A comprehensive method enhances the lifespan of electric vehicle batteries through active balancing and machine learning for accurate remaining useful life (RUL) estimation.
The study presents a novel active cell balancing method optimized for electric vehicle lithium-ion battery packs, improving overall performance and lifespan through active charge and discharge balancing strategies, alongside machine learning models for predicting remaining useful life (RUL).
The research was conducted by Y.A. Sultan, A.A. Eladl, M.A. Hassan, and their collaborative team, showcasing contributions from the Science, Technology & Innovation Funding Authority (STDF) and the Egyptian Knowledge Bank (EKB).
This study was accepted for publication on [exact date needed] and is referenced as having received and conducted extensive experimental evaluations prior to acceptance.
The research was conducted through collaborative institutions, with experimental setups possibly located at the respective universities or affiliated research institutes for battery testing across contexts.
With the increasing global adoption of electric vehicles, improving battery performance and longevity is imperative for market sustainability and reduction of fossil fuel dependence. The study addresses the challenges posed by inconsistent charging states, temperature sensitivity, and the need for efficient energy management of lithium-ion batteries.
The researchers utilized two balancing strategies for the batteries—charging balance, redistributing excess charge from higher SOC cells, and discharging balance to extend discharge duration. They also employed various machine learning models like k-nearest neighbors and random forest for predicting RUL, achieving significant accuracy metrics, thereby integrating active balancing with predictive analytics to maximize battery efficiency.
This comprehensive approach advances EV battery management, enhancing lifespan and reliability through proactive balancing and predictive insights.
The findings from this study underlined the importance of integrating sophisticated techniques for active balancing and machine learning algorithms to revolutionize electric vehicle battery management.