Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions
Advanced Science · 2026-11 · 13 (63)
DOI: 10.1002/advs.77261 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 24.08.2026. Verfasst von Joey Chan und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Industrial Engineering and Management, Shanghai Jiaotong University, Shanghai, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate forecasting of battery capacity fade is essential for the safety, reliability, and long‐term efficiency of energy storage systems. However, the heterogeneity across cell chemistries, form factors, and operating conditions makes it difficult to build a single model that generalizes beyond its training domain. This work proposes a unified capacity forecasting framework that maintains robust performance across diverse chemistries and usage scenarios. We curate 20 public aging datasets into a large‐scale corpus covering 1704 cells and 3 961 195 charge–discharge cycle segments, spanning temperatures from to , multiple C‐rates, and application‐oriented profiles such as fast charging and partial cycling. On this corpus, we adopt a Time‐Series Foundation Model (TSFM) backbone and apply parameter‐efficient Low‐Rank Adaptation (LoRA) together with physics‐guided contrastive representation learning to capture shared degradation patterns. Experiments on both “known” and held‐out “unknown” datasets show that a single unified model achieves competitive or superior accuracy compared with recent state‐of‐the‐art time‐series forecasting methods trained separately for each dataset, while retaining stable performance on chemistries, capacity scales, and operating conditions excluded from training. These results demonstrate the potential of TSFM‐based architectures as a scalable and transferable solution for capacity degradation forecasting in battery management systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Industrial Engineering and Management, Shanghai Jiaotong University, Shanghai, China.
- Department of Systems Engineering, City University of Hong Kong, Hong Kong, China.
ORCID-Profile: Joey Chan, Huan Wang, Zhen Chen, Haoyu Pan, Min Xie
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chan, J., Wang, H., Chen, Z., Pan, H., Wu, W., Wang, Z., Pan, E., Xie, M., & Xi, L. (2026). Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions. Advanced Science, 13(63). https://doi.org/10.1002/advs.77261
Vancouver
Chan J, Wang H, Chen Z, Pan H, Wu W, Wang Z, et al. Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions. Advanced Science. 2026;13(63). doi:10.1002/advs.77261
BibTeX
@article{Chan2026,
author = {Chan, Joey and Wang, Huan and Chen, Zhen and Pan, Haoyu and Wu, Wei and Wang, Zirong and Pan, Ershun and Xie, Min and Xi, Lifeng},
title = {Universal Battery Capacity Degradation Forecasting Driven by Foundation Models Across Diverse Chemistries and Conditions},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {63},
doi = {10.1002/advs.77261}
}
EUVIMED