Research on Machinery Fault Diagnostics Based on Vibration Signal Analysis

DOI

10.2991/ism3e-15.2015.140How to use a DOI?

Abstract

Aiming at the non-stationary features of mechanical vibration signals, a fault diagnosis method based on ensemble empirical mode decomposition singular value entropy and support vector machine are put forward. This method utilizes the advantage of EEMD which can effectively restrain model mixing and combined with information entropy theory, firstly, original signals were decomposed into a finite number of stationary intrinsic mode functions (IFMs). Secondly, singular value and singular entropies of a feature pattern matrix whose rows are IMFs are extracted. Finally, singular value feature vector are served as the input vectors of SVM, based on the output to identify the fault pattern. Experimental results show that this method is affective.

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  - Yan Lv
AU  - Liqing Fang
AU  - Qiantu Zhang
PY  - 2015/11
DA  - 2015/11
TI  - Research on Machinery Fault Diagnostics Based on Vibration Signal Analysis
BT  - Proceedings of the 2015 International Symposium on Material, Energy and Environment Engineering
PB  - Atlantis Press
SP  - 580
EP  - 583
SN  - 2352-5401
UR  - https://doi.org/10.2991/ism3e-15.2015.140
DO  - 10.2991/ism3e-15.2015.140
ID  - Lv2015/11
ER  -