Fault identification and analysis of complex electromechanical system using dynamic fault probability

DOI

10.2991/ifmca-16.2017.108How to use a DOI?

Keywords

dynamic Bayesian network, dynamic fault probability, complex electromechanical system, fault diagnosis.

Abstract

This paper presents a novel fault identification method based on object oriented Bayesian network (OOBN) and dynamic fault probability according to the structure-function relationship and the failure mode effect analysis (FMEA) of the diagnosed system. Fault identification of complex electromechanical system is difficult. The diagnostic model is in real time because it considers the change of fault probability depending on the working time and the system function state influenced by degradation of component reliability. The peculiarities of proposed approach are that the diagnosis model is hierarchical and dynamic, to depict actual character of nodes. Furthermore, the model is reusable and expandable. The application of ISG-engine in hybrid electric bus demonstrates the effectiveness and superiority of the approach.

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  - Hongxia Wu
AU  - Jie Han
AU  - Dongchen Qin
PY  - 2017/03
DA  - 2017/03
TI  - Fault identification and analysis of complex electromechanical system using dynamic fault probability
BT  - Proceedings of the 2016 International Forum on Mechanical, Control and Automation (IFMCA 2016)
PB  - Atlantis Press
SP  - 689
EP  - 695
SN  - 2352-5401
UR  - https://doi.org/10.2991/ifmca-16.2017.108
DO  - 10.2991/ifmca-16.2017.108
ID  - Wu2017/03
ER  -