EUVIMEDEUVIMED entdecken
Crossref

Lithium-Ion Battery SOH Estimation Driven by Multi-Level Features from Adaptive Optimal Intervals and HISSA-BiLSTM

Yuan Jiang, Xinlei Qiao, Lu Lv, Lujun Wang

Journal of The Electrochemical Society · 28.07.2026 · 173 (14) · 140504

DOI: 10.1149/1945-7111/ae8724 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of The Electrochemical Society, online erschienen am 20.07.2026. Verfasst von Yuan Jiang und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: the Hubei Provincial Science and Technology Plan Project, the Natural Science Foundation of Hubei Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate State of Health (SOH) estimation for lithium-ion batteries (LIBs) is essential for the safe and reliable operation of battery management systems (BMS). This study develops a practical SOH estimation framework based on adaptive optimal interval selection, multi-level health feature extraction, and a HISSA-assisted BiLSTM model. The main methodological focus is the adaptive interval search framework driven by the Multi-dimensional Hybrid Evaluation Index (MHEI), which improves feature relevance while reducing redundant sampling. Then, 16-dimensional health features are extracted from local charging intervals, full-curve charging behavior, and discharge/IC-curve electrochemical properties. A dual Pearson-Spearman correlation analysis retains 13 strongly correlated features. HISSA is used as a supporting hyperparameter optimization strategy to improve BiLSTM stability. Tests on selected NASA cells show that, compared with traditional full-interval features, the adaptive optimal intervals improve feature correlation by 8.3% while reducing data length by more than 50%. The proposed framework achieves competitive SOH estimation accuracy under controlled laboratory cycling conditions, while broader validation on different chemistries, larger datasets, and real-world operating profiles remains necessary.

Förderung

  • the Hubei Provincial Science and Technology Plan Project
  • the Natural Science Foundation of Hubei Province

Zitieren

APA

Jiang, Y., Qiao, X., Lv, L., & Wang, L. (2026). Lithium-Ion Battery SOH Estimation Driven by Multi-Level Features from Adaptive Optimal Intervals and HISSA-BiLSTM. Journal of The Electrochemical Society, 173(14), 140504. https://doi.org/10.1149/1945-7111/ae8724

Vancouver

Jiang Y, Qiao X, Lv L, Wang L. Lithium-Ion Battery SOH Estimation Driven by Multi-Level Features from Adaptive Optimal Intervals and HISSA-BiLSTM. Journal of The Electrochemical Society. 2026;173(14):140504. doi:10.1149/1945-7111/ae8724

BibTeX
@article{Jiang2026,
  author = {Jiang, Yuan and Qiao, Xinlei and Lv, Lu and Wang, Lujun},
  title = {Lithium-Ion Battery SOH Estimation Driven by Multi-Level Features from Adaptive Optimal Intervals and HISSA-BiLSTM},
  journal = {Journal of The Electrochemical Society},
  year = {2026},
  volume = {173},
  number = {14},
  pages = {140504},
  doi = {10.1149/1945-7111/ae8724}
}
Kostenlos starten →