A new fault diagnosis method based on deep belief network and support vector machine with Teager–Kaiser energy operator for bearings

Dongying Han,Peiming Shi,Na Zhao

doi:10.1177/1687814017743113

Dongying Han, Peiming Shi + Show 1 more

Open Access

https://doi.org/10.1177/1687814017743113

Copy DOI

Journal: Advances in Mechanical Engineering	Publication Date: Dec 1, 2017
Citations: 30	License type: cc-by

Affiliation: Yanshan University

Abstract

How to improve the accuracy and algorithm efficiency of bearing fault diagnosis has been the focus and hot topic in fault diagnosis field. Deep belief network is a typical deep learning method, which can be used to form a much higher-level abstract representation and find the distributed characteristics of data. In this article, a new method of bearing fault diagnosis is proposed based on Teager–Kaiser energy operator and the particle swarm optimization-support vector machine with deep belief network. In this method, the demodulation signal is obtained using Teager–Kaiser energy operator first. And then the time and frequency statistic characteristic of the demodulation signal is analyzed. Furthermore, the deep belief network is used to extract time and frequency feature extraction. Finally, the extracted parameters are classified by particle swarm optimization-support vector machine. The experimental results show that it not only has higher accuracy but also shortens the training time greatly, and it improves the accuracy and efficiency of fault diagnosis obviously.

Highlights

Rolling bearing is an important part of rotating machinery, and its common failure modes are wear, plastic deformation, corrosion, burn, and so on
Most of the rotating machinery faults are caused by the failure of the rolling bearing
Section deals with the basic principles of energy operator demodulation, which is followed by the section that explains fault diagnoses method based on deep belief networks (DBNs) and particle swarm optimization (PSO)-support vector machine (SVM)

Summary

Introduction

Rolling bearing is an important part of rotating machinery, and its common failure modes are wear, plastic deformation, corrosion, burn, and so on. Section deals with the basic principles of energy operator demodulation, which is followed by the section that explains fault diagnoses method based on DBN and PSO-SVM. The time and frequency characteristic statistics of fault signal is used as input and the DBN is used for feature re-selecting.

Results

Conclusion