Comparative study of PEM fuel cell parameter extraction using genetic algorithm

(in lingua inglese)

In this paper, a novel problem formulation based on derivative of power with respect to current at maximum power point is proposed. A simple Genetic Algorithm is used to solve the above formulation. The seven model parameters e1;e2;e3;e4; b; Rc and k are extracted via GA procedure. For demonstration, results obtained with GA are benchmarked with the widely used curve fitting approach. The results demonstrate that the new MPP formulation applying GA performs better than curve fitting method in terms of accuracy, convergence characteristics, convergence speed and objective function value.