Artificial immune system-based parameter extraction of proton exchange membrane fuel cell

For a better understanding of the characteristics, performance evaluation and design analysis of proton exchange membrane fuel cell (PEMFC) system an accurate mathematical model is an imperative tool. Although various models have been developed in the literature, because of the shortage of manufacture information about the precise values of the parameters required for the modeling, the parameter extraction is an essential task. So, in order to obtain the PEMFC actual performance, its parameters have to be identified by an optimization technique. Artificial immune system (AIS) is a soft computing method with promising results in the field of optimization problems. In this paper, an AIS-based algorithm for parameter identification of a PEMFC stack model is proposed. In order to study the usefulness of the proposed algorithm, the AIS-based results are compared with the obtained results by the genetic algorithm (GA) and particle swarm optimization (PSO). It is shown that the AIS algorithm is a helpful and reliable technique for identifying the model parameters so that the PEMFC model with extracted parameters agrees with the experimental data well. Moreover, the AIS algorithm outperforms the GA and PSO methods. Therefore, the AIS can be applied to solve other complex identification problems of fuel cell models.