Comparison of various metaheuristic algorithms to extract the optimal PEMFC modeling parameters

Abstract

In this study, operating parameters of a semi-empirical mathematical model of a proton-exchange membrane fuel cell (PEMFC) are extracted and compared using various metaheuristic algorithms to analyze its behavior in a fast and economical manner before setting it up for application. Sum-squared error is employed as the objective function to find the values of seven unknown modeling parameters. The parameter extraction is carried out by using the polarization curve data of a 1000 W commercial PEMFC. Three different multi-attribute decision-making methods are used to rank the metaheuristic algorithms in terms of performance. The findings indicate that Moth Flame Algorithm is ranked first considering the sum-squared error (0.4389) and runtime (1054 s); whereas Grey Wolf Optimizer gives the best objective function efficiency (98.6034%) and lowest error rate (0.1096). It was also found that JAYA and Cuckoo Search are not convenient for parameter extraction of the specified fuel cell. Overall, the distinctive features of the study provide valuable insights and advancements in the field of fuel cell modeling and optimization.