Fault diagnosis and failure analysis of motor controller by the approach of Bayesian inference
by Xiong Shu; Huan Yang; Hongguang Zhou; Kexiang Wei; Yingfu Guo; Sudong He
International Journal of Vehicle Design (IJVD), Vol. 86, No. 1/2/3/4, 2021

Abstract: Electric vehicles are growing in popularity, it is deemed that they will replace petrol and diesel vehicles in the near future. However, the failure analysis and fault diagnosis of the motor controller is still a matter of concern today. In order to solve the problems of multiple fault decoupling, location and diagnosis in motor controller hardware system of electric vehicle, a fault diagnosis method of motor controller based on Bayesian network is proposed. On the basis of decomposing hardware structure of the motor controller, the fault categories of the motor controller are classified, firstly; then the hardware fault tree of the motor controller is established. Finally, the fault diagnosis model of motor controller hardware system is established by converting fault tree to Bayesian network. In terms of data quantification, the method of leak noisy-or node was introduced to reduce the demand of conditional sample data. In order to verify the feasibility of fault diagnosis model for motor controller hardware, a case study is conducted in this paper, and the results show the effectiveness of the method.

Online publication date: Thu, 14-Apr-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Vehicle Design (IJVD):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com