Intelligent fault diagnosis method for planetary bearings based on enhanced dictionary learning

Abstract

The present invention provides a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, which belongs to the technical field of intelligent mechanical equipment. By adopting a sub-dictionary learning algorithm considering the health state and a health state intelligent identification strategy based on a sparse reconstruction error minimum discrimination criterion, different health states of the planetary bearing can be accurately identified. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning of the present invention overcomes the shortcomings of traditional methods that rely on accurate identification of weak fault characteristic frequencies, are susceptible to manufacturing errors and interferences, and are difficult to achieve robust intelligent identification of the health state of the planetary bearing, and provides technical support for fault diagnosis and health management of mechanical equipment containing planetary transmission systems.

Description

Technical Field

[0001] The invention belongs to the field of intelligent mechanical equipment, and in particular relates to an intelligent fault diagnosis method for planetary bearings based on enhanced dictionary learning. Background Art

[0002] Planetary transmission systems have the advantages of compact space, large transmission ratio, and strong load-bearing capacity. They are widely used in the transmission systems of major mechanical equipment such as helicopters, wind turbines, and gear-driven turbofan engines. Due to the long-term heavy loads, variable loads, and harsh working conditions, the planetary transmission system is prone to component damage, which can cause the system to be unable to serve normally, safely and reliably, or even cause major economic losses or even catastrophic safety accidents. Planetary bearings are the core components of planetary transmission systems. The status monitoring and fault diagnosis technology of planetary bearings is of great significance in reducing major safety accidents and greatly saving the operation and maintenance costs of major high-end mechanical equipment such as aircraft engines, wind turbines, and helicopters. However, the status and fault diagnosis of planetary bearings have always been an important problem that has plagued the field of dynamic monitoring, diagnosis, and maintenance of mechanical systems.

[0003] Existing intelligent fault diagnosis methods for planetary bearings mainly include amplitude-frequency joint demodulation analysis method (Feng et al., 2016), SKRgram method based on spectral kurtosis ratio (Wang et al., 2016), demodulation analysis method based on spectral negentropy (Feng et al., 2017), multi-point optimal minimum entropy deconvolution method (Ma et al., 2019), and an SKRgram method based on improved Gini index (CN 107525672B), etc. All of them are based on advanced signal processing methods to extract repetitive impact characteristics of weak faults of planetary bearings, and identify the location of planetary bearing faults by detecting the weak fault characteristic frequency corresponding to the local fault of the planetary bearing.

[0004] However, the existing planetary bearing intelligent fault diagnosis methods still have the following disadvantages:

[0005] 1) Too much reliance on accurate identification of weak fault characteristic frequencies;

[0006] 2) It is susceptible to manufacturing errors and interference, which makes it difficult to achieve robust intelligent identification of the health status of planetary bearings.

[0007] Therefore, there is an urgent need for a robust planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning that does not rely on the identification of weak fault characteristic frequencies. Summary of the invention

[0008] The present invention provides a planetary bearing intelligent fault diagnosis method, system, electronic device and storage medium based on enhanced dictionary learning, so as to overcome at least one technical problem existing in the prior art.

[0009] To achieve the above object, the present invention provides a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, the method comprising:

[0010] Collect vibration data of the planetary bearing to be tested;

[0011] Determining a sample to be tested according to the collected vibration data of the planetary bearing to be tested;

[0012] Determine the sparse coding of the sample to be detected for the optimized sub-dictionary matrix of the different planetary bearing health states according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of the different planetary bearing health states; and determine the sparse reconstruction error of the sample to be detected according to the optimized sub-dictionary matrix of the different planetary bearing health states and the sparse coding;

[0013] The minimum sparse reconstruction error of the sample to be detected is determined through an intelligent health status identification strategy based on the minimum sparse reconstruction error discrimination criterion; and the health status of the planetary bearing to be detected is determined according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0014] Further, preferably, the step of determining the minimum sparse reconstruction error of the sample to be detected by a health state intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determining the health state of the planetary bearing to be detected according to the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error is implemented by the following formula:

[0015]

[0016] Among them, label(z i ) is the signal to be detected z i Health status category label; is the sparse reconstruction error; z i is the signal to be detected; To optimize the sub-dictionary matrix; is the signal to be detected z i About Optimizing Sub-Dictionary Matrix Sparse coding; where l = 1, 2, ..., L; L is the type of health status of the planetary bearing.

[0017] Further, preferably, the method for obtaining the optimized sub-dictionary matrix includes:

[0018] Obtain vibration data of planetary bearings under different operating health conditions and form a training vibration data set;

[0019] Performing data set enhancement on the training vibration data set by using an overlapping segmentation strategy to determine a training signal matrix corresponding to the health state of each planetary bearing;

[0020] Using the training signal matrix corresponding to each planetary bearing health state, an initialization sub-dictionary matrix is ​​constructed; until the health state index value of the initialization sub-dictionary matrix is ​​equal to the type of the planetary bearing health state;

[0021] The K-SVD dictionary learning algorithm is used to iteratively update the initialized sub-dictionary matrix, and obtain the optimized sub-dictionary matrix corresponding to the health status of each planetary bearing.

[0022] Further, preferably, the method of iteratively updating the initialized sub-dictionary matrix using the K-SVD dictionary learning algorithm and obtaining the optimized sub-dictionary matrix corresponding to the health state of each planetary bearing includes:

[0023] Set the current health status index value l to 1;

[0024] Set the current number of iterations J to 1;

[0025] The current sub-dictionary matrix corresponding to the health state is fixed, and the orthogonal matching pursuit algorithm is used to obtain the current sparse coding matrix of the training signal matrix corresponding to the health state to the current sub-dictionary matrix corresponding to the health state;

[0026] The current sub-dictionary matrix and the current sparse coding matrix are updated based on the optimization objective function of the sub-dictionary learning to obtain the updated current optimized sub-dictionary matrix corresponding to the health state of the planetary bearing;

[0027] Update the current number of iterations J=J+1, repeat the above sparse coding and dictionary updating steps until the current number of iterations J reaches the set number of iterations, and obtain the final optimized sub-dictionary matrix corresponding to the health status of the planetary bearing;

[0028] Update the current health status index value l=l+1, repeat the above steps until the health status index value l is equal to the type L of the planetary bearing health status, and obtain the final optimized sub-dictionary matrix corresponding to each planetary bearing health status;

[0029] Among them, the method for updating the optimization objective function based on sub-dictionary learning for the current sub-dictionary matrix and the current sparse coding matrix includes updating the dictionary atoms of the current sub-dictionary matrix column by column and updating the sparse coding coefficients corresponding to the dictionary atoms in the current sparse coding matrix row by row.

[0030] Further, preferably, the optimized sub-dictionary matrix corresponding to each planetary bearing health state is obtained by the following formula:

[0031] For l=1,2,…,L,

[0032]

[0033] Among them, Y l is the training signal matrix corresponding to the planetary bearing health state l, is the training signal matrix Y l The optimized sub-dictionary matrix for sparse representation, is the training signal matrix Y l The optimized sparse coding matrix for sparse representation, D l =[d l,1 ,…,d l,k ,…,d l,K ], X l =[x l,1 ,…,x l,n ,…,x l,N ], K is the dictionary size, T is the sparse threshold, and L is the type of planetary bearing health status.

[0034] Further, preferably, the training vibration data set is enhanced by using an overlapping segmentation strategy to determine the training signal matrix corresponding to the health state of each planetary bearing, which is achieved by the following formula:

[0035] For l = 1, 2, ..., L, Y l =Γ(y l )=[Γ1(y l ),…,Γ n (y l ),…,Γ N (y l )]∈R W×N .

[0036] Among them, {y l}(l=1,...,L) is the training vibration data set corresponding to the health state l of the planetary bearing, L is the type of health state of the planetary bearing, Γ:R 1×m →R W×N is the overlapping segmentation operator, N is the training signal matrix Y l The number of columns is , and W is the window length parameter.

[0037] Further, preferably, according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states, the sparse coding of the optimized sub-dictionary matrix of the sample to be detected for the different planetary bearing health states is determined, which is achieved by the following formula:

[0038] For l=1,2,…,L,

[0039] Among them, zi For the samples to be tested, To optimize the sub-dictionary matrix, is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse coding of , T is the sparse threshold, and L is the type of health status of the planetary bearing.

[0040] Further, preferably, the sparse reconstruction error of the sample to be detected is determined according to the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states, which is achieved by the following formula:

[0041] For l=1,2,…,L,

[0042] Among them, z i For the samples to be tested, To optimize the sub-dictionary matrix, is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse coding of is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse reconstruction error is , and L is the type of health status of the planetary bearing.

[0043] In order to solve the above problems, the present invention also provides a planetary bearing intelligent fault diagnosis system based on enhanced dictionary learning, comprising:

[0044] A collection unit, used for collecting vibration data of the planetary bearing to be tested;

[0045] A data processing unit is used to determine a sample to be detected based on the collected vibration data of the planetary bearing to be detected; determine the sparse coding of the sample to be detected for the optimized sub-dictionary matrix of the different planetary bearing health states according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of the different planetary bearing health states; and determine the sparse reconstruction error of the sample to be detected according to the optimized sub-dictionary matrix of the different planetary bearing health states and the sparse coding;

[0046] The planetary bearing health status determination unit is used to determine the minimum sparse reconstruction error of the sample to be detected through a health status intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determine the health status of the planetary bearing to be detected according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0047] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0048] a memory storing at least one instruction; and

[0049] The processor executes the instructions stored in the memory to implement the steps in the above-mentioned planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning.

[0050] The present invention discloses a planetary bearing intelligent fault diagnosis method, system, electronic device and storage medium based on enhanced dictionary learning, which collects vibration data of a planetary bearing to be detected; determines a sample to be detected according to the collected vibration data of the planetary bearing to be detected; determines the sparse coding of the optimized sub-dictionary matrix of the sample to be detected for different planetary bearing health states according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states; and determines the sparse reconstruction error of the sample to be detected according to the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states; determines the minimum sparse reconstruction error of the sample to be detected through a health state intelligent identification strategy based on a minimum sparse reconstruction error discrimination criterion; and determines the health state of the planetary bearing to be detected according to the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error; and has the following beneficial effects:

[0051] 1) By proposing a planetary bearing fault diagnosis method based on enhanced dictionary learning-sparse classification, the robust intelligent identification of the health status of the planetary bearing can be achieved without relying on the identification of the weak characteristic frequency of the local fault of the planetary bearing;

[0052] 2) By adopting a sub-dictionary learning algorithm that considers the health status, the optimized sub-dictionary of the sparse representation of the training data of different planetary bearing health statuses is adaptively learned in a data-driven manner, which enhances the reconstruction function of the optimized sub-dictionary and achieves the technical effect of intelligent diagnosis of the health status of planetary bearings while having good anti-noise robustness;

[0053] 3) By adopting the intelligent identification strategy of health status based on the minimum discrimination criterion of sparse reconstruction error, the different health status of planetary bearings can be accurately identified, achieving the technical effect of not relying on any explicit classifier model and getting rid of the cumbersome feature engineering design and selection steps;

[0054] 4) It is particularly suitable for intelligent identification of the health status of planetary bearings under constant operating conditions, and can accurately identify the health status of different planetary bearings. It overcomes the shortcomings of traditional methods that rely on accurate identification of weak fault characteristic frequencies, are susceptible to manufacturing errors and interference, and are difficult to achieve robust intelligent identification of the health status of planetary bearings, providing technical support for fault diagnosis and health management of mechanical equipment containing planetary transmission systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1A schematic diagram of a flow chart of a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention;

[0056] Figure 2 A schematic diagram of the principle of a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention;

[0057] Figure 3 This is a planetary bearing health status recognition effect diagram of a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention;

[0058] Figure 4 It is a diagram showing the anti-noise performance of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention;

[0059] Figure 5 A comparison diagram of the diagnostic accuracy of a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention;

[0060] Figure 6 A logical structure block diagram of a planetary bearing intelligent fault diagnosis system based on enhanced dictionary learning according to an embodiment of the present invention;

[0061] Figure 7 The figure is a schematic diagram of the internal structure of an electronic device for implementing a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention.

[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0064] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system of simulating, extending and expanding human intelligence, perceiving the environment, acquiring knowledge and using knowledge to obtain the best results using digital computers or machines controlled by digital computers. Basic artificial intelligence technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology in the present invention is spectrum integrated sparse recognition technology.

[0065] Glossary:

[0066] Sparse representation uses a matrix of M rows and N columns to represent the data set Y. Each column represents a sample and each row represents an attribute of the sample. Generally speaking, the matrix is ​​dense, that is, most elements are not 0. Sparse representation means finding a coefficient matrix X (K rows and N columns) and a dictionary matrix D (M rows and K columns) so that the matrix product DX restores Y as much as possible and X is as sparse as possible. X is the sparse representation coefficient matrix of Y.

[0067] Dictionary Learning: Given a sample data set X, each column of X represents a sample. The goal of dictionary learning is to decompose the X matrix into D and Z matrices while satisfying the constraints: Z is as sparse as possible, and each column of D is a normalized vector. D is called a dictionary, and each column of D is called an atom. Z is called an encoding vector, feature, or coefficient matrix.

[0068] K-SVD dictionary learning algorithm, K-SVD can be seen as a generalized form of K-means; in K-SVD, each signal is represented by a linear combination of multiple atoms; K-SVD constructs a dictionary to sparsely represent the data. The algorithm solution idea is to alternately iterate the two steps of sparse coding and dictionary update; in the dictionary construction step, K-SVD not only updates the atoms in sequence, but also modifies the row vectors in the sparse coding matrix corresponding to the atoms in sequence; a new atom and a modified coefficient vector are obtained.

[0069] Specifically, as an example, Figure 1 A schematic diagram of a flow chart of a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning provided by an embodiment of the present invention. Figure 1 As shown, the present invention provides a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, which can be executed by a device, and the device can be implemented by software and / or hardware. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning includes: steps S110 to S140.

[0070] Specifically, S110, collecting vibration data of the planetary bearing to be tested; S120, determining the sample to be tested based on the collected vibration data of the planetary bearing to be tested; S130, determining the sparse coding of the optimized sub-dictionary matrix of the sample to be tested for different planetary bearing health states based on the sample to be tested and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states; and determining the sparse reconstruction error of the sample to be tested based on the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states; S140, determining the minimum sparse reconstruction error of the sample to be tested through a health state intelligent identification strategy based on the minimum discrimination criterion of the sparse reconstruction error; and determining the health state of the planetary bearing to be tested based on the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0071] Figure 2 FIG. 1 is a schematic diagram of the principle of a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention; Figure 2 As shown, the existing technology has problems such as relying on accurate identification of weak fault characteristic frequencies, being susceptible to manufacturing errors and interference, and difficulty in realizing robust intelligent identification of the health status of planetary bearings in scenarios with complex rotating mechanical structures. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning of the present invention includes three parts: 1. data collection; 2. sub-dictionary learning considering health status; 3. intelligent diagnosis strategy based on sparse reconstruction error.

[0072] Specifically, in the data collection process, training data sets and test data sets are obtained by obtaining mechanical equipment in different operating health states; in the specific execution process, a vibration acceleration sensor is installed on the housing of the planetary transmission system, and the vibration acceleration sensor is used to collect data under different planetary bearing health states to form a data set; and the data set is divided into a training data set and a test data set.

[0073] In the process of constructing training samples and test samples, the training vibration data set is enhanced by using overlapping segmentation strategy to construct training signal samples {y l}, and then obtain the training signal matrix {Y l}; L is the type of health status. The test data set is constructed into test signal samples {z i}.

[0074] In the design process of sub-dictionary learning considering the health status, the initialization sub-dictionary matrix is ​​constructed based on the training signal matrix, and then the optimized sub-dictionary matrix of the sparse representation of the training data of the health status of different planetary bearings is adaptively learned in a data-driven manner. The initialization sub-dictionary matrix is ​​continuously constructed based on the training signal matrix, and the current sub-dictionary matrix is ​​optimized to the optimized sub-dictionary matrix until the health status index value l=L of the optimized sub-dictionary matrix, and finally L optimized sub-dictionary matrices are output. Specifically, set the health status index value l = 1; construct the optimized sub-dictionary matrix Whether to continue to construct the optimized sub-dictionary matrix is ​​determined by whether the health status index value l is equal to the type L of the planetary bearing health status; if the optimized sub-dictionary matrix The health status index value l = L, then stop constructing the optimized sub-dictionary matrix And output L optimized sub-dictionary matrices If the sub-dictionary matrix is ​​optimized If the health status index value l<L, then update the health status index value l=l+1, and return to step 1 to construct the optimized sub-dictionary matrix It should be noted that when constructing the optimized sub-dictionary matrix In the process, we need to first train the signal matrix Y based on the health state l. l Construct and initialize the sub-dictionary matrix Then, the K-SVD dictionary learning algorithm is used to initialize the sub-dictionary matrix Perform iterative optimization and set the number of iterations to J = 1; first, the current sub-dictionary matrix Fix it and use the orthogonal matching pursuit algorithm to obtain the current sparse coding matrix of the training signal matrix for the current sub-dictionary matrix Then use the SVD algorithm to calculate the current sub-dictionary matrix The dictionary atoms are updated column by column, and the sparse coding coefficients corresponding to the dictionary atoms are updated row by row; the current sub-dictionary matrix and the current sparse coding matrix are iteratively updated based on the optimization objective function of sub-dictionary learning until the current number of iterations J reaches the set number of iterations J max , obtain the final optimized sub-dictionary matrix corresponding to the planetary bearing health state l

[0075] In the intelligent diagnosis process based on sparse reconstruction error, the signal sample z i About all L optimized sub-dictionary matrices Sparse coding Calculate the test signal z i The optimized sub-dictionary matrix for the health status of all L specific planetary bearings The sparse reconstruction error Specifically, set the health status index value l = 1; continuously calculate the signal to be tested z i Optimized sub-dictionary matrix for planetary bearing health status Sparse coding and sparse reconstruction error Until the signal to be tested z i The sparse reconstruction error The health status index value l = L, and finally outputs the test signal z i The L sparse reconstruction errors That is to say, whether the health status index value l is equal to L is used to determine whether to continue calculating the optimized sub-dictionary matrix of the signal to be tested sparse coding and sparse reconstruction errors; if the health state index value of the sparse reconstruction error l = L, then stop the calculation and output the L sparse reconstruction errors of the signal to be tested with respect to all optimized sub-dictionary matrices; if the health state index value of the sparse reconstruction error l < L, then update the health state index value l = l + 1, and return to the step to calculate the optimized sub-dictionary matrix of the signal to be tested with respect to the health state l of the planetary bearing Sparse coding and sparse reconstruction errors.

[0076] Finally, in the process of intelligent identification of health status, the minimum sparse reconstruction error of the signal sample to be tested is determined according to the intelligent identification strategy of health status based on the minimum discrimination criterion of sparse reconstruction error; the health status class label of the signal sample to be tested is obtained according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error, and then the health status of the signal to be tested of the planetary bearing is identified through the health status class label of the test signal sample.

[0077] In a specific implementation process, the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning includes: steps S110 to S140.

[0078] S110, collecting vibration data of the planetary bearing to be tested.

[0079] S120 . Determine a sample to be tested according to the collected vibration data of the planetary bearing to be tested.

[0080] Adopting the overlapping segmentation strategy, the samples to be tested {z i}.

[0081] Test signal sample z i The expression is as follows:

[0082] z i =Γ i (z) = z T (i start :i end )∈RW×1

[0083] Among them, index i start with i end is determined as follows:

[0084]

[0085]

[0086] in, is the floor operator; Γ:R 1×m →R W×N is the overlapping segmentation operator; W is the window length parameter; δ is the overlapping rate parameter.

[0087] S130. Determine the sparse coding of the optimized sub-dictionary matrix of the sample to be detected for different planetary bearing health states according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states; and determine the sparse reconstruction error of the sample to be detected according to the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states.

[0088] By adopting a sub-dictionary learning algorithm that takes the health status into consideration, the optimized sub-dictionary of the sparse representation of the training data of different planetary bearing health statuses is adaptively learned in a data-driven manner, which enhances the reconstruction function of the optimized sub-dictionary and achieves the technical effect of intelligent diagnosis of the health status of planetary bearings while having good noise robustness.

[0089] The method for obtaining the optimized sub-dictionary matrix includes steps S131 to S134.

[0090] S131. Obtain vibration data of the planetary bearing under different operating health conditions and form a training vibration data set.

[0091] S132: Performing data set enhancement on the training vibration data set by using an overlapping segmentation strategy to determine a training signal matrix corresponding to the health status of each planetary bearing.

[0092] In the specific implementation process, the overlapping segmentation strategy is first set; the appropriate window length parameter W and overlap rate parameter δ are selected, and the segmentation operator Γ of the one-dimensional vibration signal is designed. n :R 1×m →R W×1 With the overlap partition operator Γ:R 1×m →R W×N ;

[0093] Γ=[Γ1,…,Γ n ,…,Γ N ]

[0094] Partition operator Γn Realize the one-dimensional vibration signal y∈R 1×m (m is the data length of the vibration signal y) is extracted from a specific data segment, i.e., Γ n (y) = y T (i n,start :i n,end ); Overlapping segmentation operator Γ realizes one-dimensional vibration signal y∈R 1×m Transformation to a two-dimensional health state matrix.

[0095] Specifically, the index i start with i end is determined as follows:

[0096]

[0097]

[0098] in, is the floor operator.

[0099] Then, the overlapping segmentation strategy is used to train the vibration data set {y l}(l=1,...,L) is enhanced to construct the training signal matrix Y under L different planetary bearing health conditions l The different planetary bearing health states may include planetary bearing normal, planetary bearing outer ring fault, planetary bearing inner ring fault, and planetary bearing rolling element fault.

[0100] The training vibration data set is enhanced by using an overlapping segmentation strategy to determine the training signal matrix corresponding to the health status of each planetary bearing, which is achieved by the following formula:

[0101] For l = 1, 2, ..., L, Y l =Γ(y l )=[Γ1(y l ),…,Γ n (y l ),…,Γ N (y l )]∈R W×N ,

[0102] Among them, {y l}(l=1,...,L) is the training vibration data set corresponding to the health state l of the planetary bearing, L is the type of health state of the planetary bearing, Γ:R 1×m →R W×N is the overlapping segmentation operator, N is the training signal matrix Y l The number of columns is , and W is the window length parameter.

[0103] The number of columns N of the training signal matrix is ​​determined by the following formula:

[0104]

[0105] Among them, round(·) is the rounding operator, is the floor operator.

[0106] S133, constructing an initialization sub-dictionary matrix using the training signal matrix corresponding to each planetary bearing health state; until the health state index value of the initialization sub-dictionary matrix is ​​equal to the type of the planetary bearing health state.

[0107] In the specific implementation process, the training signal matrix corresponding to the health status of each planetary bearing is used to construct the initialization sub-dictionary matrix, that is, the training signal matrix Y corresponding to the health status of each planetary bearing is l Perform column-by-column L2 norm normalization to initialize L initialization sub-dictionary matrices for specific health states This is achieved through the following formula:

[0108] For l=1,2,,…,L,

[0109] Among them, normalize(·) means to perform L2 norm normalization operation on the matrix column by column.

[0110] S134, using the K-SVD dictionary learning algorithm, iteratively updating the initialized sub-dictionary matrix, and obtaining the optimized sub-dictionary matrix corresponding to the health status of each planetary bearing.

[0111] In general, it is a process of learning the optimized sub-dictionary matrix of the sparse representation of the training data set under different planetary bearing health states by using a sub-dictionary learning algorithm that considers the health state.

[0112] The optimized sub-dictionary matrix corresponding to the health status of each planetary bearing is obtained by the following formula:

[0113] For l=1,2,…,L,

[0114]

[0115] Among them, Y l is the training signal matrix corresponding to the planetary bearing health state l, is the training signal matrix Y l The optimized sub-dictionary matrix for sparse representation, is the training signal matrix Y l The optimized sparse coding matrix for sparse representation, D l =[d l,1 ,…,d l,k,…,d l,K ], X l =[x l,1 ,…,x l,n ,…,x l,N ], K is the dictionary size, T is the sparse threshold, and L is the type of planetary bearing health status.

[0116] Specifically, the K-SVD dictionary learning algorithm includes the following two subroutines: sparse coding and dictionary updating. In a specific embodiment, the method of iteratively updating the initialized sub-dictionary matrix and obtaining the optimized sub-dictionary matrix corresponding to the health status of each planetary bearing using the K-SVD dictionary learning algorithm includes steps S1341 to S1346.

[0117] S1341. Set the current health status index value l to 1.

[0118] S1342. Set the current number of iterations J to 1.

[0119] S1343. Fix the current sub-dictionary matrix corresponding to the health state, and use the orthogonal matching pursuit algorithm to obtain the current sparse coding matrix of the training signal matrix corresponding to the health state to the current sub-dictionary matrix corresponding to the health state.

[0120] That is to say, fix the current sub-dictionary matrix The orthogonal matching pursuit algorithm is used to solve the training signal matrix Y l Sparse coding That is, solve the following sparse coding problem:

[0121] fixed

[0122] S1344. Update the current sub-dictionary matrix and the current sparse coding matrix based on the optimization objective function of sub-dictionary learning to obtain an updated current optimized sub-dictionary matrix corresponding to the health status of the planetary bearing.

[0123] Among them, the method for updating the optimization objective function based on sub-dictionary learning for the current sub-dictionary matrix and the current sparse coding matrix includes updating the dictionary atoms of the current sub-dictionary matrix column by column and updating the sparse coding coefficients corresponding to the dictionary atoms in the current sparse coding matrix row by row.

[0124] In the specific implementation process, update the column d in the current sub-dictionary matrix column by column l,k (i.e. dictionary atom), and updates the current sparse coding matrix row by row with the dictionary atom d l,k The corresponding sparse coding coefficients Among them, the optimization objective function of sub-dictionary learning can be rewritten as:

[0125]

[0126] in, is the current sparse coding matrix By fixing E l,k , you can optimize and update the column d of the current sub-dictionary matrix column by column l,k And optimize and update the corresponding sparse coding coefficients row by row

[0127] It should be noted that in the specific implementation process, in order to maintain sparse coding The sparse structure of The non-zero elements of is the sparse coding coefficient The non-zero part of For E l,k Ignore and The result of the column corresponding to the zero element of . Then, the dictionary atom d l,k With sparse coding The optimization problem can be simplified as:

[0128]

[0129] It should be noted that the above formula is a matrix rank 1 optimization problem, and its closed-form solution can be obtained by the matrix The singular value decomposition SVD is obtained.

[0130] If you remember The singular value decomposition of Then the dictionary atom d l,k With sparse coding It can be updated as follows:

[0131] d l,k =U(:,1),

[0132] In summary, the dictionary atoms d can be optimized column by column from column 1 to column K. l,k , and finally get the updated current sub-dictionary matrix

[0133] S1345, update the current number of iterations J = J + 1, repeat the above two subroutines of sparse coding and dictionary updating (i.e. S1343 and S1344) until the current number of iterations J reaches the set maximum number of iterations J max , output the final optimized sub-dictionary matrix corresponding to the planetary bearing health state l

[0134] S1346. Update the current health status index value l=l+1, repeat the above steps S1343, S1344 and S1345 until the health status index value l is equal to the type L of the planetary bearing health status, and obtain the final optimized sub-dictionary matrix corresponding to each planetary bearing health status.

[0135] After determining the L optimized sub-dictionary matrices corresponding to each planetary bearing health state, L sparse codes of the optimized sub-dictionary matrices corresponding to the L different planetary bearing health states of the sample to be detected are determined; and based on the optimized sub-dictionary matrices of the L different planetary bearing health states and the L sparse codes, L sparse reconstruction errors of the sample to be detected are determined.

[0136] According to the sample to be detected and the pre-acquired optimized sub-dictionary matrices of L different planetary bearing health states, L sparse codes of the optimized sub-dictionary matrices of the sample to be detected for the L different planetary bearing health states are determined, which is implemented by the following formula:

[0137] For l=1,2,…,L,

[0138] Among them, z i For the samples to be tested, is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse coding of To optimize the sub-dictionary matrix, T is the sparse threshold and L is the type of health status of the planetary bearing.

[0139] Specifically, according to the optimized sub-dictionary matrices of L different planetary bearing health states and L sparse codes, the L sparse reconstruction errors of the sample to be tested are determined, which is achieved by the following formula:

[0140] For l=1,2,…,L,

[0141] Among them, z i For the samples to be tested, To optimize the sub-dictionary matrix, is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse coding of is the sample to be tested z i About Optimizing Sub-Dictionary Matrix , and L is the type of health status of the planetary bearing.

[0142] S140. Determine the minimum sparse reconstruction error of the sample to be tested through an intelligent health status identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determine the health status of the planetary bearing to be tested according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0143] By adopting an intelligent health status identification strategy based on the sparse reconstruction error minimum discrimination criterion, the different health states of planetary bearings can be accurately identified, achieving a technical effect without relying on any explicit classifier model and getting rid of tedious feature engineering design and selection steps.

[0144] The step of determining the minimum sparse reconstruction error of the sample to be detected by a health state intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determining the health state of the planetary bearing to be detected according to the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error is implemented by the following formula:

[0145]

[0146] Among them, label(z i ) is the signal to be detected z i Health status category label; is the sparse reconstruction error; z i is the signal to be detected; To optimize the sub-dictionary matrix; is the signal to be detected z i About Optimizing Sub-Dictionary Matrix Sparse coding; where l = 1, 2, ..., L; L is the type of health status of the planetary bearing.

[0147] Taking the planetary gearbox model NGW11-10 as an example, by installing a vibration acceleration sensor on the housing of the planetary gearbox, the vibration data acquisition system is used to obtain the training vibration data set and the test vibration data set with unknown health status of the planetary gearbox under L types (L=4) of different health states (including normal planetary bearing, planetary bearing outer ring fault, planetary bearing inner ring fault, and planetary bearing rolling element fault). The input shaft speed of the planetary gearbox is 1500 rpm, and the sampling frequency and sampling time of the training and test vibration data signals are 25600 Hz and 30 seconds respectively.

[0148] Figure 3 : is a planetary bearing health status recognition effect diagram of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention; Figure 3As shown, the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning of the embodiment of the present invention can effectively and accurately identify the true health status of a total of 4040 test samples of 4 different planetary bearing health states, that is, the diagnostic accuracy for the 4 different planetary bearing health states can reach 100%, 100%, 100% and 99.90% respectively, which fully demonstrates the superior diagnostic performance of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning provided by the present invention in realizing planetary bearing fault diagnosis.

[0149] Figure 4-5 The diagnostic effect of the planetary bearing intelligent fault diagnosis method (SLBC) based on enhanced dictionary learning in the embodiment of the present invention is described in comparison with the diagnostic effect of the planetary bearing intelligent fault diagnosis method in the prior art; wherein the prior art respectively adopts the enhanced sparse representation intelligent recognition method ESRIR, the sparse representation classification method based on dictionary learning DL-SRC, the sparse representation classification method based on discriminant dictionary learning DDL-SRC and the deep neural network method DCNN. Specifically, Figure 4 It is a diagram showing the anti-noise performance of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention; Figure 5 This is a comparison chart of the diagnostic accuracy of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to an embodiment of the present invention.

[0150] like Figure 4 As shown, by adding random Gaussian white noise to the training data set and the test signal data set at the same time, when the signal-to-noise ratio is -5dB, 0dB, 5dB, and 10dB respectively after adding Gaussian white noise to the data set, the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning in the embodiment of the present invention can still achieve an overall average diagnostic accuracy of 96.29%, 99.68%, 99.98% and 99.98% respectively, reflecting the strong anti-noise robustness of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning provided by the present invention in realizing planetary bearing fault diagnosis.

[0151] like Figure 5As shown, by comparing the diagnostic accuracy of the planetary bearing intelligent fault diagnosis method (SLBC) based on enhanced dictionary learning in the embodiment of the present invention with the enhanced sparse representation intelligent recognition method ESRIR, the sparse representation classification method DL-SRC based on dictionary learning, the sparse representation classification method DDL-SRC based on discriminant dictionary learning, and the deep neural network method DCNN in the prior art, it can be found that the planetary bearing intelligent fault diagnosis method (SLBC) based on enhanced dictionary learning in the embodiment of the present invention can achieve the highest diagnostic accuracy for the identification of each planetary bearing health state, and the overall average diagnostic accuracy is as high as 99.98%, which reflects the superiority of the diagnostic accuracy of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning provided by the present invention in planetary bearing fault diagnosis.

[0152] In summary, the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning of the present invention can realize robust intelligent identification of the health status of the planetary bearing without relying on the identification of the weak characteristic frequency of the local fault of the planetary bearing; firstly, by adopting the sub-dictionary learning algorithm considering the health status, the optimized sub-dictionary of the sparse representation of the training data of different planetary bearing health statuses is adaptively learned in a data-driven manner, the reconstruction function of the optimized sub-dictionary is enhanced, and the intelligent diagnosis of the health status of the planetary bearing is achieved while having good anti-noise robustness; secondly, by adopting the health status intelligent identification strategy based on the minimum discrimination criterion of sparse reconstruction error, the planetary bearing intelligent fault diagnosis method can be realized. The invention discloses a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, which can accurately identify different health states of planetary bearings, and achieves the technical effect of not relying on any explicit classifier model and getting rid of cumbersome feature engineering design and selection steps; the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning of the invention is particularly suitable for intelligent identification of the health state of planetary bearings under constant operating conditions, and can accurately identify the health states of different planetary bearings; it overcomes the shortcomings of traditional methods that rely on accurate identification of weak fault characteristic frequencies, are susceptible to manufacturing errors and interferences, and are difficult to achieve robust intelligent identification of the health state of planetary bearings, and provides technical support for fault diagnosis and health management of mechanical equipment containing planetary transmission systems.

[0153] Corresponding to the above-mentioned planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, the present invention also provides a planetary bearing intelligent fault diagnosis system based on enhanced dictionary learning. Figure 6 The functional modules of the planetary bearing intelligent fault diagnosis system based on enhanced dictionary learning according to an embodiment of the present invention are shown.

[0154] like Figure 6As shown, the planetary bearing intelligent fault diagnosis system 600 based on enhanced dictionary learning provided by the present invention can be installed in an electronic device. According to the functions implemented, the planetary bearing intelligent fault diagnosis system 600 based on enhanced dictionary learning can include an acquisition unit 610, a data processing unit 620 and a planetary bearing health status determination unit 630. The unit described in the present invention can also be called a module, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete a fixed function, which is stored in the memory of the electronic device.

[0155] In this embodiment, the functions of each module / unit are as follows:

[0156] A collection unit 610 is used to collect vibration data of the planetary bearing to be tested;

[0157] The data processing unit 620 is used to determine the sample to be detected according to the collected vibration data of the planetary bearing to be detected; determine the sparse coding of the sample to be detected for the optimized sub-dictionary matrix of the different planetary bearing health states according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of the different planetary bearing health states; and determine the sparse reconstruction error of the sample to be detected according to the optimized sub-dictionary matrix of the different planetary bearing health states and the sparse coding;

[0158] The planetary bearing health status determination unit 630 is used to determine the minimum sparse reconstruction error of the sample to be detected through a health status intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determine the health status of the planetary bearing to be detected according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0159] More specific implementation methods of the planetary bearing intelligent fault diagnosis system based on enhanced dictionary learning provided by the present invention can refer to the above-mentioned embodiment of the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, and will not be listed one by one here.

[0160] The above-mentioned planetary bearing intelligent fault diagnosis system based on enhanced dictionary learning provided by the present invention, by proposing a planetary bearing fault diagnosis method based on enhanced dictionary learning-sparse classification, can realize robust intelligent identification of the health status of the planetary bearing without relying on the identification of the weak characteristic frequency of the local fault of the planetary bearing; by adopting a sub-dictionary learning algorithm considering the health status, the optimized sub-dictionary of the sparse representation of the training data of different planetary bearing health states is adaptively learned in a data-driven manner, the reconstruction function of the optimized sub-dictionary is enhanced, and the intelligent diagnosis of the health status of the planetary bearing is realized while having good anti-noise robustness technical effects; by The intelligent identification strategy of health status based on the minimum discrimination criterion of sparse reconstruction error can accurately identify the different health status of planetary bearings, achieving the technical effect of not relying on any explicit classifier model and getting rid of tedious feature engineering design and selection steps; it is particularly suitable for the intelligent identification of the health status of planetary bearings under constant operating conditions, and can accurately identify the health status of different planetary bearings; it overcomes the shortcomings of traditional methods that rely on the precise identification of weak fault characteristic frequencies, are susceptible to manufacturing errors and interferences, and are difficult to achieve robust intelligent identification of the health status of planetary bearings, providing technical support for fault diagnosis and health management of mechanical equipment containing planetary transmission systems.

[0161] like Figure 7 As shown, the present invention provides an electronic device 7 for a planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning.

[0162] The electronic device 7 may include a processor 70, a memory 71 and a bus, and may also include a computer program stored in the memory 71 and executable on the processor 70, such as a planetary bearing intelligent fault diagnosis program 72 based on enhanced dictionary learning.

[0163] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 71 may be an internal storage unit of the electronic device 7 in some embodiments, such as a mobile hard disk of the electronic device 7. The memory 71 may also be an external storage device of the electronic device 7 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 7. Further, the memory 71 may also include both an internal storage unit of the electronic device 7 and an external storage device. The memory 71 may not only be used to store application software and various types of data installed in the electronic device 7, such as the code of the planetary bearing intelligent fault diagnosis program based on enhanced dictionary learning, but also be used to temporarily store data that has been output or is to be output.

[0164] The processor 70 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 70 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 71 (such as a planetary bearing intelligent fault diagnosis program based on enhanced dictionary learning, etc.), and calls data stored in the memory 71 to execute various functions of the electronic device 7 and process data.

[0165] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 71 and at least one processor 70, etc.

[0166] Figure 7 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 7The structure shown does not constitute a limitation on the electronic device 7, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0167] For example, although not shown, the electronic device 7 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 70 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 7 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0168] Furthermore, the electronic device 7 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 7 and other electronic devices.

[0169] Optionally, the electronic device 7 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 7 and to display a visual user interface.

[0170] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0171] The planetary bearing intelligent fault diagnosis program 72 based on enhanced dictionary learning stored in the memory 71 in the electronic device 7 is a combination of multiple instructions. When running in the processor 70, it can achieve: collecting vibration data of the planetary bearing to be detected; determining the sample to be detected based on the collected vibration data of the planetary bearing to be detected; determining the sparse coding of the optimized sub-dictionary matrix of the sample to be detected for different planetary bearing health states based on the sample to be detected and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states; and determining the sparse reconstruction error of the sample to be detected based on the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states; determining the minimum sparse reconstruction error of the sample to be detected through a health state intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and judging the health state of the planetary bearing to be detected based on the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0172] Specifically, the specific implementation method of the processor 70 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiment is not repeated here. It should be emphasized that in order to further ensure the privacy and security of the above-mentioned planetary bearing intelligent fault diagnosis program based on enhanced dictionary learning, the above-mentioned planetary bearing intelligent fault diagnosis program based on enhanced dictionary learning is stored in the node of the blockchain where the server cluster is located.

[0173] Furthermore, if the module / unit integrated in the electronic device 7 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0174] An embodiment of the present invention further provides a computer-readable storage medium, which may be non-volatile or volatile, and stores a computer program, which, when executed by a processor, implements: collecting vibration data of a planetary bearing to be detected; determining a sample to be detected based on the collected vibration data of the planetary bearing to be detected; determining sparse coding of the optimized sub-dictionary matrix of the sample to be detected for different planetary bearing health states based on the sample to be detected and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states; and determining the sparse reconstruction error of the sample to be detected based on the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states; determining the minimum sparse reconstruction error of the sample to be detected through a health state intelligent identification strategy based on a minimum sparse reconstruction error discrimination criterion; and determining the health state of the planetary bearing to be detected based on the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

[0175] Specifically, the specific implementation method when the computer program is executed by the processor can refer to the description of the relevant steps in the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning in the embodiment, which will not be repeated here.

[0176] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0177] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0179] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0180] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0181] The blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer. Blockchain can store medical data, such as personal health records, kitchens, examination reports, etc.

[0182] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0183] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning, characterized in that: include: Collect vibration data of the planetary bearing to be tested; Adopting the overlapping segmentation strategy, the samples to be tested {z i }; where the test signal sample z i The expression is as follows: With i =Γ i (with)=with T (and start :and end )∈R W×1 Among them, index i start with i end is determined as follows: in, is the floor operator; Γ:R 1×m →R W×N is the overlapping segmentation operator; W is the window length parameter; δ is the overlapping rate parameter; Determine the sparse coding of the sample to be detected for the optimized sub-dictionary matrix of the different planetary bearing health states according to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of the different planetary bearing health states; and determine the sparse reconstruction error of the sample to be detected according to the optimized sub-dictionary matrix of the different planetary bearing health states and the sparse coding; The minimum sparse reconstruction error of the sample to be detected is determined through an intelligent health status identification strategy based on the minimum sparse reconstruction error discrimination criterion; and the health status of the planetary bearing to be detected is determined according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

2. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning as described in claim 1, characterized in that: The step of determining the minimum sparse reconstruction error of the sample to be detected by a health state intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determining the health state of the planetary bearing to be detected according to the health state class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error is implemented by the following formula: Among them, label(z i ) is the signal to be detected z i Health status category label; is the sparse reconstruction error; z i is the signal to be detected; To optimize the sub-dictionary matrix; is the signal to be detected z i About Optimizing Sub-Dictionary Matrix Sparse coding; where l = 1, 2, ..., L; L is the type of health status of the planetary bearing.

3. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to claim 1, characterized in that: The method for obtaining the optimized sub-dictionary matrix includes: Obtain vibration data of planetary bearings under different operating health conditions and form a training vibration data set; Performing data set enhancement on the training vibration data set by using an overlapping segmentation strategy to determine a training signal matrix corresponding to the health state of each planetary bearing; Using the training signal matrix corresponding to each planetary bearing health state, an initialization sub-dictionary matrix is ​​constructed; until the health state index value of the initialization sub-dictionary matrix is ​​equal to the type of the planetary bearing health state; The K-SVD dictionary learning algorithm is used to iteratively update the initialized sub-dictionary matrix, and obtain the optimized sub-dictionary matrix corresponding to the health status of each planetary bearing.

4. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning as claimed in claim 3, characterized in that: The method of iteratively updating the initialized sub-dictionary matrix by using the K-SVD dictionary learning algorithm and obtaining the optimized sub-dictionary matrix corresponding to the health status of each planetary bearing includes: Set the current health status index value l to 1; Set the current number of iterations J to 1; The current sub-dictionary matrix corresponding to the health state is fixed, and the orthogonal matching pursuit algorithm is used to obtain the current sparse coding matrix of the training signal matrix corresponding to the health state to the current sub-dictionary matrix corresponding to the health state; The current sub-dictionary matrix and the current sparse coding matrix are updated based on the optimization objective function of the sub-dictionary learning to obtain the updated current optimized sub-dictionary matrix corresponding to the health state of the planetary bearing; Update the current number of iterations J=J+1, repeat the above sparse coding and dictionary updating steps until the current number of iterations J reaches the set number of iterations, and obtain the final optimized sub-dictionary matrix corresponding to the health status of the planetary bearing; Update the current health status index value l=l+1, repeat the above steps until the health status index value l is equal to the type L of the planetary bearing health status, and obtain the final optimized sub-dictionary matrix corresponding to each planetary bearing health status; Among them, the method for updating the optimization objective function based on sub-dictionary learning for the current sub-dictionary matrix and the current sparse coding matrix includes updating the dictionary atoms of the current sub-dictionary matrix column by column and updating the sparse coding coefficients corresponding to the dictionary atoms in the current sparse coding matrix row by row.

5. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning as claimed in claim 4, characterized in that: The optimized sub-dictionary matrix corresponding to the health status of each planetary bearing is obtained by the following formula: For l=1,2,…,L, Among them, Y l is the training signal matrix corresponding to the planetary bearing health state l, is the training signal matrix Y l The optimized sub-dictionary matrix for sparse representation, is the training signal matrix Y l The optimized sparse coding matrix for sparse representation, D l =[d l,1 ,…,d l,k ,…,d l,K ], X l =[x l,1 ,…,x l,n ,…,x l,N ], K is the dictionary size, T is the sparse threshold, and L is the type of planetary bearing health status.

6. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning as claimed in claim 3, characterized in that: The training vibration data set is enhanced by using an overlapping segmentation strategy to determine the training signal matrix corresponding to the health status of each planetary bearing, which is achieved by the following formula: For l = 1, 2, …, L, Y l = Γ(y l ) = [Γ1(y l ), …, Γ n (y l ), …, Γ N (y l )] ∈ R W×N . Among them, {y l }(l=1,...,L) is the training vibration data set corresponding to the health state l of the planetary bearing, L is the type of health state of the planetary bearing, Γ:R 1×m →R W×N is the overlapping segmentation operator, N is the training signal matrix Y l The number of columns is , and W is the window length parameter.

7. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to claim 1, characterized in that: According to the sample to be detected and the pre-acquired optimized sub-dictionary matrix of different planetary bearing health states, the sparse coding of the optimized sub-dictionary matrix of the sample to be detected for the different planetary bearing health states is determined, which is implemented by the following formula: For l=1,2,…,L, Among them, z i For the samples to be tested, To optimize the sub-dictionary matrix, is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse coding of , T is the sparse threshold, and L is the type of health status of the planetary bearing.

8. The planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning according to claim 1, characterized in that: According to the optimized sub-dictionary matrix and sparse coding of different planetary bearing health states, the sparse reconstruction error of the sample to be tested is determined, which is achieved by the following formula: For l=1,2,…,L, Among them, z i For the samples to be tested, To optimize the sub-dictionary matrix, is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse coding of is the sample to be tested z i About Optimizing Sub-Dictionary Matrix The sparse reconstruction error is , and L is the type of health status of the planetary bearing.

9. An intelligent fault diagnosis system for planetary bearings based on enhanced dictionary learning, characterized in that: include: A collection unit, used for collecting vibration data of the planetary bearing to be tested; The data processing unit is used to adopt an overlapping segmentation strategy to determine the sample {z i }; where the test signal sample z i The expression is as follows: With i =Γ i (with)=with T (and start :and end )∈R W×1 Among them, index i start with i end is determined as follows: in, is the floor operator; Γ:R 1×m →R W×N is an overlapping segmentation operator; W is a window length parameter; δ is an overlapping rate parameter; and according to the sample to be detected and the optimized sub-dictionary matrix of different planetary bearing health states obtained in advance, the sparse coding of the optimized sub-dictionary matrix of the sample to be detected for the different planetary bearing health states is determined; and according to the optimized sub-dictionary matrix of different planetary bearing health states and the sparse coding, the sparse reconstruction error of the sample to be detected is determined; The planetary bearing health status determination unit is used to determine the minimum sparse reconstruction error of the sample to be detected through a health status intelligent identification strategy based on the minimum sparse reconstruction error discrimination criterion; and determine the health status of the planetary bearing to be detected according to the health status class label of the optimized sub-dictionary matrix corresponding to the minimum sparse reconstruction error.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps in the planetary bearing intelligent fault diagnosis method based on enhanced dictionary learning as described in any one of claims 1 to 8.

Images