Fault Diagnosis of Rolling Bearing using Deep Belief Networks

This paper presents an approach to implement vibration signals for fault diagnosis of the rolling bearing. Due to the noise and transient impacts, it is difficulty to accurately diagnosis the faults with traditional methods. So a new type of learning architecture for deep generative model called deep belief networks (DBN) is applied. Since the unsupervised learning ability in DBN, it can extract the features from the raw data layer by layer. This article mainly research how to construct the encoder using DBN which can minimize the energy between the output and input vibration signals. Compared with existing diagnosis techniques, the proposed method can learn a good representation of features with higher accuracy. The results show that DBN can more comprehensively retain the data features in pattern recognition.