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

Xiao-Hui He,Chun-Hua Zhou,Dong Wang,Yan-Feng Li

doi:10.1155/2016/2957083

Xiao-Hui He, Chun-Hua Zhou + Show 2 more

Open Access

https://doi.org/10.1155/2016/2957083

Copy DOI

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.

Highlights

Bearing is the most important component of rotating machinery
In order to show the superiority of Gaussian RBM classifier, other methods, such as extreme learning machine (ELM), support vector machine (SVM), and deep belief network (DBN), are used for comparison in this paper
This paper has proposed a novel bearing fault diagnosis method based on Gaussian RBM

Summary

Introduction

Bearing is the most important component of rotating machinery. Feature extraction from vibration signals is a critical step in bearing fault diagnosis. In order to further improve the accuracy and efficiency of the diagnosis work, some new feature extraction methods have been proposed in recent years. The aforementioned feature extraction methods have been successfully used in the bearing fault diagnosis. Excessive irrelevant features are often extracted from vibration signals. In order to further improve the diagnosis accuracy, many feature selection techniques have to be used [9]. This often makes the fault diagnosis much more complex

Methods

Results

Conclusion