Skip to main navigation Skip to search Skip to main content

Artificial Intelligence Technique-Based EV Powertrain Condition Monitoring and Fault Diagnosis: A Review

  • Xiaotian Zhang
  • , Yihua Hu
  • , Chao Gong
  • , Jiamei Deng
  • , Gaolin Wang
  • University of York
  • University of Alberta
  • Leeds Beckett University
  • School of Electrical Engineering and Automation, Harbin Institute of Technology

Research output: Contribution to journal › Review article › peer-review

45 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)16481-16500
Number of pages20
JournalIEEE Sensors Journal
Volume23
Issue number15
DOIs
StatePublished - 1 Aug 2023
Externally publishedYes

Keywords

  • Artificial intelligence (AI)
  • condition monitoring
  • fault diagnosis
  • feature extraction
  • neural network applications

Fingerprint

Dive into the research topics of 'Artificial Intelligence Technique-Based EV Powertrain Condition Monitoring and Fault Diagnosis: A Review'. Together they form a unique fingerprint.

Cite this