FAULT DIAGNOSIS METHOD OF ROLLING BEARING BASED ON DEEP BELIEF NETWORK

Wenfeng Zhang

Abstract: A fault identification method of rolling bearing based on depth belief network is proposed, which does not need to extract fault features in advance. Vibration signal is directly used as the input of the whole system. Fault feature extraction and fault identification can be automatically accomplished by using the powerful feature extraction ability of deep confidence network. The results show that the proposed method is able to not only adaptively mine available fault characteristics from the data, but also obtain higher identification accuracy than the existing methods.

Keywords: deep belief network; RBM; feature extraction; vibration signal; fault diagnosis

DOI: https://doi.org/10.15623/ijret.2018.0709014