Employment of artificial intelligence (AI) techniques in battery management system (BMS) for electric vehicles (EV): issues and challenges

• Main Authors: Badran, Marwan Atef, Toha @ Tohara, Siti Fauziah
• Format: Article
• Language: English; English
• Published: UPM Press 2024
• Subjects: TL1 Motor vehicles
• Online Access: http://irep.iium.edu.my/111651/7/111651_Employment%20of%20artificial%20intelligence.pdf; http://irep.iium.edu.my/111651/13/111651_Employment%20of%20artificial%20intelligence_SCOPUS.pdf; http://irep.iium.edu.my/111651/; http://www.pertanika.upm.edu.my/pjst/browse/regular-issue?article=JST-4495-2023; https://doi.org/10.47836/pjst.32.2.20
• Institution: Universiti Islam Antarabangsa Malaysia

Rechargeable Lithium-ion batteries have been widely utilized in diverse mobility applications, including electric vehicles (EVs), due to their high energy density and prolonged lifespan. However, the performance characteristics of those batteries, in terms of stability, efficiency, and life cycle, greatly affect the overall performance of the EV. Therefore, a battery management system (BMS) is required to manage, monitor and enhance the performance of the EV battery pack. For that purpose, a variety of Artificial Intelligence (AI) techniques have been proposed in the literature to enhance BMS capabilities, such as monitoring, battery state estimation, fault detection and cell balancing. This paper explores the state-of-the-art research in AI techniques applied to EV BMS. Despite the growing interest in AI-driven BMS, there are notable gaps in the existing literature. Our primary output is a comprehensive classification and analysis of these AI techniques based on their objectives, applications, and performance metrics. This analysis addresses these gaps and provides valuable insights for selecting the most suitable AI technique to develop a reliable BMS for EVs with efficient energy management.