Proceedings of the 2015 International conference on Applied Science and Engineering Innovation

The study of the on-line fault diagnosis method for induction motor bearing based on AR Model Parameters Identification

Authors
Ju-mei Yuan, Lu Zhao
Corresponding Author
Ju-mei Yuan
Available Online May 2015.
DOI
10.2991/asei-15.2015.38How to use a DOI?
Keywords
AR model parameters; Identification; Motor bearing fault; On-line diagnosis
Abstract

To realize the online fault diagnosis for induction motor bearings, a method of online identification based on the AR model parameter recursive identification for induction motors vibration signal was proposed. Firstly, based on the optimal instrumental variable method, four auto-regression models were established for the vibration signals of induction motor under four conditions: the normal condition, out-race fault, inner-race fault and the ball bearing fault. Then, the state equations for the induction motor vibration signals were established by taking the autoregressive model coefficients as the state variables and the AR model coefficients in normal conditions are initial values. The online parameter identification is finished with Kalman filtering technique. Based on these, the relationship of the model coefficients under the four conditions was analyzed by making use of Hierarchical Cluster Analysis, and the online diagnosis for bearing faults in induction motors was accomplished with the Bullock distance of model parameters as criterion. Finally, the feasibility and the effectiveness of the proposed method are proved through the analysis of examples.

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)

Volume Title
Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
Series
Advances in Engineering Research
Publication Date
May 2015
ISBN
978-94-62520-94-3
ISSN
2352-5401
DOI
10.2991/asei-15.2015.38How to use a DOI?
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/).

Cite this article

TY  - CONF
AU  - Ju-mei Yuan
AU  - Lu Zhao
PY  - 2015/05
DA  - 2015/05
TI  - The study of the on-line fault diagnosis method for induction motor bearing based on AR Model Parameters Identification
BT  - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
PB  - Atlantis Press
SP  - 175
EP  - 181
SN  - 2352-5401
UR  - https://doi.org/10.2991/asei-15.2015.38
DO  - 10.2991/asei-15.2015.38
ID  - Yuan2015/05
ER  -