Modeling of a PEM Fuel-Cell Stack for Dynamic and Steady-State Operation Using ANN-Based Submodels

A simple and accurate fuel-cell model is required for fuel-cell-based power-electronic applications. An artificial neural network (ANN) model is developed in this paper to model some nonlinear structures within the hybrid model of a proton-exchange-membrane fuel-cell stack. It improves accuracy and allows the model to adapt itself to operating conditions. Moreover, the temperature effect on the fuel-cell stack is represented as the current effect by using ANN to help estimate the relationship between current and temperature. The real-time implementation of the proposed ANN model is realized via a dSPACE system. Experimental results are provided to verify the validity of the proposed model.