Motor fault diagnosis method and system based on color image fusion symmetry point mode

Abstract

The invention discloses a motor fault diagnosis method and system based on color image fusion symmetric point mode, and the method comprises the steps: converting a vibration signal and an electromagnetic signal of a motor into symmetric point mode images, and generating a color signal image fusing feature information; respectively abstracting the color signal images fused with the feature information into nodes and edges in a high-dimensional semantic space so as to construct graph structure data; and performing diagnosis classification on the graph structure data of the vibration signals and the electromagnetic signals by using respective capsule graph network models, and fusing diagnosis classification results of the vibration signals and the electromagnetic signals through a voting mechanism to obtain a final diagnosis classification result. According to the method, multi-channel time domain signals are converted into image expressions with dense information and consistent geometry, and unified feature modeling is carried out on the images based on a depth map structure network with topology perception capability, so that motor fault diagnosis with high diagnosis precision and strong robustness is realized.

Description

Technical Field

[0001] This invention relates to the field of motor fault diagnosis technology, and specifically to a motor fault diagnosis method and system based on color image fusion symmetrical point pattern. Background Technology

[0002] With the rapid development of new energy vehicles, intelligent manufacturing, and high-end CNC equipment, high-performance motors such as permanent magnet synchronous motors are widely used in critical scenarios such as traction drives, precision servo drives, and high-speed machine tools. Under complex loads, wide-frequency speed variations, and continuous long-term operation, motors are highly susceptible to early, latent faults such as rotor demagnetization, stator winding inter-turn short circuits, bearing wear, and air gap eccentricity. If these minor anomalies are not identified promptly and accurately, they can quickly evolve into severe vibrations, overheating, or even system shutdown, leading to huge economic losses and safety risks. Therefore, developing highly sensitive and robust motor fault diagnosis technologies has become a core requirement in the fields of industrial operation and maintenance and intelligent equipment.

[0003] Current research primarily relies on single-channel vibration or current signals, extracting statistical features through time-frequency analysis methods such as Fast Fourier Transform, Wavelet Packet Decomposition, and Empirical Mode Decomposition, and then using classification models such as Support Vector Machines and Convolutional Neural Networks to complete fault identification. Although these methods have achieved certain results under specific working conditions, they still have three shortcomings: First, a single signal source cannot fully characterize the electro-magnetic-mechanical coupling characteristics of the motor, resulting in limited diagnostic accuracy; second, manually designed time-frequency features are sensitive to speed fluctuations, load changes, and background noise, and lack robustness; third, although deep networks can automatically learn features, they usually require large-scale labeled samples, while early fault samples in industrial sites are extremely scarce, making the models prone to overfitting and lacking interpretability.

[0004] To address the issue of low utilization of multi-source information, some researchers have begun to explore mapping temporal signals to two-dimensional images, such as symmetric point patterns or recursive graphs, and then using traditional convolutional networks to extract texture features. However, directly stitching SDP images between different channels often results in the loss of cross-modal correlations, and ordinary CNNs struggle to explicitly capture node-edge topological relationships, making it even more difficult to handle geometric distortions caused by rotation and scale changes. On the other hand, while graph neural networks can express complex structures, a unified framework is still lacking for how to efficiently construct graphs from raw temporal data and maintain local shape invariance in the graph domain.

[0005] In summary, existing motor fault diagnosis technologies have not yet achieved full integration of vibration and electromagnetic multimodal signals, and lack deep feature extraction methods that combine scale invariance, rotation invariance, and topology awareness. At the same time, in early weak faults and operating condition transition scenarios, traditional models are prone to false detections or missed detections. Summary of the Invention

[0006] The technical problem to be solved by this invention is to provide a motor fault diagnosis method and system based on color image fusion symmetrical point pattern in response to the above-mentioned problems in the prior art. This invention aims to transform multi-channel time-domain signals into information-dense and geometrically consistent image representations, and to perform unified feature modeling on these images based on a deep graph structure network with topological awareness capabilities, thereby achieving high diagnostic accuracy and strong robustness in motor fault diagnosis.

[0007] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A motor fault diagnosis method based on color image fusion of symmetrical point patterns includes the following steps: 1) Acquire the vibration and electromagnetic signals of the motor; 2) The vibration signal and electromagnetic signal are converted into symmetrical point pattern images respectively, and a color signal image with fused feature information is generated by color image fusion technology; 3) Based on the scale-invariant feature transformation method of feature embedding, the color signal image with fused feature information is abstracted into nodes and edges in a high-dimensional semantic space, thereby constructing graph structure data composed of nodes and edges; 4) The graph structure data of vibration signals and electromagnetic signals are respectively diagnosed and classified using their respective capsule graph network models, and the diagnostic and classification results of vibration signals and electromagnetic signals are merged through a voting mechanism to obtain the final diagnostic and classification result.

[0008] Optionally, in step 2), when converting the vibration signal and electromagnetic signal into symmetrical point pattern images respectively, this includes processing the vibration signal or electromagnetic signal... X ={ x 1, x 2, ..., x n},in x 1~ x n Vibration signal or electromagnetic signal respectively X The first to nth sampled signals, where n is the number of sampled signals, are converted into points in the symmetric point space in polar coordinates according to the following formula. : , , , in, The polar radius of the transformed signal point. X max and X min Time-domain signal X The maximum and minimum values ​​in For the firsts Angles of a symmetrical plane θ s =360 m / k , m The index of the mirror-symmetric plane. m =0,1,…, k -1, k , k The number of mirror-symmetric planes. Vibration signal or electromagnetic signal X The i-th sampled data in Vibration signal or electromagnetic signal X The first in Each sampled data, To delay, The angle is the counterclockwise rotation of the mirror symmetry plane of the transformed signal point. The angle is the clockwise rotation of the mirror symmetry plane of the transformed signal point. For the gain angle; based on the point in the symmetric space under polar coordinates. The three attributes are used as color values ​​for the three RGB channels to generate a symmetrical dot pattern image.

[0009] Optionally, step 2) of generating a color signal image with fused feature information using color image fusion technology includes: firstly, calculating the signal energy entropy of each of the three RGB channels. E , cliff K and spectral peak P Construct feature vectors F k =[ E k ，K k ，P k The fusion weights of each channel signal are calculated according to the following formula: , in, The fusion weight for the k-th channel is... This represents the accuracy of this channel's classification of the current fault type based on historical data. β The adjustment factor is then used to generate a color signal image with fused feature information according to the following formula: , in, To fuse color signal images with feature information, , and These are the fusion weights for the signals from channels 1 to 3, respectively. , and These are images of the red, green, and blue channel signals in the symmetrical point pattern image, respectively.

[0010] Optionally, step 3) includes: 3.1) By performing Gaussian blurring on the input color signal image at multiple scales, a Gaussian pyramid is constructed from the Gaussian smoothed image layers obtained from the Gaussian blurring at multiple scales. The difference between adjacent scale Gaussian images in the Gaussian pyramid is then calculated according to the following formula to generate the Difference Gaussian Space (DoG): , in, Represents the difference Gaussian space DoG with respect to Gaussian difference image layers, Indicates about Gaussian kernel function, This is a two-dimensional convolution operation. Color signal images for fusing feature information At coordinate point Pixel values; This is the scale multiplication factor, used to control the interval between adjacent scales; This serves as the baseline scale parameter, used to determine the granularity of feature detection; 3.2) In the Difference Gaussian (DoG) space, the position and scale of candidate keypoints are corrected at the sub-pixel level by fitting a three-dimensional quadratic function or Taylor expansion. The contrast of extreme points is calculated using the Hessian matrix, and unstable keypoints with low contrast are removed according to a preset contrast threshold to obtain stable keypoints. , in, This is the offset of the keypoint, including corrections for spatial coordinates and scale; This is the contrast threshold, used to filter noise-sensitive points; for The inverse matrix, It is a Gaussian difference function. To stabilize the position of key points In x coordinate, Indicates the contrast at extreme points; Hessian matrix eigenvalue analysis is used to distinguish edge responses from corner responses. Based on the following formula, pseudo-stable keypoints on the edges are filtered out using the principal curvature ratio to retain features with stable geometric structures: , in, The Hessian matrix is ​​composed of the second derivatives of the Gaussian difference image layers. forH The trace of the Hessian matrix represents the sum of the principal curvatures; for H The product of curvature, r The primary curvature ratio threshold, For the image in x The second derivative in the direction represents the rate of change of the gray value along the horizontal direction. and The images are respectively in x and y The mixed second derivative of the direction represents the joint change of grayscale value in the horizontal and vertical directions. For the image in y The second derivative of the direction represents the rate of change of the gray value along the vertical direction; Calculate the neighborhood gradient magnitude and directional gradient angle based on the surrounding region of the filtered and corrected stable keypoint: , , in, For the stable key points after filtering correction The neighborhood gradient magnitude, , , and These are the positions in the Gaussian smoothed image layer. , , and grayscale value, For the stable key points after filtering correction The directional gradient angle is used to construct a multi-directional histogram based on the neighborhood gradient magnitude and the directional gradient angle. Key points in multiple directions are generated by setting the main direction as the peak value of the histogram and the secondary peaks as greater than the main peak. 3.3) Rotate the neighborhood of the key point to the main direction, divide the 16×16 neighborhood into 4×4 sub-regions, count 8 directional buckets in each region, and concatenate them into a 128-dimensional vector according to the following formula, then normalize the vector to generate nodes in the graph structure data: , in, For the first in graph structure data i The feature vector of each node For the stable key points after filtering correction The neighborhood gradient magnitude, For the first i The set of pixels in the sub-region of each node. for The pixel position in the image. For indicator functions, For the stable key points after filtering correction The direction gradient angle; Let i be the i-th directional bucket, which is one of eight angular intervals evenly divided within 360°, used to accumulate gradient energy within that angular range; the feature vectors of each node in the graph structure data are used as 128-dimensional SIFT descriptors, and the edge weights in the graph structure data are calculated according to the following formula to obtain the graph structure data: , in, For nodes v i and v j Edge weights between them This is a coefficient for balancing spatial and semantic weights. For nodes v i coordinates For nodes v j coordinates σ s The standard deviation of the Gaussian kernel for spatial distance. For nodes v i 128-dimensional SIFT descriptor, For nodes v j 128-dimensional SIFT descriptor.

[0011] Optionally, in step 4), when performing diagnostic classification on the graph structure data of vibration signals and electromagnetic signals using their respective capsule graph network models, the capsule graph network model dynamically routes the input graph structure data of vibration signals or electromagnetic signals to achieve cross-modal feature fusion and output the activated capsule vector according to the following formula: , , , in, Let j be the activated capsule vector output by the graph capsule network model. Let be the weighted sum of the dynamic routing coefficients of the j-th graph capsule network model and the feature vectors of the primary capsules. Let be the dynamic routing coefficient from capsule i to capsule j. Let i be the primary capsule feature vector from capsule i to capsule j. Let be the coupling coefficient from capsule i to capsule j. Let be the coupling coefficient from capsule i to capsule k.

[0012] Optionally, it also includes calculating training metrics after each round of training when training the graph capsule network model. If training metrics If the training threshold is exceeded, the graph capsule network model is considered to have completed training; otherwise, iterative training needs to continue. The training metrics are calculated as follows. include: Adjust the initial diagnostic weights of each graph capsule network model according to the following formula: , in, The initial diagnostic weights for the m-th graph capsule network model are... Let m be the activated capsule vector output by the m-th graph capsule network model. for The vector magnitude, The activated capsule vector is the output of the nth graph capsule network model. for The vector magnitude, For coefficients, The number of graph capsule network models; the entropy weight coefficients are calculated according to the following formula: ,

[0013] in, Let m be the entropy weight coefficient of the m-th graph capsule network model. Let m be the information entropy of the m-th graph capsule network model. The information entropy of the nth graph capsule network model is... Number of fault categories The predicted probability distribution for each fault category; the training index is calculated according to the following formula. : , in, The voting score for the k types of faults in the m-th graph capsule network model.

[0014] Optionally, before step 1), a step of training graph network models for vibration signals and electromagnetic signals is included. Training the graph network models involves collecting vibration signals and electromagnetic signals of the motor under different operating conditions as fault diagnosis data. These different operating conditions include normal conditions and various fault conditions. The obtained fault diagnosis data includes the motor fault electromagnetic signal dataset shown in the following formula. :

[0015] in, For the first iOne motor fault signal, For fault labels, Electromagnetic signal dataset for motor faults The number of samples, T The number of sampling points. This is a dataset of electromagnetic fault signals for motors. This is a dataset for motor electromagnetic fault categories. And the motor fault vibration signal dataset shown in the following formula :

[0016] in, For the first i Vibration signal of a motor fault. For fault labels, Data set of vibration signals for motor faults The number of samples.

[0017] Furthermore, the present invention also provides a motor fault diagnosis system based on color image fusion symmetrical point pattern, including a microprocessor and a memory interconnected thereto, wherein the microprocessor is programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetrical point pattern.

[0018] Furthermore, the present invention also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetric point pattern by a processor.

[0019] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetrical point pattern by a processor.

[0020] Compared with existing technologies, the present invention mainly achieves the following beneficial effects: First, the method of the present invention collects vibration signals and electromagnetic time-domain signals of the motor under different operating conditions to provide data for fault diagnosis. Then, color image fusion technology is used to convert these time-domain signals into Symmetric Dot Pattern (SDP) images, generating color signal images that fuse multi-dimensional feature information. Next, using the SIFT graph construction method based on feature embedding, the image is abstracted into nodes and edges in a high-dimensional semantic space to construct graph structure data. This graph structure data is input into a graph capsule network, where image features are extracted through the graph capsule layer, and vibration signals and electromagnetic signals are classified. Finally, an enhanced voting strategy is used to fuse the diagnostic results of different signal sources to improve the accuracy and reliability of the diagnosis. The motor fault diagnosis method and system described in this invention, by integrating multiple advanced technologies, can effectively process multi-source signals, achieving efficient and accurate fault diagnosis, and has broad application prospects, especially in the field of complex and high-risk motor fault detection. By combining image processing with deep learning, the accuracy and robustness of fault diagnosis are improved, demonstrating strong industrial application value. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the basic process of the method in an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram illustrating the principle of the method in an embodiment of the present invention.

[0023] Figure 3 Examples of color signal images that integrate feature information according to embodiments of the present invention are shown below: (a) is a color signal image of a normal motor; (b) is a color signal image of a rotor imbalance fault; (c) is a color signal image of a rotor misalignment fault; (d) is a color signal image of a shaft bending fault; (e) is a color signal image of a bearing fault; (f) is a color signal image of a rotor bar fault; (g) is a color signal image of a stator winding fault; and (h) is a color signal image of a single-phase open circuit fault.

[0024] Figure 4 This is a flowchart of the data preprocessing process for graph structure data in an embodiment of the present invention.

[0025] Figure 5 This is a flowchart illustrating the training process of the graphical capsule network model in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0027] like Figure 1 As shown, the motor fault diagnosis method based on color image fusion symmetrical point pattern in this embodiment includes the following steps: 1) Acquire the vibration and electromagnetic signals of the motor; 2) The vibration signal and electromagnetic signal are converted into symmetrical point pattern images respectively, and a color signal image with fused feature information is generated by color image fusion technology; 3) Based on the scale-invariant feature transformation method of feature embedding, the color signal image with fused feature information is abstracted into nodes and edges in a high-dimensional semantic space, thereby constructing graph structure data composed of nodes and edges; 4) The graph structure data of vibration signals and electromagnetic signals are respectively diagnosed and classified using their respective capsule graph network models, and the diagnostic and classification results of vibration signals and electromagnetic signals are merged through a voting mechanism to obtain the final diagnostic and classification result.

[0028] like Figure 2 As shown, the method in this embodiment mainly includes signal acquisition, symmetric point pattern image generation, color image fusion, graph structure data generation, diagnostic classification using a capsule graph network model, and a voting mechanism to obtain the final diagnostic classification result. It also includes training the capsule graph network model. When performing diagnostic classification on the graph structure data of vibration signals and electromagnetic signals using their respective capsule graph network models, in order to facilitate the differentiation of the respective capsule graph network models, Figure 2 They are named the electromagnetic-capsule graph network model and the vibration-capsule graph network model, respectively. The electromagnetic-capsule graph network model is used for the diagnostic classification of graph structure data of electromagnetic signals, and the vibration-capsule graph network model is used for the diagnostic classification of graph structure data of vibration signals.

[0029] In this embodiment, before step 1), there is a step of training graph network models for the vibration signal and electromagnetic signal respectively. The training of the graph network model includes collecting vibration signals and electromagnetic signals of the motor under different operating states as fault diagnosis data. The different operating states include normal state and various fault states (e.g., bearing inner ring fault state, bearing outer ring fault state, and bearing rolling element fault state, etc., and the fault states can be added or reduced according to actual needs). The obtained fault diagnosis data includes the motor fault electromagnetic signal dataset shown in the following formula. :

[0030] in, For the first i One motor fault signal, For fault labels, Electromagnetic signal dataset for motor faults The number of samples, T The number of sampling points. This is a dataset of electromagnetic fault signals for motors. This is a dataset for motor electromagnetic fault categories. And the motor fault vibration signal dataset shown in the following formula :

[0031] in, For the first i Vibration signal of a motor fault. For fault labels, Data set of vibration signals for motor faults The number of samples. In this embodiment, during signal acquisition, an AC flux sensor and a triaxial piezoelectric accelerometer are used to collect electromagnetic signals and vibration signals of the permanent magnet synchronous motor under different operating conditions as fault diagnosis data. The vibration signals collected by the triaxial piezoelectric accelerometer include vibration signal components in the X, Y, and Z axes, and the final vibration signal is obtained by adding the vibration signal components in the X, Y, and Z axes.

[0032] Step 2) converts the obtained time-domain data into a symmetric point pattern image (SDP image) to obtain the SDP image of the vibration and electromagnetic signals, and then uses a color image fusion method to obtain a multi-source signal fused SDP color image. In this embodiment, step 2) converts the vibration signal and electromagnetic signal into symmetric point pattern images respectively, including for vibration signals or electromagnetic signals... X ={ x 1, x 2, ..., x n},in x 1~ x n Vibration signal or electromagnetic signal respectively X The first to nth sampled signals, where n is the number of sampled signals, are converted into points in the symmetric point space in polar coordinates according to the following formula. : , , , in, The polar radius of the transformed signal point. X max and X min Time-domain signal X The maximum and minimum values ​​in For the first s Angles of a symmetrical plane θ s =360 m / k , m The index of the mirror-symmetric plane. m =0,1,…, k -1, k , k The number of mirror-symmetric planes. Vibration signal or electromagnetic signal X The i-th sampled data in Vibration signal or electromagnetic signal X The first in Each sampled data, To delay, The angle is the counterclockwise rotation of the mirror symmetry plane of the transformed signal point. The angle is the clockwise rotation of the mirror symmetry plane of the transformed signal point. For the gain angle; based on the point in the symmetric space under polar coordinates. The three attributes are used as color values ​​for the three RGB channels to generate a symmetrical dot pattern image. The shape of the symmetrical point pattern image is determined by the combination of these factors. This method can be used to convert one-dimensional electromagnetic and vibration signals into two-dimensional images to extract their subtle features.

[0033] In step 2) of this embodiment, generating a color signal image with fused feature information using color image fusion technology includes: firstly, calculating the signal energy entropy of each of the three RGB channels. E , cliff K and spectral peak P Construct feature vectors F k =[ E k ，K k ，P k The fusion weights of each channel signal are calculated according to the following formula: , in, The fusion weight for the k-th channel is... This represents the accuracy of this channel's classification of the current fault type based on historical data. β As the adjustment factor, the three-channel signal images are then weighted and superimposed according to the following formula to generate a color signal image with fused feature information: , in, To fuse color signal images with feature information, , and These are the fusion weights for the signals from channels 1 to 3, respectively. , and These are images of the red, green, and blue channel signals from a symmetrical point pattern image, respectively. The color signal image generated by fusing feature information using the above method can accurately characterize various motor faults. Figure 3 Examples of color signal images with integrated feature information in this embodiment are shown below: (a) is a color signal image of a normal motor; (b) is a color signal image of a rotor imbalance fault; (c) is a color signal image of a rotor misalignment fault; (d) is a color signal image of a shaft bending fault; (e) is a color signal image of a bearing fault; (f) is a color signal image of a rotor bar fault; (g) is a color signal image of a stator winding fault; and (h) is a color signal image of a single-phase open circuit fault.

[0034] Step 3) The color image is abstracted into nodes and edges in a high-dimensional semantic space using the SIFT graph construction method based on feature embedding, thus constructing graph structure data. Specifically, as follows... Figure 4 As shown, step 3) of this embodiment includes: 3.1) SIFT feature extraction, including: performing Gaussian blurring on the input color signal image at multiple scales, constructing a Gaussian pyramid from the Gaussian smoothed image layers obtained from the Gaussian blurring at multiple scales, and generating the Difference Gaussian Space (DoG) by calculating the difference between adjacent scale Gaussian images in the Gaussian pyramid according to the following formula: , in, Represents the difference Gaussian space DoG with respect to Gaussian difference image layers, Indicates about Gaussian kernel function, This is a two-dimensional convolution operation. Color signal images for fusing feature information At coordinate point Pixel values; This is the scale multiplication factor, used to control the interval between adjacent scales; The baseline scale parameter σ is used to determine the granularity of feature detection. A Gaussian pyramid is generated through multi-scale Gaussian convolution, with each group containing multiple layers of images. Downsampling is performed group by group to cover features at different scales. Within each group, a multi-scale image layer is generated using an incrementally increasing baseline scale parameter σ, providing a foundation for subsequent Gaussian difference calculations. A difference Gaussian space (DoG) is generated by calculating the difference between Gaussian images at adjacent scales in the Gaussian pyramid, which can highlight high-frequency features (such as edges and corners) and is used to detect extrema in the scale space. 3.2) Keypoint selection includes: sub-pixel-level correction of the position and scale of candidate keypoints in the Difference Gaussian (DoG) space using 3D quadratic function fitting or Taylor expansion; calculation of the contrast of extreme points using the Hessian matrix; and elimination of unstable keypoints with low contrast based on a preset contrast threshold to obtain stable keypoints. , in, This is the offset of the keypoint, including corrections for spatial coordinates and scale; This is the contrast threshold, used to filter noise-sensitive points; for The inverse matrix, It is a Gaussian difference function. To stabilize the position of key points In x coordinate, This represents the contrast of extreme points. In the difference-of-Gaussian pyramid, each pixel is compared with its neighbors in the same layer and the neighbors in the adjacent layers above and below. If it is a maximum or minimum value, it is marked as a candidate keypoint. Subsequently, stable keypoints are selected through contrast threshold and edge response, where the contrast threshold... The normalized threshold is used to remove low-contrast points; the contrast threshold is... The value can be selected as needed; for example, in this embodiment, the value is 0.03. Hessian matrix eigenvalue analysis is used to distinguish edge responses from corner responses. Based on the following formula, pseudo-stable keypoints on the edges are filtered out using the principal curvature ratio to retain features with stable geometric structures: , in, The Hessian matrix is ​​composed of the second derivatives of the Gaussian difference image layers. for H The trace of the Hessian matrix represents the sum of the principal curvatures; for H The product of curvature, r The primary curvature ratio threshold, For the image in x The second derivative in the direction represents the rate of change of the gray value along the horizontal direction. and The images are respectively in x and y The mixed second derivative of the direction represents the joint change of grayscale value in the horizontal and vertical directions. For the image in y The second derivative of the direction represents the rate of change of the gray value along the vertical direction; Calculate the neighborhood gradient magnitude and directional gradient angle based on the surrounding region of the filtered and corrected stable keypoint: , , in, For the stable key points after filtering correction The neighborhood gradient magnitude, , , and These are the positions in the Gaussian smoothed image layer. , , and grayscale value, For the stable key points after filtering correction The directional gradient angle is used to construct a multi-directional histogram based on the neighborhood gradient magnitude and the directional gradient angle. Key points in multiple directions are generated by setting the main direction as the peak value of the histogram and the secondary peaks as greater than the main peak. 3.3) Generate SIFT descriptors, including: rotating the keypoint neighborhood to the main direction, dividing the 16×16 neighborhood into 4×4 sub-regions, counting 8 directional buckets in each region, concatenating them into a 128-dimensional vector according to the following formula, and performing normalization to generate nodes in the graph structure data: , in, For the first in graph structure data i The feature vector of each node For the stable key points after filtering correction The neighborhood gradient magnitude, For the first i The set of pixels in the sub-region of each node. for The pixel position in the image. For indicator functions, For the stable key points after filtering correction The direction gradient angle; Let i be the i-th directional bucket, which is one of eight angular intervals evenly divided within 360°, used to accumulate gradient energy within that angular range; the feature vectors of each node in the graph structure data are used as 128-dimensional SIFT descriptors, and the edge weights in the graph structure data are calculated according to the following formula to obtain the graph structure data: , in, For nodes v i and v j Edge weights between them This is a coefficient for balancing spatial and semantic weights. For nodes v i coordinates For nodes v j coordinates σ s The standard deviation of the Gaussian kernel for spatial distance. For nodes v i 128-dimensional SIFT descriptor, For nodes v j 128-dimensional SIFT descriptor.

[0035] In step 4) of this embodiment, when the graph structure data of vibration signals and electromagnetic signals are used for diagnostic classification using their respective capsule graph network models, the capsule graph network model dynamically routes the input graph structure data of vibration signals or electromagnetic signals to achieve cross-modal feature fusion and output the activated capsule vector according to the following formula: , , , in, Let j be the activated capsule vector output by the graph capsule network model. Let be the weighted sum of the dynamic routing coefficients of the j-th graph capsule network model and the feature vectors of the primary capsules. Let be the dynamic routing coefficient from capsule i to capsule j. Let i be the primary capsule feature vector from capsule i to capsule j. Let be the coupling coefficient from capsule i to capsule j. Let be the coupling coefficient from capsule i to capsule k. Step 4) uses a voting mechanism to fuse the diagnostic classification results of vibration and electromagnetic signals to obtain the final diagnostic classification result, a well-known existing method. For example, voting can be used to select the largest or smallest value of the diagnostic classification result as the final result. Alternatively, the diagnostic classification results of vibration and electromagnetic signals can be weighted and summed as needed to obtain the final diagnostic classification result. Another method is to use a classifier to map the diagnostic classification results of vibration and electromagnetic signals to obtain the final diagnostic classification result.

[0036] This embodiment also includes calculating training metrics after each round of training when training the graphical capsule network model. If training metrics If the training threshold is exceeded, the graph capsule network model is considered to have completed training; otherwise, iterative training needs to continue. The training metrics are calculated as follows. include: Adjust the initial diagnostic weights of each graph capsule network model according to the following formula: , in, The initial diagnostic weights for the m-th graph capsule network model are... Let m be the activated capsule vector output by the m-th graph capsule network model. for The vector magnitude, The activated capsule vector is the output of the nth graph capsule network model. for The vector magnitude, For coefficients, The number of graph capsule network models; the entropy weight coefficients are calculated according to the following formula: ,

[0037] in, Let m be the entropy weight coefficient of the m-th graph capsule network model. Let m be the information entropy of the m-th graph capsule network model. The information entropy of the nth graph capsule network model is... Number of fault categories The predicted probability distribution for each fault category; the training index is calculated according to the following formula. : , in, The voting score for the k types of faults in the m-th graph capsule network model.

[0038] The enhanced voting mechanism in this embodiment uses weighted voting on the diagnostic weights of vibration and electromagnetic signals, and introduces the entropy weight method to dynamically adjust the voting weights, thereby suppressing low-quality signal interference and achieving the training targets. Then it indicates that the graph capsule network model training is complete. For example, in this embodiment, if the following conditions are met: Diagnosis If the accuracy is ≥ 95%, it means the graph capsule network model meets the usage requirements and the modeling is complete. For example... Figure 5As shown, the training of the graph capsule network model includes: initializing the graph capsule network model (electromagnetic-capsule graph network model and vibration-capsule graph network model); randomly selecting I sets of training sets ((x(i), y(i)) and J sets of test sets ((x(j), y(j)) as training data for the graph capsule network model, where x(i) and x(j) are vibration signals / electromagnetic signals, and y(i) and y(j) are fault classification labels; using the training data to perform forward propagation of the graph capsule network model (electromagnetic-capsule graph network model and vibration-capsule graph network model), i.e., computing graph capsules, including node message passing and capsule aggregation within the graph capsule network model; iteratively optimizing capsule alignment and updating coupling coefficients and redistributing feature weights using a dynamic routing algorithm; obtaining vibration signal output / electromagnetic signal output (from the electromagnetic-capsule graph network model and vibration-capsule graph network model); voting on the vibration signal output / electromagnetic signal output to obtain the final result, and calculating the training metric using the test set after each round of training. If training metrics If the target is met, the electromagnetic-capsule graph network model and the vibration-capsule graph network model are considered to have completed training. Otherwise, the Adam optimizer or other optimizers are needed to update the parameters of the electromagnetic-capsule graph network model and the vibration-capsule graph network model, and then continue to iterate and perform forward propagation.

[0039] To verify the motor fault diagnosis method based on color image fusion symmetric point pattern in this embodiment, the method of this embodiment (MCFRes-CapsGNN) is compared with existing motor fault diagnosis methods. Existing motor fault diagnosis methods include Long Short-Term Memory Network (LSTM), Multilayer Perceptron (MLP), Symmetric Equal Variation Convolutional Neural Network (SECNN), CapsNet, and Dynamic Graph Convolutional Network (DGCN). The metrics used include accuracy, precision, recall, and F-score. The final results are shown in Table 1.

[0040] Table 1: Comparison of results between the method in this embodiment and existing motor fault diagnosis methods

[0041] As shown in Table 1, the method in this embodiment (MCFRes-CapsGNN) achieves better results than Long Short-Term Memory Network (LSTM), Multilayer Perceptron (MLP), Symmetric Equivariant Convolutional Neural Network (SECNN), CapsNet, and Dynamic Graph Convolutional Network (DGCN) in terms of accuracy, precision, recall, and F-score.

[0042] Furthermore, considering that the vibration signal collected by the triaxial piezoelectric accelerometer in this embodiment includes vibration signal components in the X, Y, and Z axes, and the final vibration signal is obtained by adding the vibration signal components in the X, Y, and Z axes, an ablation experiment was conducted in this embodiment to fuse the vibration signal components in the X, Y, and Z axes with the final vibration signal. The accuracy of detection was compared using two well-known deep learning models, LeNet and AlexNet, and the results are shown in Table 2.

[0043] Table 2: Comparison of the effectiveness of vibration signal components in the X, Y, and Z axes and the final vibration signal (fusion).

[0044] In Table 2, "X Channel" to "Z Channel" represent the vibration signal components in the X, Y, and Z axes, respectively, and "fusion" indicates the final vibration signal (fusion). As can be seen from Table 2, this embodiment uses a triaxial piezoelectric accelerometer to collect vibration signal components in the X, Y, and Z axes and adds them together to obtain the final vibration signal, which can significantly improve the detection accuracy.

[0045] In summary, the method in this embodiment first collects vibration signals and electromagnetic time-domain signals of the motor under different operating conditions to provide data for fault diagnosis. Then, color image fusion technology is used to convert these time-domain signals into Symmetric Dot Pattern (SDP) images, generating color signal images that fuse multi-dimensional feature information. Next, using the SIFT graph construction method based on feature embedding, the image is abstracted into nodes and edges in a high-dimensional semantic space to construct graph structure data. This graph structure data is input into a graph capsule network, where image features are extracted through the graph capsule layers, and vibration and electromagnetic signals are classified. Finally, an enhanced voting strategy is used to fuse the diagnostic results from different signal sources to improve the accuracy and reliability of the diagnosis. The motor fault diagnosis method and system described in this invention, by integrating multiple advanced technologies, can effectively process multi-source signals, achieving efficient and accurate fault diagnosis, and has broad application prospects, especially in the field of complex and high-risk motor fault detection. By combining image processing with deep learning, the accuracy and robustness of fault diagnosis are improved, demonstrating strong industrial application value.

[0046] Furthermore, this embodiment also provides a motor fault diagnosis system based on color image fusion symmetrical point patterns, including a microprocessor and a memory interconnected, wherein the microprocessor is programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetrical point patterns. Additionally, this embodiment provides a computer-readable storage medium storing a computer program or instructions programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetrical point patterns via a processor. Furthermore, this embodiment also provides a computer program product including a computer program or instructions programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetrical point patterns via a processor.

[0047] Those skilled in the art will understand that the technical solutions provided by this invention may take the form of a method, system, or computer program product. Therefore, this invention may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this invention may take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce an implementation of the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0048] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for motor fault diagnosis based on color image fusion symmetrical point patterns, characterized in that, Includes the following steps: 1) Acquire the vibration and electromagnetic signals of the motor; 2) The vibration signal and electromagnetic signal are converted into symmetrical point pattern images respectively, and a color signal image with fused feature information is generated by color image fusion technology; 3) Based on the scale-invariant feature transformation method of feature embedding, the color signal image with fused feature information is abstracted into nodes and edges in a high-dimensional semantic space, thereby constructing graph structure data composed of nodes and edges; 4) The graph structure data of vibration signals and electromagnetic signals are respectively diagnosed and classified using their respective capsule graph network models, and the diagnostic and classification results of vibration signals and electromagnetic signals are merged through a voting mechanism to obtain the final diagnostic and classification result.

2. The motor fault diagnosis method based on color image fusion symmetrical point pattern according to claim 1, characterized in that, In step 2), when converting the vibration signal and electromagnetic signal into symmetrical point pattern images respectively, this includes processing either the vibration signal or the electromagnetic signal. X ={ x 1, x 2, ..., x n },in x 1~ x n Vibration signal or electromagnetic signal respectively X The first to nth sampled signals, where n is the number of sampled signals, are converted into points in the symmetric point space in polar coordinates according to the following formula. : ， ， ， in, The polar radius of the transformed signal point. X max and X min Time-domain signal X The maximum and minimum values ​​in For the first s Angles of a symmetrical plane θ s =360 m / k , m The index of the mirror-symmetric plane. m =0,1,…, k -1, k , k The number of mirror-symmetric planes. Vibration signal or electromagnetic signal X The i-th sampled data in Vibration signal or electromagnetic signal X The first in One sampled data, To delay, The angle of counterclockwise rotation of the mirror symmetry plane of the transformed signal point. The angle is the clockwise rotation of the mirror symmetry plane of the transformed signal point. For gain angle; based on the point in the symmetric space under polar coordinates The three attributes are used as color values ​​for the three RGB channels to generate a symmetrical dot pattern image.

3. The motor fault diagnosis method based on color image fusion symmetrical point pattern according to claim 1, characterized in that, Step 2) involves generating a color signal image with fused feature information using color image fusion technology. This includes: firstly, calculating the signal energy entropy of each of the three RGB channels. E , cliff K and spectral peak P Construct feature vectors F k =[ E k ， K k ，P k The fusion weights of each channel signal are calculated according to the following formula: ， in, The fusion weight for the k-th channel. This represents the accuracy of this channel in classifying the current fault type based on historical data. β As the adjustment factor, a color signal image with fused feature information is then generated according to the following formula: ， in, To fuse feature information in color signal images, , and These are the fusion weights for the signals from channels 1 to 3, respectively. , and These are images of the red, green, and blue channel signals in the symmetrical point pattern image, respectively.

4. The motor fault diagnosis method based on color image fusion symmetrical point pattern according to claim 1, characterized in that, Step 3) includes: 3.1) By performing Gaussian blurring on the input color signal image at multiple scales, a Gaussian pyramid is constructed from the Gaussian smoothed image layers obtained from the Gaussian blurring at multiple scales. The difference between adjacent scale Gaussian images in the Gaussian pyramid is then calculated according to the following formula to generate the Difference Gaussian Space (DoG): ， in, Represents the difference Gaussian space DoG with respect to Gaussian difference image layers, Indicates about Gaussian kernel function, This is a two-dimensional convolution operation. Color signal images for fusing feature information At coordinate point Pixel values; This is the scale multiplication factor, used to control the interval between adjacent scales; This serves as the baseline scale parameter, used to determine the granularity of feature detection; 3.2) In the Difference Gaussian (DoG) space, the position and scale of candidate keypoints are corrected at the sub-pixel level by fitting a three-dimensional quadratic function or Taylor expansion. The contrast of extreme points is calculated using the Hessian matrix, and unstable keypoints with low contrast are removed according to a preset contrast threshold to obtain stable keypoints. ， in, This is the offset of the keypoint, including corrections for spatial coordinates and scale; This is the contrast threshold, used to filter noise-sensitive points; for The inverse matrix, It is a Gaussian difference function. To stabilize the position of key points In x coordinate, Indicates the contrast at extreme points; Hessian matrix eigenvalue analysis is used to distinguish edge responses from corner responses. Based on the following formula, pseudo-stable keypoints on the edges are filtered out using the principal curvature ratio to retain features with stable geometric structures: ， in, The Hessian matrix is ​​composed of the second derivatives of the Gaussian difference image layers. for H The trace of the Hessian matrix represents the sum of the principal curvatures; for H The product of curvature, r The primary curvature ratio threshold, For the image in x The second derivative in the direction represents the rate of change of the gray value along the horizontal direction. and The images are respectively in x and y The mixed second derivative of the direction represents the joint change of grayscale value in the horizontal and vertical directions. For the image in y The second derivative of the direction represents the rate of change of the gray value along the vertical direction; Calculate the neighborhood gradient magnitude and directional gradient angle based on the surrounding region of the filtered and corrected stable keypoint: ， ， in, For the stable key points after filtering correction The neighborhood gradient magnitude, , , and These are the positions in the Gaussian smoothed image layer. , , and grayscale value, For the stable key points after filtering correction The directional gradient angle is used to construct a multi-directional histogram based on the neighborhood gradient magnitude and the directional gradient angle. Key points in multiple directions are generated by setting the main direction as the peak value of the histogram and the secondary peaks as greater than the main peak. 3.3) Rotate the neighborhood of the key point to the main direction, divide the 16×16 neighborhood into 4×4 sub-regions, count 8 directional buckets in each region, and concatenate them into a 128-dimensional vector according to the following formula, then normalize the vector to generate nodes in the graph structure data: ， in, For the first in graph structure data i The feature vector of each node For the stable key points after filtering correction The neighborhood gradient magnitude, For the first i The set of pixels in the sub-region of each node. for The pixel position in the image. For indicator functions, For the stable key points after filtering correction The direction gradient angle; Let i be the i-th directional bucket, which is one of eight angular intervals evenly divided within 360°, used to accumulate gradient energy within that angular range; the feature vectors of each node in the graph structure data are used as 128-dimensional SIFT descriptors, and the edge weights in the graph structure data are calculated according to the following formula to obtain the graph structure data: ， in, For nodes v i and v j Edge weights between them This is a coefficient for balancing spatial and semantic weights. For nodes v i coordinates For nodes v j coordinates σ s The standard deviation of the Gaussian kernel for spatial distance. For nodes v i 128-dimensional SIFT descriptor, For nodes v j 128-dimensional SIFT descriptor.

5. The motor fault diagnosis method based on color image fusion symmetrical point pattern according to claim 1, characterized in that, In step 4), when using their respective capsule graph network models to diagnose and classify the graph structure data of vibration and electromagnetic signals, the capsule graph network model dynamically routes the input graph structure data of vibration or electromagnetic signals to achieve cross-modal feature fusion and output the activated capsule vector according to the following formula: ， ， ， in, Let j be the activated capsule vector output by the graph capsule network model. Let be the weighted sum of the dynamic routing coefficients of the j-th graph capsule network model and the feature vectors of the primary capsules. Let be the dynamic routing coefficient from capsule i to capsule j. Let i be the primary capsule feature vector from capsule i to capsule j. Let be the coupling coefficient from capsule i to capsule j. Let be the coupling coefficient from capsule i to capsule k.

6. The motor fault diagnosis method based on color image fusion symmetrical point pattern according to claim 1, characterized in that, This also includes calculating the training metrics after each training round when training the graph capsule network model. If training metrics If the preset threshold is exceeded, the graph capsule network model is considered to have completed training; otherwise, iterative training needs to continue. The calculation obtains the training index. include: Adjust the initial diagnostic weights of each graph capsule network model according to the following formula: ， in, The initial diagnostic weights for the m-th graph capsule network model are... Let m be the activated capsule vector output by the m-th graph capsule network model. for The vector magnitude, The activated capsule vector is the output of the nth graph capsule network model. for The vector magnitude, For coefficients, The number of graph capsule network models; the entropy weight coefficients are calculated according to the following formula: ， in, Let m be the entropy weight coefficient of the m-th graph capsule network model. Let m be the information entropy of the m-th graph capsule network model. The information entropy of the nth graph capsule network model is... Number of fault categories The predicted probability distribution for each fault category; the training index is calculated according to the following formula. : ， in, The voting score for the k types of faults in the m-th graph capsule network model.

7. The motor fault diagnosis method based on color image fusion symmetrical point pattern according to claim 1, characterized in that, Step 1) includes training graph network models for vibration and electromagnetic signals respectively. Training the graph network models involves collecting vibration and electromagnetic signals of the motor under different operating conditions as fault diagnosis data. These different operating conditions include normal conditions and various fault conditions. The obtained fault diagnosis data includes the motor fault electromagnetic signal dataset shown in the following formula. : in, For the first i One motor fault signal, For fault labels, Electromagnetic signal dataset for motor faults The number of samples, T The number of sampling points. This is a dataset of electromagnetic fault signals for motors. This is a dataset for motor electromagnetic fault categories. And the motor fault vibration signal dataset shown in the following formula : in, For the first i Vibration signal of a motor fault. For fault labels, Data set of vibration signals for motor faults The number of samples.

8. A motor fault diagnosis system based on color image fusion symmetrical point pattern, comprising a microprocessor and a memory interconnected, characterized in that, The microprocessor is programmed or configured to execute the motor fault diagnosis method based on color image fusion symmetric point pattern as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the motor fault diagnosis method based on color image fusion symmetric point pattern as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the motor fault diagnosis method based on color image fusion symmetric point pattern as described in any one of claims 1 to 7.

Images