Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?
Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur Graph Search.
The focus of this study is to evaluate the effects of porous media inside the gas flow channel of Proton Exchange Membrane Fuel Cells (PEMFC) on four different output parameters of voltage, power density, pressure drop, and Nusselt number (Nu) considering the impacts of its thickness, viscous resistance, and current density. Although it is proved that the new design will improve the convective heat transfer, there have not been studies to evaluate the effects of this porous layer on the electrochemical performance and heat transfer simultaneously. The results showed that viscous resistance has by far the highest impact on the power densities in high current densities while thicker inserted porous layer improves the performance. Results also demonstrate that a parameter is needed to consider all these output parameters at the same time, hence the Evaluation Criterion of Proton Exchange Membrane (ECPEM) is defined using artificial neural network (ANN) modeling. Single-objective optimization of the ECPEM is developed using the ANN models to produce 250,000 data. The optimum value of ECPEM was obtained 78.88 in the thickness of 500 mu m and the viscous resistance of 2,111,000 (1/m(2)) while the current density is equal to 0.65 (A/cm(2)).
Jan Van Herle, Hossein Pourrahmani