Intelligent fault diagnosis of rotating machinery using locally connected restricted boltzmann machine in big data era

In intelligent fault diagnosis, unsupervised feature learning is a potential tool to replace the manual feature extraction in big data era. Therefore, we first develop a locally connected restricted Boltzmann machine (LCRBM) from the traditional RBM in order to handle the periodic appearance of fault characteristics in the raw signals of rotating machinery. Then, using LCRBM, we propose a method for intelligent fault diagnosis of rotating machinery. In the method, LCRBM is used to obtain features directly from raw signals. Based on the features learned by LCRBM, the method uses softmax regression to recognize faults. The proposed method is verified by the dataset of locomotive bearings and its superiority is demonstrated by the comparison with methods using the traditional RBM and eighteen widely used manual features. Results indicate that the proposed method is able to automatically learn fine features from raw signals of rotating machinery and achieves higher diagnosis accuracies.

I. Introduction

Rotating machinery is widely utilized in modern industries and has been more automatic, precise and efficient. Once faults exist, the machinery has to stop operating, which finally leads to serious economic losses. Therefore, fault diagnosis methods are studied to recognize faults, provide advice of machinery maintenance and ensure the operation reliability of machinery. Nowadays, mechanical big data are collected by multiple sensors after the long-time operation of machinery, which pushes the fault diagnosis into the big data era.