Sign in Subscribe
Energy management

Advanced Energy Management Strategy for Hydrogen Fuel Cell Electric Vehicles Utilizes Artificial Neural Networks

Strategic Insights

— 1 min read

Researchers from the University of Basque Country have developed an innovative energy management strategy for hydrogen fuel cell electric vehicles (FCEVs) utilizing artificial neural networks (ANNs). This approach aims to optimize power distribution between the fuel cell and the battery, enhancing overall system efficiency. The strategy was evaluated through real-time hardware-in-the-loop simulations and compared to a traditional rule-based controller. Results demonstrate significant reductions in hydrogen consumption and improvements in fuel cell and motor efficiency.

Key Takeaways:

  • The proposed energy management strategy utilizes two ANNs: one for optimizing power distribution and the other for gear selection to enhance motor efficiency.
  • The ANNs were trained on data generated from a cost function designed to minimize hydrogen consumption, stabilize battery state of charge (SOC), and maximize fuel cell efficiency.
  • The proposed system was evaluated through real-time hardware-in-the-loop (HIL) simulations under a Worldwide Harmonized Light Vehicle Test Cycle (WLTC) driving cycle.
  • The strategy reduced hydrogen consumption by up to 16.05% and improved average fuel cell and motor efficiency by 1.75% and 1.13%, respectively.
  • The study concludes that the ANN-based strategy is a robust and scalable solution for next-generation FCEV energy management systems.
  • Financial supporters for this research include the Basque Government, UPV/EHU, Spain, and ACEV Foundation.
  • The research team includes Jokin Uralde, Oscar Barambones, Isidro Calvo, Asier del Rio, and Mohammed Yousri Silaa from the University of Basque Country.

Statistics:

  • Up to 16.05% reduction in hydrogen consumption using the ANN-based strategy.
  • Average fuel cell efficiency improvement of 1.75% using the proposed strategy.
  • Average motor efficiency improvement of 1.13% using the proposed strategy under WLTC driving cycle.

Sources:

  • "Neural Network Approach for the Energy Management and Gear Selection of a Fuel Cell Electric Vehicle" (International Journal of Hydrogen Energy, 2025; 171).
  • Pergamon-elsevier Science Ltd, The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, England (Elsevier - www.elsevier.com).
  • International Journal of Hydrogen Energy (www.journals.elsevier.com/international-journal-of-hydrogen-energy/).

Read more