Data-Driven State of Health for Lithium-ion Batteries: Feature Engineering, Estimation Approaches, and Future Directions

Strategic Insights -

Research published in Batteries & Supercaps by a team of scientists from Anhui University reveals a comprehensive exposition of data-driven methodologies for estimating the state of health of lithium-ion batteries. The study aims to ensure the safe and efficient operation of electric vehicles by identifying key factors influencing battery state of health. Funded by the National Natural Science Foundation of China (NNSFC) and Anhui University, the research combines feature engineering, estimation approaches, and future directions to provide a thorough understanding of SOH estimation.

Key Takeaways:

  • The study emphasizes the importance of state of health estimation for the safe and efficient operation of electric vehicles, particularly in the context of convergence with new energy vehicles and big data.
  • Feature engineering, including feature extraction and selection, plays a crucial role in data-driven SOH estimation.
  • Nonprobabilistic and probabilistic models are discussed as data-driven approaches to battery SOH management.
  • The research highlights the limitations of existing methods for SOH estimation, emphasizing the need for multisource data fusion, enhancement through small-sample and transfer learning techniques, and incorporation with physical modeling.
  • The study concludes that advancements in data-driven SOH estimation will significantly enhance precision and reliability, catalyzing broader deployment of battery technologies across various sectors.
  • The research team includes Yuan Chen, Zhiqiang Lyu, Xiang'en Li, Zhirui Jin, Hao Wang, and Longxing Wu from Anhui University.

Statistics:

  • The study focuses on lithium-ion batteries, which are widely used in electric vehicles and energy storage systems.
  • The research team estimates that data-driven SOH estimation will lead to a significant enhancement of precision and reliability, with potential applications in various sectors.
  • The study cites the importance of multisource data fusion, with plans for future research in this domain.
  • The National Natural Science Foundation of China (NNSFC) and Anhui University funded the research, indicating a growing interest in battery technology and data-driven methods.
  • The study highlights the need for increased research in small-sample and transfer learning techniques to enhance the precision and reliability of SOH estimation.

Sources:

  • Data-driven State of Health for Lithium-ion Batteries: Feature Engineering, Estimation Approaches, and Future Directions. Batteries & Supercaps, 2025.
  • Bayerste, A. (2025, p 129). Findings from Anhui University Update Knowledge of Information Technology (Data-driven State of Health for Lithium-ion Batteries: Feature Engineering, Estimation Approaches, and Future Directions). Information Technology Newsweekly. November 4, 2025; p 129.