Title: Fault diagnosis and failure analysis of motor controller by the approach of Bayesian inference

Authors: Xiong Shu; Huan Yang; Hongguang Zhou; Kexiang Wei; Yingfu Guo; Sudong He

Addresses: School of Mechanical Engineering, Hunan University of Science and Technology, Hunan, Xiangtan, 411201, China;Hunan Provincial Key Laboratory of Vehicle Power and Transmission System, Hunan Institute of Engineering, Hunan, Xiangtan, 411104, China ' School of Humanities and Education, Hunan Vocational College of Electronic and Technology, Changsha, 410217, China ' Hunan Provincial Key Laboratory of Vehicle Power and Transmission System, Hunan Institute of Engineering, Hunan, Xiangtan, 411104, China ' Hunan Provincial Key Laboratory of Vehicle Power and Transmission System, Hunan Institute of Engineering, Hunan, Xiangtan, 411104, China ' School of Mechanical Engineering, Hunan University of Science and Technology, Hunan, Xiangtan, 411201, China ' School of Mechanical Engineering, Hunan University of Science and Technology, Hunan, Xiangtan, 411201, China

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.

Keywords: motor controller; electric vehicle; faults diagnosis; Bayesian network; faults tree analysis.

DOI: 10.1504/IJVD.2021.122251

International Journal of Vehicle Design, 2021 Vol.86 No.1/2/3/4, pp.52 - 70

Received: 19 May 2020
Accepted: 12 Mar 2021
Published online: 14 Apr 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article