration acceleration signal of the bearing to be diagnosed, so as to acquire the to-be-diagnosed eigenvector;

[0127] The sample set acquisition weighted term acquisition module is used to acquire a weighted term according to the vibration acceleration signal of the bearing to be diagnosed and the sample set;

[0128] The clustering result acquisition module is used to perform clustering according to the weighted term, the to-be-diagnosed eigenvector, and the sample set by using the weighted sparse subspace clustering method and acquire the clustering result.

[0129] Through a motor bearing fault diagnosis method based on weighted sparse subspace clustering provided by this application, first, the vibration signals of the test set collected are subjected to wavelet packet transform and singular value decomposition to extract signal features. Then, the similarity of signal features between the test set and the sample set is calculated through a Gaussian similarity function as a weighting term, which is introduced into the sparse subspace clustering algorithm. Finally, the fault diagnosis of the bearing is completed through the clustering result of the algorithm. Moreover, the present invention introduces the similarity degree between data as a weighting term in the algorithm, which is beneficial to accurately diagnosing bearing faults.

[0130] It should be noted that the foregoing explanation of the method embodiment also applies to the device of this embodiment, and will not be elaborated here.

[0131] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, it implements the above-mentioned motor bearing fault diagnosis method based on weighted sparse subspace clustering.

[0132] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it can implement the above-mentioned motor bearing fault diagnosis method based on weighted sparse subspace clustering.

[0133] Figure 6 It is an exemplary structural diagram of an electronic device capable of implementing the motor bearing fault diagnosis method based on weighted sparse subspace clustering provided by an embodiment of this application.

[0134] As Figure 6 shown, the electronic device includes an input device 501, an input interface 502, a central processing unit 503, a memory 504, an output interface 505, and an output device 506. Among them, the input interface 502, the central processing unit 503, the memory 504, and the output interface 505 are connected to each other through a bus 507. The input device 501 and the output device 506 are respectively connected to the bus 507 through the input interface 502 and the output interface 505, and then connected to other components of the electronic device. Specifically, the input device 501 receives input information from the outside and transmits the input information to the central processing unit 503 through the input interface 502; the central processing unit 503 processes the input information based on the computer-executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for the user to use.

[0135] That is to say, Figure 6The electronic device shown can also be implemented to include: a memory storing computer-executable instructions; and one or more processors that, when executing the computer-executable instructions, can implement the method for diagnosing motor bearing faults based on weighted sparse subspace clustering in combination with Figure 1 the described method for diagnosing motor bearing faults based on weighted sparse subspace clustering.

[0136] In one embodiment, Figure 6 the electronic device shown can be implemented to include: a memory 504 configured to store executable program code; one or more processors configured to run the executable program code stored in the memory 504 to execute the method for diagnosing motor bearing faults based on weighted sparse subspace clustering in the above embodiment.

[0137] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0138] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0139] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code, which includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks marked may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or overall flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0141] In this embodiment, the so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), 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.

[0142] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the device / terminal device by running or executing the computer programs and / or modules stored in the memory, and by invoking the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, applications required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0143] In this embodiment, if the modules / units integrated in the device / terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. Although this application is disclosed above with preferred embodiments, it is not actually used to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application.

[0144] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] In addition, it is obvious that the term "including" does not exclude other units or steps.

[0146] Although the present invention has been described in detail above with general descriptions and specific embodiments, based on the present invention, some modifications or improvements can be made, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope claimed by the present invention.

Claims

1. A motor bearing fault diagnosis method based on weighted sparse subspace clustering, characterized in that: The motor bearing fault diagnosis method based on weighted sparse subspace clustering includes: Acquire a sample set, wherein the sample set includes vibration signals of the bearing under different fault types; Obtaining a vibration acceleration signal of the bearing to be diagnosed; Performing feature extraction on the vibration acceleration signal of the bearing to be diagnosed, thereby obtaining a feature vector to be diagnosed; Acquire a weighted item according to the vibration acceleration signal of the bearing to be diagnosed and the sample set; According to the weighted items, the feature vector to be diagnosed and the sample set, clustering is performed by a weighted sparse subspace clustering method to obtain a clustering result; The step of extracting features from the vibration acceleration signal of the bearing to be diagnosed, thereby obtaining a feature vector to be diagnosed, comprises: Performing three-layer wavelet packet decomposition and reconstruction on the vibration acceleration signal; Perform singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain the feature vector to be diagnosed; The step of performing singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain the feature vector to be diagnosed comprises: Select the low-frequency signal among the decomposed and reconstructed signals to form the initial feature matrix; Perform singular value decomposition on the initial feature matrix to obtain the feature vector to be diagnosed; The low-frequency signal in the selected decomposed and reconstructed signal is used to form an initial feature matrix, which includes: Select the first five low-frequency node signals among the node signals of the third-layer wavelet packet transform; The five low-frequency node signals are combined to form an initial feature matrix; The step of clustering and obtaining a clustering result by a weighted sparse subspace clustering method according to the weighted item, the feature vector to be diagnosed and the sample set comprises: A Gaussian similarity matrix between signals is formed according to the feature vector to be diagnosed and the sample set; wherein the similarity between the test set and all data in the sample set is calculated as a weighted item by using a Gaussian similarity function; Solving the weighted sparse representation model according to the Gaussian similarity matrix to obtain a representation coefficient matrix; Calculate a similarity matrix based on the obtained representation coefficient matrix; The spectral clustering algorithm is applied to the similarity matrix to obtain the clustering results.

2. The motor bearing fault diagnosis method based on weighted sparse subspace clustering according to claim 1, characterized in that: The step of applying a spectral clustering algorithm to the similarity matrix to obtain a clustering result comprises: Apply the normalized cut method to the similarity matrix for spectral clustering; The clustering results of the vibration acceleration signal of the bearing to be diagnosed are obtained according to the spectral clustering results.

3. The motor bearing fault diagnosis method based on weighted sparse subspace clustering according to claim 2, characterized in that: The vibration signals of the bearing under different fault types include a bearing health vibration signal, a rolling element fault vibration signal, an inner ring fault vibration signal, and an outer ring fault vibration signal.

4. A motor bearing fault diagnosis device based on weighted sparse subspace clustering, characterized in that: The motor bearing fault diagnosis device based on weighted sparse subspace clustering comprises: A sample set acquisition module, the sample set acquisition module is used to acquire a sample set, the sample set includes vibration signals of bearings under different fault types; A vibration acceleration signal acquisition module, wherein the vibration acceleration signal acquisition module is used to acquire a vibration acceleration signal of a bearing to be diagnosed; A module for acquiring feature vectors to be diagnosed, wherein the module is used for extracting features of the vibration acceleration signal of the bearing to be diagnosed, thereby acquiring feature vectors to be diagnosed; A sample set acquisition weighted item acquisition module, wherein the sample set acquisition weighted item acquisition module is used to acquire a weighted item according to the vibration acceleration signal of the bearing to be diagnosed and the sample set; A clustering result acquisition module, which is used to perform clustering and obtain clustering results by using a weighted sparse subspace clustering method according to the weighted items, the feature vector to be diagnosed and the sample set; The step of extracting features from the vibration acceleration signal of the bearing to be diagnosed, thereby obtaining a feature vector to be diagnosed, comprises: Performing three-layer wavelet packet decomposition and reconstruction on the vibration acceleration signal; Perform singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain the feature vector to be diagnosed; The step of performing singular value decomposition on the decomposed and reconstructed low-frequency signal to obtain the feature vector to be diagnosed comprises: Select the low-frequency signal among the decomposed and reconstructed signals to form the initial feature matrix; Perform singular value decomposition on the initial feature matrix to obtain the feature vector to be diagnosed; The low-frequency signal in the selected decomposed and reconstructed signal is used to form an initial feature matrix, which includes: Select the first five low-frequency node signals among the node signals of the third-layer wavelet packet transform; The five low-frequency node signals are combined to form an initial feature matrix; The step of clustering and obtaining a clustering result by a weighted sparse subspace clustering method according to the weighted item, the feature vector to be diagnosed and the sample set comprises: A Gaussian similarity matrix between signals is formed according to the feature vector to be diagnosed and the sample set; wherein the similarity between the test set and all data in the sample set is calculated as a weighted item by using a Gaussian similarity function; Solving the weighted sparse representation model according to the Gaussian similarity matrix to obtain a representation coefficient matrix; Calculate a similarity matrix based on the obtained representation coefficient matrix; The spectral clustering algorithm is applied to the similarity matrix to obtain the clustering results.

Images