|
J. Comput. Sci. Eng.
Vol. 72 (2025) 1-15 |
| |
Fault Diagnosis Technologies for Electric Vehicle Energy Regeneration Systems: A Review |
|
|
|
Zheng Lin, Yu Xinyao,Wang Jiawang, Zhu Hailin,Gao Mingkai |
|
|
|
J. Comput. Sci. Eng. 72(2025) 1 - 8 —Published https://doi.org/10.54762/jcse2025-72.1-8 (registering DOI) 25 Dec 2025 |
|
|
| |
Abstract: The regenerative braking system is a key technology for improving the energy efficiency and driving range of electric vehicles. Comprising multiple interconnected components, including the traction motor, power battery, braking actuator, and controller, the system exhibits considerable structural complexity and is therefore vulnerable to various faults during operation. These faults can significantly compromise driving safety and regenerative braking efficiency. This paper provides a comprehensive review of recent advances in fault diagnosis technologies for electric vehicle regenerative braking systems. First, the typical fault types and their underlying mechanisms are analyzed, including motor faults, battery faults, regenerative braking system faults, and controller and sensor faults. Subsequently, the current development and application characteristics of model based and data driven fault diagnosis methods are systematically reviewed. Finally, the major challenges faced by existing research are discussed, and future research directions are proposed to support the continued development and engineering application of fault diagnosis technologies for electric vehicle regenerative braking systems.
|
|
|
|
Keywords: Electric Vehicles; Regenerative Braking System; Regenerative Braking; Fault Diagnosis; Intelligent Fault Diagnosis
 :
Download (free)  CSE-PDF |
|
|
| |
Fault Diagnosis Technologies for Permanent Magnet Synchronous Motors in Electric Vehicles: A Review |
|
|
|
Zheng Lin, Wang Jiawang, Yu Xinyao, Gao Mingkai, Zhu Hailin |
|
|
|
J. Comput. Sci. Eng. 72(2025) 9 - 18 —Published https://doi.org/10.54762/jcse2025-72.9-18 (registering DOI) 25 Dec 2025 |
|
|
| |
Abstract: With the rapid development of new energy vehicles, Permanent Magnet Synchronous Motors (PMSMs) have become the core driving components of electric vehicles. However, under complex operating conditions, PMSMs are susceptible to various faults, including electrical faults, mechanical faults, and permanent magnet demagnetization, which may significantly affect the safety and reliability of the drive system. This paper reviews the recent research progress in fault diagnosis technologies for PMSMs, with particular emphasis on signal processing based, model based, and artificial intelligence based diagnostic methods. The characteristics, advantages, limitations, and application scenarios of these approaches are systematically analyzed and compared. In addition, the development trends of multi sensor information fusion and intelligent fault diagnosis are summarized. Finally, the current challenges in hybrid fault identification, insufficient fault data, and real time diagnosis are discussed, and future research directions are presented.
|
|
|
|
Keywords: Electric Vehicle; Permanent Magnet Synchronous Motor (PMSM); Fault Diagnosis; Deep Learning; Multi Source Information Fusion
:
Download (free) CSE-PDF |
|
|
！！ from ACSS |