Abstract
In the field of energy storage, it is very important to predict the state of charge and the state of health of lithium-ion batteries. In this paper, we review the current widely used equivalent circuit and electrochemical models for battery state predictions. The review demonstrates that machine learning and deep learning approaches can be used to construct fast and accurate data-driven models for the prediction of battery performance. The details, advantages, and limitations of these approaches are presented, compared, and summarized. Finally, future key challenges and opportunities are discussed.
| Original language | English |
|---|---|
| Pages (from-to) | 159-173 |
| Number of pages | 15 |
| Journal | Journal of Energy Chemistry |
| Volume | 74 |
| Early online date | 2 Jul 2022 |
| DOIs | |
| Publication status | Published (in print/issue) - 30 Nov 2022 |
Bibliographical note
Funding Information:Zhicong Shi received his Ph.D. degree in Physical Chemistry from Xiamen University in 2005. He joined the Dalian University of Technology as an associate professor after a postdoctoral fellowship from the University of Alberta, Canada. Now, he is a professor at the School of Materials and Energy, Guangdong University of Technology. His current research interests focus on design, characterization, and understanding of the working mechanism of materials for supercapacitors, batteries, and fuel cells.
Funding Information:
We thank the research funding support from the Department of Science and Technology of Guangdong Province (2019A050510043), the Department of Science and Technology of Zhuhai City (ZH22017001200059PWC), the National Natural Science Foundation of China ( 2210050123 ) and the China Postdoctoral Science Foundation ( 2021TQ0161 and 2021M691709 ).
Publisher Copyright:
© 2022 Science Press and Dalian Institute of Chemical Physics, Chinese Academy of Sciences
Keywords
- Data-driven
- Lithium-ion battery
- Remaining useful life
- State of charge
- State of health
