TY - JOUR
T1 - Artificial Intelligence Technique-Based EV Powertrain Condition Monitoring and Fault Diagnosis
T2 - A Review
AU - Zhang, Xiaotian
AU - Hu, Yihua
AU - Gong, Chao
AU - Deng, Jiamei
AU - Wang, Gaolin
N1 - Publisher Copyright:
© 2001-2012 IEEE.
PY - 2023/8/1
Y1 - 2023/8/1
N2 - Electric powertrain used in electric vehicles (EVs), which is constituted of a motor, transmission unit, inverter, battery packs, and so on, is a highly integrated system. Its reliability and safety are not only related to industrial costs but more importantly to the safety of human life. This review contributes to comprehensively summarizing artificial intelligence (AI)-based/AI-supported approaches in EV powertrain condition monitoring and fault diagnosis that can be used in EV applications. The application of AI on PE in EV is a new attempt, which can solve many issues with better performance than traditional methods and even achieve functions that the conventional methods cannot achieve. This article thoroughly discusses the motivation, advantages, limitations, and challenges associated with AI-supported methods through case summaries, classification, comparisons, and quantitative analyses between conventional and AI-based approaches. Furthermore, the review concludes by proposing forward-looking future trends in this field.
AB - Electric powertrain used in electric vehicles (EVs), which is constituted of a motor, transmission unit, inverter, battery packs, and so on, is a highly integrated system. Its reliability and safety are not only related to industrial costs but more importantly to the safety of human life. This review contributes to comprehensively summarizing artificial intelligence (AI)-based/AI-supported approaches in EV powertrain condition monitoring and fault diagnosis that can be used in EV applications. The application of AI on PE in EV is a new attempt, which can solve many issues with better performance than traditional methods and even achieve functions that the conventional methods cannot achieve. This article thoroughly discusses the motivation, advantages, limitations, and challenges associated with AI-supported methods through case summaries, classification, comparisons, and quantitative analyses between conventional and AI-based approaches. Furthermore, the review concludes by proposing forward-looking future trends in this field.
KW - Artificial intelligence (AI)
KW - condition monitoring
KW - fault diagnosis
KW - feature extraction
KW - neural network applications
UR - http://www.scopus.com/inward/record.url?scp=85163501496&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2023.3285531
DO - 10.1109/JSEN.2023.3285531
M3 - 文献综述
AN - SCOPUS:85163501496
SN - 1530-437X
VL - 23
SP - 16481
EP - 16500
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 15
ER -