EUVIMEDEUVIMED entdecken
Crossref

DANet demand power prediction model with cross-power level transfer learning for PEMFCs

Jing Wang, Biaoyi Liu, Xiaoming Zou, Yan Sun, Wenxuan Wei, Hua Ding, Donghai Hu, Yamin Hu

Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering · 16.11.2026

DOI: 10.1177/09544070261506856 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, online erschienen am 16.11.2026. Verfasst von Jing Wang und 7 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Key Core Technology Research Project in Jiangsu Province - Key Technology Research for High Insulation and Intelligent Liquid Hydrogen Storage and Transportati…, Zhangjiagang City Science and Technology Bureau of Science and Technology projects - cryogenic tank intelligent virtual prototype development.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Frequent power fluctuations under real driving conditions affect the dynamic performance and durability of proton exchange membrane fuel cells (PEMFCs), making accurate demand power prediction important for fuel cell vehicle (FCV) applications. PEMFCs are modular (30 kW/unit), enabling upgrades from 90 to 120 kW. However, demand power data are non-stationary, and target-domain data at new power levels are limited. Therefore, this study proposes the dual-path attention network (DANet) demand power prediction model. The DANet model combines a temporal convolutional network (TCN) with a bidirectional gated recurrent unit (BiGRU) and introduces channel and temporal attention mechanisms. Through a freeze-and-fine-tune transfer learning strategy, the DANet model trained at the 90 kW power level is adapted to the 120 kW power level. The results indicate that prior to transfer learning, the DANet model at the 90 kW power level exhibited an RMSE of 0.316 kW and an MAE of 0.228 kW, significantly outperforming long short-term memory model (LSTM), and Transformer model. After transfer learning, the mean error of the adjusted DANet model at the 120 kW power level decreased from 0.6 to 0.2 kW under 70% of the training sets. The proposed PEMFC demand power prediction model can effectively accelerate the development of new vehicles.

Förderung

  • Key Core Technology Research Project in Jiangsu Province - Key Technology Research for High Insulation and Intelligent Liquid Hydrogen Storage and Transportati…
  • Zhangjiagang City Science and Technology Bureau of Science and Technology projects - cryogenic tank intelligent virtual prototype development

Zitieren

APA

Wang, J., Liu, B., Zou, X., Sun, Y., Wei, W., Ding, H., Hu, D., & Hu, Y. (2026). DANet demand power prediction model with cross-power level transfer learning for PEMFCs. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. https://doi.org/10.1177/09544070261506856

Vancouver

Wang J, Liu B, Zou X, Sun Y, Wei W, Ding H, et al. DANet demand power prediction model with cross-power level transfer learning for PEMFCs. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. 2026. doi:10.1177/09544070261506856

BibTeX
@article{Wang2026,
  author = {Wang, Jing and Liu, Biaoyi and Zou, Xiaoming and Sun, Yan and Wei, Wenxuan and Ding, Hua and Hu, Donghai and Hu, Yamin},
  title = {DANet demand power prediction model with cross-power level transfer learning for PEMFCs},
  journal = {Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering},
  year = {2026},
  doi = {10.1177/09544070261506856}
}
Kostenlos starten →