Navigating the spectrum of battery health management in electric vehicles: A comprehensive review

Lithium-ion batteries (LIBs) are a cornerstone of modern electric vehicles (EVs) due to their high energy density, long lifespan, and excellent performance. However, ensuring their reliability and longevity presents substantial challenges due to degradation caused by various internal and external factors. This review paper addresses the critical problem of accurately estimating the state of health (SoH), remaining useful life (RUL), and battery ageing in dynamic operating environments. The existing literature lacks a consolidated comparative analysis of traditional, adaptive, and emerging data-driven approaches to battery health management, particularly in the context of real-world applications. This review presents an in-depth synthesis of conventional methods, model-based techniques, adaptive filtering, and artificial intelligence (AI)-driven strategies including machine learning (ML), fuzzy logic, and cloud-integrated frameworks for SoH, RUL, and ageing prediction. Furthermore, the paper discusses the implications of battery cycling databases and highlights how open-source data and modern computational advancements support scalable predictive analytics. A comparative critique of various methodologies is provided to evaluate performance, adaptability, and real-world feasibility. The review identifies key challenges and research gaps, emphasizing the need for model interpretability, real-time validation, and long-term performance assessment. Overall, this paper contributes to the academic and industrial understanding of predictive battery management, guiding future research toward the development of accurate, interpretable, and scalable models that ensure sustainable EV battery operation.