Zheng Chen received the B.S. and M.S. degrees in electrical engineering and the Ph.D. degree in control science engineering from Northwestern Polytechnical University, Xi'an, China, in 2004, 2007 and 2012, respectively. He is currently a Professor with the Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming, Yunnan, China. He was a Post-Doctoral Fellow and a Research Scholar with the University of Michigan, Dearborn, MI, USA from 2008 to 2014, and a Marie-Curie Research Fellow with Queen Mary University of London, London, U.K. from 2019 to 2021. His research interests include battery management system, and energy control of intelligent electric vehicles. He is a Fellow of the Institution of Engineering and Technology.

Accurate state of health (SOH) prediction and reliable fault diagnosis are vital to healthy management of lithium-ion batteries. With the substantial development of artificial intelligence technologies, a body of research has been performed towards precise and effective SOH prediction and malfunctions detection based on data driven techniques. In this report, the conception of battery SOH and battery fault are defined, and the state-of-the-art prediction methods and diagnosis methods are classified based on their primary implementation procedures. As an essential step in data driven-based battery SOH prediction and fault diagnosis, the health feature extraction methods and fault feature selection methods are comprehensively summarized. An exhausted comparison is conducted to elaborate the development of data driven-based SOH prediction and fault diagnosis techniques. Some detailed works in terms of the data-driven approach employed by our team in battery SOH prediction and failure diagnosis are introduced.