EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Remaining Useful Life Prediction of Lithium-Ion Batteries Under Capacity Regeneration: An Adaptive Decomposition and Hybrid Deep Learning Framework

Shuyi Wang, Leyan Zhang, Zichuan Ni, Lei Li

Batteries · 27.05.2026 · 12 (6) · 192

DOI: 10.3390/batteries12060192 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Batteries, online erschienen am 27.05.2026. Verfasst von Shuyi Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nanjing University of Information Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable estimation of battery remaining useful life (RUL) becomes difficult when the capacity trajectory contains regenerative rebounds, short-term oscillations, and long-range temporal dependence. To address this problem, an adaptive decomposition and hybrid deep-learning framework is proposed. First, the phototropic growth algorithm (PGA) is used to tune variational mode decomposition (VMD), allowing the capacity series to be separated into low-frequency trend information and high-frequency fluctuation information so that the influence of regeneration and noise is weakened. Next, a component-level predictor combining a temporal convolutional network (TCN), an attention mechanism (AM), and a Transformer is constructed. In this architecture, TCN learns multi-scale local features, AM enhances salient degradation cues, and the Transformer captures global long-horizon dependencies. To deduce the future capacity degradation path and the associated RUL, these estimated elements are synthesized. Results on the NASA, CALCE, and BIT datasets verify the effectiveness of the proposed framework. On NASA dataset, the average root mean square error (RMSE), mean absolute error (MAE), and absolute error (AE) reach 0.0123 Ah, 0.0073 Ah, and 0.5 cycles, respectively, improving on the strongest baseline by 11.9%, 19.7%, and 50.0%. On CALCE dataset, the corresponding values are 0.00695 Ah, 0.00499 Ah, and 1.75 cycles, and all R2 values are higher than 0.9989, indicating strong accuracy and robustness in the presence of complex regeneration behavior. Supplementary BIT validation on three higher-capacity cells further achieves average RMSE, MAE, and AE of 0.01201 Ah, 0.00771 Ah, and 1.0 cycle, respectively.

Förderung

  • Nanjing University of Information Science and Technology

Zitieren

APA

Wang, S., Zhang, L., Ni, Z., & Li, L. (2026). Remaining Useful Life Prediction of Lithium-Ion Batteries Under Capacity Regeneration: An Adaptive Decomposition and Hybrid Deep Learning Framework. Batteries, 12(6), 192. https://doi.org/10.3390/batteries12060192

Vancouver

Wang S, Zhang L, Ni Z, Li L. Remaining Useful Life Prediction of Lithium-Ion Batteries Under Capacity Regeneration: An Adaptive Decomposition and Hybrid Deep Learning Framework. Batteries. 2026;12(6):192. doi:10.3390/batteries12060192

BibTeX
@article{Wang2026,
  author = {Wang, Shuyi and Zhang, Leyan and Ni, Zichuan and Li, Lei},
  title = {Remaining Useful Life Prediction of Lithium-Ion Batteries Under Capacity Regeneration: An Adaptive Decomposition and Hybrid Deep Learning Framework},
  journal = {Batteries},
  year = {2026},
  volume = {12},
  number = {6},
  pages = {192},
  doi = {10.3390/batteries12060192}
}
Kostenlos starten →