State-of-Health Estimation of LiFePO4 Batteries via High-Frequency EIS and Feature-Optimized Random Forests
Source abstract
Abstract
Accurate state-of-health (SOH) estimation of lithium iron phosphate (LiFePO4) batteries is critical for ensuring the safety and performance of electric vehicles, particularly under extreme operating conditions. This study presents a data-driven SOH prediction framework based on high-frequency electrochemical impedance spectroscopy (EIS) measurements conducted at −5 °C across various states of charge (SOCs). Feature parameters were extracted from the impedance spectra using equivalent circuit modeling. These features were optimized through Bayesian weighting and subsequently fed into three machine learning models: Random Forest (RF), Gradient Boosting (GB), and Extreme Gradient Boosting (XGB). To mitigate SOC-dependent variations, the models were trained, validated, and tested using features from different SOC levels for each aging cycle. This work provides a practical and interpretable approach for battery health monitoring using high-frequency EIS data, even under sub-zero temperature and partial-SOC conditions. The findings offer valuable insights for developing SOC-agnostic SOH estimation models, advancing the reliability of battery management systems in real-world applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · IoT-based Smart Home Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automotive Studies, Tongji University, Shanghai 201804, China
Shanghai Qiyuan Green Power Technology Co., Ltd., Beijing 100044, China
Funding
National Natural Science Foundation of China
References (26)
Show source-provided references
1. Wang, Z., Huang, G., Chen, Z., and An, C. (2025). Accidents involving lithium-ion batteries in non-application stages: Incident characteristics, environmental impacts, and response strategies. BMC Chem., 19.10.1186/s13065-025-01445-x ↗
2. Shi, P., Zhu, H., Dong, X., and Hai, B. (2025). Research progress on thermal runaway warning methods and fire extinguishing technologies for lithium-ion batteries. World Electr. Veh. J., 16.10.3390/wevj16020081 ↗
3. Comanescu, C. (2025). Ensuring safety and reliability: An overview of lithium-ion battery service assessment. Batteries, 11.10.3390/batteries11010006 ↗
4. Defects in lithium-ion batteries: From origins to safety risks10.1016/j.geits.2024.100235 ↗
5. Enhancing EV battery lifecycle management: Robotic disassembly, design for disassembly, and sustainable solutions10.1016/j.est.2025.116368 ↗
6. Madani, S.S., Shabeer, Y., Allard, F., Fowler, M., Ziebert, C., Wang, Z., Panchal, S., Chaoui, H., Mekhilef, S., and Dou, S.X. (2025). A comprehensive review on lithium-ion battery lifetime prediction and aging mechanism analysis. Batteries, 11.10.3390/batteries11040127 ↗
7. Understanding materials failure mechanisms for the optimization of lithium-ion battery recycling10.1038/s41578-025-00783-5 ↗
8. A review of state-of-health estimation for lithium-ion battery packs10.1016/j.est.2025.116078 ↗
9. Piecewise linear approximation of battery open-circuit voltage characteristics using dynamic programming10.1109/TIM.2025.3553951 ↗
10. State of health estimation of lithium-ion battery based on constant current charging time feature extraction and internal resistance compensation10.1016/j.energy.2025.134472 ↗
11. Electrochemical impedance spectroscopy as a diagnostic and prognostic tool for EV batteries: A review10.33961/jecst.2024.01060 ↗
12. Modeling and applications of electrochemical impedance spectroscopy (EIS) for lithium-ion batteries10.33961/jecst.2019.00528 ↗
13. Vasta, E., Scimone, T., Nobile, G., Eberhardt, O., Dugo, D., De Benedetti, M.M., Lanuzza, L., Scarcella, G., Patanè, L., and Arena, P. (2023). Models for battery health assessment: A comparative evaluation. Energies, 16.10.3390/en16020632 ↗
14. A model for state-of-health estimation of lithium ion batteries based on charging profiles10.1016/j.energy.2019.04.070 ↗
15. Lithium-ion battery state-of-health estimation using voltage-position encoding CNN and incremental capacity analysis with a novel smoothing parameter selection strategy10.1016/j.est.2025.117296 ↗
16. A systematic review of lumped-parameter equivalent circuit models for real-time estimation of lithium-ion battery states10.1016/j.jpowsour.2016.03.042 ↗
17. Li, W., Xiong, Y., Zhang, S., Fan, X., Wang, R., and Wong, P. (2025). A novel method of parameter identification for lithium-ion batteries based on elite opposition-based learning snake optimization. World Electr. Veh. J., 16.10.3390/wevj16050268 ↗
18. Peng, J., Gao, Y., Cai, L., Zhang, M., Sun, C., and Liu, H. (2025). State of health estimation for lithium-ion batteries using electrochemical impedance spectroscopy and a multi-scale kernel extreme learning machine. World Electr. Veh. J., 16.10.3390/wevj16040224 ↗
19. A review on the distribution of relaxation times analysis: A powerful tool for process identification of electrochemical systems10.1016/j.jpowsour.2023.233845 ↗
20. Progress in estimating the state of health using transfer learning–based electrochemical impedance spectroscopy of lithium-ion batteries10.1007/s11581-025-06065-y ↗
21. A domain-adversarial neural network for transferable lithium-ion battery state-of-health estimation10.1109/TTE.2025.3530536 ↗
22. State of health estimation of lithium-ion battery during fast charging process based on BiLSTM-transformer10.1016/j.energy.2024.133418 ↗
23. Machine learning and neural network supported state of health simulation and forecasting model for lithium-ion battery10.1007/s11708-023-0891-7 ↗
24. A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery10.1109/ACCESS.2019.2925468 ↗
25. Hosen, M.S., Gopalakrishnan, R., Kalogiannis, T., Jaguemont, J., Van Mierlo, J., and Berecibar, M. (2021). Impact of relaxation time on electrochemical impedance spectroscopy characterization of the most common lithium battery technologies—Experimental study and chemistry-neutral modeling. World Electr. Veh. J., 12.10.2139/ssrn.3778330 ↗
26. Tonima, M.A., DeHart, A., Tabakci, D., Tisapramotkul, P., Munro-West, A., Mehra, A., and Shoa, T. (2023, January 5–7). Electrochemical impedance spectroscopy (EIS) and machine learning based battery state of health (SoH) estimation. Proceedings of the 2023 IEEE International Conference on Prognostics and Health Management (ICPHM), Montreal, QC, Canada.10.1109/ICPHM57936.2023.10194065 ↗