Artificial intelligence-driven rechargeable batteries in multiple fields of development and application towards energy storage

Rechargeable batteries are vital in the domain of energy storage. However, traditional experimental or computational simulation methods for rechargeable batteries still pose time and resource constraints. Artificial intelligence (AI), especially machine learning (ML) technology, has experienced rapid growth in recent years. The excellent classification and regression abilities of ML have been successfully applied to various fields of rechargeable battery research, resulting in numerous outstanding achievements. Herein, it is worthwhile to summarize the work of AI in rechargeable battery technology. This review aims to present a comprehensive account of the multiple fields where AI has been utilized for rechargeable battery research. First, the concept of ML and the key steps of processing are summarized. We then discuss how AI enables prediction of battery states and parameters in battery management systems, mainly including state of charge, state of health. Following this, the applications of AI to the discovery of key materials for rechargeable batteries, including cathodes, anodes, and electrolytes, are stated. We subsequently provide illustrations of how rechargeable batteries are utilized in charging protocols for energy storage. Additionally, we briefly outline the potential for developing AI’s new elements of machine vision and digital twins in battery research. Finally, we conclude by addressing challenges and perspectives for ML to drive innovations in battery technology. •Research database summary, key processing steps and algorithms for artificial intelligence in rechargeable batteries.•Research on rechargeable battery management systems, internal status.•Analysis of artificial intelligence in rechargeable battery crucial materials and charging protocols.•Challenges and insights on the application of artificial intelligence to rechargeable batteries.•Potential for digital twins, machine vision in new elements of artificial intelligence.