Multi-Parameter Sensitivity Analysis of a Proton Exchange Membrane Fuel Cell Model
Résumé
In recent years, fuel cell systems to produce electricity have come to be viewed as one of the cleanest practical alternative to internal combustion engines for transportation use. Considering this aim, Proton Exchange Membrane Fuel Cells (PEMFC) are the most promising fuel cell technologies and a simulation model of such a whole fuel cell system may offer a powerful tool to test alternative energy sources for Electric Vehicle (EV). In this paper, a Dynamic Recurrent Neural Network (DRNN) model of a PEMFC is investigated. In our case, a 500 W fuel cell is considered but the proposed black box-model can easily be extrapolated to more powerful fuel cell systems. For black-box models, simulation results are strongly dependant on the choice of input parameters. Thus, a sensitivity analysis is performed to assess the influences or relative importance of each input parameter on the output variable. Many different ways to perform a sensitivity analysis are possible. In this paper, a Multi Parameter Sensitivity Analysis (MPSA) is proposed to evaluate the relative importance of each input parameter independently on the fuel cell voltage.