Bevel gear capacity expansion diagnosis method and system based on three-direction vibration fusion angle field image

Abstract

The invention discloses a bevel gear capacity expansion diagnosis method and system based on a three-direction vibration fusion angle field image, belongs to the field of mechanical fault diagnosis, and realizes conversion from a vibration signal to an angle field image by adopting a Grubby angle difference field of three-direction measurement data fusion of an acceleration sensor. The image after the three-channel data fusion can highlight the running state characteristics of the helical gear in color and texture. And designing a generative adversarial network model of double-branch discriminator deep feature fusion, so that the capacity expansion quality of small sample data can be improved. A stacked block convolutional neural network model with inverted triangular channel distribution is designed, and the feature extraction capability of a fault diagnosis model can be improved by performing matching design on the number of channels input in each stage. According to the method, intelligent and accurate fault diagnosis of the helical gear is realized, and the problem of inaccurate fault diagnosis caused by insufficient sample quantity, unprominent sample features and insufficient model feature extraction capability of a conventional method is solved.

Description

Technical Field

[0001] The present invention belongs to the field of mechanical fault diagnosis, relates to the field of helical gear fault diagnosis, and specifically relates to a helical gear expansion diagnosis method and system based on three-way vibration fusion angular field images. Background Art

[0002] Gearboxes are an important component of industrial equipment. They have the advantages of high transmission efficiency and strong load-bearing capacity, and are widely used in various industrial fields. However, due to the complex working conditions of gearboxes, the gear failure rate is high during the transmission process, which poses a hidden danger to the safety of the equipment. Helical gears are more stable than spur gears, but their force characteristics determine that it is unreliable to use unidirectional sensors to express the working status. When monitoring the condition of mechanical equipment, since it is in a healthy or normally degraded state most of the time, a large amount of multi-type fault data is difficult to obtain in a short time. At the same time, the collection and manual annotation of big data is time-consuming and labor-intensive. Therefore, data-driven gear fault diagnosis technology needs to deal with the problem that small samples cannot be effectively deep-learned.

[0003] Generally, mechanical equipment is very sensitive to vibration signals, and vibration is the primary means of mechanical fault diagnosis. However, vibration signals are usually affected by complex working conditions, environmental interference, etc. and show non-stationary characteristics. Images can make up for the defects of one-dimensional signals such as vibration in expressing equipment operation characteristics, and can significantly enhance the expression of mechanical equipment operation characteristics, which is conducive to accurate fault diagnosis. In addition, intelligent fault diagnosis based on convolutional neural networks is one of the mainstream methods of gear fault diagnosis at present, but deep learning models such as convolutional neural networks have data adaptability problems, that is, the intelligent diagnosis model of mechanical faults based on deep learning methods is difficult to generalize, and needs to be trained and verified according to the specific characteristics of different data to meet the actual needs of engineering. Summary of the invention

[0004] The purpose of the present invention is to provide a helical gear expansion diagnosis method and system based on three-way vibration fusion angular field image, so as to overcome the problems of sensor direction measurement differences and difficulty in deep learning of small samples in helical gear fault diagnosis. The present invention designs a three-way vibration fusion Gram angular difference field image conversion method, and uses a generative adversarial network model with deep feature fusion of a dual-branch discriminator to expand the sample capacity of a small sample data set, combined with a stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution with strong generalization ability, to achieve intelligent and accurate fault diagnosis of helical gears under small samples.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] The helical gear expansion diagnosis method based on three-way vibration fusion angular field image includes the following steps:

[0007] 1) Constructing a helical gear fault feature dataset

[0008] A three-dimensional acceleration sensor is used to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear to obtain a three-dimensional vibration signal. The three-dimensional vibration signal is segmented and approximated according to the specified number of points and normalized to be converted into a GADF image. The pixel points of the GADF image corresponding to the three directions are normalized to between 0 and 255, and their colors are mapped to R, G, and B respectively to establish an RGB-GADF image. The RGB-GADF image is downsampled to a preset size to obtain a new image. After manually labeling the new image, a helical gear fault feature dataset is established, and it is divided into a training set and a test set.

[0009] 2) Build a sample expansion model

[0010] A sample expansion model is constructed using a helical gear fault feature dataset. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a test image with the same size as the RGB-GADF image. The discriminator is a double-branch deep feature fusion structure. The double-branch discriminator is composed of multiple layers of convolution and batch normalization and activation functions are added. The deep features extracted by the double-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the deep overall features and significant features extracted by the two are spliced ​​into a vector and input into a multi-layer perceptron composed of several fully connected layers. Finally, the multi-layer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator inputs the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability. The weight parameters of the optimal expansion model are selected and saved using the index for evaluating the similarity of the sample structure, and the weight parameters are called to expand the sample. The new training set is composed of a mixture of the generated samples and the original training samples, that is, the helical gear fault feature dataset;

[0011] 3) Build a fault diagnosis model

[0012] A stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is constructed, wherein the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution comprises a feature extractor and a classifier, wherein the feature extractor comprises four-stage stacked block layers, and the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is trained using a helical gear fault feature data set, and after training, the optimal fault diagnosis model weight parameters are saved to obtain a fault diagnosis model;

[0013] 4) Fault diagnosis

[0014] According to step 1), the helical gear test data is collected and converted into RGB-GADF images as a test set. The fault diagnosis model is used to perform fault diagnosis on the test set data to complete the fault diagnosis of the helical gear.

[0015] Furthermore, in step 1), a helical gear fault feature data set is constructed, specifically:

[0016] 1.1) Use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear. The three-dimensional vibration signals are subjected to PAA at the specified number of points and normalized and then converted into GADF images. The PAA is to segment the vibration signal through a pre-set local window, calculate the average value of each segment of the vibration signal after segmentation, and reconstruct the time series data using the average values ​​of all segments. The GADF image conversion process is as follows:

[0017] ① For time series data X = {x1, x2, ..., x n} to normalize and transform the amplitude to [-1,1]. The calculation formula is as follows:

[0018]

[0019] Where: x i is the i-th value of the time series data; is the i-th value of the time series data after normalization; max(X) is the maximum value of the time series data; min(X) is the minimum value of the time series data;

[0020] ② Convert the normalized value into the cosine value of the angle through calculation, use the timestamp as the radius, and convert the transformed time series data from the Cartesian coordinate system to the polar coordinate system. The calculation formulas for the polar angle and polar diameter in the polar coordinates are as follows:

[0021]

[0022] Where: is the i-th value of the normalized time series data; for The corresponding polar angle; t i is the timestamp corresponding to the i-th value of the time series data; N is the constant factor for adjusting the span of the polar coordinate system; r i is the polar radius corresponding to the i-th value of the time series data;

[0023] ③ Use trigonometric function difference to represent the correlation between each time point of the GADF image. During the conversion, the GADF image is established by calculating the angle difference of the sine function. The GADF image calculation is as follows:

[0024]

[0025] Where GADF is the GADF image; sin is the sine function; φ1 is the polar angle corresponding to the first data point; φ n The polar angle corresponding to the nth data point;

[0026] 1.2) Normalize the GADF image pixels corresponding to the three directions to between 0 and 255, and map their colors to R, G, and B respectively. Input the image information corresponding to the three directions into the three channels of the RGB image to construct the RGB-GADF image.

[0027] 1.3) Proportionally transform the converted RGB-GADF image to 256×256 pixels;

[0028] 1.4) All the obtained RGB-GADF images are marked according to different bevel gear states, and divided into training sets and test sets according to preset requirements.

[0029] Furthermore, the designated number of points is set according to the sampling frequency and the rotation speed of the shaft where the bevel gear is located, and each signal segment of the designated number of points contains at least 1 / 4 cycle information.

[0030] Furthermore, in step 1.1), the local window size preset by PAA is 2.

[0031] Furthermore, in step 1.4), x RGB-GADF images of each category are preset in the training set, and y RGB-GADF images of each category are preset in the test set, where x≥y.

[0032] Furthermore, in step 2), a sample expansion model is constructed, specifically:

[0033] 2.1) A sample expansion model is constructed using the helical gear fault feature dataset. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a new image with the same size as the RGB-GADF image.

[0034] 2.2) The discriminator is a dual-branch deep feature fusion structure, which is composed of multi-layer convolution and adds batch normalization and activation function. The deep features extracted by the dual-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the deep overall features and significant features extracted by the two are spliced ​​into a vector, which is input into a multi-layer perceptron composed of several fully connected layers. Finally, the multi-layer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator input is the new sample output by the generator and the training sample in the training set, and the output is the sample discrimination probability;

[0035] 2.3) Using the index for evaluating sample structure similarity, the weight parameters of the optimal expansion model are selected and saved, and the weight parameters are called to expand the sample. The new training set is composed of a mixture of generated samples and original training samples.

[0036] Furthermore, in step 3), a fault diagnosis model is constructed, specifically:

[0037] 3.1) constructing a stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution, wherein the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution comprises a feature extractor and a classifier, and the feature extractor comprises four-stage stacked block layers;

[0038] 3.2) Use the new training set expanded in step 2) to train the fault diagnosis model, update the weight parameters of the fault diagnosis model based on the performance of the fault diagnosis model on the training set, and use the classification accuracy of the fault diagnosis model on the test set as the evaluation index. The classification accuracy calculation formula is:

[0039]

[0040] Where: A represents the classification accuracy of the test set, P represents the number of correctly classified samples in the test set, and Q represents the total number of samples in the test set;

[0041] 3.3) In the model testing phase, the test set in 3.2) is substituted into the fault diagnosis model, and the classification accuracy of the fault diagnosis model on the test set is used as an evaluation indicator. When the classification accuracy is greater than or equal to 90%, the optimal fault diagnosis model weight parameters are saved.

[0042] Furthermore, the stacking ratio of the number of layers of the stacked block layers in the four stages is 3:3:9:3, and the number of input channels decreases successively, namely 128, 64, 32 and 16, respectively.

[0043] Furthermore, the fault diagnosis in step 4) is specifically as follows:

[0044] 4.1) Using the operation in step 1), collect the vibration signal of the helical gear, convert the vibration signal into an RGB-GADF image and use it as the test set data;

[0045] 4.2) Use the fault diagnosis model trained with the new training set expanded in step 3), import the fault diagnosis weights, and input the test set data to complete the fault diagnosis of the helical gear.

[0046] Helical gear expansion diagnosis system based on three-way vibration fusion angular field image, including:

[0047] Helical gear fault feature data set construction module: used to use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear to obtain the three-dimensional vibration signal. The three-dimensional vibration signal is segmented and approximated according to the specified number of points and normalized to be converted into a GADF image. Then, the pixel points of the GADF image corresponding to the three directions are normalized to between 0 and 255, and their colors are mapped to R, G, and B respectively to establish an RGB-GADF image. The RGB-GADF image is downsampled to a preset size to obtain a new image. After manually labeling the new image, a helical gear fault feature data set is established, and it is divided into a training set and a test set.

[0048] Sample expansion model construction module: used to construct a sample expansion model using the helical gear fault feature data set. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a test image with the same size as the RGB-GADF image. The discriminator is a double-branch deep feature fusion structure. The double-branch discriminator is composed of multiple layers of convolution and batch normalization and activation functions are added. The deep features extracted by the double-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the The deep overall features and significant features extracted by the two are spliced ​​into a vector and input into a multilayer perceptron composed of several fully connected layers. Finally, the multilayer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator inputs the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability. The weight parameters of the optimal expansion model are selected and saved by using the index for evaluating the similarity of sample structures. The weight parameters are called for sample expansion. The new training set is composed of a mixture of generated samples and original training samples, that is, the helical gear fault feature data set.

[0049] Fault diagnosis model construction module: used to construct a stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution, the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution includes a feature extractor and a classifier, the feature extractor includes four-stage stacked block layers, the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is trained using a helical gear fault feature data set, and after training, the optimal fault diagnosis model weight parameters are saved to obtain a fault diagnosis model;

[0050] Fault diagnosis module: It is used to collect the helical gear test data in the manner of building a module based on the helical gear fault feature dataset, and convert it into RGB-GADF images as a test set. The fault diagnosis model is used to perform fault diagnosis on the test set data to complete the fault diagnosis of the helical gear.

[0051] Compared with the prior art, the present invention has the following beneficial technical effects:

[0052] 1) Aiming at the problem that the vibration signal collected by a single-direction sensor cannot fully characterize the operating state of the helical gear, a sample conversion method is proposed to use the RGB-GADF image fused with the three-way vibration sensor data to characterize the fault characteristics of the helical gear. The RGB-GADF image can highlight the operating characteristics of different helical gear states in terms of color and texture, avoiding the influence of the number of sensors installed and the measurement direction, and is suitable for helical gear fault diagnosis.

[0053] 2) In order to solve the problem that small samples are difficult to learn deeply in helical gear fault diagnosis, an intelligent fault diagnosis model combining generative adversarial network with stacked block convolutional neural network is proposed, and a generative adversarial network model with deep feature fusion of dual-branch discriminator is designed. By fusing the deep overall information and significant information of the discriminator, the sample expansion quality is improved compared with the traditional generative adversarial network. The matching design of the number of input channels of the stacked block convolutional neural network fault diagnosis model improves the generalization ability and diagnostic accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings in the specification are used to provide further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0055] Figure 1 It is a flow chart of the helical gear expansion diagnosis method based on three-way vibration fusion angular field image;

[0056] Figure 2 RGB-GADF images generated from the three-way vibration signals of helical gears in different states, where (a) is the normal state, (b) is the local broken tooth, (c) is the pitting on the tooth surface, (d) is the tooth surface wear, and (e) is the tooth root crack;

[0057] Figure 3 Schematic diagram of constructing a sample expansion model, where (a) is a schematic diagram of the generator structure, and (b) is a schematic diagram of the discriminator structure;

[0058] Figure 4 Schematic diagram of sample generation, where (a) is the normal state of data set A after expansion, (b) is the local tooth breakage after data set A expansion, (c) is the tooth surface pitting after data set A expansion, (d) is the tooth surface wear after data set A expansion, (e) is the tooth root crack after data set A expansion, (f) is the normal state of data set B after expansion, (g) is the local tooth breakage after data set B expansion, (h) is the tooth surface pitting after data set B expansion, (i) is the tooth surface wear after data set B expansion, (j) is the tooth root crack after data set B expansion;

[0059] Figure 5 To construct a schematic diagram of a fault diagnosis model;

[0060] Figure 6 The corresponding diagnosis results before and after expansion under different data sets, where (a) is the diagnosis result of data set A before expansion, (b) is the diagnosis result of data set A after expansion, (c) is the diagnosis result of data set B before expansion, and (d) is the diagnosis result of data set B after expansion;

[0061] Figure 7 Schematic diagram comparing the fault diagnosis results of the fault diagnosis model of the present invention and the ConvNeXt-Tiny model, wherein (a) is the diagnosis result of the ConvNeXt-Tiny model, and (b) is the diagnosis result of the present invention. DETAILED DESCRIPTION

[0062] 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.

[0063] It should be understood that the numbers used in this way are interchangeable where appropriate, so that the embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein. In addition, the terms "comprises" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or apparatus.

[0064] Embodiment 1

[0065] The helical gear expansion diagnosis method based on three-way vibration fusion angular field image includes the following steps:

[0066] 1) Construct a helical gear fault feature dataset: Use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear to obtain a three-dimensional vibration signal. The three-dimensional vibration signal is piecewise aggregation approximation (PAA) according to the specified number of points and normalized and converted into a Gramian angular difference field (GADF) image. Then, the pixels of the GADF image corresponding to the three directions are normalized to between 0 and 255 and their colors are mapped to red (R), green (G), and blue (B) respectively to establish an RGB-GADF image. The RGB-GADF image is downsampled to the image input size required by the sample expansion model and the fault diagnosis model to obtain a new image. After manually labeling the new image, a helical gear fault feature dataset is established and divided into a training set and a test set.

[0067] The specific steps for constructing the helical gear fault feature dataset in step 1) are as follows:

[0068] 1.1) Use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear. The three-dimensional vibration signals are subjected to PAA at the specified number of points and normalized and then converted into GADF images. The PAA is to segment the vibration signal through a pre-set local window, calculate the average value of each segment of the vibration signal after segmentation, and reconstruct the time series data using the average values ​​of all segments. The GADF image conversion process is as follows:

[0069] ① For time series data X = {x1, x2, ..., x n} to normalize and transform the amplitude to [-1,1]. The calculation formula is as follows:

[0070]

[0071] Where: x i is the i-th value of the time series data; is the i-th value of the time series data after normalization; max(X) is the maximum value of the time series data; min(X) is the minimum value of the time series data.

[0072] ② Convert the normalized value into the cosine value of the angle through calculation, use the timestamp as the radius, and convert the transformed time series data from the Cartesian coordinate system to the polar coordinate system. The calculation formulas for the polar angle and polar diameter in the polar coordinates are as follows:

[0073]

[0074] Where: is the i-th value of the normalized time series data; for The corresponding polar angle; t i is the timestamp corresponding to the i-th value of the time series data; N is the constant factor for adjusting the span of the polar coordinate system; r i is the polar radius corresponding to the i-th value of the time series data.

[0075] ③ Use trigonometric function difference to represent the correlation between each time point of the GADF image. During the conversion, the GADF image is established by calculating the angle difference of the sine function. The GADF image calculation is as follows:

[0076]

[0077] Where GADF is the GADF image; sin is the sine function; φ1 is the polar angle corresponding to the first data point; φ n The polar angle corresponding to the nth data point.

[0078] 1.2) Normalize the GADF image pixels corresponding to the three directions to between 0 and 255, and map their colors to red, green, and blue, respectively. Input the image information corresponding to the three directions into the three channels of the RGB image to construct the RGB-GADF image.

[0079] 1.3) Proportionally transform the converted RGB-GADF image to 256×256 pixels;

[0080] 1.4) All the RGB-GADF images obtained are marked according to different bevel gear states, and divided into training sets and test sets according to preset requirements. The training set is preset with x RGB-GADF images per category, and the test set is preset with y RGB-GADF images per category, where x ≥ y, "category" refers to bevel gears with different fault types, and x and y refer to the number of training sets and test sets per category, respectively.

[0081] 2) Constructing a sample expansion model: constructing a helical gear fault feature dataset through the operation in step 1), and constructing a sample expansion model using the helical gear fault feature dataset. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a test image with the same size as the RGB-GADF image. The discriminator is a double-branch deep feature fusion structure. The double-branch discriminator is composed of multiple layers of convolution and batch normalization and activation functions are added. The deep features extracted by the double-branch discriminator are shunted to the adaptive average pooling and Adaptive maximum pooling, and concatenate the deep overall features and significant features extracted by the two into a vector, input it into a multilayer perceptron composed of several fully connected layers, and finally the multilayer perceptron outputs the result and updates the gradient through the loss function feedback. The discriminator inputs the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability. The weight parameters of the optimal expansion model are selected and saved by using the index for evaluating the similarity of the sample structure, and the weight parameters are called for sample expansion. The new training set is composed of a mixture of the generated samples and the original training samples, that is, the helical gear fault feature data set;

[0082] The specific steps for building the sample expansion model in step 2) are as follows:

[0083] 2.1) constructing a helical gear fault feature dataset through the operation in step 1), and constructing a sample expansion model using the helical gear fault feature dataset, wherein the sample expansion model comprises a generator and a discriminator, wherein the generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added, the input is random noise, and the output is a new image of the same size as the RGB-GADF image;

[0084] 2.2) The discriminator is a dual-branch deep feature fusion structure, which is composed of multi-layer convolution and adds batch normalization and activation function. The deep features extracted by the dual-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the deep overall features and significant features extracted by the two are spliced ​​into vectors and input into a multi-layer perceptron composed of several fully connected layers. Finally, the multi-layer perceptron outputs the results and performs gradient update through loss function feedback. The discriminator input is the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability;

[0085] 2.3) Using the index for evaluating sample structure similarity, the weight parameters of the optimal expansion model are selected and saved, and the weight parameters are called to expand the sample. The new training set is composed of a mixture of generated samples and original training samples.

[0086] 3) Constructing a fault diagnosis model: Use the helical gear fault feature dataset constructed in step 2) to construct a stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution, wherein the stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution comprises a feature extractor and a classifier, wherein the feature extractor comprises four-stage stacked block layers, wherein the stacking ratio of the four-stage stacked block layers is 3:3:9:3, and the number of input channels decreases successively, namely, 128, 64, 32 and 16, respectively. The helical gear fault feature dataset is used to train the stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution, and after training, the optimal fault diagnosis model weight parameters are saved to obtain a fault diagnosis model.

[0087] The specific steps of building a fault diagnosis model in step 3) are as follows:

[0088] 3.1) constructing a stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution, wherein the stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution comprises a feature extractor and a classifier, wherein the feature extractor comprises four-stage stacked block layers, wherein the stacking ratio of the number of layers of the four-stage stacked block layers is 3:3:9:3, and the number of input channels decreases in sequence, namely, 128, 64, 32, and 16;

[0089] 3.2) Use the new training set expanded in step 2) to train the fault diagnosis model, update the weight parameters of the fault diagnosis model based on the performance of the fault diagnosis model on the training set, and use the classification accuracy of the fault diagnosis model on the test set as the evaluation index. According to the fault diagnosis algorithm evaluation requirements in the "National Standard of the People's Republic of China (GB / T 43555-2023)" "Intelligent Service Predictive Maintenance Algorithm Evaluation Method", the accuracy qualification index of the machine learning algorithm is greater than 70%, and the classification accuracy calculation formula is:

[0090]

[0091] Where: A represents the classification accuracy of the test set, P represents the number of correctly classified samples in the test set, and Q represents the total number of test set samples.

[0092] 3.3) In the model testing phase, the test set in 3.2) is substituted into the fault diagnosis model, and the classification accuracy of the fault diagnosis model on the test set is used as an evaluation indicator. When the classification accuracy is greater than or equal to 90%, the optimal fault diagnosis model weight parameters are saved.

[0093] 4) Fault diagnosis: According to step 1), the helical gear test data is collected and converted into RGB-GADF images as a test set. The fault diagnosis model is used to perform fault diagnosis on the test set data to complete the fault diagnosis of the helical gear.

[0094] The specific steps for fault diagnosis in step 4) are as follows:

[0095] 4.1) Using the operation in step 1), collect the vibration signal of the helical gear, convert the vibration signal into an RGB-GADF image and use it as the test set data;

[0096] 4.2) Use the fault diagnosis model trained with the new training set expanded in step 3), import the fault diagnosis weights, and input the test set data to complete the fault diagnosis of the helical gear.

[0097] Embodiment 2

[0098] The present invention is further described in detail below in conjunction with specific examples. The above contents are all explanations of the present invention, but these descriptions cannot be understood as limiting the scope of the present invention. The scope of protection of the present invention is defined by the attached claims, and any changes based on the claims of the present invention are within the scope of protection of the present invention.

[0099] See attached Figure 1 The helical gear expansion diagnosis method based on three-way vibration fusion angular field image of the present invention mainly comprises the following steps:

[0100] 1) A helical gear fault simulation test bench was used to conduct a helical gear fault simulation experiment. The experiment set up motors in five different states, including normal, partial tooth breakage, tooth surface pitting, tooth surface wear, and tooth root cracks. The motor speed was set to 700 r / min and the load was 25 N·m. A three-axis vibration acceleration sensor was installed above the helical gear box to collect vibration signals.

[0101] 1.1) The vibration signal of the helical gear is collected to obtain the original data, and the obtained original data is divided into multiple groups of data without duplication, with 2048 sampling points as a group. The PAA method with a local window of 2 is used to approximately aggregate each group of data into 1024 points, and the GADF image corresponding to each direction is constructed respectively. The GADF image conversion process is as follows:

[0102] ① For time series data X = {x1, x2, ..., x n} to normalize and transform the amplitude to [-1,1]. The calculation formula is as follows:

[0103]

[0104] Where: x i is the i-th value of the time series data; is the i-th value of the time series data after normalization; max(X) is the maximum value of the time series data; min(X) is the minimum value of the time series data.

[0105] ② Convert the normalized value into the cosine value of the angle through calculation, use the timestamp as the radius, and convert the transformed time series data from the Cartesian coordinate system to the polar coordinate system. The calculation formulas for the polar angle and polar diameter in the polar coordinates are as follows:

[0106]

[0107] Where: is the i-th value of the normalized time series data; for The corresponding polar angle; t i is the timestamp corresponding to the i-th value of the time series data; N is the constant factor for adjusting the span of the polar coordinate system; r i is the polar radius corresponding to the i-th value of the time series data;

[0108] ③ Use trigonometric function difference to represent the correlation between each time point of the GADF image. During the conversion, the GADF image is established by calculating the angle difference of the sine function. The GADF image calculation is as follows:

[0109]

[0110] Where GADF is the GADF image; sin is the sine function; φ1 is the polar angle corresponding to the first data point; φ n The polar angle corresponding to the nth data point.

[0111] 1.2) Normalize the GADF image pixels corresponding to the three directions to between 0 and 255, and map their colors to red, green, and blue, respectively. Input the image information corresponding to the three directions into the three channels of the RGB image to construct the RGB-GADF image.

[0112] 1.3) Proportionally transform the converted RGB-GADF image to 256×256 pixels;

[0113] The RGB-GADF image samples of various states generated after processing are shown in the attached figure. Figure 2 shown.

[0114] 1.4) All the obtained RGB-GADF images are labeled according to different bevel gear states. The preset training sets are 50 and 70 RGB-GADF images per category, and the test sets are 50 RGB-GADF images per category.

[0115] 2) Construct a sample expansion model, which includes the following steps:

[0116] 2.1) constructing a helical gear fault feature dataset through the operation in step 1), and constructing a sample expansion model using the helical gear fault feature dataset, wherein the sample expansion model comprises a generator and a discriminator, wherein the generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added, the input is random noise, and the output is a new image of the same size as the RGB-GADF image;

[0117] 2.2) The discriminator is a dual-branch deep feature fusion structure, which is composed of multi-layer convolution and adds batch normalization and activation function. The deep features extracted by the dual-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the deep overall features and significant features extracted by the two are spliced ​​into vectors and input into a multi-layer perceptron composed of several fully connected layers. Finally, the multi-layer perceptron outputs the results and performs gradient update through loss function feedback. The discriminator input is the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability;

[0118] The network structure diagram of the generator and discriminator is shown in the attached figure. Figure 3 As shown, the specific parameter settings of each layer of the model are shown in Table 1 and Table 2;

[0119] Table 1 Generator layer parameter settings

[0120]

[0121] Table 2 Parameter settings of each layer of the discriminator

[0122]

[0123] 2.3) Use FID (Frechet inception distance, FID) which can measure the similarity and diversity of generated samples to evaluate the quality of sample expansion, select the weight parameters of the optimal expansion model and save it, call the weight parameters and set different expansion ratios to expand the sample, and the new training set is composed of a mixture of generated samples and original training samples.

[0124] The generated samples are as follows Figure 4 To prove the superiority of the method of the present invention, the method of the present invention is compared with two generative adversarial network models, DCGAN and WGAN-GP. The comparison results are shown in Table 3. In the table, data set A represents 50 training samples of each category, and data set B represents 70 training samples of each category.

[0125] Table 3 Minimum and average FID values ​​of different data sets and sample expansion models at 700 r / min and 25 N·m

[0126]

[0127]

[0128] 3) Construct a fault diagnosis model, which specifically includes the following steps:

[0129] 3.1) constructing a stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution, wherein the stacked block convolutional neural network fault diagnosis model with an inverted triangle channel distribution comprises a feature extractor and a classifier, wherein the feature extractor comprises four-stage stacked block layers, wherein the stacking ratio of the number of layers of the four-stage stacked block layers is 3:3:9:3, and the number of input channels decreases in sequence, namely, 128, 64, 32, and 16;

[0130] The structure of the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is shown in the attached figure. Figure 5 As shown, the comparison of the fault diagnosis parameters of the present invention and the ConvNeXt-Tiny model at each layer is shown in Table 4, where s represents the convolution kernel size, and dim represents the number of input channels.

[0131] Table 4 ConvNeXt Block layer parameters in four stages of ConvNeXt-Tiny and the method of the present invention

[0132]

[0133] 3.2) Use the new training set expanded in step 2) to train the fault diagnosis model, update the weight parameters of the fault diagnosis model based on the performance of the fault diagnosis model on the training set, and use the classification accuracy of the fault diagnosis model on the test set as the evaluation index. According to the fault diagnosis algorithm evaluation requirements in the "National Standard of the People's Republic of China (GB / T 43555-2023)" "Intelligent Service Predictive Maintenance Algorithm Evaluation Method", the accuracy qualification index of the machine learning algorithm is greater than 70%, and the classification accuracy calculation formula is:

[0134]

[0135] Where: A represents the classification accuracy of the test set, P represents the number of correctly classified samples in the test set, and Q represents the total number of test set samples.

[0136] 3.3) In the model testing phase, the test set in 3.2) is substituted into the fault diagnosis model, and the classification accuracy of the fault diagnosis model on the test set is used as an evaluation indicator. When the classification accuracy is greater than or equal to 90%, the optimal fault diagnosis model weight parameters are saved.

[0137] 4) Fault diagnosis, including the following steps:

[0138] 4.1) Using the operation in step 1), collect the vibration signal of the helical gear, convert the vibration signal into an RGB-GADF image and use it as the test set data;

[0139] 4.2) Use the fault diagnosis model trained with the new training set expanded in step 3), import the fault diagnosis weights, and input the test set data to complete the fault diagnosis of the helical gear.

[0140] Table 5 shows the diagnostic accuracy of the two training data sets before and after expansion at 700 r / min and load 25 N·m. When there are 50 images in each category, the accuracy reaches 93.6% after expansion, and when there are 70 images in each category, the accuracy reaches 98.4% after expansion. The corresponding diagnostic results before and after expansion of different data sets are shown in the attached figure. Figure 6 shown.

[0141] Table 5 Diagnostic accuracy of two training data sets before and after expansion at 700 r / min and load 25 N·m

[0142]

[0143] To prove the superiority of the method of the present invention, the present invention is compared with the ConvNeXt-Tiny model, with 50 samples in each class in the training set and 50 samples in each class in the test set. The results are shown in Table 6. Figure 7 Classification of two fault diagnosis models.

[0144] Table 6 Training parameters of two fault diagnosis models

[0145]

[0146] Embodiment 3

[0147] Helical gear expansion diagnosis system based on three-way vibration fusion angular field image, including:

[0148] Helical gear fault feature data set construction module: used to use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear to obtain the three-dimensional vibration signal. The three-dimensional vibration signal is segmented and approximated according to the specified number of points and normalized to be converted into a GADF image. Then, the pixel points of the GADF image corresponding to the three directions are normalized to between 0 and 255, and their colors are mapped to R, G, and B respectively to establish an RGB-GADF image. The RGB-GADF image is downsampled to a preset size to obtain a new image. After manually labeling the new image, a helical gear fault feature data set is established, and it is divided into a training set and a test set.

[0149] Sample expansion model construction module: used to construct a sample expansion model using the helical gear fault feature data set. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a test image with the same size as the RGB-GADF image. The discriminator is a double-branch deep feature fusion structure. The double-branch discriminator is composed of multiple layers of convolution and batch normalization and activation functions are added. The deep features extracted by the double-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the The deep overall features and significant features extracted by the two are spliced ​​into a vector and input into a multilayer perceptron composed of several fully connected layers. Finally, the multilayer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator inputs the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability. The weight parameters of the optimal expansion model are selected and saved by using the index for evaluating the similarity of sample structures. The weight parameters are called for sample expansion. The new training set is composed of a mixture of generated samples and original training samples, that is, the helical gear fault feature data set.

[0150] Fault diagnosis model construction module: used to construct a stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution, the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution includes a feature extractor and a classifier, the feature extractor includes four-stage stacked block layers, the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is trained using a helical gear fault feature data set, and after training, the optimal fault diagnosis model weight parameters are saved to obtain a fault diagnosis model;

[0151] Fault diagnosis module: It is used to collect the helical gear test data in the manner of building a module based on the helical gear fault feature dataset, and convert it into RGB-GADF images as a test set. The fault diagnosis model is used to perform fault diagnosis on the test set data to complete the fault diagnosis of the helical gear.

[0152] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0154] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0156] 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 its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims of the invention.

Claims

1. A helical gear expansion diagnosis method based on three-way vibration fusion angular field images, characterized in that: The following steps are involved: 1) Constructing a helical gear fault feature dataset A three-dimensional acceleration sensor is used to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear to obtain a three-dimensional vibration signal. The three-dimensional vibration signal is segmented and approximated according to the specified number of points and normalized to be converted into a GADF image. The pixel points of the GADF image corresponding to the three directions are normalized to between 0 and 255, and their colors are mapped to R, G, and B respectively to establish an RGB-GADF image. The RGB-GADF image is downsampled to a preset size to obtain a new image. After manually labeling the new image, a helical gear fault feature dataset is established, and it is divided into a training set and a test set. 2) Build a sample expansion model A sample expansion model is constructed using a helical gear fault feature dataset. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a test image with the same size as the RGB-GADF image. The discriminator is a double-branch deep feature fusion structure. The double-branch discriminator is composed of multiple layers of convolution and batch normalization and activation functions are added. The deep features extracted by the double-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the deep overall features and significant features extracted by the two are spliced ​​into a vector and input into a multi-layer perceptron composed of several fully connected layers. Finally, the multi-layer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator inputs the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability. The weight parameters of the optimal expansion model are selected and saved using the index for evaluating the similarity of the sample structure, and the weight parameters are called to expand the sample. The new training set is composed of a mixture of the generated samples and the original training samples, that is, the helical gear fault feature dataset; 3) Build a fault diagnosis model A stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is constructed, wherein the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution comprises a feature extractor and a classifier, wherein the feature extractor comprises four-stage stacked block layers, and the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is trained using a helical gear fault feature data set, and after training, the optimal fault diagnosis model weight parameters are saved to obtain a fault diagnosis model; 4) Fault diagnosis According to step 1), the helical gear test data is collected and converted into RGB-GADF images as a test set. The fault diagnosis model is used to perform fault diagnosis on the test set data to complete the fault diagnosis of the helical gear.

2. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 1 is characterized in that: In the step 1), a helical gear fault feature data set is constructed, specifically: 1.1) Use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear. The three-dimensional vibration signals are subjected to PAA at the specified number of points and normalized and then converted into GADF images. The PAA is to segment the vibration signal through a pre-set local window, calculate the average value of each segment of the vibration signal after segmentation, and reconstruct the time series data using the average values ​​of all segments. The GADF image conversion process is as follows: ① For time series data X = {x1, x2, ..., x n } to normalize and transform the amplitude to [-1,1]. The calculation formula is as follows: Where: x i is the i-th value of the time series data; is the i-th value of the time series data after normalization; max(X) is the maximum value of the time series data; min(X) is the minimum value of the time series data; ② Convert the normalized value into the cosine value of the angle through calculation, use the timestamp as the radius, and convert the transformed time series data from the Cartesian coordinate system to the polar coordinate system. The calculation formulas for the polar angle and polar diameter in the polar coordinates are as follows: Where: is the i-th value of the normalized time series data; for The corresponding polar angle; t i is the timestamp corresponding to the i-th value of the time series data; N is the constant factor for adjusting the span of the polar coordinate system; r i is the polar radius corresponding to the i-th value of the time series data; ③ Use trigonometric function difference to represent the correlation between each time point of the GADF image. During the conversion, the GADF image is established by calculating the angle difference of the sine function. The GADF image calculation is as follows: Where GADF is the GADF image; sin is the sine function; φ1 is the polar angle corresponding to the first data point; φ n The polar angle corresponding to the nth data point; 1.2) Normalize the GADF image pixels corresponding to the three directions to between 0 and 255, and map their colors to R, G, and B respectively. Input the image information corresponding to the three directions into the three channels of the RGB image to construct the RGB-GADF image. 1.3) Proportionally transform the converted RGB-GADF image to 256×256 pixels; 1.4) All the obtained RGB-GADF images are marked according to different bevel gear states, and divided into training sets and test sets according to preset requirements.

3. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 2 is characterized in that: The designated number of points is set according to the sampling frequency and the rotation speed of the shaft where the helical gear is located, and each signal segment of the designated number of points contains at least 1 / 4 cycle information.

4. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 2 is characterized in that: The local window size preset by PAA in step 1.1) is 2.

5. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 2 is characterized in that: In step 1.4), the training set is preset with x RGB-GADF images per category and the test set is preset with y RGB-GADF images per category, where x ≥ y.

6. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 1 is characterized in that: In step 2), a sample expansion model is constructed, specifically: 2.1) A sample expansion model is constructed using the helical gear fault feature dataset. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a new image with the same size as the RGB-GADF image. 2.2) The discriminator is a dual-branch deep feature fusion structure, which is composed of multi-layer convolution and adds batch normalization and activation function. The deep features extracted by the dual-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the deep overall features and significant features extracted by the two are spliced ​​into a vector, which is input into a multi-layer perceptron composed of several fully connected layers. Finally, the multi-layer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator input is the new sample output by the generator and the training sample in the training set, and the output is the sample discrimination probability; 2.3) Using the index for evaluating sample structure similarity, the weight parameters of the optimal expansion model are selected and saved, and the weight parameters are called to expand the sample. The new training set is composed of a mixture of generated samples and original training samples.

7. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 1 is characterized in that: The fault diagnosis model is constructed in step 3), specifically: 3.1) constructing a stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution, wherein the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution comprises a feature extractor and a classifier, and the feature extractor comprises four-stage stacked block layers; 3.2) Use the new training set expanded in step 2) to train the fault diagnosis model, update the weight parameters of the fault diagnosis model based on the performance of the fault diagnosis model on the training set, and use the classification accuracy of the fault diagnosis model on the test set as the evaluation index. The classification accuracy calculation formula is: Where: A represents the classification accuracy of the test set, P represents the number of correctly classified samples in the test set, and Q represents the total number of samples in the test set; 3.3) In the model testing phase, the test set in 3.2) is substituted into the fault diagnosis model, and the classification accuracy of the fault diagnosis model on the test set is used as an evaluation indicator. When the classification accuracy is greater than or equal to 90%, the optimal fault diagnosis model weight parameters are saved.

8. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 7 is characterized in that: The stacking ratio of the number of stacked block layers in the four stages is 3:3:9:3, and the number of input channels decreases successively, namely 128, 64, 32 and 16.

9. The helical gear expansion diagnosis method based on three-way vibration fusion angular field image according to claim 1 is characterized in that: The fault diagnosis in step 4) is specifically as follows: 4.1) Using the operation in step 1), collect the vibration signal of the helical gear, convert the vibration signal into an RGB-GADF image and use it as the test set data; 4.2) Use the fault diagnosis model trained with the new training set expanded in step 3), import the fault diagnosis weights, and input the test set data to complete the fault diagnosis of the helical gear.

10. Helical gear expansion diagnosis system based on three-way vibration fusion angular field image, characterized in that: include: Helical gear fault feature data set construction module: used to use a three-dimensional acceleration sensor to collect the horizontal radial, vertical radial and axial vibration signals of the helical gear to obtain the three-dimensional vibration signal. The three-dimensional vibration signal is segmented and approximated according to the specified number of points and normalized to be converted into a GADF image. Then, the pixel points of the GADF image corresponding to the three directions are normalized to between 0 and 255, and their colors are mapped to R, G, and B respectively to establish an RGB-GADF image. The RGB-GADF image is downsampled to a preset size to obtain a new image. After manually labeling the new image, a helical gear fault feature data set is established, and it is divided into a training set and a test set. Sample expansion model construction module: used to construct a sample expansion model using the helical gear fault feature data set. The sample expansion model includes a generator and a discriminator. The generator is composed of multiple layers of deconvolution and batch normalization and activation functions are added. The input is random noise, and the output is a test image with the same size as the RGB-GADF image. The discriminator is a double-branch deep feature fusion structure. The double-branch discriminator is composed of multiple layers of convolution and batch normalization and activation functions are added. The deep features extracted by the double-branch discriminator are shunted to adaptive average pooling and adaptive maximum pooling, and the The deep overall features and significant features extracted by the two are spliced ​​into a vector and input into a multilayer perceptron composed of several fully connected layers. Finally, the multilayer perceptron outputs the result and performs gradient update through loss function feedback. The discriminator inputs the new samples output by the generator and the training samples in the training set, and the output is the sample discrimination probability. The weight parameters of the optimal expansion model are selected and saved by using the index for evaluating the similarity of sample structures. The weight parameters are called for sample expansion. The new training set is composed of a mixture of generated samples and original training samples, that is, the helical gear fault feature data set. Fault diagnosis model construction module: used to construct a stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution, the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution includes a feature extractor and a classifier, the feature extractor includes four-stage stacked block layers, the stacked block convolutional neural network fault diagnosis model with inverted triangle channel distribution is trained using a helical gear fault feature data set, and after training, the optimal fault diagnosis model weight parameters are saved to obtain a fault diagnosis model; Fault diagnosis module: It is used to collect the helical gear test data in the manner of building a module based on the helical gear fault feature dataset, and convert it into RGB-GADF images as a test set. The fault diagnosis model is used to perform fault diagnosis on the test set data to complete the fault diagnosis of the helical gear.

Images