Rolling bearing fault diagnosis method and system based on multi-source vibration signals and medium

Abstract

The application discloses a rolling bearing fault diagnosis method and system based on multi-source vibration signals and a medium, and relates to the field of rolling bearing fault diagnosis. The method comprises the following steps: fusing vibration signals collected by all acceleration sensors by using a PCA method; dividing the fused signal samples into multiple sub-samples by using a sliding window method; calculating multiple characteristic values of each sub-sample by using a time-frequency feature extraction method, and discriminating the fault types of the rolling bearing based on a random forest model to obtain important characteristic values of each sub-sample; generating a two-dimensional image of each sub-sample by using an MTF, and dynamically adjusting the brightness and RGB color channel of the two-dimensional image corresponding to each sub-sample based on a CBAM and the important characteristic values of each sub-sample; and inputting the two-dimensional images of all sub-samples after dynamic adjustment into a trained CBAM-CNN model to output a probability graph of the fault types of the rolling bearing. The application improves the accuracy of rolling bearing fault diagnosis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rolling bearing fault diagnosis, and in particular to a rolling bearing fault diagnosis method and system based on multi-source vibration signals and a medium. BACKGROUND

[0002] Rolling bearings are widely used in modern machinery, and their main function is to support rotating parts and reduce friction, thereby achieving efficient and stable transmission. Rolling bearings are widely used in various equipment such as electric motors, fans, vehicles, aerospace equipment, and precision instruments due to their simple structure, reliable operation, and low maintenance cost.

[0003] However, since rolling bearings are subjected to complex working conditions such as high-speed rotation, heavy load, and impact in mechanical systems, once a rolling bearing fails, it will cause severe vibration of the entire device, and may further cause damage to other components, and will also cause a decline in the overall performance of the device. Therefore, regular monitoring and diagnosis of the health status of rolling bearings is an important part of daily maintenance of rolling bearings.

[0004] In the prior art, the fault of a rolling bearing is generally diagnosed by feature extraction analysis and image recognition analysis. Feature extraction analysis is to extract inherent modal functions, envelope spectrum, singular value decomposition, etc. by using time-frequency analysis, wavelet transform, empirical mode decomposition, etc. to characterize faults based on vibration signals collected by a single measuring point. These fault features are processed and classified for rolling bearing diagnosis. Image recognition analysis is to generate images based on measuring point vibration signals, and then classify and determine them by using a convolutional neural network. Although the above methods can achieve rolling bearing fault diagnosis, feature extraction analysis is based on a single signal source, which may lead to incomplete fault features. Image recognition analysis generates two-dimensional images containing a large amount of redundant information, which may interfere with fault diagnosis. Therefore, the rolling bearing fault diagnosis result based on the above methods is not accurate. SUMMARY

[0005] The purpose of the present application is to provide a rolling bearing fault diagnosis method, system and medium based on multi-source vibration signals, which improves the accuracy of rolling bearing fault diagnosis.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In a first aspect, the present application provides a rolling bearing fault diagnosis method based on multi-source vibration signals, which comprises:

[0008] Acquire vibration signals collected by multiple acceleration sensors; the multiple acceleration sensors are respectively arranged at different locations of a target device; the target device is a device containing a rolling bearing to be diagnosed;

[0009] The vibration signals collected by all acceleration sensors are fused using the PCA method to obtain fused signal samples;

[0010] The fused signal sample is divided into a plurality of subsamples using a sliding window method; each subsample contains a fused signal of a set sliding window length;

[0011] Time-frequency feature extraction is used to calculate multiple eigenvalues ​​of each subsample, and the rolling bearing fault type is identified based on the random forest model to screen out the important eigenvalues ​​of each subsample;

[0012] Generate a 2D image of each subsample using MTF; and dynamically adjust the brightness and RGB color channels of the 2D image corresponding to each subsample based on CBAM and the important eigenvalues ​​of each subsample;

[0013] The two-dimensional images of all sub-samples after dynamic adjustment are input into the trained CBAM-CNN model, and a rolling bearing fault type probability map is output; the rolling bearing fault type probability map is used to determine the fault type of the rolling bearing to be diagnosed in the target device.

[0014] In the second aspect, the present application also provides a computer system comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the rolling bearing fault diagnosis method based on multi-source vibration signals described in the first aspect.

[0015] In a third aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements the rolling bearing fault diagnosis method based on multi-source vibration signals described in the first aspect.

[0016] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0017] The present application first obtains vibration signals collected by different acceleration sensors, realizes the collection of multi-source vibration signals, and at the same time uses the principal component analysis (PCA) method to realize the fusion of multi-source vibration signals, thereby improving the comprehensiveness of rolling bearing fault information acquisition. In order to facilitate the subsequent feature extraction, the present application also uses a sliding window to divide the fused signal sample into multiple sub-samples, and through time-frequency feature extraction and random forest model screening, determines the most important eigenvalue with the strongest correlation with the rolling bearing fault type discrimination from multiple eigenvalues ​​of each sub-sample. After using the Markov Transition Field (MTF) to generate a two-dimensional image of each sub-sample, the two-dimensional image of each sub-sample is dynamically adjusted by the above-mentioned important eigenvalues ​​to ensure that the dynamically adjusted two-dimensional image contains the most representative feature information for rolling bearing fault diagnosis. In addition, in order to achieve accurate recognition of two-dimensional images, the present application introduces a convolutional block attention mechanism module (CBAM) in the convolutional neural network (CNN) model. The CBAM focuses on the dynamically adjusted area in the MTF image, effectively reducing the interference of redundant information. Therefore, the present application improves the accuracy of rolling bearing fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is an overall flow chart of a rolling bearing fault diagnosis method based on multi-source vibration signals provided in an embodiment of the present application;

[0020] Figure 2 This is an execution module diagram of the rolling bearing fault diagnosis method based on multi-source vibration signals provided in an embodiment of the present application;

[0021] Figure 3 A decision tree structure diagram provided for an embodiment of the present application;

[0022] Figure 4 A statistical diagram showing the contribution of various characteristic values ​​to rolling bearing fault identification provided in the embodiments of the present application;

[0023] Figure 5The MTF image provided in the embodiment of the present application is not dynamically adjusted.

[0024] Figure 6 The MTF image generated through dynamic adjustment provided in the embodiment of the present application;

[0025] Figure 7 A rolling bearing fault type probability diagram provided in an embodiment of the present application;

[0026] Figure 8 This is a diagram of the internal structure of the computer system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] The purpose of this application is to provide a rolling bearing fault diagnosis method, system and medium based on multi-source vibration signals, thereby improving the accuracy of rolling bearing fault diagnosis.

[0029] The development of intelligent manufacturing has placed higher demands on early-stage rolling bearing fault diagnosis. Therefore, collecting information from multiple accelerometers to more completely describe the system state has become an important research direction in rolling bearing fault diagnosis. Compared with a single accelerometer, the fusion of multiple accelerometers can significantly improve detection accuracy, robustness, and reliability.

[0030] Feature extraction is the process of simplifying complex data into key numerical indicators (such as mean and standard deviation). It effectively identifies key information that aids in fault diagnosis and is widely used in machine learning and signal processing. Common feature extraction methods include time-frequency analysis, wavelet transform coefficient features, intrinsic mode function features after empirical mode decomposition, envelope spectrum features, and singular value decomposition features.

[0031] MTF is a technique for converting time series data into images, aiming to capture temporal dependencies and patterns in the sequence. Its core idea is to use the state transition matrix of a Markov chain to represent the transition probabilities between moments in the time series, and then represent this probabilistic information as a two-dimensional image.

[0032] The emergence of CNNs has greatly advanced the field of image recognition. Their unique convolutional layer structure, in particular, automatically extracts and learns features from images, eliminating the need for manually designed features. This has enabled them to excel in a variety of image classification tasks. Compared to traditional manual feature extraction methods, CNNs not only reduce reliance on expert experience but also extract deeper fault features from raw data, thereby improving diagnostic accuracy and robustness. Despite their impressive performance in image processing and fault diagnosis, CNNs can often contain a significant amount of redundant information in their extracted features, increasing computational burden and potentially reducing model efficiency and accuracy.

[0033] CBAM is a module that combines spatial and channel attention, designed to enhance convolutional neural networks' focus on important features. CBAM first calculates channel attention to identify which channels contain more critical information, and then calculates spatial attention to determine which spatial regions in the feature map are more important. This dual attention mechanism effectively guides the model to focus on the more diagnostically relevant parts during feature extraction, avoiding interference from redundant information and helping to improve model performance.

[0034] The above methods are widely used in the classification of other fault fields, but there are few studies that combine the above methods and apply them to the fault diagnosis of rolling bearings. This application considers combining these advanced technologies and applying them to the fault diagnosis of rolling bearings. By introducing CBAM and dynamically adjusting the MTF image according to the key features in the vibration signal to highlight its key features, it can effectively guide the model to focus on the more diagnostically significant parts during the feature extraction process, avoid the interference of redundant information, and help improve the performance of the model. Through this fault diagnosis method that combines time-frequency domain feature optimization and utilizes the fusion of vibration signals with a convolutional neural network containing an attention mechanism, the accuracy and reliability of the model classification are significantly improved. This combined method has broad application prospects and is expected to play an important role in the field of fault diagnosis of other equipment.

[0035] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0036] Example 1

[0037] This embodiment provides a rolling bearing fault diagnosis method based on multi-source vibration signals. Figure 1 and Figure 2 As shown, the rolling bearing fault diagnosis method based on multi-source vibration signals includes:

[0038] Step S1: Acquire vibration signals collected by multiple acceleration sensors.

[0039] In this embodiment, multiple acceleration sensors are respectively arranged at different locations of the target device; the target device is a device containing a rolling bearing to be diagnosed; and the sampling frequencies and transmission rates of all acceleration sensors are the same.

[0040] As a preferred implementation method, three accelerometers of the same model are selected and respectively set at the base end, fan end and drive end of the target device, ensuring that the sampling frequency of the three accelerometers is 12KHz, so that they can simultaneously collect vibration signals from the base end, fan end and drive end.

[0041] Step S2: The vibration signals collected by all acceleration sensors are fused using the PCA method to obtain fused signal samples.

[0042] In this embodiment, step S2 specifically includes:

[0043] The first step is to construct the initial signal matrix X based on the vibration signals collected by all acceleration sensors.

[0044] Where X is an n×m matrix, n is the number of accelerometers, m is the number of data points collected by each accelerometer, and each row of X corresponds to a vibration signal collected by an accelerometer.

[0045] The second step is to normalize the initial signal matrix to obtain the standardized signal matrix X std .

[0046] X std =(X-μ) / σ;

[0047] Where μ is the mean of each column in X, and σ is the standard deviation of each column in X.

[0048] The third step is to calculate the covariance matrix of the standardized signal matrix and perform eigendecomposition on the covariance matrix to obtain multiple eigenvalues ​​and multiple eigenvectors.

[0049]

[0050] Cv i =λ i v i ;

[0051] Where C is the covariance matrix, λ i is the i-th eigenvalue, v i is the same as λ i The corresponding i-th eigenvector.

[0052] Fourthly, select the first k eigenvalues from all eigenvalues as principal component components, and select the maximum eigenvalue from the first k eigenvalues as a principal component eigenvalue.

[0053]

[0054] λ' = max {λ1, λ2, …, λ k};

[0055] In the formula, η is the cumulative contribution rate, and λ' is the principal component eigenvalue.

[0056] Fifthly, determine the eigenvector corresponding to the principal component eigenvalue, and fuse the normalized signal matrix and the eigenvector corresponding to the principal component eigenvalue to obtain a fused signal sample.

[0057] Z = X std v';

[0058] In the formula, Z is the fused signal sample, and v' is the eigenvector corresponding to λ'.

[0059] Step S3: The fused signal sample is divided into multiple sub-samples by using a sliding window method.

[0060] In the embodiment, in order to facilitate subsequent feature extraction of the fused signal, the fused signal sample is divided into multiple sub-samples which are convenient for direct processing by using a sliding window, each sub-sample contains a fused signal with a set sliding window length, so as to ensure that the complete vibration feature of the rolling bearing in one running cycle can be captured, and subsequent feature extraction and fault recognition are facilitated. Wherein, the set sliding window length is:

[0061] k * L min ;

[0062] L min = F s *[1 / (N / 60)];

[0063] In the formula, k is an integer greater than or equal to 1, L min is the data length collected by each acceleration sensor after the rolling bearing to be diagnosed runs for one cycle (the data length collected by each acceleration sensor is the same), F s is the sampling frequency of the acceleration sensor, and N is the rotating speed of the rolling bearing to be diagnosed.

[0064] As a preferred embodiment, in order to further enrich the fault feature and improve the accuracy of rolling bearing fault diagnosis, L min is set to 401, and the sliding window length is set to 2L min(i.e. 802), the sliding step is set to 802 to ensure that the data in each window is completely independent, reduce repeated calculations of the same information, save computing resources, and avoid redundancy.

[0065] Step S4: Calculate multiple eigenvalues ​​of each subsample using time-frequency feature extraction, and discriminate the rolling bearing fault type based on the random forest model to screen out the important eigenvalues ​​of each subsample (the important eigenvalues ​​of each subsample are the same).

[0066] In this embodiment, step S4 specifically includes:

[0067] In the first step, time-frequency feature extraction is used to calculate the multi-class feature values ​​under each sliding window.

[0068] Among them, one sliding window corresponds to one subsample, and the number of eigenvalue categories under each sliding window is the same. For example, 10 categories of eigenvalues ​​are extracted under each sliding window.

[0069] In the second step, based on the multi-class eigenvalues ​​under all sliding windows and the out-of-bag error increment in the random forest model (the out-of-bag error increment measures the importance of features by evaluating the contribution of each feature to the prediction performance in the random forest model), the contribution value of each type of eigenvalue to the rolling bearing fault type discrimination is determined.

[0070] like Figure 3 The random forest structure shown in the figure is a random forest model with 100 decision trees. Each leaf node includes at least one sample. All features are selected at each split, and the maximum split depth is not limited. This method uses out-of-bag data that has not been seen in the decision tree construction process as a test set. For each feature, its value in the out-of-bag data is randomly shuffled, and the out-of-bag error of the model is recalculated. The difference between the out-of-bag error of a feature after shuffling and the original error is the increment of the feature, indicating its importance. The larger the error increment, the more significant the impact of the feature on the model effect. Figure 4 As shown in the figure, s1, s2, s3...s15 are 15 feature labels (corresponding to 15 types of feature values), and the vertical axis is the contribution value of each type of feature value to the judgment of the rolling bearing fault type.

[0071] In the third step, the multi-category eigenvalues ​​whose contribution values ​​are greater than the set threshold are taken as important eigenvalues, and the important eigenvalues ​​of each subsample are screened.

[0072] As a preferred embodiment, Figure 4 The top four eigenvalues ​​in terms of contribution value are taken as the important eigenvalues ​​of each subsample and used in subsequent analysis. Alternatively, multiple eigenvalues ​​with contribution values ​​greater than 2.5 can be taken as the important eigenvalues ​​of each subsample and used in subsequent analysis.

[0073] Step S5: generate MTF images of each sub-sample by CBAM, and dynamically adjust the brightness and RGB color channel of the corresponding MTF image during MTF image generation according to the important feature value of each sub-sample.

[0074] In this embodiment, first, on each sub-sample, the segment of the fusion signal is converted into a two-dimensional image by the Markov transition field. Specifically, for the fusion signal Z1, Z2, …, Z n , according to the amplitude size, it is discretized into Q bins, obtaining a QxQ Markov transition matrix. In order to make up for the shortcomings of the Markov transition field that is not sensitive to time series and step length, and considering the time position information, the matrix containing the amplitude is expanded to a Markov transition field containing a time axis, which retains the time correlation of the original signal, calculates the transition probability between the states to which each time series data point belongs, obtains an n x n transition matrix, and encodes the transition matrix into image pixels, thereby retaining the dynamic characteristics and local dependencies of the time series data.

[0075] Further, CBAM (different from CBAM in CBAM-CNN model, independent existence) is introduced mainly through channel attention and spatial attention to enhance the feature extraction capability of the subsequent model. If the four types of feature parameters of margin factor, barycenter frequency, amplitude average value and spectral entropy are determined according to the feature importance output by the random forest, different scaling factors are applied to each color channel, and the response of each channel is adjusted using various feature values to enhance specific features; adjust the contrast of each channel through the imadjust function, so that the model pays attention to important features on different channels; generate a spatial attention map according to the spatial position of the image, and adjust the spatial structure of the image to enhance the feature expression of specific regions. The before and after effect comparison of the MTF image generated through the above adjustment can be seen in Figure 5 and Figure 6 .

[0076] Step S6: input the MTF images of all sub-samples into the trained CBAM-CNN model, and output the rolling bearing fault type probability map.

[0077] In this embodiment, in order to obtain the trained CBAM-CNN model, the following steps also need to be performed:

[0078] First, build a CBAM-CNN model. The CBAM-CNN model is a convolutional neural network model with a convolution block attention mechanism module. The convolution block attention mechanism module in the CBAM-CNN model is used to strengthen the attention to the brightness and RGB color channel of the MTF image of each sub-sample, so that it focuses on the feature area that is crucial to rolling bearing fault diagnosis through channel attention mechanism and spatial attention mechanism, and improves the accuracy and efficiency of feature extraction.

[0079] Specifically, the CBAM-CNN model consists of one CBAM layer, two convolutional layers, a max pooling layer, a tiling layer, and a fully connected layer. The CBAM-CNN model uses the Adam optimizer, the LeakyReLU activation function, and Dropout to prevent overfitting. The first convolutional layer consists of 64 3×3 convolution kernels; the activation layer uses LeakyReLU; the second convolutional layer consists of 128 3×3 convolution kernels; the max pooling layer uses a 2×2 pooling window; and the fully connected layer contains 512 neurons, using the ReLU activation function. To prevent overfitting in the CBAM-CNN model, Dropout is added, randomly dropping 30% of the neurons. The output layer uses a softmax activation function to achieve rolling bearing fault classification, with the output dimension being the number of categories.

[0080] The second step is to acquire and process training data. The data source is the Case Western Reserve University Bearing Data (CWRU). The bearing speed in CWRU is 1796 RPM, the accelerometer sampling frequency is 12 kHz, and the vibration signals come from the base, fan, and drive.

[0081] Based on the CWRU data, steps S2 through S5 were performed to obtain MTF images for multiple subsamples. These images were then divided into a training set and a validation set in an 8:2 ratio. Through cropping, 151 subsamples were obtained for each fault type, generating a total of 1,963 MTF images, including 1,573 for the training set and 390 for the validation set.

[0082] The third step is training the CBAM-CNN model. The MTF images from the training set are fed into the CBAM-CNN model. The CNN uses CBAM to calculate spatial attention and channel attention. Channel attention ensures that the color adjustment portion of the image is prioritized. The channel attention reduction ratio is set to 9 to control the degree of compression of each channel's features, proportionally reducing the number of neurons. Two Dense layers are used: the first compresses the channel dimension, and the second restores it to the original number of channels. The ReLU activation function is used as the activation for the first layer, and the Sigmoid activation function is used to generate the final weights.

[0083] The spatial attention strengthens the regions that are adjusted by the spatial position. A 2D convolution layer with a kernel size of 4*4 is used to extract spatial information, and a sigmoid activation function is used to generate a spatial attention map. These modules focus on and weight the channel and spatial features of the image through the above parameters and structures, ensuring that the CBAM-CNN model pays more attention to the key parts of the image during the classification process, i.e., the parts adjusted by important features.

[0084] Finally, the performance of the CBAM-CNN model is evaluated by accuracy and classification cross-entropy loss function. The trained CBAM-CNN model is tested using the test set, and the final output is a visualization result, i.e., a rolling bearing fault type probability graph, which is used to determine the fault type of the rolling bearing to be diagnosed in the target device. As shown in Figure 7 , F1, F2, F3……F13 correspond to 13 types of rolling bearing fault types respectively. By comparing the size of the probability value of the ordinate, the fault type of the rolling bearing to be diagnosed in the target device can be determined.

[0085] Embodiment 2

[0086] This embodiment provides a computer system, which can be a server or a terminal, and its internal structure diagram can be as shown in Figure 8 . The computer system includes a processor, a memory, an input / output interface (I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer system is used to provide computing and control ability. The memory of the computer system includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer system is used to store the vibration signals collected by multiple acceleration sensors. The input / output interface of the computer system is used to exchange information between the processor and external devices. The communication interface of the computer system is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement the above-mentioned rolling bearing fault diagnosis method based on multiple vibration signals.

[0087] Those skilled in the art can understand, Figure 8 the structure shown in the figure, only the block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer system to which the scheme of the present application is applied. The specific computer system can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0088] Embodiment 3

[0089] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0090] In summary, this application has the following advantages:

[0091] (1) Multi-source signal fusion improves detection accuracy: By extracting the principal components from multi-source signals through a fusion algorithm, signals with relatively high noise content but low contribution are shielded, highlighting key fault characteristics and significantly improving diagnostic accuracy and robustness. This approach can integrate information from multi-dimensional signals, making up for the shortcomings of a single signal source in terms of comprehensiveness and noise immunity, and providing more comprehensive diagnostic support.

[0092] (2) Dynamic feature image generation and CBAM to enhance CNN accuracy: In the image generation and recognition process, in order to reduce the interference of redundant information on the model recognition ability, this application introduces a dynamic image adjustment technology based on feature screening. By screening out the feature values ​​with the strongest correlation with the rolling bearing fault type, the image is dynamically adjusted to ensure that the image contains the most representative feature information for fault diagnosis. Furthermore, CBAM is introduced into the CNN used for rolling bearing fault diagnosis, so that the CNN focuses on the dynamic adjustment area during the learning process, thereby effectively reducing the interference of redundant information. This method is equivalent to artificially prompting important features to the neural network, which helps the network to accurately capture key information and significantly improve classification accuracy.

[0093] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0094] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0095] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0096] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0097] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A rolling bearing fault diagnosis method based on multi-source vibration signals, characterized in that: The rolling bearing fault diagnosis method based on multi-source vibration signals includes: Acquire vibration signals collected by multiple acceleration sensors; the multiple acceleration sensors are respectively arranged at different locations of a target device; the target device is a device containing a rolling bearing to be diagnosed; The vibration signals collected by all acceleration sensors are fused using the PCA method to obtain fused signal samples; The fused signal sample is divided into a plurality of subsamples using a sliding window method; each subsample contains a fused signal of a set sliding window length; Time-frequency feature extraction is used to calculate multiple eigenvalues ​​of each subsample, and the rolling bearing fault type is identified based on the random forest model to screen out the important eigenvalues ​​of each subsample; The MTF is used to generate a two-dimensional image of each sub-sample, and the brightness and RGB color channels of the two-dimensional image corresponding to each sub-sample are dynamically adjusted based on the CBAM and the important eigenvalues ​​of each sub-sample. The two-dimensional images of all sub-samples after dynamic adjustment are input into the trained CBAM-CNN model, and a rolling bearing fault type probability map is output; the rolling bearing fault type probability map is used to determine the fault type of the rolling bearing to be diagnosed in the target device.

2. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 1, characterized in that: The vibration signals collected by all acceleration sensors are fused using the PCA method to obtain fused signal samples, which specifically include: Based on the vibration signals collected by all acceleration sensors, an initial signal matrix is ​​constructed; each row element in the initial signal matrix corresponds to a vibration signal collected by an acceleration sensor; performing normalization processing on the initial signal matrix to obtain a normalized signal matrix; Calculating a covariance matrix of the standardized signal matrix and performing eigendecomposition on the covariance matrix to obtain a plurality of eigenvalues ​​and a plurality of eigenvectors; Select the first k eigenvalues ​​from all eigenvalues ​​as the principal component components, and take the largest eigenvalue among the first k eigenvalues ​​as the principal component eigenvalue; Determine the eigenvector corresponding to the principal component eigenvalue, and fuse the standardized signal matrix with the eigenvector corresponding to the principal component eigenvalue to obtain a fused signal sample.

3. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 1, characterized in that: The sliding window length is set to k*L min ; k is an integer greater than or equal to 1, L min It is the length of data collected by each acceleration sensor after the rolling bearing to be diagnosed runs for one cycle.

4. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 3 is characterized in that: The formula for calculating the length of data collected by each acceleration sensor after the rolling bearing to be diagnosed runs for one cycle is: L min =F s *[1 / (N / 60)]; Where, F s is the sampling frequency of the acceleration sensor, and N is the rotational speed of the rolling bearing to be diagnosed.

5. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 1, characterized in that: Time-frequency feature extraction is used to calculate multiple eigenvalues ​​of each subsample. The rolling bearing fault type is identified based on the random forest model, and the important eigenvalues ​​of each subsample are screened, including: Time-frequency feature extraction is used to calculate multi-class eigenvalues ​​under each sliding window; one sliding window corresponds to one subsample; the number of eigenvalue categories under each sliding window is the same; Based on the multi-class eigenvalues ​​under all sliding windows and the out-of-bag error increment in the random forest model, the contribution value of each eigenvalue to the identification of rolling bearing fault types is determined; The multi-category eigenvalues ​​whose contribution values ​​are greater than the set threshold are taken as important eigenvalues, and the important eigenvalues ​​of each subsample are screened.

6. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 1, characterized in that: All accelerometers have the same sampling frequency and transmission rate.

7. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 1, characterized in that: The CBAM-CNN model is a convolutional neural network model that introduces a convolutional block attention mechanism module.

8. The rolling bearing fault diagnosis method based on multi-source vibration signals according to claim 7, characterized in that: The convolutional block attention mechanism module in the CBAM-CNN model is used to strengthen the attention to the brightness and RGB color channels in the MTF image of each sub-sample.

9. A computer system comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the rolling bearing fault diagnosis method based on multi-source vibration signals according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the rolling bearing fault diagnosis method based on multi-source vibration signals according to any one of claims 1 to 8 is implemented.

Images