Artificial intelligence estimates the state of health of cylindrical lithium iron phosphate batteries via data-driven model
Source abstract
Abstract
Accurate state of health (SOH) estimation for lithium iron phosphate (LFP) batteries remains challenging under long-cycle conditions. Conventional data-driven approaches typically demand extensive aging data and are often validated over only a few hundred cycles. This paper proposes an SOH estimation method for long-life LFP batteries, integrating electrochemical insight with statistical feature engineering to improve interpretability. Using cycling data from two types of cylindrical 26650 LFP batteries with different capacities and lifespans, eight statistical metrics are extracted from the first peak of the incremental capacity curve during early charging. These features are denoised via Gaussian-weighted moving average filtering and evaluated through Spearman correlation analysis, confirming strong correlation with capacity degradation. After comparing three feature selection strategies, the six most relevant metrics are used as health indicators to train an LSTM model. Validation across two independent datasets shows SOH estimation with mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE) as low as 0.258%, 0.298%, and 0.235%, respectively. Even with significantly reduced training samples, the maximum errors remain below 0.528%, 0.604%, and 0.472%. The results demonstrate the practicality of the approach for accurate, data-efficient SOH estimation of long-life LFP batteries. • A statistical-electrochemical method extracts interpretable features from IC curve. • Comparing three strategies shows filter placement affects features preservation. • SOH estimation for long-life LFP batteries is achieved with minimal data. • Providing insights for selection of IC curve regions and filtering strategies.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advanced Battery Materials and Technologies · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (40)
Show source-provided references
1. Fast and scalable preparation of metal–organic coordination polymeric precursor for bifunctional electrocatalysts for high performance lithium–oxygen batteries10.1016/j.ces.2024.120750 ↗
2. Li2Se as cathode additive to prolong the next generation high energy lithium-ion batteries
3. Movable SiO2 reinforced polymethyl methacrylate dual network coating for highly stable zinc anodes10.1016/j.est.2025.117752 ↗
4. In-situ construction of tetraethylene glycol diacrylate based gel polymer electrolyte for long lifespan lithium metal batteries
5. Interface synergistic stabilization of zinc anodes via polyacrylic acid doped polyvinyl alcohol ultra-thin coating10.1016/j.est.2024.111444 ↗
6. Lv · Energies · 2026 · 28410.3390/en19010284 ↗
7. Numerical analysis on the aging characteristics of a LiFePO4 battery: effect of active particle sizes in electrodes10.1016/j.est.2023.107546 ↗
8. Catalytic chemistry derived artificial solid electrolyte interphase for stable lithium metal anodes working at 20 mA cm−2 and 20 mAh cm−210.1002/anie.202305723 ↗
9. Nonlinear health evaluation for lithium-ion battery within full-lifespan10.1016/j.jechem.2022.04.013 ↗
10. Source-load coordinated optimization framework for distributed energy systems using quasi-potential game method10.23919/PCMP.2024.000161 ↗
11. State estimation for advanced battery management: key challenges and future trends10.1016/j.rser.2019.109334 ↗
12. A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries10.1016/j.jechem.2022.06.049 ↗
13. A multi-scale framework for unsupervised anomaly detection in lithium-ion battery packs10.1016/j.est.2026.120341 ↗
14. Marri · Energies · 2023
15. A simple feature extraction method for estimating the whole life cycle state of health of lithium-ion batteries using transformer-based neural network10.1016/j.jpowsour.2023.233139 ↗
16. SOH estimation for lithium-ion batteries: an improved GPR optimization method based on the developed feature extraction10.1016/j.est.2024.110678 ↗
17. Feature-enhanced ensemble learning for accurate capacity estimation of lithium-ion batteries using partial discharging segments in initial stage based on second-order voltage derivatives10.1016/j.geits.2025.100388 ↗
18. Data-driven battery state-of-health estimation and prediction using IC based features and coupled model10.1016/j.est.2023.108413 ↗
19. A feature extraction approach for state-of-health estimation of lithium-ion battery10.1016/j.est.2023.108871 ↗
20. Improved LSTM based state of health estimation using random segments of the charging curves for lithium-ion batteries10.1016/j.est.2023.109370 ↗
21. State of health estimation of lithium-ion batteries based on multi-health features extraction and improved long short-term memory neural network10.1016/j.energy.2023.128956 ↗
22. Flexible method for estimating the state of health of lithium-ion batteries using partial charging segments10.1016/j.energy.2024.131009 ↗
23. Understanding the mechanism of capacity increase during early cycling of commercial NMC/graphite lithium-ion batteries10.1016/j.jechem.2022.07.005 ↗
24. Capacity fade characteristics of lithium iron phosphate cell during dynamic cycle10.1016/j.energy.2020.118155 ↗
25. Capacity estimation of lithium-ion batteries based on optimized charging voltage section and virtual sample generation10.1016/j.apenergy.2022.120516 ↗
26. Electric vehicle battery state of health estimation using incremental capacity analysis10.1016/j.est.2023.107110 ↗
27. Solid electrolyte interphase on lithium metal anodes10.1002/cssc.202301777 ↗
28. A review on lithium-ion battery ageing mechanisms and estimations for automotive applications10.1016/j.jpowsour.2013.05.040 ↗
29. A review on the key issues of the lithium ion battery degradation among the whole life cycle10.1016/j.etran.2019.100005 ↗
30. Lithium-diffusion induced capacity losses in lithium-based batteries10.1002/adma.202108827 ↗
31. Comprehensive study of high-temperature calendar aging on cylinder Li-ion battery10.1016/j.ces.2024.120355 ↗
32. Operando detection of Li plating during fast charging of Li-ion batteries using incremental capacity analysis10.1016/j.jpowsour.2022.231601 ↗
33. State of health estimation method for lithium-ion batteries using incremental capacity and long short-term memory network10.1016/j.est.2023.107063 ↗
34. A quick on-line state of health estimation method for Li-ion battery with incremental capacity curves processed by Gaussian filter10.1016/j.jpowsour.2017.10.092 ↗
35. High rate capability of LiFePO4 cathodes doped with a high amount of Ti10.1016/j.ceramint.2016.01.115 ↗
36. Intercalation chemistry of graphite: alkali metal ions and beyond10.1039/C9CS00162J ↗
37. A review on energy chemistry of fast-charging anodes10.1039/C9CS00728H ↗
38. Aging behavior of lithium iron phosphate based 18650-type cells studied by in situ neutron diffraction10.1016/j.jpowsour.2017.01.134 ↗
39. Fan · Metals · 2022 · 133110.3390/met12081331 ↗
40. State of health estimation for Li-ion battery via partial incremental capacity analysis based on support vector regression10.1016/j.energy.2020.117852 ↗