Efficient PEM fuel cells parameters identification using hybrid artificial bee colony differential evolution optimizer

Abstract

On the bases of meta-heuristic optimizers and experimental datasets, the parameter extraction of the proton exchange membrane fuel cells (PEMFCs) model to reach accurate current/voltage (I/V) curves remain an active research area during these last years. In this paper, an improved hybridized optimizer is developed to accurately estimate the PEMFC model parameters namely artificial bee colony differential evolution optimizer (ABCDE). In the developed ABCDE, the double execution of the mutation strategy allows enhancing the exploitation phase and avoiding to get stuck into the local minima. To assess the proposed ABCDE based parameter's identification, a comparative study with the recently published techniques including shuffled complex evolution, artificial ecosystem-based optimizer, and enhanced Lévy flight bat algorithm is performed using five typical PEMFCs modules. In this context, the reached sum of squared errors (SSE) and the standard deviations (STD) are very competitive among the challenging methodologies. ABCDE reaches the best SSE values within interesting overall STD and CPU run time less than 3e−15 and 0.225 s, respectively, for the five cases under study. It can be confirmed that the cropped SSE values and the STD among other challenging methodologies are very competitive with the best convergence speed. The ABCDE reaches 0.011697781, 2.07916558, 0.85360752, 9.6536060e−02, and 1.42098181379214e−04 for BCS 500W, NedStack PS6, Ballard Mark V, Horizon H-12, and Modular SR-12; respectively. In addition to that, the comparison results indicate that the proposed ABCDE is successfully utilized to characterize the PEMFC's model reliably and rapidly.