Optimal identification of model parameters for PEMFCs using neoteric metaheuristic methods

In this paper, the neoteric metaheuristic methods of artificial ecosystem-based optimization (AEO), Coot Bird-based optimization (COOT), Equilibrium optimizer (EQO), Runge-Kutta Method (RUN), Hunger games search (HGS), and Weighted Mean of Vectors (INFO) have been applied and evaluated to discover a preferable estimation for the Proton Exchange Membrane Fuel Cells (PEMFCs) model. The validation of the applied methods has been done for valuing the model parameters of BCS 500W-PEM, 500W-SR-12PEM, and 250W-stack. The objective function has been formulated as the sum of square errors (SSEs) between the measured and estimated data. MATLAB has been used for the verification of the optimization techniques. The results show that for BCS 500W-PEM: (1) the six algorithms can accurately solve the problem of the FC parameter assessment; (2) there are small distinguished between the six algorithms concerning their best value of the objective function; this distinction between the best and worst techniques is 2.4 x 10(-9); (3) the best algorithm is INFO with 0.011556306 while the worst algorithm is RUN with 0.011556308; (4) statistical results prove that the six algorithms have the tracking efficiencies of 99.99961329%, 99.97114568%, 99.83529736%, 100%, 99.89195368%, and 99.90200833% for AEO, COOT, EQO, INFO, HGS, and RUN, respectively based on 30 individual runs.