EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Degradation Prediction of Proton Exchange Membrane Fuel Cell Based on Multi-Head Attention Neural Network and Transformer Model

Yikai Tang, Xing Huang, Yanju Li, Haoran Ma, Kai Zhang, Ke Song

Energies · 17.06.2025 · 18 (12) · 3177

DOI: 10.3390/en18123177 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 17.06.2025. Verfasst von Yikai Tang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Science and Technology Planning Project, Shanghai Key Laboratory of Vehicle Aerodynamics and Thermal Management Systems.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Proton exchange membrane fuel cells are a clean energy technology with wide application in transportation and stationary energy systems. Due to the problem of voltage degradation under long-term dynamic loads, predicting their performance degradation trend is of great significance for extending the life of proton exchange membrane fuel cells and improving system reliability. This study adopts a data-driven approach to construct a degradation prediction model. In view of the problem of many input parameters and complex distribution of degradation features, a neural network model based on a multi-head attention mechanism and class token is first proposed to analyze the impact of different operating parameters on the output voltage prediction. The importance of each input variable is quantified by the attention weight matrix to assist feature screening. Subsequently, a prediction model is constructed based on Transformer to characterize the voltage degradation trend of fuel cells under dynamic conditions. The experimental results show that the root mean square error and mean absolute error of the model in the test phase are 0.008954 and 0.006590, showing strong prediction performance. Based on the importance evaluation provided by the first model, 11 key parameters were selected as inputs. After this input simplification, the model still maintained a prediction accuracy comparable to that of the full-feature model. This result verifies the effectiveness of the feature screening strategy and demonstrates its contribution to improved generalization and robustness.

Förderung

  • Shanghai Science and Technology Planning Project
  • Shanghai Key Laboratory of Vehicle Aerodynamics and Thermal Management Systems

Zitieren

APA

Tang, Y., Huang, X., Li, Y., Ma, H., Zhang, K., & Song, K. (2025). Degradation Prediction of Proton Exchange Membrane Fuel Cell Based on Multi-Head Attention Neural Network and Transformer Model. Energies, 18(12), 3177. https://doi.org/10.3390/en18123177

Vancouver

Tang Y, Huang X, Li Y, Ma H, Zhang K, Song K. Degradation Prediction of Proton Exchange Membrane Fuel Cell Based on Multi-Head Attention Neural Network and Transformer Model. Energies. 2025;18(12):3177. doi:10.3390/en18123177

BibTeX
@article{Tang2025,
  author = {Tang, Yikai and Huang, Xing and Li, Yanju and Ma, Haoran and Zhang, Kai and Song, Ke},
  title = {Degradation Prediction of Proton Exchange Membrane Fuel Cell Based on Multi-Head Attention Neural Network and Transformer Model},
  journal = {Energies},
  year = {2025},
  volume = {18},
  number = {12},
  pages = {3177},
  doi = {10.3390/en18123177}
}
Kostenlos starten →