Fault Diagnosis Based on EEMD-KPCA-MTS for Rolling Bearing

DOI

10.2991/assehr.k.200207.068How to use a DOI?

Keywords

fault diagnosis, KPCA, MTS, EEMD, IMF

Abstract

To improve the accuracy of fault diagnosis for rolling bearing, an integrated fault diagnosis method based on EEMD (Ensemble Empirical Mode Decomposition), KPCA (Kernel Principal Component Analysis) and MTS (Mahalanobis Taguchi System) is proposed. Firstly, EEMD decompose the non-stationary and nonlinear vibration signals into a series of IMFs (intrinsic mode functions). Then some of IMFs sensitive to the fault information is selected by the IMF sensitive discriminant algorithm and establish the initial feature vector. Then, KPCA further reduces the dimensionality of the vector. Finally, an effective MTS fault detectors and classifiers is established to identify fault types of sample data. The experimental results show that compared with conventional single fault diagnosis methods, the EEMD-KPCA-MTS model has strong adaptability and accuracy.

Copyright

© 2020, 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  - Weiyu Han
AU  - Longsheng Cheng
PY  - 2020
DA  - 2020/02/17
TI  - Fault Diagnosis Based on EEMD-KPCA-MTS for Rolling Bearing
BT  - Proceedings of the International Academic Conference on Frontiers in Social Sciences and Management Innovation (IAFSM 2019)
PB  - Atlantis Press
SP  - 439
EP  - 445
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.200207.068
DO  - 10.2991/assehr.k.200207.068
ID  - Han2020
ER  -