A Comprehensive Review on Data‐Driven Methods of Lithium‐Ion Batteries State‐of‐Health Forecasting

Abstract

Lithium‐ion batteries are widely used in moving devices due to their many advantages compared to other battery types. The prevalence of Lithium‐ion batteries is evident, playing its clear role in the operation of small devices as well as large systems such as electric vehicles, flying devices, mobile devices, and more. Monitoring lithium‐ion battery health is crucial for assessing, minimizing degradation, preventing explosions, and enabling timely replacements. Assessing health often involves predicting state‐of‐health (SoH) or remaining useful life (RUL), with numerous studies dedicated to this field. Hence, many research studies have been conducted on predicting SoH, with a primary focus on data‐driven methods based on machine learning, owing to the recent advancements in artificial intelligence (AI) techniques. To provide a systematic overview of the trends in this emerging problem, we present a comprehensive survey of classified SoH forecasting methods, with a primary focus on data‐driven approaches. The paper also offers an in‐depth focus on recent advancements in deep learning (DL) models, an area that has not been thoroughly discussed previously. Furthermore, we highlight the importance of input features and emphasize the critical role of temporal attributes incorporated into the models. The insights provided in this paper offer readers a comprehensive understanding of the field, equipping them to effectively advance related future work.