EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance–Complexity Trade‐Offs in Battery Lifetime Prediction with Task‐Aware Transformers

Jingyuan Zhao iD, Misheng Cai, Zhenghong Wang, Yan Wang, Yuqi Li, Bo Dong, Hewu Wang, Andrew F Burke, Simona Onori, Stephen J Harris

Advanced Science · 2026-10 · 13 (56)

DOI: 10.1002/advs.202524179 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 16.07.2026. Verfasst von Jingyuan Zhao und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Transportation Studies, University of California Davis, Davis, California, USA. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate battery lifetime prediction is essential for improving reliability and safety in energy storage systems. However, balancing predictive accuracy, inference latency, and energy consumption remains challenging. We introduce FAST‐BatPro, a Flash‐Attention Sparse Transformer for Battery Prognosis. This task‐aware architecture combines convolutional feature extraction with dual attention mechanisms to enable robust, efficient, and scalable prediction. The 1.869‐million‐parameter model is evaluated from both perspectives. Across four datasets comprising more than 240,000 cycles across chemistries, FAST‐BatPro demonstrates consistent performance across fast‐charging and discharging protocols, temperature variations, and chemistry‐dependent degradation behaviors. With limited early‐cycle data, it achieves high accuracy, with coefficient of determination values approaching or exceeding 0.90 in most test settings. It maintains an inference time of 0.103 s and requires 1.65 billion FLOPs per battery over the full lifecycle. Hidden‐dimension scaling identifies a compact configuration that preserves comparable accuracy while reducing inference latency, FLOPs, and energy consumption by 12.6%, 68.1%, and 12.6%, respectively. Module‐level pruning further shows that a feed‐forward‐network‐pruned lightweight variant improves accuracy while reducing inference latency, FLOPs, and energy consumption by 11.65%, 54.64%, and 11.65%, respectively, indicating that FAST‐BatPro can serve as a reference architecture for identifying task‐specific redundancy and guiding efficient AI model design for battery diagnostics and predictive maintenance.

Schlagwörter

Stichwörter der Autor:innen

batteryflash‐attentionhealthsparse‐attentiontransformer

Autor:innen und Institutionen

  • Institute of Transportation Studies, University of California Davis, Davis, California, USA.
  • School of Automotive and Traffic Engineering, Hubei University of Arts and Science, Xiangyang, Hubei, China.
  • Qingdao University of Technology, Qingdao, Shandong, China.
  • Department of Materials Science and Engineering, Stanford University, Stanford, California, USA.
  • Department of Control Science and Engineering, Changchun University of Technology, Changchun, Jilin, China.
  • School of Vehicle and Mobility, Tsinghua University, Beijing, China.

ORCID-Profile: Jingyuan Zhao

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Zhao, J., Cai, M., Wang, Z., Wang, Y., Li, Y., Dong, B., Wang, H., Burke, A. F., Onori, S., & Harris, S. J. (2026). Performance–Complexity Trade‐Offs in Battery Lifetime Prediction with Task‐Aware Transformers. Advanced Science, 13(56). https://doi.org/10.1002/advs.202524179

Vancouver

Zhao J, Cai M, Wang Z, Wang Y, Li Y, Dong B, et al. Performance–Complexity Trade‐Offs in Battery Lifetime Prediction with Task‐Aware Transformers. Advanced Science. 2026;13(56). doi:10.1002/advs.202524179

BibTeX
@article{Zhao2026,
  author = {Zhao, Jingyuan and Cai, Misheng and Wang, Zhenghong and Wang, Yan and Li, Yuqi and Dong, Bo and Wang, Hewu and Burke, Andrew F and Onori, Simona and Harris, Stephen J},
  title = {Performance–Complexity Trade‐Offs in Battery Lifetime Prediction with Task‐Aware Transformers},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {56},
  doi = {10.1002/advs.202524179}
}
Kostenlos starten →