Bearings Fault Diagnosis based on Wavelet Analysis and Support Vector Machine

DOI

10.2991/cmfe-15.2015.205How to use a DOI?

Keywords

Support vector machine; Rolling bearings; Fault diagnosis; Wavelet packet; Wind Turbines

Abstract

Drive system of generator is an important part of wind turbine, once the fault occurs it will cause huge economic losses. For this reason, in this paper, a fault diagnosis method is proposed for generator rolling bearings, it combined with wavelet packet and support vector machine. Acquisition of wind farm FAG6332 rolling bearings vibration signal in real-time database, which contains the normal operation?inner ring fault and outer ring fault. Firstly, using wavelet packets decomposed the vibration signals into different frequency bands, so extract energy spectrum as a fault feature vector, then put the fault feature vector into the support vector machine training the SVM; Using MATLAB for simulation experimental, put the test sample into the trained SVM for fault pattern recognition, the results show that the fault diagnosis model can make a 93.3333% high precision, can make a fast and effective fault diagnosis for rolling bearings. The conclusion is that the fault diagnosis method can recognition the drive system fault, improve the utilization of wind turbines, and it offer a good guide to the operation of wind farm.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xinli Li
AU  - Wanye Yao
AU  - Xiao Yang
AU  - Jianming Wang
PY  - 2015/07
DA  - 2015/07
TI  - Bearings Fault Diagnosis based on Wavelet Analysis and Support Vector Machine
BT  - Proceedings of the International Conference on Chemical, Material and Food Engineering
PB  - Atlantis Press
SP  - 896
EP  - 899
SN  - 2352-5401
UR  - https://doi.org/10.2991/cmfe-15.2015.205
DO  - 10.2991/cmfe-15.2015.205
ID  - Li2015/07
ER  -