A Tribe Particle Swarm Optimization for Parameter Identification of Proton Exchange Membrane Fuel Cell

In recent years, identification of proton exchange membrane fuel cell (PEMFC) parameters has drawn attention of many researchers. Polarization curve has a key role in proton exchange membrane fuel cell. However, the main problem associated with accurate modeling is lack of information on precise parameters of the model. In this regard, the most common method for actual parametric identification of PEMFC is use of optimization techniques. In this paper, we have employed a Tribe-PSO algorithm, multi-layered and multi-phased hybrid particle swarm optimization model to identify parameters of PEMFC model. In addition, the results of Tribe-PSO are compared to Particle Swarm Optimization (PSO) algorithm, Genetic Algorithm, and Artificial Immune System (AIS). The results of computer simulations show that the Tribe-PSO algorithm has an appropriate convergence feature and acceptable computation capability, and it is an efficient method in deriving parameters of the PEMFC stack model.