Application of CEEMD-SVM in Rolling Bearing Fault Recognition

DOI

10.2991/mcei-16.2016.304How to use a DOI?

Keywords

Complementary ensemble empirical mode decomposition; Support vector machine; Rolling bearing; Fault recognition

Abstract

To extract effective fault features from the nonstationary vibration signals of rolling bearing, this paper provides a fault recognition method by using complementary ensemble empirical mode decomposition (CEEMD) and support vector machine (SVM). Firstly, CEEMD is applied to process vibration signals of rolling bearing. Then some time domain features of the first several intrinsic mode functions (IMFs) are calculated to construct feature set, and it is utilized as the input of SVM. Finally, different fault states of rolling bearing are classified through SVM. The experiment results indicate that the presented method is effective, and it can significantly improve the classification accuracy of fault recognition.

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  - Xiang Li
AU  - Feng Ding
PY  - 2016/12
DA  - 2016/12
TI  - Application of CEEMD-SVM in Rolling Bearing Fault Recognition
BT  - Proceedings of the 2016 6th International Conference on Mechatronics, Computer and Education Informationization (MCEI 2016)
PB  - Atlantis Press
SP  - 1497
EP  - 1501
SN  - 1951-6851
UR  - https://doi.org/10.2991/mcei-16.2016.304
DO  - 10.2991/mcei-16.2016.304
ID  - Li2016/12
ER  -