Review of The Application of Deep Learning in Fault Diagnosis

Abstract

In recent years, deep learning has shown its unique potentials and advantages in feature extraction and model fitting. Many scholars have applied deep learning to the field of fault diagnosis, and have achieved many results. In this paper, several typical methods based on deep learning have been introduced first, which can be employed to realize the fault diagnosis for industrial system. And then, this paper analyzes the characteristics and limitations of the fault detection model based on deep learning, and points out the importance of multi-diagnostic method fusion for the development of current intelligent fault diagnosis. Finally, the main functions and problems of in-depth learning in fault diagnosis are summarized, and the future research directions are prospected.