Time to Market Reduction for Hydrogen Fuel Cell Stacks using Generative Adversarial Networks

Nicolas Morizet (1) , Perceval Desforges (1) , Christophe Geissler (1) , Elodie Pahon (2) , Samir Jemeï (2) , Daniel Hissel (2)

1 Advestis
2 FCLAB - Fuel Cell LAB : Vers des Systèmes Pile à Combustible Efficients

To face the dependency on fossil fuels and limit carbon emissions, fuel cells are a very promising technology and appear to be a key candidate to tackle the increase of the energy demand and promote the energy transition. To meet future needs for both transport and stationary applications, the time to market of fuel cell stacks must be drastically reduced. Here, a new concept to shorten their development time by introducing a disruptive and highefficiency data augmentation approach based on artificial intelligence is presented. Our results allow reducing the testing time before introducing a product on the market from a thousand to a few hours. The innovative concept proposed here can support engineering and research tasks during the fuel cell development process to achieve decreased development costs alongside a reduced time to market.

Mots clés: Hydrogen fuel cell; Generative Adversarial Networks

Domaines: Energie électrique; Machine Learning [stat.ML]; Intelligence artificielle [cs.AI]

Nicolas Morizet, Perceval Desforges, Christophe Geissler, Elodie Pahon, Samir Jemeï, et al.. Time to Market Reduction for Hydrogen Fuel Cell Stacks using Generative Adversarial Networks. 2022. ⟨hal-03906212⟩