A Hybrid Transformer Network Optimized by Kalman Filter for State of Health Prediction on Lithium-Ion Battery
Batteries · 13.07.2026 · 12 (7) · 251
DOI: 10.3390/batteries12070251 ↗Kurz gefasst
Fachartikel in der Zeitschrift Batteries, online erschienen am 13.07.2026. Verfasst von Lei Xu und 2 weiteren Autor:innen. Die Arbeit nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of Electrochemical Energy Safety, Ministry of Emergency Management.
Abstract (Originalsprache)
State of Health (SOH) is a critical metric for evaluating the efficient and reliable operation of lithium-ion batteries (LIBs), although it cannot be directly measured. Accurate SOH prediction throughout the entire lifecycle of LIBs remains a significant challenge, primarily due to severe signal fluctuations and complex degradation mechanisms. In this paper, a novel hybrid Transformer-based architecture for SOH prediction is introduced, termed KF–SAMformer–GRU, which integrates a Kalman filter (KF) optimizer, a sharpness-aware minimization Transformer (SAMformer) model, and a multi-layer gated recurrent unit (GRU). To overcome the challenges of multivariate long-term forecasting, we innovatively integrate SAMformer to extract robust feature indicators, actively mitigating data distribution shifts via sharpness-aware minimization. Furthermore, reversible instance normalization (RevIN) is first introduced to tackle non-stationarity in multi-source datasets, effectively eliminating uncertainty and significantly boosting generalization capability. Complementing this, the KF mechanism is uniquely employed to fuse multi-dimensional features, reducing computational overhead while accelerating training. Finally, the multi-layer GRU precisely refines the mapping between SOH metrics and predicted values. Experimental validation on the NASA and CALCE datasets demonstrates the superiority of our approach, achieving a MAPE of 0.01, an RMSE of 0.91%, and an R2 of 0.99. Notably, the method accurately captures phenomena such as battery capacity regeneration, exhibiting superior performance at peaks and valleys while maintaining high computational efficiency.
Förderung
- Key Laboratory of Electrochemical Energy Safety, Ministry of Emergency Management
Zitieren
APA
Xu, L., Sun, P., & Zhou, N. (2026). A Hybrid Transformer Network Optimized by Kalman Filter for State of Health Prediction on Lithium-Ion Battery. Batteries, 12(7), 251. https://doi.org/10.3390/batteries12070251
Vancouver
Xu L, Sun P, Zhou N. A Hybrid Transformer Network Optimized by Kalman Filter for State of Health Prediction on Lithium-Ion Battery. Batteries. 2026;12(7):251. doi:10.3390/batteries12070251
BibTeX
@article{Xu2026,
author = {Xu, Lei and Sun, Peng and Zhou, Nan},
title = {A Hybrid Transformer Network Optimized by Kalman Filter for State of Health Prediction on Lithium-Ion Battery},
journal = {Batteries},
year = {2026},
volume = {12},
number = {7},
pages = {251},
doi = {10.3390/batteries12070251}
}
EUVIMED