A novel deep autoencoder feature learning method for rotating machinery fault diagnosis. (October 2017)

• Record Type: Journal Article
• Authors: Shao, Haidong; Jiang, Hongkai; Zhao, Huiwei; Wang, Fuan
• Is Part Of: Mechanical systems and signal processing. Volume 95(2017)
• Page Start: 187
• Page End: 204
• Publication Date: 2017-10
• Subjects: Deep autoencoder -- Feature learning -- Fault diagnosis -- Maximum correntropy -- Artificial fish swarm algorithm; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2017.03.034
• Languages: English
• ISSNs: 0888-3270

Abstract

Graphical abstract: Highlights: A deep autoencoder feature learning method is proposed. Maximum correntropy is used to design the new deep autoencoder loss function. Artificial fish swarm algorithm is used to optimize parameters. Abstract: The operation conditions of the rotating machinery are always complex and variable, which makes it difficult to automatically and effectively capture the useful fault features from the measured vibration signals, and it is a great challenge for rotating machinery fault diagnosis. In this paper, a novel deep autoencoder feature learning method is developed to diagnose rotating machinery fault. Firstly, the maximum correntropy is adopted to design the new deep autoencoder loss function for the enhancement of feature learning from the measured vibration signals. Secondly, artificial fish swarm algorithm is used to optimize the key parameters of the deep autoencoder to adapt to the signal features. The proposed method is applied to the fault diagnosis of gearbox and electrical locomotive roller bearing. The results confirm that the proposed method is more effective and robust than other methods.