Parameter estimation of PEM fuel cells employing the hybrid grey wolf optimization method

Abstract

Scheming and creating a precise model of fuel cell systems is essential to simulate, control, manage, and obtain the optimized parameters accurately in the case of Proton Exchange Membrane Fuel Cell. To get the optimal parameters of the Proton Exchange Membrane Fuel Cell, in this work, a new optimization method, which is called Hybrid Grey Wolf Optimizer, is presented. Hybrid Grey wolf optimizer is an innovative metaheuristic algorithm which is according to the behavior of the pack of the grey wolves. The basic Grey Wolf Optimizer is hybridized by including crossover and mutation operators in the optimization process for better efficiency in the evaluation of the primary parameters of Proton Exchange Membrane Fuel cells. In the process of searching, the adopted operators (crossover and mutation) increase the search potential capability and also evades the trapping in the local optima. The fulfilled analysis of some benchmarks showed that the Hybrid Grey Wolf Optimizer method works efficiently in all investigated criteria, such as convergence and exactness. Besides, Hybrid Grey Wolf Optimizer has been used to estimate the model of PEMFC, and then the achieved data shows a satisfactory efficiency of the proposed Hybrid Grey Wolf Optimizer.