Adaptive Fusion SOH Assessment of Lithium-Ion Batteries Based on EIS Multi-Band Features
Journal of Computing and Electronic Information Management · 23.07.2026 · 22 (1) · 49-51
DOI: 10.54097/5ye2zp82 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Electronic Information Management, online erschienen am 23.07.2026. Verfasst von Chao Li und 4 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Electrochemical impedance spectroscopy (EIS) can quantitatively reflect internal aging mechanisms of lithium-ion batteries, serving as an effective non-destructive tool for State of Health (SOH) evaluation. Single prediction models either fail to balance precision for fresh and aged cells or lack adaptability under variable temperature and SOC conditions. This paper proposes an adaptive dual-model fusion SOH estimation method combining weighted Mahalanobis-distance KNN and power-law capacity fading model. Four-dimensional features extracted from medium-high frequency EIS, real-time SOC and ambient temperature are standardized via Z-score transformation. Dynamic weight allocation is implemented according to battery health intervals: higher weight is assigned to KNN for cells with SOH ≥ 95%, while power-law model dominates for severely degraded cells with SOH < 95%. Multi-temperature full-cycle aging tests on 314 Ah LiFePO4 cells verify the proposed method. The full-life SOH prediction error is controlled below 5%, which outperforms single KNN and pure power-law fitting. This fusion algorithm can be embedded into embedded EIS measurement hardware, supporting online health diagnosis for energy storage and vehicle power batteries.
Zitieren
APA
Li, C., Han, S., Zhao, L., Yang, Z., & Li, F. (2026). Adaptive Fusion SOH Assessment of Lithium-Ion Batteries Based on EIS Multi-Band Features. Journal of Computing and Electronic Information Management, 22(1), 49-51. https://doi.org/10.54097/5ye2zp82
Vancouver
Li C, Han S, Zhao L, Yang Z, Li F. Adaptive Fusion SOH Assessment of Lithium-Ion Batteries Based on EIS Multi-Band Features. Journal of Computing and Electronic Information Management. 2026;22(1):49-51. doi:10.54097/5ye2zp82
BibTeX
@article{Li2026,
author = {Li, Chao and Han, Shunli and Zhao, Luo and Yang, Zunheng and Li, Fei},
title = {Adaptive Fusion SOH Assessment of Lithium-Ion Batteries Based on EIS Multi-Band Features},
journal = {Journal of Computing and Electronic Information Management},
year = {2026},
volume = {22},
number = {1},
pages = {49--51},
doi = {10.54097/5ye2zp82}
}
EUVIMED