Recent approach based heterogeneous comprehensive learning Archimedes optimization algorithm for identifying the optimal parameters of different fuel cells

A consistent and precise mathematical modeling play a vital role in the performance analysis of fuel cells (FCs) system. Model's efficiency completely depends on design accuracy. Thereby the modeling and estimation of FCs' parameters attracted numerous researchers. In this article, new innovative algorithms named heterogeneous comprehensive learning Archimedes optimization algorithm (HCLAOA) for effective modeling of proton exchange membrane fuel cell (PEMFC) and solid oxide fuel cell (SOFC) is proposed. To assess the performance of the proposed algorithm, two ratings of PEMFC stacks such as PEMFC 250 W and 500 W (NedStack PS6, BCS 500W, and SR-12PEM 500W) are considered and evaluated under different levels of pressures and temperatures. Further, in case of SOFC, steady-state and dynamic-state models are considered. The steady-state SOFC model is investigated with four different levels of temperatures, and the dynamic SOFC model is evaluated with the subject of change in demand power. To verify the consistency and effectiveness of HCLAOA algorithm, extensive statistical analysis and various evaluation criteria are thoroughly performed and are successfully compared with the state of the art algorithms like Harris hawks optimizer, Atom search optimizer, Salp swarm optimization algorithm. In addition, a non-parametric test for all considered cases is performed. From the carried-out analysis, the obtained results, and the observations, it is derived that the proposed HCLAOA approach is the most suitable for modeling both PEMFC and SOFC.