Inter-shaft bearing fault diagnosis apparatus and method under complex working condition

Abstract

The present invention relates to an inter-shaft bearing fault diagnosis method and apparatus under a complex working condition. The apparatus comprises: a data collection module, which collects an inter-shaft bearing vibration signal by means of mounting an acceleration sensor; a data preprocessing module, which converts the collected vibration signal into a time-frequency graph, so as to express features of the signal in terms of a time domain and a frequency domain; a feature extraction module, which effectively captures a complex mode and correlation from a converted signal by means of combining an attention mechanism and a deep residual network, so as to improve the accuracy of fault diagnosis; and a model verification module, which trains the feature extraction module on the basis of a constructed data set, and evaluates a model effect on the basis of a verification set. The inter-shaft bearing fault diagnosis method and apparatus under a complex working condition in the present invention can improve the accuracy of fault diagnosis of a bearing under a complex working condition.

Description

A device and method for diagnosing intermediate bearing faults under complex working conditions Technical Field

[0001] The present invention relates to the technical field of mechanical fault diagnosis, and in particular to a device and method for diagnosing intermediate bearing faults under complex working conditions, which are applied to the detection of bearing faults in rotating mechanical equipment. Background Art

[0002] Fault diagnosis is an essential component of rotating machinery health management and plays a crucial role in ensuring the healthy and safe operation of manufacturing equipment. As a key component of rotating machinery, the engine's complex structure makes disassembly and assembly expensive. Rolling bearings, core components within the engine, operate in harsh environments, and failures can result in significant economic losses and even casualties, necessitating regular inspections. However, frequent disassembly and inspections can lead to high engine maintenance costs. With the continuous advancement of information technology, the use of computer technology to perform non-disassembly fault diagnosis on rolling bearings in rotating machinery engines, in order to reduce engine maintenance costs, has become a research hotspot in the manufacturing industry.

[0003] When actually collecting aircraft engine bearing signals, the signals are collected over a period of time while maintaining a nearly stable speed without the application of external forces. However, maintaining a stable speed in this situation is difficult. The engine operates under complex operating conditions such as variable load and speed, making the vibration signal a more complex non-stationary signal. The changes in operating speed during signal feature extraction are very similar to the characteristic changes caused by faults. Furthermore, in real-world environments, the collected bearing signals often contain a large amount of noise from the environment and other component resonances, resulting in nonlinear characteristics in the collected data. Existing deep learning-based bearing fault diagnosis solutions struggle to meet the requirements for classifying bearing health status under noise and variable loads.

[0004] Summary of the Invention

[0005] Based on the technical problems raised above, the present invention proposes a device and method for diagnosing intermediate bearing faults under complex working conditions to solve the problem that the signals collected in complex scenarios such as variable speed and variable load are complex non-stationary signals, thereby eliminating the problem that the fault features are difficult to extract.

[0006] The technical solution adopted by the present invention to achieve the above-mentioned purpose is:

[0007] A device for diagnosing intermediate bearing faults under complex working conditions, comprising:

[0008] A signal acquisition module is used to control the acceleration sensor to acquire the vibration signal of the intermediate bearing through the acquisition controller;

[0009] A data preprocessing module, used for converting the intermediate bearing vibration signal into a time-frequency diagram through short-time Fourier transform;

[0010] Feature extraction module, used to extract key features from time-frequency graphs through void residual convolutional networks, global residual networks, and feature fusion networks;

[0011] The model verification module is used to train and verify the key feature extraction module and convert its output features into bearing status for fault diagnosis.

[0012] The acquisition controller is implemented by FPGA.

[0013] The dilated residual convolutional network is composed of four sequentially connected convolutional basic blocks Block. Block0 and Block2 have the same structure, which are: a sequentially connected dilated convolution layer Dconv, a batch normalization layer BN and an activation function ReLU, and the features output by the activation function ReLU are fused through a feature fusion network; Block1 and Block3 have the same structure, which are based on Block0 or Block2, and the fusion results are corrected by the features output by ReLU.

[0014] The global residual block consists of sequentially connected convolutional layers and batch normalization layers.

[0015] The feature fusion network is composed of a stack of maximum pooling layer, average pooling layer, fully connected layer and activation function layer, specifically:

[0016] Among them, x represents the input data, MaxPool represents the adaptive maximum pooling layer, FC represents the fully connected layer, δ represents the use of activation function ReLU, σ represents the use of activation function Sigmoid, y1 represents the first layer feature extraction result, y se The method of diagnosing intermediate bearing faults under complex working conditions includes the following steps:

[0017] The signal acquisition module controls the acceleration sensor to acquire the vibration signal of the intermediate bearing through the acquisition controller;

[0018] The data preprocessing module converts the intermediate bearing vibration signal into a time-frequency diagram through short-time Fourier transform;

[0019] The feature extraction module extracts key features from the time-frequency graph through the dilated residual convolutional network, the global residual network, and the feature fusion network;

[0020] The model verification module trains and verifies the key feature extraction module and converts its output features into bearing status for fault diagnosis.

[0021] A system for diagnosing intermediate bearing faults under complex working conditions comprises a memory and a processor; the memory is used to store a computer program; the processor is used to implement a method for diagnosing intermediate bearing faults under complex working conditions when executing the computer program.

[0022] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, a method for diagnosing intermediate bearing faults under complex working conditions is implemented.

[0023] The present invention has the following beneficial effects and advantages:

[0024] 1. This paper constructs a new intermediate bearing fault diagnosis model, which combines the advantages of attention mechanism and void convolution.

[0025] 2. The network structure proposed in the present invention achieves a good balance between speed and accuracy, has strong robustness, and is suitable for the field of aircraft engine intermediate bearing fault diagnosis. It can also be extended to various signal processing problems and has good practicality.

[0026] 3. The present invention establishes a method for diagnosing intermediate bearing faults in complex scenarios, which can perform accurate fault diagnosis at a faster reasoning speed and has strong stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] FIG1 is an overall schematic diagram of an intermediate bearing fault diagnosis device according to the present invention;

[0028] FIG2 is a diagram showing the overall structure of the intermediate bearing fault diagnosis method of the present invention;

[0029] FIG3 is a schematic diagram of the sensor installation position of the present invention;

[0030] FIG4 is a structural diagram of a dilated residual convolutional network and a global residual network of the present invention;

[0031] FIG5 is a structural diagram of the feature fusion network of the present invention. DETAILED DESCRIPTION

[0032] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0033] To make the above-mentioned objects, features, and advantages of the present invention more readily apparent, the specific implementation methods of the present invention are described in detail below with reference to the accompanying drawings. The following description sets forth many specific details to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways than those described herein, and those skilled in the art may make similar modifications without departing from the scope of the invention. Therefore, the present invention is not limited to the specific implementation methods disclosed below.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art of the art to which the present invention pertains. The terms used in the specification of the invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention.

[0035] A device for diagnosing intermediate bearing faults under complex operating conditions, as shown in Figure 1, comprises a signal acquisition module, a data preprocessing module, a feature extraction module, and a model verification module. The signal acquisition module controls the accelerometer to acquire signals. The acquired vibration signals are fed into the data preprocessing module to convert them into time-frequency plots. The time-frequency plots are then fed into the feature extraction module for fault feature extraction. Finally, the extracted results are fed into the model verification module for bearing fault diagnosis. The overall architecture of the intermediate bearing fault diagnosis method is shown in Figure 2.

[0036] During signal acquisition, to reduce noise interference, the sensor is installed close to the intermediate bearing, capturing as much vibration signal as possible related to the intermediate bearing fault for more accurate fault diagnosis and monitoring, as shown in Figure 3.

[0037] The structure of the dilated residual convolutional network is shown in Figures 4(a) and 4(b). Its basic blocks consist of a dilated convolutional layer (Dconv), a batch normalization layer (BN), and an activation function (ReLU). These three layers work together on the data, enabling the model to better extract features, normalize data distribution, and enhance the model's nonlinear expression capabilities, thereby improving model performance. The batch normalization layer accelerates network convergence, suppresses gradient vanishing or exploding, and increases the network's generalization capability. The dilated convolutional layer is a convolutional layer with an adjustable receptive field that can perform full convolution on the image, extracting richer information from the input image. Block 0 and Block 2 have the same structure, as shown in Figure 4(a); Block 1 and Block 3 have the same structure, as shown in Figure 4(b).

[0038] The structure of the global residual block (GRB), shown in Figure 4(c), addresses the issue of information loss caused by operations like convolution. The GRB module consists of a convolutional layer and a batch normalization layer. Here, the convolutional layer uses a standard convolution, with the dilation ratio set to 1. This is because, compared to dilated convolution, standard convolution requires fewer computations and parameters, thus improving computational efficiency and, to a certain extent, improving model accuracy without significantly impacting performance.

[0039] The architecture of the feature fusion network (MAB) is shown in Figure 5. Its main structure includes pooling layers, fully connected layers, and activation function layers. Specifically, in the MAB block, we first use a maximum pooling layer to compress the information of each channel, reducing the computational burden and improving the computational efficiency of the model. Next, the pooled feature map is input into a fully connected layer for feature transformation. A nonlinear transformation is then performed using the ReLU activation function, mapping the input values ​​to a non-negative range. This increases the model's nonlinearity and helps improve model performance. Furthermore, this module passes through a fully connected layer and a Sigmoid activation function, mapping the input values ​​to a range between 0 and 1. This indicates the importance of each feature channel, reduces the risk of overfitting, and increases generalization. To avoid the vanishing gradient problem and speed up training, this module introduces a residual connection, which adds the output of the previous layer to the output of the current layer. This process is expressed in the following equation.

[0040] Among them, MaxPool represents the adaptive maximum pooling layer, FC represents the fully connected layer, δ represents the use of activation function ReLU, and σ represents the use of activation function Sigmoid.

[0041] The obtained output is then input into the SE module to obtain the importance of each feature channel, and a weight value is assigned to each feature channel according to the importance, and then directly multiplied with the output of the previous layer, as shown in Equations (2) and (3). Finally, these weight values ​​are weighted and summed with the output of each channel of the previous layer of the feature map to obtain the final output, as shown in Equation (4).

[0042] Through the above steps, the MAB module can adaptively adjust the weight of each channel according to the importance of each channel to improve the network's ability to identify key features, thereby improving the performance and accuracy of the entire model.

[0043] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should be regarded as within the scope of protection of the present invention.

Claims

1. A device for diagnosing intermediate bearing faults under complex working conditions, characterized in that: include: A signal acquisition module, used to control the acceleration sensor to acquire the vibration signal of the intermediate bearing through an acquisition controller; A data preprocessing module, used for converting the intermediate bearing vibration signal into a time-frequency diagram through short-time Fourier transform; Feature extraction module, used to extract key features in the time-frequency graph through the hole residual convolution network, the global residual network, and the feature fusion network; The model verification module is used to train and verify the key feature extraction module and convert its output features into bearing status for fault diagnosis.

2. The device for diagnosing intermediate bearing faults under complex working conditions according to claim 1 is characterized in that: The acquisition controller is implemented by FPGA.

3. The device for diagnosing intermediate bearing faults under complex working conditions according to claim 1 is characterized in that: The dilated residual convolutional network is composed of four sequentially connected convolutional basic blocks Block, where Block0 and Block2 have the same structure, which are: sequentially connected dilated convolutional layer Dconv, batch normalization layer BN and activation function ReLU, and the features output by the activation function ReLU are fused through the feature fusion network; Block1 and Block3 have the same structure, which are based on Block0 or Block2, and the fusion results are corrected through the features output by ReLU.

4. The device for diagnosing intermediate bearing faults under complex working conditions according to claim 1 is characterized in that: The global residual block consists of sequentially connected convolutional layers and batch normalization layers.

5. The device for diagnosing intermediate bearing faults under complex working conditions according to claim 1 is characterized in that: The feature fusion network is composed of a stack of a maximum pooling layer, an average pooling layer, a fully connected layer, and an activation function layer, specifically: Among them, x represents the input data, MaxPool represents the adaptive maximum pooling layer, FC represents the fully connected layer, δ represents the use of activation function ReLU, σ represents the use of activation function Sigmoid, y1 represents the first layer feature extraction result, y se represents the feature extraction result after SENet, y2 represents the feature extraction result of the first layer after SENet, and y represents the final feature extraction result.

6. A method for diagnosing intermediate bearing faults under complex working conditions, characterized in that: The following steps are involved: The signal acquisition module controls the acceleration sensor to acquire the vibration signal of the intermediate bearing through the acquisition controller; The data preprocessing module converts the intermediate bearing vibration signal into a time-frequency diagram through short-time Fourier transform; The feature extraction module extracts key features from the time-frequency graph through the hole residual convolution network, the global residual network, and the feature fusion network; The model verification module trains and verifies the key feature extraction module and converts its output features into bearing status for fault diagnosis.

7. A fault diagnosis system for intermediate bearings under complex working conditions, characterized in that: It comprises a memory and a processor; the memory is used to store a computer program; the processor is used to implement a method for diagnosing intermediate bearing faults under complex working conditions as described in claim 6 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the method for diagnosing intermediate bearing faults under complex working conditions as described in claim 6 is implemented.

Images