An experimentally optimized PEM fuel cell model using PSO algorithm

This paper presents a semi-empirical fuel cell model with parameters identified using an optimization approach. The Proton Exchange Membrane Fuel Cell (PEMFC) model is characterized by technological and empirical parameters and their identification is a hard task if is intended to have precise simulation results in a wide range of operating conditions. It is verified that the Particle Swarm Optimization (PSO) method is an adequate tool to extract the correct parameter values. This is achieved minimizing the difference between experimental and simulated results. Both PEMFC model and PSO algorithm are implemented in Matlab/Simulink software.