EUVIMEDEUVIMED entdecken
Crossref

Physics‐Informed Meta‐Learning With Graph Attention for Lithium‐Ion Battery Remaining Useful Life Prediction

Yehua Ling, Zexian Wei, Zhuangsong Wu, Feiyan Pan, Yong Zhou, Xiuqiong Li, Jinxin Wu

Energy Storage · 2026-12 · 8 (8)

DOI: 10.1002/est2.70561 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energy Storage, online erschienen am 06.11.2026. Verfasst von Yehua Ling und 6 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of lithium‐ion battery (LIB) remaining useful life (RUL) is important for assessing battery degradation and supporting reliable operation of energy systems. However, prediction across different operating conditions remains challenging because of complex spatial–temporal dependencies, limited degradation observations, and difficulties in incorporating degradation‐related physical knowledge. To overcome these challenges, this study presents a physics‐informed meta‐graph attention network (PIMGAN) that integrates degradation feature learning, dynamical regularization, and few‐shot adaptation. Firstly, a multi‐scale graph attention mechanism is combined with adaptive bidirectional temporal convolution to characterize correlations among heterogeneous battery measurements and their temporal evolution. Then, a physics‐guided regulator (PGR) learns a nonlinear differential operator in the latent feature space, whose residual serves as an additional regularization term during model training. Finally, a first‐order meta‐learning strategy is integrated to learn transferable model initialization parameters across multiple degradation tasks, enabling rapid adaptation to unseen battery conditions with limited target‐domain observations while avoiding explicit second‐order meta‐gradient computations. The proposed PIMGAN is evaluated on two publicly available LIB datasets under cross‐cycle and cross‐condition prediction settings. Under cross‐condition evaluation, PIMGAN achieves mean absolute percentage errors of 0.267% and 0.336% on the MIT and XJTU datasets, respectively, demonstrating its effectiveness in battery RUL prediction with limited target‐domain data.

Zitieren

APA

Ling, Y., Wei, Z., Wu, Z., Pan, F., Zhou, Y., Li, X., & Wu, J. (2026). Physics‐Informed Meta‐Learning With Graph Attention for Lithium‐Ion Battery Remaining Useful Life Prediction. Energy Storage, 8(8). https://doi.org/10.1002/est2.70561

Vancouver

Ling Y, Wei Z, Wu Z, Pan F, Zhou Y, Li X, et al. Physics‐Informed Meta‐Learning With Graph Attention for Lithium‐Ion Battery Remaining Useful Life Prediction. Energy Storage. 2026;8(8). doi:10.1002/est2.70561

BibTeX
@article{Ling2026,
  author = {Ling, Yehua and Wei, Zexian and Wu, Zhuangsong and Pan, Feiyan and Zhou, Yong and Li, Xiuqiong and Wu, Jinxin},
  title = {Physics‐Informed Meta‐Learning With Graph Attention for Lithium‐Ion Battery Remaining Useful Life Prediction},
  journal = {Energy Storage},
  year = {2026},
  volume = {8},
  number = {8},
  doi = {10.1002/est2.70561}
}
Kostenlos starten →