Rolling Bearing Fault Pattern Recognitionÿof Wind Turbine Based on VMD and PNN

DOI

10.2991/icreet-16.2017.28How to use a DOI?

Keywords

variational mode decomposition, multiscale permutation entropy, probabilistic neural network, rolling bearing, pattern recognition

Abstract

A novel method based on variational modal decomposition (VMD), improved multiscale permutation entropy (IMPE) and probabilistic neural network (PNN) is proposed to solve the problem of the rolling bearing fault pattern recognition for wind turbine. Firstly, the vibration signal is decomposed into several components using VMD. Then, the IMPE of the optimal component which has the maximum kurtosis is computed and constructed to feature vector. Finally, the feature vector is inputted into PNN classifier to train and test the fault pattern respectively. Experimental analysis results show that the proposed method can effectively identify the damage locations and different damage degree for bearing. It has good engineering application value.

Copyright

© 2017, 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  - Guiji Tang
AU  - Shangkun Liu
PY  - 2017/03
DA  - 2017/03
TI  - Rolling Bearing Fault Pattern Recognitionÿof Wind Turbine Based on VMD and PNN
BT  - Proceedings of the 2016 4th International Conference on Renewable Energy and Environmental Technology (ICREET 2016)
PB  - Atlantis Press
SP  - 161
EP  - 165
SN  - 2352-5401
UR  - https://doi.org/10.2991/icreet-16.2017.28
DO  - 10.2991/icreet-16.2017.28
ID  - Tang2017/03
ER  -