Battery fault diagnosis methods for electric vehicle lithium-ion batteries: Correlating codes and battery management system

• Published in: Process safety and environmental protection Vol. 196; p. 106919
• Main Authors: G, Naresh, Praveenkumar, T., Madheswaran, Dinesh Kumar, Varuvel, Edwin Geo, Pugazhendhi, Arivalagan, Thangamuthu, Mohanraj, Muthiya, S. Jenoris
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2025
• Subjects: Battery fault diagnostics; Battery Management System (BMS); Electric vehicles; Li-ion batteries; Machine learning; Thermal runaway; Battery fault diagnostics; Electric vehicles; Battery Management System (BMS); Li-ion batteries; Machine learning; Thermal runaway
• ISSN: 0957-5820
• DOI: 10.1016/j.psep.2025.106919

Lithium-ion batteries are the heart of modern electric vehicle technology. Operational stresses such as temperature changes, mechanical impacts, and electrochemical aging often subject them to faults, necessitating accurate fault diagnosis that adheres to international safety standards. Consequently, this review examines state-of-the-art fault diagnosis methodologies, emphasizing their integration with global safety frameworks such as the International Organization for Standardization, International Electrotechnical Commission, Society of Automotive Engineers, etc. A thorough analysis of artificial fault induction techniques—such as overcharging and overheating—is presented to assess their effectiveness in validating diagnostic algorithms. Additionally, the role of machine learning in battery management systems is reviewed, where the Feature Fusion and Expert Knowledge Integration network emerged effective, achieving an anomaly detection rate of 98.5 %, outperforming conventional methods in accuracy and speed. Hybrid diagnostic frameworks integrating model-based and machine-learning techniques are also highlighted for their scalability and precision in addressing sub-extreme fault scenarios. Looking ahead, this study emphasizes the importance of interdisciplinary research to enhance fault detection, focusing on adaptive machine learning algorithms and real-world testing to ensure the long-term viability of contemporary battery technologies. [Display omitted] •Identified critical gaps in safety standards for EV battery fault diagnosis systems.•Analyzed artificial fault induction methods for validating diagnostic algorithms.•Highlighted machine learning applications as effective tools for fault detection.•Emphasized aligning diagnostic algorithms with safety codes for practical deployment.