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

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...

Full description

Saved in:
Bibliographic Details
Published in:Mathematical problems in engineering 2016-01, Vol.2016 (2016), p.1-8
Main Authors: Zhou, Chun-hua, Li, Yan-feng, Wang, Dong, He, Xiao-hui
Format: Article
Language:English
Subjects:
Artificial neural networks
Bearing
Belief networks
Classifiers
Datasets
Engineering
Envelopes
Fault diagnosis
Feature extraction
Machine learning
Mathematical analysis
Methods
Neural networks
Normal distribution
Support vector machines
Vectors (mathematics)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1024-123X
1563-5147
DOI:10.1155/2016/2957083