EUVIMEDEUVIMED entdecken
Crossref

Lag-Llama-Based Remaining Useful Life Prediction for Lithium-Ion Batteries of Electric Vehicles With Autocorrelation Analysis

Muaaz Bin Kaleem, Heng Li, Zeyu Zhu, Xiaolong Chen, Yunsheng Fan, Lisen Yan, Weirong Liu

IEEE Transactions on Transportation Electrification · 2026-06 · 12 (3) · 4911-4924

DOI: 10.1109/tte.2026.3673041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2026-06. Verfasst von Muaaz Bin Kaleem und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Laboratory of Electrochemical Energy Safety, Ministry of Emergency Management.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs) is essential for applications like electric vehicles (EVs), but current methods often struggle to generalize across different battery types and operational conditions due to their reliance on large labeled datasets. This article proposes a novel approach that integrates the Lag-Llama foundation model with autocorrelation analysis for RUL prediction. First, the tokenization scheme of Lag-Llama is enhanced using autocorrelation to identify degradation patterns in historical capacity sequences, improving the model’s ability to capture capacity fluctuations. The model is pretrained on the large Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen University dataset to learn degradation trends and fine-tuned using smaller, target-specific datasets, including the Center for Advanced Life Cycle Engineering (CALCE), National Aeronautics and Space Administration (NASA), Massachusetts Institute of Technology (MIT), and battery analytics with artificial intelligence (BAWAII) datasets. Compared to the baselines, the proposed method reduces mean absolute errors (MAEs) by 43.2% on CALCE, 55.2% on NASA, 78.9% on MIT, and 91.1% on BAWAII. In terms of relative error (RE), improvements of 48.7%, 54.9%, 80.2%, and 91.2% are achieved on the same datasets, respectively. These results demonstrate the model’s superior accuracy and generalizability for data-driven RUL prediction of LIBs, even with limited fine-tuning data.

Förderung

  • National Natural Science Foundation of China
  • Key Laboratory of Electrochemical Energy Safety, Ministry of Emergency Management

Zitieren

APA

Kaleem, M. B., Li, H., Zhu, Z., Chen, X., Fan, Y., Yan, L., & Liu, W. (2026). Lag-Llama-Based Remaining Useful Life Prediction for Lithium-Ion Batteries of Electric Vehicles With Autocorrelation Analysis. IEEE Transactions on Transportation Electrification, 12(3), 4911-4924. https://doi.org/10.1109/tte.2026.3673041

Vancouver

Kaleem MB, Li H, Zhu Z, Chen X, Fan Y, Yan L, et al. Lag-Llama-Based Remaining Useful Life Prediction for Lithium-Ion Batteries of Electric Vehicles With Autocorrelation Analysis. IEEE Transactions on Transportation Electrification. 2026;12(3):4911-4924. doi:10.1109/tte.2026.3673041

BibTeX
@article{Kaleem2026,
  author = {Kaleem, Muaaz Bin and Li, Heng and Zhu, Zeyu and Chen, Xiaolong and Fan, Yunsheng and Yan, Lisen and Liu, Weirong},
  title = {Lag-Llama-Based Remaining Useful Life Prediction for Lithium-Ion Batteries of Electric Vehicles With Autocorrelation Analysis},
  journal = {IEEE Transactions on Transportation Electrification},
  year = {2026},
  volume = {12},
  number = {3},
  pages = {4911--4924},
  doi = {10.1109/tte.2026.3673041}
}
Kostenlos starten →