Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network

Abstract

Rolling bearings are the most fault-prone parts in rotating machinery. In order to find faults in time and reduce losses, this paper presents an intelligent diagnosis method for rolling bearings. At present, the deep residual network (RESNET) is the most widely used convolutional neural network (CNN) and has become one of the hotspots in fault diagnosis. However, the fully connected layer of the deep residual network has the disadvantage of too many training parameters, which makes the model training and testing time longer. So, we proposed a new network structure which the global average pooling (GAP) technology replaces the fully connected layer part of the traditional RESNET. It effectively solves the problem of too many parameters of the traditional RESNET model, and uses data enhancement, dropout, and other deep learning training techniques to prevent the model from overfitting. Experiments show that the accuracy of fault diagnosis of the improved algorithm reaches 99.83%, training time has been shortened. Also, the whole process of rolling bearing fault detection does not need any manually extract features, and this “end-to-end” algorithm has good versatility and operability.

Fault Classification of Wind Turbine Gearbox Bearings Based on Convolutional Neural Networks

“…The window size was defined as 25000. Dropout is a common method to solve the overfitting problem in DL algorithms [16]. Some neurons are randomly dropped by Dropout to ensure that the neural network only propagates forward during the training iteration.…”

“…Manual feature selection is a blind, labor-oriented, and subjective process that mainly depends on advanced expertise knowledge. In addition, the traditional fault diagnosis methods consist of shallow structures that are not suitable for learning complicated nonlinear relationships [16]. So, the conventional methods cannot meet the wind farms' actual implementation needs.…”

“…Consequently, it was observed that the proposed method could classify different WT-bearing faults with a recognition accuracy of 98.2%. Hao et al [16] proposed a new network structure based on a deep belief network (ResNet) to reduce losses and diagnose bearing faults. The researchers replaced the fully connected layer part of the ResNet with the general average pooling technology.…”

Combination of Optimized Variational Mode Decomposition and Deep Transfer Learning: A Better Fault Diagnosis Approach for Diesel Engines

“…While Figure 4a shows the standard residual structure block, Figure 4b depict the residual structure block with a down-sampling layer. The two residual blocks gener ally consist of two convolutional layers, two batch normalization, and two ReLU activa tion functions [34]. On the other hand, the residual structure block with the down-sam pling layer has a shortcut path directly connecting the input and output, which is practica The down(•) represents the pooling function; b l and β l denote layer l bias and weight, respectively.…”

Condition Monitoring of Rolling Bearing Based on Multi-Order FRFT and SSA-DBN

“…Therefore, the condition monitoring of rolling bearings has very important theoretical significance and application value for ensuring its safe and reliable operation [3]. If the rolling bearing fault is not detected and dealt with early, the incipient fault will gradually develop into a more serious fault [4,5]. For example, in 1992, a Japanese power plant caused an overload accident due to a bearing fault, which not only lost billions of yen, but also caused casualties.…”