Synergizing physics and machine learning for advanced battery management
Manashita Borah, Qiao Wang, Scott Moura, Dirk Uwe Sauer, Weihan Li
Abstract
Improving battery health and safety motivates the synergy of a powerful duo: physics and machine learning. Through seamless integration of these disciplines, the efficacy of mathematical battery models can be significantly enhanced. This paper delves into the challenges and potentials of managing battery health and safety, highlighting the transformative impact of integrating physics and machine learning to address those challenges. Based on our systematic review in this context, we outline several future directions and perspectives, offering a comprehensive exploration of efficient and reliable approaches. Our analysis emphasizes that the integration of physics and machine learning stands as a disruptive innovation in the development of emerging battery health and safety management technologies. Lithium-ion batteries are integral to modern technologies but the sustainability of long-term battery health is a significant and persistent challenge. In this perspective Borah and colleagues discuss the integration of physics and machine learning to support developments in battery performance and safety.