Machine Learning Applied to Lithium‐Ion Battery State Estimation for Electric Vehicles: Method Theoretical, Technological Status, and Future Development

Yang Xiao, Xiong Shi, Xiangmin Li, Yifan Duan, Xiyu Li, Jiaxing Zhang, Tong Luo, Jiayang Wang, Yihang Tan, Zhenhai Gao, Deping Wang, Quan YuanEnergy 2024 · DOI

Abstract

ABSTRACT Lithium‐ion batteries (LIBs) are extensively utilized in electric vehicles due to their high energy density and cost‐effectiveness. LIBs exhibit dynamic and nonlinear characteristics, which raise significant safety concerns for electric vehicles. Accurate and real‐time battery state estimation can enhance safety performance and prolong battery lifespan. With the rapid advancement of big data, machine learning (ML) holds substantial promise for state estimation. This paper systematically reviews several common ML algorithms, detailing the basic principles of each and illustrating their structures with flowcharts. We compare the advantages and disadvantages of various methods. Subsequently, we discuss feature extraction techniques employed in recent studies for estimating state of charge (SOC), state of health (SOH), state of power (SOP), and remaining useful life (RUL), as well as the application of these ML methods in state estimation. Finally, we discuss the challenges associated with using ML methods for state estimation and outline future development trends.
BibTeX
@inproceedings{xiao2024machine,
  author = {Yang Xiao and Xiong Shi and Xiangmin Li and Yifan Duan and Xiyu Li and Jiaxing Zhang and Tong Luo and Jiayang Wang and Yihang Tan and Zhenhai Gao and Deping Wang and Quan Yuan},
  title = {{Machine Learning Applied to Lithium‐Ion Battery State Estimation for Electric Vehicles: Method Theoretical, Technological Status, and Future Development}},
  booktitle = {Energy},
  year = {2024},
  doi = {10.1002/est2.70080},
}

Loading related content...

Figure