Gear multi-sensor cooperative fault diagnosis method

Abstract

The invention provides a gear multi-sensor cooperative fault diagnosis method, which comprises the steps of fusing data of sensors of a gear monitoring platform, emphasizing a mutual relation and time correlation between different time points in time sequence data, and generating a multi-dimensional distance matrix image; and constructing a multi-scale adaptive feature fusion convolutional neural network diagnosis model, and accurately identifying a gear fault by using multi-scale features and pyramid features. In the diagnosis model, designing a multi-scale adaptive feature fusion convolutional neural network, and inputting a multi-dimensional distance matrix image to realize fault diagnosis; a new convolution block is constructed, two large-size depth separable convolves with different sizes are arranged in the convolution block, spatial information is obtained, and attention branches of the convolution block gather position information in two directions; an adaptive fusion module is constructed to adaptively fuse pyramid features, efficient attention and cross-space learning are introduced, learnable weights are generated according to respective importance of features in different stages, and deep and shallow information is comprehensively utilized to diagnose gear faults.

Description

Technical Field

[0001] The present invention relates to the technical field of rotating equipment fault diagnosis, and in particular to a gear multi-sensor collaborative fault diagnosis method based on a multi-dimensional distance matrix and a convolutional network. Background Art

[0002] Multi-sensor collaborative fault diagnosis uses multiple sensors to obtain monitoring data, enhances key information that can reflect the operating status of the equipment, effectively fuses multi-source complementary information through data fusion technology, and effectively diagnoses different types of faults in combination with deep learning models. The existing multi-sensor collaborative fault diagnosis methods for some rotating machinery, including gears, still have the following three problems:

[0003] 1) Existing methods usually develop multi-input models to promote data fusion, but lack solutions to achieve fusion in the data-to-image process. Multi-input models increase computational costs, reduce diagnostic efficiency, and have problems such as difficulty in fitting, which do not meet the requirements of intelligent fault diagnosis in industry.

[0004] 2) Existing methods usually use more traditional deep learning models as the diagnostic framework. These models have problems such as weak feature extraction capabilities and complex calculations, and are not suitable for direct use in intelligent fault diagnosis in industry.

[0005] 3) Existing methods usually only use abstract features in the deep layer of the network for classification, while ignoring favorable diagnostic features such as texture information in shallow features, which limits the performance of intelligent diagnosis models. Summary of the invention

[0006] According to the technical problems raised above, in order to further improve the recognition accuracy of the existing multi-sensor collaborative fault diagnosis method for some rotating machinery, a gear multi-sensor collaborative fault diagnosis method based on multi-dimensional distance matrix and convolutional network is proposed.

[0007] The technical means adopted by the present invention are as follows:

[0008] A gear multi-sensor collaborative fault diagnosis method based on a multi-dimensional distance matrix and a convolutional network, comprising:

[0009] S1, integrates the data of different sensors of the gear monitoring platform, and emphasizes the mutual relationship and time correlation between different time points in the time series data to generate a multi-dimensional distance matrix image;

[0010] S2. Construct a multi-scale adaptive feature fusion convolutional neural network diagnosis model and use multi-scale features and pyramid features to achieve accurate gear fault identification.

[0011] Furthermore, step S1 specifically includes:

[0012] S11. In the data fusion process of multidimensional distance matrix, let A = [a1, a2, ..., a n ],B=[b1,b2,...,b n ],C=[c1,c2,...,c n ] are three sets of time series data with length n;

[0013] S12. Combine the three sets of time series data with length n and timestamp t to obtain X = [(a1, b1, c1, 1), (a2, b2, c2, 2), ..., (a n ,b n ,c n ,n)]; Encode X into a two-dimensional matrix M, and each element in M ​​is recorded as

[0014]

[0015] In the above formula, x i and x j Respectively represent (a i ,b i ,c i ,i) and (a j ,b j ,c j ,j), It is obtained from the multidimensional standard Euclidean distance matrix as follows:

[0016]

[0017] The above formula is a process of solving the multi-dimensional standard Euclidean distance. The above formula calculates the relationship between any two time points in the original time series data from different sources. The purpose of dividing by the standard deviation is to eliminate the influence of different scales. In the formula, σ a ,σ b ,σ c ,σ t are the standard deviations of A, B, C, and t respectively;

[0018] S13, transform M into an antisymmetric matrix M am And mapped to the range of [0,255], the multidimensional distance matrix (MDM) image is obtained as follows:

[0019]

[0020] Furthermore, the multi-scale adaptive feature fusion convolutional neural network diagnostic model constructed in step S2 includes a new convolution block and an adaptive feature fusion module, specifically including:

[0021] S21. Construct a new convolutional block to extract multi-scale information in the image. The attention branch can aggregate the position information of the image in two directions.

[0022] S22. Construct an adaptive feature fusion module to comprehensively utilize pyramid features at different stages for classification tasks.

[0023] Furthermore, the new convolution block utilizes two large-sized depthwise separable convolutions of the main branch to obtain spatial information of different scales, utilizes the attention branch to aggregate position information in two directions and adds two one-dimensional convolution layers on the low dimension to alleviate the limitations of the shared convolution kernel mechanism.

[0024] Furthermore, step S21 specifically includes:

[0025] S211, assuming that the intermediate feature of the processing is The intermediate features are divided into two features in the channel dimension and And use two convolutions to extract features as follows:

[0026] Y1=DWconv 7×7 (X1)

[0027] Y2=DWconv 11×11 (X2)

[0028] Among them, DWconv 7×7 and DWconv 11×11 There are two channel-by-channel convolutions of size 7 and 11. The features processed by these two convolutions are Y1 and Y2 respectively; Y1 and Y2 are concatenated into new main branch features in the channel dimension.

[0029] S212. In the attention branch, use the pooling layers (1, W) and (H, 1) to aggregate the features of X in two directions:

[0030]

[0031] in, and are the output features of width w and height h on the cth channel respectively;

[0032] S213, will and Reduce the dimension and obtain the low-dimensional feature f w and f h :

[0033] f w =σ1(F w1 (z w))

[0034] f h =σ1(F h1 (z h ))

[0035] Among them, F w1 and F h1 There are two convolutional layers of size 1, and σ1 represents the activation function;

[0036] S214, use two one-dimensional convolutional layers to process the features and map them back to high dimensions to obtain the output features g of the attention branch w and g h :

[0037] g w =σ2(F w2 (DWconv1D3(f w )))

[0038] g h =σ2(F h2 (DWconv1D3(f h )))

[0039] Among them, F w1 and F h1 is a convolutional layer of size 1, DWconv1D3 is a one-dimensional convolutional layer of size 3, and σ2 represents the activation function

[0040] S215. Use the output feature of the attention branch to re-weight the output feature Y of the main branch to obtain feature R:

[0041]

[0042] S216. Use a multi-layer perceptron to process R and add it to the body X to obtain the output Q of the convolution block:

[0043] Q=F4(σ1(F3(σ1(R))))+X

[0044] Among them, F3 and F4 are two convolutional layers of size 1.

[0045] Furthermore, the adaptive feature fusion module introduces efficient attention and cross-space learning to extract important local and global information of pre-fused features.

[0046] Further, step S22 specifically includes:

[0047] S221, for a given n different stage features S i , i∈n, alignment feature S i The size of the obtained n S is equal in sizei ′:

[0048] S i ′=Avgpool(F5(S i ))

[0049] Among them, Avgpool is the average pooling operation, F5 is a convolutional layer of size 1;

[0050] S222, use global average pooling to change S i ′ to 1, and concatenate in the H dimension to get a new tensor

[0051] S223. Using efficient attention and cross-space learning to generate a set of learnable weights S″′:

[0052] S″′ L =F6(S″)

[0053] S″′ G =F7(DWconv n×1 (S″)

[0054] S″′=Sigmoid(GAP(S″′ L ))⊙S″′ G +Sigmoid(S″′ G )⊙S″′ L

[0055] Among them, S″′ L and S″′ G are local features and global features, F6 and F7 are two convolutional layers of size 1, DWconv n×1 is a channel-by-channel convolution, and GAP is a global average pooling operation;

[0056] S224, use the softmax function operation on the H dimension to obtain i weights

[0057]

[0058] S225, w i Alignment features S at different stages i ′ are multiplied and then added to obtain the output T of the adaptive feature fusion module:

[0059]

[0060] Compared with the prior art, the present invention has the following advantages:

[0061] 1. The present invention provides a gear multi-sensor collaborative fault diagnosis method based on a multi-dimensional distance matrix and a convolutional network. The proposed multi-dimensional distance matrix method can convert multi-source signals into images. The scheme uses the standard Euclidean distance to emphasize the relationship between any two points in the time series data and retains the time correlation. The multi-dimensional distance matrix fuses data from multiple sensors and is a new scheme for information fusion while encoding images.

[0062] 2. The present invention provides a gear multi-sensor collaborative fault diagnosis method based on a multi-dimensional distance matrix and a convolutional network. In order to enhance the network's ability to obtain multi-scale information, a novel convolution block is constructed. Two large-scale depth-separable convolutions of different sizes in the convolution block are used to obtain spatial information. Its attention branch aggregates position information in two directions, and introduces two one-dimensional convolution layers in low dimensions to suppress the limitation of convolution parameter sharing and enhance the representation of spatial information.

[0063] 3. The present invention provides a gear multi-sensor collaborative fault diagnosis method based on a multi-dimensional distance matrix and a convolutional network, and proposes an adaptive feature fusion module that can utilize the features of different stages of the network to achieve adaptive fusion of pyramid features. The adaptive feature fusion module introduces efficient attention and cross-space learning to extract important local and global information about pre-fusion features. It generates learnable weights for the features at different stages according to their respective importance, and effectively utilizes multi-layer features to improve fault diagnosis performance.

[0064] Based on the above reasons, the present invention can be widely promoted in the fields of rotating equipment fault diagnosis and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0066] Figure 1 Flowchart of the gear diagnosis method of the present invention.

[0067] Figure 2 A multidimensional distance matrix image of multi-source signal encoding of a gear in nine different health states provided by an embodiment of the present invention.

[0068] Figure 3 This is the multi-scale adaptive feature fusion convolutional neural network of the present invention.

[0069] Figure 4 Schematic diagram of the new convolution block of the present invention.

[0070] Figure 5 Schematic diagram of the adaptive feature fusion module of the present invention.

[0071] Figure 6 A rotating equipment test bench is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0073] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0074] like Figure 1 As shown, the present invention provides a gear multi-sensor collaborative fault diagnosis method based on a multi-dimensional distance matrix and a convolutional network, comprising:

[0075] S1, integrates the data of different sensors of the gear monitoring platform, and emphasizes the mutual relationship and time correlation between different time points in the time series data to generate a multi-dimensional distance matrix image;

[0076] S2. Construct a multi-scale adaptive feature fusion convolutional neural network diagnosis model and use multi-scale features and pyramid features to achieve accurate gear fault identification.

[0077] In specific implementation, as a preferred embodiment of the present invention, step S1 specifically includes:

[0078] S11. In the data fusion process of multidimensional distance matrix, let A = [a1, a2, ..., a n ],B=[b1,b2,...,b n ],C=[c1,c2,...,cn ] are three sets of time series data with length n;

[0079] S12. Combine the three sets of time series data with length n and timestamp t to obtain X = [(a1, b1, c1, 1), (a2, b2, c2, 2), ..., (a n ,b n ,c n ,n)]; Encode X into a two-dimensional matrix M, and each element in M ​​is recorded as

[0080]

[0081] In the above formula, x i and x j Respectively represent (a i ,b i ,c i ,i) and (a j ,b j ,c j ,j), It is obtained from the multidimensional standard Euclidean distance matrix as follows:

[0082]

[0083] The above formula is a process of solving the multi-dimensional standard Euclidean distance. The above formula calculates the relationship between any two time points in the original time series data from different sources. The purpose of dividing by the standard deviation is to eliminate the influence of different scales. In the formula, σ a ,σ b ,σ c ,σ t are the standard deviations of A, B, C, and t respectively;

[0084] S13, transform M into an antisymmetric matrix M am And mapped to the range of [0,255], such as Figure 2 As shown, the multidimensional distance matrix (MDM) image is obtained as follows:

[0085]

[0086] When specifically implemented, as a preferred embodiment of the present invention, Figure 3 As shown, the multi-scale adaptive feature fusion convolutional neural network diagnostic model constructed in step S2 includes a new convolution block and an adaptive feature fusion module, specifically including:

[0087] S21. Construct a new convolutional block to extract multi-scale information in the image. The attention branch can aggregate the position information of the image in two directions.

[0088] S22. Construct an adaptive feature fusion module to comprehensively utilize pyramid features at different stages for classification tasks.

[0089] In specific implementation, as a preferred embodiment of the present invention, the new convolution block uses two large-size depth-separable convolutions of the main branch to obtain spatial information of different scales, uses the attention branch to aggregate position information in two directions and adds two one-dimensional convolution layers on the low dimension to alleviate the limitations of the shared convolution kernel mechanism.

[0090] In specific implementation, as a preferred embodiment of the present invention, step S21, as Figure 4 As shown, specifically including:

[0091] S211, assuming that the intermediate feature of the processing is The intermediate features are divided into two features in the channel dimension and And use two convolutions to extract features as follows:

[0092] Y1=DWconv 7×7 (X1)

[0093] Y2=DWconv 11×11 (X2)

[0094] Among them, DWconv 7×7 and DWconv 11×11 There are two channel-by-channel convolutions of size 7 and 11. The features processed by these two convolutions are Y1 and Y2 respectively; Y1 and Y2 are concatenated into new main branch features in the channel dimension.

[0095] S212. In the attention branch, use the pooling layers (1, W) and (H, 1) to aggregate the features of X in two directions:

[0096]

[0097] in, and are the output features of width w and height h on the cth channel respectively;

[0098] S213, will and Reduce the dimension and obtain the low-dimensional feature f w and f h :

[0099] f w=σ1(F w1 (z w ))

[0100] f h =σ1(F h1 (z h ))

[0101] Among them, F w1 and F h1 There are two convolutional layers of size 1, and σ1 represents the activation function;

[0102] S214, use two one-dimensional convolutional layers to process the features and map them back to high dimensions to obtain the output features g of the attention branch w and g h :

[0103] g w =σ2(F w2 (DWconv1D3(f w )))

[0104] g h =σ2(F h2 (DWconv1D3(f h )))

[0105] Among them, F w1 and F h1 is a convolutional layer of size 1, DWconv1D3 is a one-dimensional convolutional layer of size 3, and σ2 represents the activation function

[0106] S215. Use the output feature of the attention branch to re-weight the output feature Y of the main branch to obtain feature R:

[0107]

[0108] S216. Use a multi-layer perceptron to process R and add it to the body X to obtain the output Q of the convolution block:

[0109] Q=F4(σ1(F3(σ1(R))))+X

[0110] Among them, F3 and F4 are two convolutional layers of size 1.

[0111] In specific implementation, as a preferred embodiment of the present invention, the adaptive feature fusion module introduces efficient attention and cross-space learning to extract important local and global information of pre-fused features. It generates learnable weights for features at different stages according to their respective importance, which is an efficient feature fusion technology.

[0112] In specific implementation, as a preferred embodiment of the present invention, step S22, as Figure 5 As shown, specifically including:

[0113] S221, for a given n different stage features S i , i∈n, alignment feature S i The size of the obtained n S is equal in size i ′:

[0114] S i ′=Avgpool(F5(S i ))

[0115] Among them, Avgpool is the average pooling operation, F5 is a convolutional layer of size 1;

[0116] S222, use global average pooling to change S i ′ to 1, and concatenate in the H dimension to get a new tensor

[0117] S223. Using efficient attention and cross-space learning to generate a set of learnable weights S″′:

[0118] S″′ L =F6(S″)

[0119] S″′ G =F7(DWconv n×1 (S″)

[0120] S″′=Sigmoid(GAP(S″′ L ))⊙S″′ G +Sigmoid(S″′ G )⊙S″′ L

[0121] Among them, S″′ L and S″′ G are local features and global features, F6 and F7 are two convolutional layers of size 1, DWconv n×1 is a channel-by-channel convolution, and GAP is a global average pooling operation;

[0122] S224, use the softmax function operation on the H dimension to obtain i weights

[0123]

[0124] S225, w i Alignment features S at different stages i ′ are multiplied and then added to obtain the output T of the adaptive feature fusion module:

[0125]

[0126] Example

[0127] Experimental data introduction

[0128] By Figure 6 The rotating equipment test bench shown in the figure collects data of gears in various health states to verify the effectiveness of the proposed method. The test bench includes two accelerometers, a microphone, a gearbox and a data collector. The sampling frequency is set to 20kHz and the motor speed is 1430r / min. The constructed dataset includes a set of healthy data and eight sets of fault data. Failure modes such as cracks, pitting, spalling and wear are simulated. Each type of data is divided into 1000 samples with a sample length of 1000. The fault modes and labels are shown in Table 1.

[0129] Table 1 Detailed classification information of category labels and samples

[0130]

[0131] Comparative Experimental Setup

[0132] The purpose of this section is to verify the effectiveness and superiority of the proposed multi-dimensional distance matrix image and multi-scale adaptive feature fusion convolutional neural network. The hardware environment of the experimental verification process is Intel Core i5-12400F CPU processor, a single NVIDIA GeForce RTX 3060 graphics processing unit, and Win11 operating system. During the training process of the proposed method and the comparative method, the number of model updates was set to 50 times and the number of batch processing was set to 32. The Adam optimization algorithm was used to update the feature extractor, set the initial learning rate to 0.001, and decrease it by 0.5 times with 5 steps. In order to reduce the randomness of the experimental results, each group of comparative experiments was repeated 5 times during algorithm verification.

[0133] In order to further verify the performance of the proposed method, this embodiment introduces several comparison methods. The experimental results are shown in Table 2, where MAFFCNN is the proposed multi-scale adaptive feature fusion convolutional neural network (multi-scaleadaptive feature fusion CNN, MAFFCNN). Among them, ConvNext-tiny, ResNet18, MobileNetV3-small and MobileNetV3-large are popular CNN models, which are used in many artificial intelligence applications including fault diagnosis. LICNN and SC-MSCNN are the latest proposed fault diagnosis models. RGB images are a commonly used method in multi-sensor fault diagnosis schemes to fuse data from multiple sources.

[0134] Results Analysis

[0135] This embodiment was tested five times, and the classification results were expressed by the average value and the maximum value of the diagnostic accuracy. It should be noted that the self-built gear dataset has a certain degree of noise in the data acquisition process, which is more in line with the real industrial environment and increases the rationality of the proposed method. Table 2 shows the statistical results of the diagnostic accuracy of the proposed method and other comparative methods.

[0136] Table 2 Statistics of the accuracy of different diagnostic methods

[0137]

[0138] 1) The multidimensional distance matrix image can achieve good performance in different models, and the diagnostic accuracy is quite stable, which proves that the multidimensional distance matrix image has excellent ability and good generalization performance in fusion encoding of multiple gear fault signals.

[0139] 2) On the multi-scale adaptive feature fusion convolutional neural network, the gear diagnosis method based on the multi-dimensional distance matrix image can achieve an accuracy of 99.6%, which is better than the 99.2% accuracy of the traditional RGB image. This proves that the multi-dimensional distance matrix image has better performance than the traditional method in multi-source information fusion.

[0140] 3) Among the various diagnostic models that use multi-dimensional distance matrix images as input, the diagnostic accuracy of the multi-scale adaptive feature fusion convolutional neural network is 99.6%, and the diagnostic accuracy of other models ranges from 97.2% to 99.0%. This proves the superiority of the multi-scale adaptive feature fusion convolutional neural network as a gear diagnosis model.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A gear multi-sensor collaborative fault diagnosis method, characterized in that: include: S1, integrates the data of different sensors of the gear monitoring platform, and emphasizes the mutual relationship and time correlation between different time points in the time series data to generate a multi-dimensional distance matrix image; S2. Construct a multi-scale adaptive feature fusion convolutional neural network diagnosis model and use multi-scale features and pyramid features to achieve accurate gear fault identification.

2. A gear multi-sensor collaborative fault diagnosis method according to claim 1, characterized in that: Step S1 specifically includes: S11. In the data fusion process of multidimensional distance matrix, let A = [a1, a2, ..., a n ],B=[b1,b2,...,b n ],C=[c1,c2,...,c n ] are three sets of time series data with length n; S12. Combine the three sets of time series data with length n and timestamp t to obtain X = [(a1, b1, c1, 1), (a2, b2, c2, 2), ..., (a n ,b n ,c n ,n)]; Encode X into a two-dimensional matrix M, and each element in M ​​is recorded as In the above formula, x i and x j Respectively represent (a i ,b i ,c i ,i) and (a j ,b j ,c j ,j), It is obtained from the multidimensional standard Euclidean distance matrix as follows: The above formula is a process of solving the multi-dimensional standard Euclidean distance. The above formula calculates the relationship between any two time points in the original time series data from different sources. The purpose of dividing by the standard deviation is to eliminate the influence of different scales. In the formula, σ a ,σ b ,σ c ,σ t are the standard deviations of A, B, C, and t respectively; S13, transform M into an antisymmetric matrix M am And mapped to the range of [0,255], the multidimensional distance matrix (MDM) image is obtained as follows:

3. The gear multi-sensor collaborative fault diagnosis method according to claim 1, characterized in that: The multi-scale adaptive feature fusion convolutional neural network diagnostic model constructed in step S2 includes a new convolution block and an adaptive feature fusion module, specifically including: S21. Construct a new convolutional block to extract multi-scale information in the image. The attention branch can aggregate the position information of the image in two directions. S22. Construct an adaptive feature fusion module to comprehensively utilize pyramid features at different stages for classification tasks.

4. A gear multi-sensor collaborative fault diagnosis method according to claim 3, characterized in that: The new convolutional block utilizes two large-sized depthwise separable convolutions of the main branch to obtain spatial information of different scales, utilizes the attention branch to aggregate position information in two directions and adds two one-dimensional convolutional layers on the low dimension to alleviate the limitations of the shared convolution kernel mechanism.

5. A gear multi-sensor collaborative fault diagnosis method according to claim 4, characterized in that: Step S21 specifically includes: S211, assuming that the intermediate feature of the processing is The intermediate features are divided into two features in the channel dimension and And use two convolutions to extract features as follows: Y1=DWconv 7×7 (X1) Y2=DWconv 11×11 (X2) Among them, DWconv 7×7 and DWconv 11×11 There are two channel-by-channel convolutions of size 7 and 11. The features processed by these two convolutions are Y1 and Y2 respectively; Y1 and Y2 are concatenated into new main branch features in the channel dimension. S212. In the attention branch, use the pooling layers (1, W) and (H, 1) to aggregate the features of X in two directions: in, and are the output features of width w and height h on the cth channel respectively; S213, will and Reduce the dimension and obtain the low-dimensional feature f w and f h : f w =σ1(F w1 (z w )) f h =σ1(F h1 (z h )) Among them, F w1 and F h1 There are two convolutional layers of size 1, and σ1 represents the activation function; S214, use two one-dimensional convolutional layers to process the features and map them back to high dimensions to obtain the output features g of the attention branch w and g h : g w =σ2(F w2 (DWconv1D3(f w ))) g h =σ2(F h2 (DWconv1D3(f h ))) Among them, F w1 and F h1 is a convolutional layer of size 1, DWconv1D3 is a one-dimensional convolutional layer of size 3, and σ2 represents the activation function S215. Use the output feature of the attention branch to re-weight the output feature Y of the main branch to obtain feature R: S216. Use a multi-layer perceptron to process R and add it to the body X to obtain the output Q of the convolution block: Q=F4(σ1(F3(σ1(R))))+X Among them, F3 and F4 are two convolutional layers of size 1.

6. A gear multi-sensor collaborative fault diagnosis method according to claim 3, characterized in that: The adaptive feature fusion module introduces efficient attention and cross-space learning to extract important local and global information of pre-fused features.

7. A gear multi-sensor collaborative fault diagnosis method according to claim 6, characterized in that: Step S22 specifically includes: S221, for a given n different stage features S i , i∈n, alignment feature S i The size of the obtained n S is equal in size i ′: S i ′=Avgpool(F5(S i )) Among them, Avgpool is the average pooling operation, F5 is a convolutional layer of size 1; S222, use global average pooling to change S i ′ to 1, and concatenate in the H dimension to get a new tensor S223. Using efficient attention and cross-space learning to generate a set of learnable weights S″′: S′ L ″=F6(S″) S′ G ″=F7(DWconv n×1 (S″)) S″′=Sigmoid(GAP(S′ L ″))⊙S′ G ″+Sigmoid(S′ G )⊙S″′L Among them, S′ L ″ and S′ G ″ is the local feature and the global feature, F6 and F7 are two convolutional layers of size 1, DWconv n×1 is a channel-by-channel convolution, and GAP is a global average pooling operation; S224, use the softmax function operation on the H dimension to obtain i weights S225, w i Alignment features S at different stages i ′ are multiplied and then added to get the output T of the adaptive feature fusion module:

Images