Work

A Novel Bearing Fault Diagnosis Method Based on Gaussian Restricted Boltzmann Machine

Year: 2016

Type: article

Abstract: To realize the fault diagnosis of bearing effectively, this paper presents a novel bearing fault diagnosis method based on Gaussian restricted Boltzmann machine (Gaussian RBM). Vibration signals are firstly resampled to the same equivalent speed. Subsequently, the envelope spectrums of the resampled data are used directly as the feature vectors to represent the fault types of bearing. Finally, in order to deal with the high-dimensional feature vectors based on envelope spectrum, a classifier model based on Gaussian RBM is applied. Gaussian RBM has the ability to provide a closed-form representation of the distribution underlying the training data, and it is very convenient for modeling high-dimensional real-valued data. Experiments on 10 different data sets verify the performance of the proposed method. The superiority of Gaussian RBM classifier is also confirmed by comparing with other classifiers, such as extreme learning machine, support vector machine, and deep belief network. The robustness of the proposed method is also studied in this paper. It can be concluded that the proposed method can realize the bearing fault diagnosis accurately and effectively.

Source: Mathematical Problems in Engineering

DOI: 10.1155/2016/2957083

Authors: Xiao-hui He, Dong Wang, Yan-feng Li, Chun-hua Zhou

Institutions: PLA Army Engineering University, Ningbo University

Language: English

Topic: Machine Fault Diagnosis Techniques

Subfield: Control and Systems Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,550

Funder: National Natural Science Foundation of China