Bearing fault diagnosis method and system, electronic equipment and storage medium
The characteristics of bearing vibration signals are extracted through the VMD method and combined with the deep learning network, which solves the problem of low computing efficiency in the prior art and achieves high accuracy and robust bearing fault diagnosis.
Patent Information
- Application Number
- CN202411957814.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-05-09
AI Technical Summary
The prior art has low computational efficiency when processing large data sets, especially when complex time-frequency transformation or deep learning model training is required, it is difficult to effectively diagnose bearing faults.
The VMD method is used to decompose the bearing vibration signal, extract the sample feature sequence set, and input it into the deep learning network, especially the CNN and BiLSTM networks, for rolling bearing failure diagnosis.
Through the combination of multimodal feature extraction and deep learning technology, the accuracy and robustness of the model are improved, the over-decomposition and under-decomposition problems caused by VMD parameter adjustment are solved, and the calculation efficiency of bearing fault diagnosis is significantly improved.
Smart Images
Figure CN119961782A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of fault diagnosis, and in particular relates to a bearing fault diagnosis method, system, electronic equipment and storage medium. Background Art
[0002] The ship power system is the core system of the entire ship, and its safety and reliability directly affect the safe navigation of the ship. Effective fault monitoring and diagnosis technology can prevent power system failures, thereby ensuring navigation safety. Ship rolling bearings are key components in the ship power transmission system, and their performance and life directly affect the reliability and safety of the ship. Since rolling bearings are prone to failure, even a small problem in the rolling bearing may accidentally damage the entire system. This may lead to increased maintenance and downtime costs, which significantly increase the operating costs of the machinery. Therefore, it is very important to identify bearing failures in machinery, which can improve the reliability of the system by avoiding unexpected accidents.
[0003] When a rolling bearing is working abnormally, the rolling bearing fault diagnosis can be effectively performed by collecting and analyzing the vibration signal. The vibration signal contains a wealth of equipment status symptom information. How to extract features from the original signal comprehensively and effectively has always been a hot topic for scholars at home and abroad. In recent years, some progress has been made in the research on rolling bearing fault diagnosis at home and abroad. However, the computational efficiency is low when processing large data sets, especially when complex time-frequency transformation or deep learning model training is required.
[0004] Therefore, how to provide a bearing fault diagnosis method, system, electronic device and storage medium has become a technical problem that urgently needs to be solved in this field. Summary of the invention
[0005] The purpose of the present invention is to provide a bearing fault diagnosis method, system, electronic equipment and storage medium.
[0006] According to a first aspect of the present invention, there is provided a bearing fault diagnosis method, comprising:
[0007] Step S1, using the VMD method to decompose the bearing vibration signal and extract a sample feature sequence set of the bearing vibration signal;
[0008] Step S2: input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform fault category diagnosis of the rolling bearing.
[0009] According to the method of the first aspect of the present invention, in step S1, the use of the VMD method to decompose the bearing vibration signal and extract a sample feature sequence set of the bearing vibration signal includes:
[0010]
[0011] Among them, u k represents the kth component of the K decomposed modal signals, ω k represents the centroid frequency of the kth component of the K decomposed modal signals, f represents the bearing vibration signal, δ(t) represents the Dirac function, * represents the convolution operator, and j represents the imaginary unit.
[0012] According to the method of the first aspect of the present invention, in step S1, the sparrow optimization algorithm integrating Osprey and Cauchy mutation is used to dynamically adjust the VMD method parameters according to the fitness function.
[0013] According to the method of the first aspect of the present invention, in step S2, inputting the sample feature sequence set of the bearing vibration signal into a deep learning network to perform rolling bearing fault category diagnosis includes:
[0014] Firstly, the sample feature sequence set is input into the CNN network to extract bearing fault features; then the bearing fault features are summarized by the fully connected layer and input into the BiLSTM network layer with the attention mechanism, and deep feature extraction is realized through weight allocation to obtain deep features; the deep features are used to realize the fault category diagnosis of rolling bearings through the Softmax layer classifier.
[0015] A second aspect of the present invention discloses a bearing fault diagnosis system; the system comprises:
[0016] The first processing module is configured to decompose the bearing vibration signal using a VMD method to extract a sample feature sequence set of the bearing vibration signal;
[0017] The second processing module is configured to input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform fault category diagnosis of the rolling bearing.
[0018] According to the system of the second aspect of the present invention, the first processing module is specifically configured as follows: the step of decomposing the bearing vibration signal using the VMD method to extract a sample feature sequence set of the bearing vibration signal comprises:
[0019]
[0020] Among them, u k represents the kth component of the K decomposed modal signals, ω k represents the centroid frequency of the kth component of the K decomposed modal signals, f represents the bearing vibration signal, δ(t) represents the Dirac function, * represents the convolution operator, and j represents the imaginary unit.
[0021] According to the system of the second aspect of the present invention, the first processing module is specifically configured to use a sparrow optimization algorithm that integrates Osprey and Cauchy mutations to dynamically adjust the VMD method parameters according to a fitness function.
[0022] According to the system of the second aspect of the present invention, the second processing module is specifically configured to input the sample feature sequence set of the bearing vibration signal into the deep learning network to perform fault category diagnosis of the rolling bearing, including:
[0023] Firstly, the sample feature sequence set is input into the CNN network to extract bearing fault features; then the bearing fault features are summarized by the fully connected layer and input into the BiLSTM network layer with the attention mechanism, and deep feature extraction is realized through weight allocation to obtain deep features; the deep features are used to realize the fault category diagnosis of rolling bearings through the Softmax layer classifier.
[0024] The third aspect of the present invention discloses an electronic device. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in any one of the bearing fault diagnosis methods in the first aspect of the present disclosure are implemented.
[0025] The fourth aspect of the present invention discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any one of the bearing fault diagnosis methods in the first aspect of the present disclosure are implemented.
[0026] The beneficial effects brought by the present invention are as follows:
[0027] It can be seen from the above scheme that the embodiments of the present invention provide a bearing fault diagnosis method, system, electronic device and storage medium, which have the following beneficial effects: a multimodal feature extraction method is used to more comprehensively capture the time-frequency characteristics of the bearing vibration signal and solve the over-decomposition and under-decomposition problems caused by the specified VMD parameters; CNN and BiLSTM are used for in-depth feature learning and fault diagnosis, thereby improving the accuracy and robustness of the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A flow chart of a bearing fault diagnosis method provided according to an embodiment;
[0029] Figure 2 A technical roadmap of a bearing fault diagnosis method provided according to an embodiment;
[0030] Figure 3 A diagram showing the diagnostic classification results of each sample provided in the embodiment;
[0031] Figure 4A VMD-CNN-BiLSTM fault classification identification confusion matrix provided according to an embodiment;
[0032] Figure 5 is a structural diagram of a bearing fault diagnosis system according to an embodiment of the present invention;
[0033] Figure 6 The figure is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0034] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0035] Embodiment 1:
[0036] According to a first aspect of the present invention, the present invention discloses a bearing fault diagnosis method. Figure 1 FIG. 1 is a flow chart of a bearing fault diagnosis method according to an embodiment of the present invention. Figure 1 As shown, the method includes:
[0037] Step S1, using the VMD method to decompose the bearing vibration signal and extract a sample feature sequence set of the bearing vibration signal;
[0038] Step S2: input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform fault category diagnosis of the rolling bearing.
[0039] In step S1, the bearing vibration signal is decomposed using the VMD method to extract a sample feature sequence set of the bearing vibration signal.
[0040] In some embodiments, in step S1, Figure 2 As shown in Figure 1, the pseudo bearing vibration signal f is decomposed into K components to ensure that the decomposition sequence is a modal component with a limited bandwidth and a center frequency. At the same time, the sum of the estimated bandwidths of each mode is minimized. The constraint condition is that the sum of all modes is equal to the original signal. The corresponding constrained variational expression is:
[0041]
[0042] Among them, u k represents the kth component of the K decomposed modal signals, ω kIt represents the centroid frequency of the kth component of K decomposed modal signals, f represents the bearing vibration signal, δ(t) represents the Dirac function, * represents the convolution operator, and j represents the imaginary unit. When the signal is converted from the time domain to the frequency domain, Fourier transform is usually used, and the signal is represented as the sum of complex numbers of different frequencies. j appears as an imaginary unit and is used to represent the imaginary part of the complex number.
[0043] In order to solve equation (1), the Lagrange multiplication operator λ and the quadratic penalty term are introduced to transform the constrained variational problem into an unconstrained variational problem, and the augmented Lagrange expression is obtained as follows:
[0044]
[0045] Among them, α represents the quadratic penalty factor, which is used to reduce the interference of Gaussian noise. The alternating direction multiplier method (ADMM) combined with Fourier isometric transform is used to transform the variational solution problem into an alternating solution problem of multipliers, and each modal component and center frequency are optimized. The modal signal multiplier after alternating optimization iteration is obtained. Center of gravity frequency multiplier The expression is as follows:
[0046]
[0047] Follow these steps to update each modal component:
[0048] a) Reconstruct the original signal using the current modal set;
[0049] b) demodulate each modal component and shift its frequency to baseband;
[0050] c) Calculate the gradient of the demodulated modal component and estimate its bandwidth;
[0051] d) Using gradient information to update the modal components, usually involves a variational problem to minimize the bandwidth.
[0052] Finally, the error of the decomposed modal signal is calculated for iterative calculation. After each iteration, the reduction of the objective function or other convergence criteria are checked. If the convergence condition is met, the iteration is stopped; otherwise, it returns to continue the iteration.
[0053] The sparrow optimization algorithm integrating Osprey and Cauchy mutation is used to dynamically adjust the parameters of the VMD method according to the fitness function, specifically including:
[0054] a) VMD objective function is
[0055]
[0056] Among them, u={u1,u2,…,u K} are the decomposed modal signals, ω={ω1,ω2,…,ω K} is the centroid frequency of each modal signal, Indicates u k (t) The value at a specific time t represents the specific performance of the modal component in the time domain. α represents the penalty factor.
[0057] b) BFOA Predator Position Update:
[0058]
[0059] Among them, x i is the position of the ith predator, x b is the position of the optimal predator and β is a random scaling factor.
[0060] c) SSA sparrow position update:
[0061]
[0062] Where γ is a random vector and ⊙ represents element-wise multiplication.
[0063] d) Cauchy variation:
[0064]
[0065] Among them, C is the parameter that controls the intensity of variation, k is the parameter that controls the shape of the distribution, and x j is another solution in the population.
[0066] e) Fitness calculation:
[0067]
[0068] Among them, F(x i ) is the fitness of the ith solution, and ∈ is a constant to ensure numerical stability.
[0069] The variable x in formulas (6)-(9) represents a set of solutions for the penalty factor α and the modal decomposition number K.
[0070] Update VMD parameters according to the rules of BFOA and SSA, and perform local search in combination with Cauchy mutation. After each iteration, check whether the algorithm meets the stopping conditions, such as the fitness no longer significantly improves or reaches the maximum number of iterations. Select the solution with the highest fitness in all iterations as the optimal solution for VMD parameters.
[0071] In step S2, the sample feature sequence set of the bearing vibration signal is input into a deep learning network to perform fault category diagnosis of the rolling bearing.
[0072] In some embodiments, in step S2, inputting the sample feature sequence set of the bearing vibration signal into a deep learning network to perform rolling bearing fault category diagnosis includes:
[0073] Firstly, the sample feature sequence set is input into the CNN network to extract bearing fault features; then the bearing fault features are summarized by the fully connected layer and input into the BiLSTM network layer with the attention mechanism, and deep feature extraction is realized through weight allocation to obtain deep features; the deep features are used to realize the fault category diagnosis of rolling bearings through the Softmax layer classifier.
[0074] Specific experiments: Data from 10 states under different working conditions and different fault forms are selected to verify the model proposed in this study. The comparison between the prediction results and actual results of the model under different data sets and the confusion matrix of fault classification and recognition are shown as follows: Figure 3 , Figure 4 As shown in the figure, the true category is the category to which the sample actually belongs, and the predicted category is the category to which the model predicts the sample belongs. It can be seen from the figure that the fault classification accuracy of the model proposed in this paper is 100% in 7 samples, and the accuracy of the remaining 3 samples is 96.7%, with an average accuracy of 99.33%.
[0075] In summary, the solution proposed in the present invention adopts a multimodal feature extraction method to more comprehensively capture the time-frequency characteristics of the bearing vibration signal and solve the over-decomposition and under-decomposition problems caused by the specified VMD parameters. Furthermore, the deep learning technology is combined with the signal processing technology, and preliminary feature extraction is performed through VMD, and then CNN and BiLSTM are used for in-depth feature learning and fault diagnosis, thereby improving the accuracy and robustness of the model. Adding CNN before the traditional BiLSTM model and fusing the spatial features extracted by CNN and the temporal features extracted by BiLSTM through the cross-attention mechanism can improve the prediction accuracy of the fused feature data. According to actual application cases, compared with the CNN-LSTM, CNN-BiLSTM and VMD-CNN-LSTM models, the VMD-CNN-BiLSTM model shows high accuracy in bearing fault diagnosis, fast convergence speed during training, and superior performance. The classification accuracy can be further improved through appropriate parameter adjustment.
[0076] Embodiment 2:
[0077] The invention discloses a bearing fault diagnosis system. Figure 5 is a structural diagram of a bearing fault diagnosis system according to an embodiment of the present invention; Figure 5 As shown, the system 100 includes:
[0078] The first processing module 101 is configured to decompose the bearing vibration signal using the VMD method to extract a sample feature sequence set of the bearing vibration signal;
[0079] The second processing module 102 is configured to input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform fault category diagnosis of the rolling bearing.
[0080] According to the system of the second aspect of the present invention, the first processing module 101 is specifically configured as follows: Figure 2 As shown in Figure 1, the pseudo bearing vibration signal f is decomposed into K components to ensure that the decomposition sequence is a modal component with a limited bandwidth and a center frequency. At the same time, the sum of the estimated bandwidths of each mode is minimized. The constraint condition is that the sum of all modes is equal to the original signal. The corresponding constrained variational expression is:
[0081]
[0082] Among them, u k represents the kth component of the K decomposed modal signals, ω k represents the centroid frequency of the kth component of the K decomposed modal signals, f represents the bearing vibration signal, δ(t) represents the Dirac function, * represents the convolution operator, and j represents the imaginary unit;
[0083] In order to solve equation (1), the Lagrange multiplication operator λ and the quadratic penalty term are introduced to transform the constrained variational problem into an unconstrained variational problem, and the augmented Lagrange expression is obtained as follows:
[0084]
[0085] Among them, α represents the quadratic penalty factor, which is used to reduce the interference of Gaussian noise. The alternating direction multiplier method (ADMM) combined with Fourier isometric transform is used to transform the variational solution problem into an alternating solution problem of multipliers, and each modal component and center frequency are optimized. The modal signal multiplier after alternating optimization iteration is obtained. Center of gravity frequency multiplier The expression is as follows:
[0086]
[0087] Follow these steps to update each modal component:
[0088] a) Reconstruct the original signal using the current modal set;
[0089] b) demodulate each modal component and shift its frequency to baseband;
[0090] c) Calculate the gradient of the demodulated modal component and estimate its bandwidth;
[0091] d) Using gradient information to update the modal components, usually involves a variational problem to minimize the bandwidth.
[0092] Finally, the error of the decomposed modal signal is calculated for iterative calculation. After each iteration, the reduction of the objective function or other convergence criteria are checked. If the convergence condition is met, the iteration is stopped; otherwise, it returns to continue the iteration.
[0093] The sparrow optimization algorithm integrating Osprey and Cauchy mutation is used to dynamically adjust the parameters of the VMD method according to the fitness function, specifically including:
[0094] a) VMD objective function is
[0095]
[0096] Among them, u={u1,u2,…,u K} are the decomposed modal signals, ω={ω1,ω2,…,ω K} is the centroid frequency of each modal signal, Indicates u k (t) The value at a specific time t represents the specific performance of the modal component in the time domain. α represents the penalty factor.
[0097] b) BFOA Predator Position Update:
[0098]
[0099] Among them, x i is the position of the ith predator, x b is the position of the optimal predator and β is a random scaling factor.
[0100] c) SSA sparrow position update:
[0101]
[0102] Where γ is a random vector and ⊙ represents element-wise multiplication.
[0103] d) Cauchy variation:
[0104]
[0105] Among them, C is the parameter that controls the intensity of variation, k is the parameter that controls the shape of the distribution, and x j is another solution in the population.
[0106] e) Fitness calculation:
[0107]
[0108] Among them, F(xi ) is the fitness of the ith solution, and ∈ is a constant to ensure numerical stability.
[0109] The variable x in formulas (6)-(9) represents a set of solutions for the penalty factor α and the modal decomposition number K:
[0110] Update VMD parameters according to the rules of BFOA and SSA, and perform local search in combination with Cauchy mutation. After each iteration, check whether the algorithm meets the stopping conditions, such as the fitness no longer significantly improves or reaches the maximum number of iterations. Select the solution with the highest fitness in all iterations as the optimal solution for VMD parameters.
[0111] According to the system of the second aspect of the present invention, the second processing module 102 is specifically configured to input the sample feature sequence set of the bearing vibration signal into the deep learning network to perform fault category diagnosis of the rolling bearing, including:
[0112] Firstly, the sample feature sequence set is input into the CNN network to extract bearing fault features; then the bearing fault features are summarized by the fully connected layer and input into the BiLSTM network layer with the attention mechanism, and deep feature extraction is realized through weight allocation to obtain deep features; the deep features are used to realize the fault category diagnosis of rolling bearings through the Softmax layer classifier.
[0113] Embodiment 3:
[0114] The present application discloses an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a bearing fault diagnosis method in any one of the embodiments 1 disclosed in the present invention are implemented.
[0115] Figure 6 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 6 As shown, the electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the housing of the electronic device, or an external keyboard, touch pad or mouse, etc.
[0116] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a structural diagram of the part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0117] Embodiment 4:
[0118] The present invention discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any one of the bearing fault diagnosis methods in Embodiment 1 of the present invention are implemented.
[0119] Please note that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the patent in this application shall be based on the attached claims.
[0120] The embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules in computer program instructions encoded on a tangible non-temporary program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
[0121] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits), and the apparatus can also be implemented as special purpose logic circuits.
[0122] Computers suitable for executing computer programs include, for example, general and / or special microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, the computer will also include one or more large-capacity storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to this large-capacity storage device to receive data from it or to transmit data to it, or both. However, the computer does not necessarily have such a device. In addition, the computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, just to name a few.
[0123] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuitry.
[0124] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claim protection, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.
[0125] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.
[0126] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.
[0127] The above are preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.
Claims
1. A bearing fault diagnosis method, characterized in that: include: Step S1, using the VMD method to decompose the bearing vibration signal and extract a sample feature sequence set of the bearing vibration signal; Step S2: input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform fault category diagnosis of the rolling bearing.
2. The bearing fault diagnosis method according to claim 1, characterized in that: In step S1, the VMD method is used to decompose the bearing vibration signal, and the sample feature sequence set of the bearing vibration signal is extracted, which includes: Among them, u k represents the kth component of the K decomposed modal signals, ω k represents the centroid frequency of the kth component of the K decomposed modal signals, f represents the bearing vibration signal, δ(t) represents the Dirac function, * represents the convolution operator, and j represents the imaginary unit.
3. The bearing fault diagnosis method according to claim 2, characterized in that: In the step S1, the sparrow optimization algorithm integrating Osprey and Cauchy mutation is used to dynamically adjust the VMD method parameters according to the fitness function.
4. The bearing fault diagnosis method according to claim 1, characterized in that: In step S2, inputting the sample feature sequence set of the bearing vibration signal into a deep learning network to perform rolling bearing fault category diagnosis includes: Firstly, the sample feature sequence set is input into the CNN network to extract bearing fault features; then the bearing fault features are summarized by the fully connected layer and input into the BiLSTM network layer with the attention mechanism, and deep feature extraction is realized through weight allocation to obtain deep features; the deep features are used to realize the fault category diagnosis of rolling bearings through the Softmax layer classifier.
5. A bearing fault diagnosis system, characterized in that: The system comprises: The first processing module is configured to decompose the bearing vibration signal using a VMD method to extract a sample feature sequence set of the bearing vibration signal; The second processing module is configured to input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform fault category diagnosis of the rolling bearing.
6. The bearing fault diagnosis system according to claim 5, characterized in that: The first processing module is specifically configured as follows: the VMD method is used to decompose the bearing vibration signal, and the sample feature sequence set of the bearing vibration signal is extracted, including: Among them, u k represents the kth component of the K decomposed modal signals, ω k represents the centroid frequency of the kth component of the K decomposed modal signals, f represents the bearing vibration signal, δ(t) represents the Dirac function, * represents the convolution operator, and j represents the imaginary unit.
7. The bearing fault diagnosis system according to claim 6, characterized in that: The first processing module is specifically configured to use a sparrow optimization algorithm that integrates Osprey and Cauchy mutations to dynamically adjust the VMD method parameters according to a fitness function.
8. The bearing fault diagnosis system according to claim 5, characterized in that: The second processing module is specifically configured to input the sample feature sequence set of the bearing vibration signal into a deep learning network to perform rolling bearing fault category diagnosis, including: Firstly, the sample feature sequence set is input into the CNN network to extract bearing fault features; then the bearing fault features are summarized by the fully connected layer and input into the BiLSTM network layer with the attention mechanism, and deep feature extraction is realized through weight allocation to obtain deep features; the deep features are used to realize the fault category diagnosis of rolling bearings through the Softmax layer classifier.
9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in a bearing fault diagnosis method according to any one of claims 1 to 4 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in a bearing fault diagnosis method according to any one of claims 1 to 4 are implemented.