Publication: Advanced data-driven fault diagnosis in lithium-ion battery management systems for electric vehicles: Progress, challenges, and future perspectives
Date
2024
Authors
Abdolrasol M.G.M.
Ayob A.
Lipu M.S.H.
Ansari S.
Kiong T.S.
Saad M.H.M.
Ustun T.S.
Kalam A.
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier B.V.
Abstract
Hazards in electric vehicles (EVs) often stem from lithium-ion battery (LIB) packs during operation, aging, or charging. Robust early fault diagnosis algorithms are essential for enhancing safety, efficiency, and reliability. LIB fault types involve internal batteries, sensors, actuators, and system faults, managed by the battery management system (BMS), which handles state estimation, cell balancing, thermal management, and fault diagnosis. Prompt identification and isolation of defective cells, coupled with early warning measures, are critical for safety. This review explores data-driven methods for fault diagnosis in LIB management systems, covering implementation, classification, fault types, and feature extraction. It also discusses BMS roles, sensor types, challenges, and future trends. The findings aim to guide researchers and the automotive industry in advancing fault diagnosis methods to support sustainable EV transportation. ? 2024 Elsevier B.V.
Description
Keywords
Battery management systems , Battery Management , Data driven , Data-driven fault diagnosis , Fault types , Faults diagnosis , Future perspectives , Ion batteries , Lithium ions , Machine-learning , Management systems , Battery Pack