An Edge Intelligent Method for Bearing Fault Diagnosis Based on a Parameter Transplantation Convolutional Neural Network

Abstract

A bearing is a key component in rotating machinery. The prompt monitoring of a bearings’ condition is critical for the reduction of mechanical accidents. With the rapid development of artificial intelligence technology in recent years, machine learning-based intelligent fault diagnosis (IFD) methods have achieved remarkable success in the field of bearing condition monitoring. However, most algorithms are developed based on computer platforms that focus on analyzing offline, rather than real-time, signals. In this paper, an edge intelligence diagnosis method called S-AlexNet, which is based on a parameter transplantation convolutional neural network (CNN), is proposed. The method deploys the lightweight IFD method in a low-cost embedded system to monitor the bearing status in real time. Firstly, a lightweight IFD algorithm model is designed for embedded systems. The model is trained on a PC to obtain optimal parameters, such as the model’s weights and bias. Finally, the optimal parameters are transplanted into the embedded system model to identify the bearing status on the edge side. Two datasets were used to validate the performance of the proposed method. The validation using the CWRU dataset shows that the proposed method achieves an average prediction accuracy of 94.4% on the test set. The validation using self-built data shows that the proposed method can identify bearing operating status in embedded systems with an average prediction accuracy of 99.81%. The results indicate that the proposed method has the advantages of high recognition accuracy, low model complexity, low cost, and high portability, which allow for the simple and effective implementation of the edge IFD of bearings in embedded systems.

A Bearing Fault Diagnosis Method Based on Improved Transfer Component Analysis and Deep Belief Network

“…To verify the effectiveness of the proposed method, it was compared with the different methods: DBN, IG-CWT-CNN [31], TF-MDA [32], ICPW-HPF-CNN [33], ML [34], JDA [35], TCA-DBN [36], DSAN [18], and S-Alexnet [37]. The structure of the DBN was [80,40,40,20], and the learning rate was 0.05.…”

Bearing Fault Diagnosis Method Based on Adversarial Transfer Learning for Imbalanced Samples of Portal Crane Drive Motor

“…The results consistently demonstrated that the proposed method outperforms existing state-of-the-art techniques in terms of diagnostic performance. Ding et al [33] proposed an intelligent edge diagnosis method based on parameter transplantation in convolutional neural networks (CNN). Verification using the CWRU dataset revealed an average prediction accuracy of 94.4% on the test set with this approach.…”

Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network

“…Except for machine learning methods, deep learning methods have been widely applied to prognostics for health monitoring in recent years. As a classic deep learning method, a convolutional neural network (CNN) utilizes the advantages of multiple neural layers to represent input data in feature values and reduce higher numbers of dimensions and improve prognostic recognition [ 25 , 26 , 27 , 28 , 29 ]. However, CNNs suffer from overfitting, exploding gradients, and class imbalances that reduce recognition performance.…”