Zhao, C.H., Hu, H.X., Chen, B.J., Zhang, Y.N. and Xiao, J.W. (2019) Bearing Fault Diagnosis Based on the Deep Learning Feature Extraction and WOA SVM State Recognition. Journal of Vibration and Shock, 38, 31-37.

has been cited by the following article:

• TITLE: One-Dimensional Convolutional Neural Network Based Bearing Fault Diagnosis

  AUTHORS: Jiaxue Chen, Xiaoqi Yin, Chenxue Li, Hang Yang, Li Hong

  KEYWORDS: Convolutional Neural Network, Fault Diagnosis, Rolling Bearing, Intelligent Diagnosis

  JOURNAL NAME: Open Access Library Journal, Vol.9 No.4, April 13, 2022

  ABSTRACT: Fault diagnosis based on time-domain signals has become mainstream in recent years. Traditional methods require signal processing to extract fault features before feeding them into a neural network for diagnostic classification, which is a cumbersome process. This paper proposes an adaptive fault diagnosis model based on a one-dimensional convolutional neural network, and the structure and parameters of the model are analyzed and designed in detail. The segmented pre-processed vibration signal is fed directly into a convolutional neural network, where fault features can be extracted adaptively, and finally classify the diagnostic results using a Softmax classifier. This method directly processes the vibration signals in an end-to-end way, which improves the timeliness of diagnosis. The effectiveness of the method is verified through bearing experiments and compared with KNN, SVM, LSTM and AlexNet models. The results show that the model is accurate for fault diagnosis of bearings.