Bearing fault diagnosis method based on stacked autoencoder and softmax regression

• Published in: 2015 34th Chinese Control Conference (CCC) pp. 6331 - 6335
• Main Authors: Tao, Siqin, Zhang, Tao, Yang, Jun, Wang, Xueqian, Lu, Weining
• Format: Conference Proceeding Journal Article
• Language: English
• Published: Technical Committee on Control Theory, Chinese Association of Automation 01.07.2015
• Subjects: Accuracy; Algorithms; Bearing; Classification; Computer simulation; Conferences; Cost function; Fault diagnosis; Neural networks; Noise; Regression; Robustness; Softmax Regression; Stacked Autoencoder; Training
• DOI: 10.1109/ChiCC.2015.7260634

As bearings are the most common components of mechanical structure, it will be helpful to research bearing fault and diagnose the fault as early as possible in case of suffering greater losses. This paper proposes a deep neural network algorithm framework for bearing fault diagnosis based on stacked autoencoder and softmax regression. The simulation results verify the feasibility of the algorithm and show the excellent classification performance. In addition, this deep neural network represents strong robustness and eliminates the impact of noise remarkably. Last but not least, an integrated deep neural network method consisting of ten different structure parameter networks is proposed and it has better generalization capability.