Federated Learning With a Temporal-Degradation-Aware Transformer for Robust Joint SOC and SOH Estimation in Electric Vehicle Batteries
IEEE Transactions on Transportation Electrification · 2026-04 · 12 (2) · 3663-3678
DOI: 10.1109/tte.2025.3646926 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2026-04. Verfasst von Prasanta Kumar Mohanty und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Anusandhan National Research Foundation (ANRF), Government of India.
Abstract (Originalsprache)
Accurate estimation of state of charge (SOC) and state of health (SOH) is critical for the safe and reliable operation of electric vehicle (EV) batteries. However, centralized approaches face challenges such as data privacy, communication overhead, and poor scalability under nonindependent and identically distributed (non-IID) data. Although some methods attempt joint estimation, most rely on centralized learning, lack computational efficiency for embedded systems, and overlook uncertainty quantification (UQ), limiting real-world applicability. To address these limitations, this article proposes a federated framework for joint SOC and SOH estimation that is privacy-preserving, lightweight, and uncertainty-aware. The core model is a temporal-degradation-aware informer (TDA-Informer), which incorporates an Informer-Lite encoder and a multitask prediction structure. A battery-focused multifeature attention (BFMFA) module emphasizes critical inputs such as voltage, current, and temperature. The stochastic controlled averaging for federated learning (SCAFFOLD) algorithm is employed to mitigate client drift under non-IID conditions, enhancing convergence across distributed EV clients. UQ is achieved via Monte Carlo Dropout to provide confidence intervals for SOC and SOH predictions. The framework is trained and validated on the NASA battery dataset and tested for generalization on the unseen Oxford dataset, with realistic sensor noise added to simulate practical conditions. Extensive experiments, including ablation studies and comparisons with baseline models, confirm its superior accuracy, robustness, and scalability. While physical deployment remains future work, the results confirm the framework’s potential for intelligent, scalable battery management systems (BMSs).
Förderung
- Anusandhan National Research Foundation (ANRF), Government of India
Zitieren
APA
Mohanty, P. K., Jena, P., & Padhy, N. P. (2026). Federated Learning With a Temporal-Degradation-Aware Transformer for Robust Joint SOC and SOH Estimation in Electric Vehicle Batteries. IEEE Transactions on Transportation Electrification, 12(2), 3663-3678. https://doi.org/10.1109/tte.2025.3646926
Vancouver
Mohanty PK, Jena P, Padhy NP. Federated Learning With a Temporal-Degradation-Aware Transformer for Robust Joint SOC and SOH Estimation in Electric Vehicle Batteries. IEEE Transactions on Transportation Electrification. 2026;12(2):3663-3678. doi:10.1109/tte.2025.3646926
BibTeX
@article{Mohanty2026,
author = {Mohanty, Prasanta Kumar and Jena, Premalata and Padhy, Narayana Prasad},
title = {Federated Learning With a Temporal-Degradation-Aware Transformer for Robust Joint SOC and SOH Estimation in Electric Vehicle Batteries},
journal = {IEEE Transactions on Transportation Electrification},
year = {2026},
volume = {12},
number = {2},
pages = {3663--3678},
doi = {10.1109/tte.2025.3646926}
}
EUVIMED