Benchmark of proton exchange membrane fuel cell parameters extraction with metaheuristic optimization algorithms

Proton exchange membrane fuel cell (PEMFC) models are multivariate with different nonlinear elements which should be identified accurately to assure dependable modeling. Metaheuristic algorithms are perfect candidates for this purpose since they do an informed search for finding the parameters. This paper utilizes three algorithms, namely shuffled frog-leaping algorithm (SFLA), firefly optimization algorithm (FOA), and imperialist competitive algorithm (ICA) for the PEMFC model calibration. In this regard, firstly, the algorithms are employed to find the parameters of a benchmark PEMFC model by minimizing the sum of squared errors (SSE) between the measured and estimated voltage for two available case studies in the literature. After conducting 100 independent runs, the algorithms are compared in terms of the best and the worst SSEs, the variance, and standard deviation. This comparison indicates that SFLA marginally outperforms ICA and FOA regarding the best SSE in both cases while it performs 20% and twofold better than other algorithms concerning the worst SSE. Furthermore, the obtained variance and standard deviation by SFLA are much less than the other algorithms showing the precision and repeatability of this method. Finally, SFLA is used to calibrate the model for a new case study (Horizon 500-W PEMFC) with variable temperature. © 2019 Elsevier Lt