A novel approach based on hybrid vortex search algorithm and differential evolution for identifying the optimal parameters of PEM fuel cell

Abstract

Fuel cells (FCs) penetrated strongly in many applications, modeling of FCs became a major challenge in recent years due to their characteristics, there are some missing data in the datasheet. This paper presents a novel hybrid optimization approach comprising vortex search algorithm (VSA) and differential evolution (DE) for estimating the optimal unspecified parameters of the proton exchange membrane fuel cell (PEMFC). The parameters to be evaluated are seven, ξ1, ξ2, ξ3, ξ4, λ, Rc and b to minimize sum squared deviation between the experimental and calculated polarization curves. The hybridization between VSA and DE is proposed to enhance the performance of VSA and prevent falling in local optima, DE is used as a local search method to promote the process of exploitation followed in VSA. The analysis is performed on different PEMFCs, 250 W stack, NedStack PS6, BCS 500-W, and SR-12 PEM 500 W, the obtained results are compared to those obtained via other approaches. In 250 W stack, four sets of actual voltage have been used, two of them are used for the optimization process while the others are employed to check the validity of the obtained model. The obtained results confirmed the superiority and reliability of the proposed approach.