Motor bearing fault intelligent diagnosis system and method

Abstract

The invention relates to the field of motor bearing fault diagnosis, in particular to a motor bearing fault intelligent diagnosis system and method. The method comprises the following steps: performing data analysis on a vibration signal of a motor bearing accessory by adopting an artificial intelligence technology based on deep learning, extracting frequency domain feature representation of each IMF component of the vibration signal, optimizing the frequency domain feature representation based on the feature correlation of each IMF component, and further obtaining the vibration signal of the motor bearing accessory based on the full frequency domain aggregation feature of each IMF component after optimization. And the fault type of the motor bearing is intelligently identified. Therefore, early discovery and accurate diagnosis of motor bearing faults can be realized, and the stability and safety of a production system are improved.

Description

Technical Field

[0001] The present application relates to the field of motor bearing fault diagnosis, and specifically to a motor bearing fault intelligent diagnosis system and method. Background Art

[0002] In the modern industrial system, motors are the core components that drive the operation of various mechanical equipment. Their operating status is directly related to the stability and efficiency of the entire production system. As an important component of the motor, motor bearings play a key role in supporting rotating parts, reducing friction and transmitting power. However, due to the influence of various factors such as long-term operation, load changes, poor lubrication, and foreign body intrusion, motor bearings are prone to wear, cracks, looseness and other faults. If these faults are not discovered and handled in time, they will not only lead to a decline in motor performance, but may even cause serious production accidents.

[0003] Traditional motor bearing fault diagnosis methods mainly rely on manual inspection, regular maintenance and empirical judgment. These methods have the disadvantages of strong subjectivity, low efficiency, high cost and difficulty in detecting early faults. With the rapid development of Industry 4.0 and intelligent manufacturing, higher requirements are placed on the intelligence, automation and real-time performance of motor bearing fault diagnosis.

[0004] Therefore, an intelligent motor bearing fault diagnosis method is expected. Summary of the invention

[0005] This application is made in view of the above problems. One object of this application is to provide a motor bearing fault intelligent diagnosis system and method.

[0006] The embodiment of the present application provides a method for intelligent diagnosis of motor bearing faults, which includes: Acquire a vibration signal collected by a vibration sensor installed near a motor bearing; Performing CEEMDAN decomposition on the vibration signal to obtain a set of IMF components of the vibration signal; Performing frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of vibration signal IMF components; Performing feature association optimization on the set of frequency domain feature vectors of the IMF component of the vibration signal to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal; The fault type of the motor bearing is determined based on the full frequency domain aggregation characteristics of the set of frequency domain feature vectors optimized by the IMF component of the vibration signal.

[0007] For example, according to the intelligent diagnosis method for motor bearing faults of an embodiment of the present application, frequency domain feature extraction is performed on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of vibration signal IMF components, including: Each vibration signal IMF component in the set of vibration signal IMF components is respectively input into a component frequency domain feature extractor based on a 1D-CNN model to obtain a set of frequency domain feature vectors of the vibration signal IMF components.

[0008] For example, according to the intelligent diagnosis method for motor bearing faults of an embodiment of the present application, the set of frequency domain feature vectors of the vibration signal IMF component is subjected to feature association optimization to obtain a set of optimized frequency domain feature vectors of the vibration signal IMF component, including: The set of frequency domain feature vectors of the IMF component of the vibration signal is input into a feature association optimization network based on a semantic measure of endogenous correlation of a sequence to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal.

[0009] For example, according to the motor bearing fault intelligent diagnosis method of an embodiment of the present application, the set of frequency domain feature vectors of the IMF component of the vibration signal is input into a feature association optimization network based on the semantic measurement of sequence endogenous correlation to obtain the set of optimized frequency domain feature vectors of the IMF component of the vibration signal, including: Calculating a semantic association score vector between any two vibration signal IMF component frequency domain feature vectors in the set of vibration signal IMF component frequency domain feature vectors to obtain a set of vibration signal IMF component frequency domain feature semantic association score vectors; Calculating the mean vector of the set of frequency domain feature semantic association score vectors of the IMF component of the vibration signal to obtain a global representation vector of the endogenous correlation of the set; Based on the global representation vector of the set intrinsic correlation, calculating the correlation optimization factor of each vibration signal IMF component frequency domain feature vector in the set of vibration signal IMF component frequency domain feature vectors to obtain a set of correlation optimization factors; Inputting the set of association optimization factors into a Softmax activation function to obtain a set of association optimization weight factors; Taking each associated optimization weight factor in the set of associated optimization weight factors as a weight, each vibration signal IMF component frequency domain feature vector in the set of vibration signal IMF component frequency domain feature vectors is weighted respectively to obtain the set of vibration signal IMF component optimized frequency domain feature vectors.

[0010] For example, according to the motor bearing fault intelligent diagnosis method of an embodiment of the present application, the semantic association score vector between any two vibration signal IMF component frequency domain feature vectors in the set of the vibration signal IMF component frequency domain feature vectors is calculated to obtain a set of vibration signal IMF component frequency domain feature semantic association score vectors, including: Any two vibration signal IMF component frequency domain feature vectors in the set of the vibration signal IMF component frequency domain feature vectors are cascaded and multiplied by a weight coefficient matrix, and then dotted with a bias vector to obtain the vibration signal IMF component frequency domain feature semantic association score vector.

[0011] For example, according to the intelligent diagnosis method for motor bearing faults of an embodiment of the present application, based on the global representation vector of the endogenous correlation of the set, the associated optimization factor of each vibration signal IMF component frequency domain feature vector in the set of the vibration signal IMF component frequency domain feature vector is calculated to obtain a set of associated optimization factors, including: The frequency domain feature vector of the IMF component of the vibration signal and the global representation vector of the endogenous correlation of the set are multiplied by different weight coefficient vectors respectively and then added to obtain a semantic correlation coefficient; The semantic association coefficient is added with a bias parameter and then passed through a sigmoid activation function to obtain the association optimization factor.

[0012] For example, according to the intelligent diagnosis method for motor bearing faults of an embodiment of the present application, the fault type of the motor bearing is determined based on the full frequency domain aggregation characteristics of the set of frequency domain feature vectors optimized by the IMF component of the vibration signal, including: Cascading a set of optimized frequency domain feature vectors of the IMF component of the vibration signal to obtain a full frequency domain feature vector of the vibration signal; The full-frequency-domain feature vector of the vibration signal is input into a classifier-based fault diagnoser to obtain a diagnosis result, and the diagnosis result is used to represent a fault type label.

[0013] For example, according to the intelligent diagnosis method for motor bearing faults of an embodiment of the present application, the full-frequency domain feature vector of the vibration signal is input into a fault diagnostic device based on a classifier to obtain a diagnosis result, and the diagnosis result is used to represent a fault type label, including: Using the fully connected layer of the classifier-based fault diagnostic device to perform fully connected encoding on the full frequency domain feature vector of the vibration signal to obtain an encoded classification feature vector; The encoded classification feature vector is input into the Softmax classification function of the classifier-based fault diagnoser to obtain the diagnosis result.

[0014] The embodiment of the present application also provides a motor bearing fault intelligent diagnosis system, which includes: A vibration signal acquisition module, used to acquire a vibration signal collected by a vibration sensor installed on the motor bearing attachment; A signal decomposition module, used for performing CEEMDAN decomposition on the vibration signal to obtain a set of IMF components of the vibration signal; A frequency domain feature extraction module, used for performing frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of vibration signal IMF components; A feature association optimization module, used for performing feature association optimization on the set of frequency domain feature vectors of the IMF component of the vibration signal to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal; The fault type analysis module is used to determine the fault type of the motor bearing based on the full frequency domain aggregation characteristics of the set of frequency domain feature vectors optimized by the IMF component of the vibration signal.

[0015] For example, according to the intelligent diagnosis method for motor bearing faults of an embodiment of the present application, the frequency domain feature extraction module is used to: Each vibration signal IMF component in the set of vibration signal IMF components is respectively input into a component frequency domain feature extractor based on a 1D-CNN model to obtain a set of frequency domain feature vectors of the vibration signal IMF components.

[0016] According to the motor bearing fault intelligent diagnosis system and method of the embodiment of the present application, it uses artificial intelligence technology based on deep learning to perform data analysis on the vibration signal of the motor bearing accessories, extracts the frequency domain feature representation of each IMF component of the vibration signal, and optimizes it based on the feature correlation of each IMF component, and then intelligently identifies the fault type of the motor bearing based on the full frequency domain aggregation features of each optimized IMF component. In this way, early detection and accurate diagnosis of motor bearing faults can be achieved, and the stability and safety of the production system can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0018] Figure 1 A schematic diagram of the application architecture of the motor bearing fault intelligent diagnosis method in an embodiment of the present application is shown; Figure 2 A flow chart of a method for intelligent diagnosis of motor bearing faults in an embodiment of the present application is shown; Figure 3A flowchart of sub-step S540 of the motor bearing fault intelligent diagnosis method in an embodiment of the present application is shown; Figure 4 A flowchart of sub-step S550 of the motor bearing fault intelligent diagnosis method in an embodiment of the present application is shown; Figure 5 A schematic diagram of the structure of the intelligent diagnosis system for motor bearing faults in an embodiment of the present application is shown; and Figure 6 An application scenario diagram of the motor bearing fault intelligent diagnosis method in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0020] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0023] Figure 1 A schematic diagram of the application architecture of the motor bearing fault intelligent diagnosis method in an embodiment of the present application is shown, including a server 100 and a terminal device 200.

[0024] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, the data exchanged through the network can be represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0025] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.

[0026] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present application, the memory 120 may be used to store the program of the motor bearing fault intelligent diagnosis method in the embodiment of the present application.

[0027] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any one of the motor bearing fault intelligent diagnosis methods in the embodiments of the present application according to the obtained program instructions.

[0028] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.

[0029] The following is a non-restrictive description of the intelligent diagnosis method for motor bearing faults provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present application.

[0030] In response to the above technical problems, the technical concept of this application is to use artificial intelligence technology based on deep learning to perform data analysis on the vibration signal of the motor bearing accessories, extract the frequency domain feature representation of each IMF component of the vibration signal, and optimize it based on the feature correlation of each IMF component, and then intelligently identify the fault type of the motor bearing based on the full frequency domain aggregation features of each optimized IMF component. In this way, early detection and accurate diagnosis of motor bearing faults can be achieved, and the stability and safety of the production system can be improved.

[0031] Based on this, Figure 2 The flowchart of the motor bearing fault intelligent diagnosis method in the embodiment of the present application is shown. For example, the motor bearing fault intelligent diagnosis method can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 2 As shown, the intelligent diagnosis method for motor bearing faults according to the embodiment of the present application includes the following steps: S510, acquiring a vibration signal collected by a vibration sensor installed on the motor bearing accessory; S520, performing CEEMDAN decomposition on the vibration signal to obtain a set of IMF components of the vibration signal; S530, performing frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of the vibration signal IMF components; S540, performing feature association optimization on the set of frequency domain feature vectors of the vibration signal IMF components to obtain a set of optimized frequency domain feature vectors of the vibration signal IMF components; S550, determining the fault type of the motor bearing based on the full frequency domain aggregation features of the set of optimized frequency domain feature vectors of the vibration signal IMF components.

[0032] Specifically, in the technical solution of the present application, first, a vibration signal collected by a vibration sensor installed on the motor bearing attachment is obtained. It should be understood that vibration is an inevitable physical phenomenon in the operation of mechanical equipment, and the motor bearing is a key component that supports the rotating parts. Bearing failures are often accompanied by significant changes in vibration characteristics, and different types of bearing failures (such as wear, cracks, peeling, etc.) will present specific frequency components or patterns in the vibration signal, such as increased vibration amplitude, changes in frequency distribution, etc. Therefore, by monitoring the vibration signal of the bearing, the current operating status of the bearing can be directly and real-time reflected.

[0033] Considering that the vibration signal of the motor bearing often has nonlinear and non-stationary characteristics during operation, the traditional Fourier transform method is often difficult to effectively analyze its frequency domain characteristics. Therefore, in the technical solution of this application, the CEEMDAN (Ensembled Empirical Mode Decomposition Adaptive Noise) method is used to decompose the vibration signal. By gradually adding noise and step-by-step averaging, the modal aliasing and noise interference problems are effectively reduced, making the decomposition result more accurate and stable, thereby obtaining a series of intrinsic mode function (IMF) components with different frequency characteristics, so as to describe the local frequency domain characteristics of the vibration signal and provide a more accurate data basis for subsequent fault type identification.

[0034] Each vibration signal IMF component obtained after modal decomposition has different frequency components and physical meanings. In order to effectively capture its frequency domain characteristics, this application adopts a 1D-CNN (one-dimensional convolutional neural network) model as a component frequency domain feature extractor to perform feature extraction on each vibration signal IMF component in the set of vibration signal IMF components. By performing a sliding convolution operation on each vibration signal IMF component, the main distribution patterns of the frequency components in each IMF component, such as periodic vibration, harmonic vibration, etc., are mined, thereby obtaining a set of frequency domain feature vectors of the vibration signal IMF components.

[0035] Correspondingly, in step S530, frequency domain feature extraction is performed on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of vibration signal IMF component frequency domain feature vectors, including: inputting each vibration signal IMF component in the set of vibration signal IMF components into a component frequency domain feature extractor based on a 1D-CNN model to obtain a set of vibration signal IMF component frequency domain feature vectors.

[0036] Secondly, since there is an inherent correlation between the various IMF components of the vibration signal, in order to further reveal the possible resonance phenomenon or phase relationship of the frequency components in the vibration signal, the present application introduces a feature association optimization network based on the semantic measurement of the intrinsic correlation of the sequence to process the set of frequency domain feature vectors of the IMF components of the vibration signal. By considering the intrinsic correlation between the features, the frequency domain feature representation of each IMF component is optimized to enhance the accuracy of fault diagnosis. Specifically, the feature association optimization network first quantifies the similarity or difference between any two frequency domain feature vectors of the IMF components of the vibration signal by calculating the semantic association, so as to understand the semantic structure within the sequence and generate a set of semantic association score vectors. Then, the aggregate information of the set of semantic association score vectors is used as the overall context information to calculate the association optimization factor of the frequency domain feature vector of each IMF component of the vibration signal, and quantitatively describe the consistency or deviation between the frequency domain features of each IMF component and the overall semantic structure of the sequence, so as to serve as a guide for feature association optimization. Furthermore, after the associated optimization factor is normalized, it is used as a weight coefficient to perform weighted optimization on the original set of frequency domain feature vectors of the IMF component of the vibration signal, so as to reduce the interference of signal noise and redundant information and enhance the expression of important frequency component characteristics, thereby obtaining a purer and more efficient set of optimized frequency domain feature vectors of the IMF component of the vibration signal.

[0037] Correspondingly, in step S540, feature association optimization is performed on the set of frequency domain feature vectors of the IMF component of the vibration signal to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal, including: inputting the set of frequency domain feature vectors of the IMF component of the vibration signal into a feature association optimization network based on sequence intrinsic correlation semantic measurement to obtain the set of optimized frequency domain feature vectors of the IMF component of the vibration signal.

[0038] Specifically, Figure 3As shown, the set of frequency domain feature vectors of the vibration signal IMF component is input into a feature association optimization network based on the semantic measurement of sequence intrinsic correlation to obtain the set of optimized frequency domain feature vectors of the vibration signal IMF component, including: S541, calculating the semantic association score vector between any two frequency domain feature vectors of the vibration signal IMF component in the set of frequency domain feature vectors of the vibration signal IMF component to obtain a set of frequency domain feature semantic association score vectors of the vibration signal IMF component; S542, calculating the mean vector of the set of frequency domain feature semantic association score vectors of the vibration signal IMF component to obtain a global representation vector of the intrinsic correlation of the set; S543, based on the A global representation vector of the intrinsic correlation of the set is obtained, and the associated optimization factor of each vibration signal IMF component frequency domain feature vector in the set of the vibration signal IMF component frequency domain feature vector is calculated to obtain a set of associated optimization factors; S544, the set of associated optimization factors is input into the Softmax activation function to obtain a set of associated optimization weight factors; S545, each associated optimization weight factor in the set of associated optimization weight factors is used as a weight, and each vibration signal IMF component frequency domain feature vector in the set of the vibration signal IMF component frequency domain feature vector is weighted respectively to obtain a set of optimized frequency domain feature vectors of the vibration signal IMF component.

[0039] Among them, in step S541, the semantic association score vector between any two vibration signal IMF component frequency domain feature vectors in the set of the vibration signal IMF component frequency domain feature vectors is calculated to obtain a set of vibration signal IMF component frequency domain feature semantic association score vectors, including: cascading any two vibration signal IMF component frequency domain feature vectors in the set of the vibration signal IMF component frequency domain feature vectors and multiplying them by a weight coefficient matrix, and then dot-adding them with a bias vector to obtain the vibration signal IMF component frequency domain feature semantic association score vector.

[0040] Among them, in step S543, based on the global representation vector of the intrinsic correlation of the set, the association optimization factor of each vibration signal IMF component frequency domain feature vector in the set of the vibration signal IMF component frequency domain feature vector is calculated to obtain a set of association optimization factors, including: multiplying the vibration signal IMF component frequency domain feature vector and the global representation vector of the intrinsic correlation of the set by different weight coefficient vectors and then performing an addition operation to obtain a semantic association coefficient; adding a bias parameter to the semantic association coefficient and then passing it through a sigmoid activation function to obtain the association optimization factor.

[0041] In one example, the set of frequency domain feature vectors of the IMF component of the vibration signal is input into a feature association optimization network based on a semantic metric of endogenous correlation of a sequence to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal, including: processing the set of frequency domain feature vectors of the IMF component of the vibration signal with the following semantic feature association optimization formula to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal, wherein the semantic feature association optimization formula is: ;in, represents the set of frequency domain feature vectors of the IMF component of the vibration signal, and Respectively represent the first, second, and third in the set of frequency domain feature vectors of the IMF component of the vibration signal , and The frequency domain eigenvector of the IMF component of the vibration signal, The value of is the number of eigenvectors in the set of frequency domain eigenvectors of the IMF component of the vibration signal, Indicates cascade operation, is the weight coefficient matrix, is the bias vector, is the first in the set of frequency domain feature semantic association score vectors of the vibration signal IMF component The semantic association score vector of the frequency domain features of the IMF components of the vibration signal, The value of is the number of vectors in the set of semantic association score vectors, is the global representation vector of the intrinsic correlation of the set, and Represent different weight coefficient vectors, is the bias parameter, is the sigmoid activation function, is the normalized exponential function, For the The associated optimization factor, Indicates The IMF components of the vibration signal are optimized in the frequency domain.

[0042] Furthermore, in order to comprehensively reflect the full-frequency domain characteristics of the vibration signal, the present application adopts a cascade fusion method to perform feature integration on the set of optimized frequency domain feature vectors of the IMF component of the vibration signal, so as to capture the characteristic information of the vibration signal within the global frequency range, thereby obtaining the full-frequency domain feature vector of the vibration signal, so as to more comprehensively characterize the operating status of the motor bearing.

[0043] Next, the full-frequency domain feature vector of the vibration signal is input into a classifier-based fault diagnostic device to obtain a diagnosis result, and the diagnosis result is used to represent a fault type label. In the technical solution of the present application, the classifier-based fault diagnostic device can effectively learn the frequency feature patterns of the vibration signal corresponding to different fault types through training optimization, so that in practical applications, the input full-frequency domain feature vector of the vibration signal can be accurately learned and classified, and the corresponding fault type label can be output to achieve intelligent diagnosis of motor bearing faults.

[0044] Accordingly, if Figure 4 As shown, based on the full-frequency domain aggregated features of the set of frequency domain feature vectors optimized by the IMF components of the vibration signal, the fault type of the motor bearing is determined, including: S551, cascading the set of frequency domain feature vectors optimized by the IMF components of the vibration signal to obtain the full-frequency domain feature vector of the vibration signal; S552, inputting the full-frequency domain feature vector of the vibration signal into a classifier-based fault diagnoser to obtain a diagnosis result, and the diagnosis result is used to represent a fault type label.

[0045] Among them, in step S552, the full-frequency domain feature vector of the vibration signal is input into a classifier-based fault diagnoser to obtain a diagnosis result, and the diagnosis result is used to represent the fault type label, including: using the fully connected layer of the classifier-based fault diagnoser to fully connect encode the full-frequency domain feature vector of the vibration signal to obtain an encoded classification feature vector; inputting the encoded classification feature vector into the Softmax classification function of the classifier-based fault diagnoser to obtain the diagnosis result.

[0046] In a preferred example, the full-frequency domain feature vector of the vibration signal is input into a classifier-based fault diagnoser to obtain a diagnosis result, including the steps of: optimizing the full-frequency domain feature vector of the vibration signal to obtain an optimized full-frequency domain feature vector of the vibration signal; and inputting the optimized full-frequency domain feature vector of the vibration signal into the classifier-based fault diagnoser to obtain a diagnosis result.

[0047] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression, SVM, etc. are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification, but this is prone to errors and inefficient. Commonly used multi-classification methods include the Softmax classification function.

[0048] Here, considering that the set of optimized frequency domain feature vectors of the IMF components of the vibration signal respectively represents the full sample domain correlation features of the single sample domain endogenous correlation semantic measurement of the one-dimensional local correlation features of each vibration signal IMF component, when further cascade aggregation is performed, the weight excitation alignment conflict in the full sample domain will be caused due to the difference in the endogenous correlation semantic measurement between the sample domains, thereby causing classification regression offset, affecting the accuracy of the diagnosis result obtained by the fault diagnoser based on the classifier when the full frequency domain feature vector of the vibration signal is input.

[0049] Based on this, when the full-frequency domain feature vector of the vibration signal is input into the fault diagnosis device based on the classifier for classification probability regression, the full-frequency domain feature vector of the vibration signal is first optimized, and the optimization process specifically includes: Determine the mean and variance of the feature set composed of the eigenvalues ​​of the full-frequency domain eigenvector of the vibration signal, and divide the mean by the variance to obtain a probability weight ,in, and represent the mean and variance of the feature set composed of the eigenvalues ​​of the full-frequency domain eigenvector of the vibration signal, respectively, represents the probability weight; The first intermediate eigenvector is obtained by multiplying the full frequency domain eigenvector of the vibration signal by the inverse of its maximum eigenvalue. ,in, represents the full frequency domain feature vector of the vibration signal, represents the maximum eigenvalue in the full-frequency eigenvector of the vibration signal, It means point multiplication by position. represents the first intermediate eigenvector; The first intermediate feature vector is added with the probability weight and then the logarithm with the base 2 is calculated to obtain the second intermediate feature vector ;in, represents the first intermediate eigenvector, represents the probability weight, Indicates adding by position point. represents the second intermediate eigenvector; After subtracting the first intermediate eigenvector from the probability weight point, the inverse of each eigenvalue is calculated to obtain a third intermediate eigenvector ;in, represents the first intermediate eigenvector, represents the probability weight, It means to subtract by position point. represents the third intermediate eigenvector; Finally, the second intermediate eigenvector is added to the third intermediate eigenvector to obtain the optimized vibration signal full frequency domain eigenvector ,in, represents the second intermediate eigenvector, Indicates adding by position point. represents the third intermediate eigenvector, Represents the optimized full-frequency feature vector of the vibration signal.

[0050] That is, considering that when the weight matrix during classification probability regression acts on the full-frequency domain feature vector of the vibration signal, the uncertainty of the weight stimulus parameters of the weight matrix caused by the classification regression offset of the full-frequency domain feature vector of the vibration signal makes the posterior probability density inference of the full-frequency domain feature vector of the vibration signal missing through the weight matrix, which will affect the accuracy of the probability regression result. The above optimization process simulates the mesoscale interaction structure under probability constraints between the eigenvalue scale and the eigenvector scale of the full-frequency domain feature vector of the vibration signal through the probability statistical characteristics of the full-frequency domain feature vector of the vibration signal, so as to construct a bidirectional hidden variable motif based on the mesoscale short sequence relative to the probability statistical value to perform mesoscale bidirectional migration, and perform posterior recovery based on the sequence constraints on the interactive information, so as to improve the convergence effect of the full-frequency domain feature vector of the vibration signal in the probability density domain, thereby improving the accuracy of the diagnosis result obtained by the fault diagnoser based on the classifier when the full-frequency domain feature vector of the vibration signal is input.

[0051] Based on the above embodiments, see Figure 5 As shown, it is a structural schematic diagram of a motor bearing fault intelligent diagnosis system 800 in an embodiment of the present application. The motor bearing fault intelligent diagnosis system 800 includes: a vibration signal acquisition module 810, which is used to acquire a vibration signal collected by a vibration sensor installed on the motor bearing attachment; a signal decomposition module 820, which is used to perform CEEMDAN decomposition on the vibration signal to obtain a set of vibration signal IMF components; a frequency domain feature extraction module 830, which is used to perform frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of vibration signal IMF component frequency domain feature vectors; a feature association optimization module 840, which is used to perform feature association optimization on the set of vibration signal IMF component frequency domain feature vectors to obtain a set of vibration signal IMF component optimized frequency domain feature vectors; a fault type analysis module 850, which is used to determine the fault type of the motor bearing based on the full frequency domain aggregation features of the set of vibration signal IMF component optimized frequency domain feature vectors.

[0052] In one example, in the above-mentioned motor bearing fault intelligent diagnosis system 800, the frequency domain feature extraction module 830 is used to: input each vibration signal IMF component in the set of vibration signal IMF components into a component frequency domain feature extractor based on a 1D-CNN model to obtain a set of frequency domain feature vectors of the vibration signal IMF components.

[0053] Here, those skilled in the art can understand that the specific functions and operations of each module in the above-mentioned motor bearing fault intelligent diagnosis system 800 have been described in the above reference. Figures 2 to 4 The description of the intelligent diagnosis method for motor bearing faults has been introduced in detail, and therefore, its repeated description will be omitted.

[0054] Figure 6 FIG. 1 is an application scenario diagram of the motor bearing fault intelligent diagnosis method according to an embodiment of the present application. Figure 6 As shown, in this application scenario, first, a vibration signal collected by a vibration sensor installed in the motor bearing attachment is obtained (for example, Figure 6 D), and then, the vibration signal is input to a server (for example, Figure 6 In S) as shown in , the server can use the motor bearing fault intelligent diagnosis algorithm to process the vibration signal to obtain a diagnosis result for representing a fault type label.

[0055] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the motor bearing fault intelligent diagnosis method in the above embodiments can be implemented when the processor executes the program.

[0056] For example, in the case of electronic equipment Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0057] The embodiment of the present application also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the motor bearing fault intelligent diagnosis method according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0058] The embodiment of the present application also provides a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the motor bearing fault intelligent diagnosis method according to the embodiment of the present application.

[0059] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0060] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.

[0061] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0062] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0063] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.

Claims

1. An intelligent diagnosis method for motor bearing faults, characterized in that: include: Acquire a vibration signal collected by a vibration sensor installed near a motor bearing; Performing CEEMDAN decomposition on the vibration signal to obtain a set of IMF components of the vibration signal; Performing frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of vibration signal IMF components; Performing feature association optimization on the set of frequency domain feature vectors of the IMF component of the vibration signal to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal; The fault type of the motor bearing is determined based on the full frequency domain aggregation characteristics of the set of frequency domain feature vectors optimized by the IMF component of the vibration signal.

2. The intelligent diagnosis method for motor bearing fault according to claim 1 is characterized in that: Performing frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of vibration signal IMF components, including: Each vibration signal IMF component in the set of vibration signal IMF components is respectively input into a component frequency domain feature extractor based on a 1D-CNN model to obtain a set of frequency domain feature vectors of the vibration signal IMF components.

3. The intelligent diagnosis method for motor bearing fault according to claim 2 is characterized in that: Performing feature association optimization on the set of frequency domain feature vectors of the IMF component of the vibration signal to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal, including: The set of frequency domain feature vectors of the IMF component of the vibration signal is input into a feature association optimization network based on a semantic measure of endogenous correlation of a sequence to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal.

4. The intelligent diagnosis method for motor bearing fault according to claim 3 is characterized in that: Inputting the set of frequency domain feature vectors of the IMF component of the vibration signal into a feature association optimization network based on sequence endogenous correlation semantic measurement to obtain the set of optimized frequency domain feature vectors of the IMF component of the vibration signal, including: Calculating a semantic association score vector between any two vibration signal IMF component frequency domain feature vectors in the set of vibration signal IMF component frequency domain feature vectors to obtain a set of vibration signal IMF component frequency domain feature semantic association score vectors; Calculating the mean vector of the set of frequency domain feature semantic association score vectors of the IMF component of the vibration signal to obtain a global representation vector of the endogenous correlation of the set; Based on the global representation vector of the set intrinsic correlation, calculating the correlation optimization factor of each vibration signal IMF component frequency domain feature vector in the set of vibration signal IMF component frequency domain feature vectors to obtain a set of correlation optimization factors; Inputting the set of association optimization factors into a Softmax activation function to obtain a set of association optimization weight factors; Taking each associated optimization weight factor in the set of associated optimization weight factors as a weight, each vibration signal IMF component frequency domain feature vector in the set of vibration signal IMF component frequency domain feature vectors is weighted respectively to obtain the set of vibration signal IMF component optimized frequency domain feature vectors.

5. The intelligent diagnosis method for motor bearing fault according to claim 4 is characterized in that: Calculating the semantic association score vector between any two vibration signal IMF component frequency domain feature vectors in the set of vibration signal IMF component frequency domain feature vectors to obtain a set of vibration signal IMF component frequency domain feature semantic association score vectors, including: Any two vibration signal IMF component frequency domain feature vectors in the set of the vibration signal IMF component frequency domain feature vectors are cascaded and multiplied by a weight coefficient matrix, and then dotted with a bias vector to obtain the vibration signal IMF component frequency domain feature semantic association score vector.

6. The intelligent diagnosis method for motor bearing fault according to claim 5, characterized in that: Based on the global representation vector of the set intrinsic correlation, the correlation optimization factor of each vibration signal IMF component frequency domain feature vector in the set of the vibration signal IMF component frequency domain feature vector is calculated to obtain a set of correlation optimization factors, including: The frequency domain feature vector of the IMF component of the vibration signal and the global representation vector of the endogenous correlation of the set are multiplied by different weight coefficient vectors respectively and then added to obtain a semantic correlation coefficient; The semantic association coefficient is added with a bias parameter and then passed through a sigmoid activation function to obtain the association optimization factor.

7. The intelligent diagnosis method for motor bearing fault according to claim 6, characterized in that: Determining the fault type of the motor bearing based on the full frequency domain aggregation feature of the set of frequency domain feature vectors optimized by the IMF component of the vibration signal, including: Cascading a set of optimized frequency domain feature vectors of the IMF component of the vibration signal to obtain a full frequency domain feature vector of the vibration signal; The full-frequency-domain feature vector of the vibration signal is input into a classifier-based fault diagnoser to obtain a diagnosis result, and the diagnosis result is used to represent a fault type label.

8. The intelligent diagnosis method for motor bearing fault according to claim 7, characterized in that: The full frequency domain feature vector of the vibration signal is input into a fault diagnostic device based on a classifier to obtain a diagnosis result, and the diagnosis result is used to represent a fault type label, including: Using the fully connected layer of the classifier-based fault diagnostic device to perform fully connected encoding on the full frequency domain feature vector of the vibration signal to obtain an encoded classification feature vector; The encoded classification feature vector is input into the Softmax classification function of the classifier-based fault diagnoser to obtain the diagnosis result.

9. An intelligent diagnosis system for motor bearing faults, characterized in that: include: A vibration signal acquisition module, used to acquire a vibration signal collected by a vibration sensor installed on the motor bearing attachment; A signal decomposition module, used for performing CEEMDAN decomposition on the vibration signal to obtain a set of IMF components of the vibration signal; A frequency domain feature extraction module, used for performing frequency domain feature extraction on each vibration signal IMF component in the set of vibration signal IMF components to obtain a set of frequency domain feature vectors of vibration signal IMF components; A feature association optimization module, used for performing feature association optimization on the set of frequency domain feature vectors of the IMF component of the vibration signal to obtain a set of optimized frequency domain feature vectors of the IMF component of the vibration signal; The fault type analysis module is used to determine the fault type of the motor bearing based on the full frequency domain aggregation characteristics of the set of frequency domain feature vectors optimized by the IMF component of the vibration signal.

10. The motor bearing fault intelligent diagnosis system according to claim 9, characterized in that: The frequency domain feature extraction module is used to: Each vibration signal IMF component in the set of vibration signal IMF components is respectively input into a component frequency domain feature extractor based on a 1D-CNN model to obtain a set of frequency domain feature vectors of the vibration signal IMF components.

Images