An Effective Model Parameter Estimation of PEMFCs Using Modified GWO Algorithms
ABSTRACT This paper introduces the application of modified Grey Wolf Optimization (GWO) algorithms for the sake of assessing unknown parameters of Proton Exchange Membrane Fuel Cells (PEMFC) models. Three different GWO algorithms are applied: Conventional GWO, Improved GWO (I-GWO) based on dimension learning-based hunting (DLH), and Selective Opposition-based Grey Wolf Optimization (SOGWO). These algorithms are applied to three commercial PEMFC stacks: BCS 500W-PEM, 500W-SR-12PEM and 250W-stack. The analyses are executed considering several operational circumstances. Sum of square errors (SSEs) value of the results based on parameters estimation and those experimentally tested are calculated. The objective function is chosen as SSEs value. The results are compared with those obtained using well-known methods in the literature to validate the effectiveness of the proposed methods. It is noticeable that the simulated I/V curves momentously match the datasheet curves for all the studied cases. In addition, considering the accuracy of the solution and the convergence speed, the PEMFC model based on the I-GWO algorithm excels all other algorithms. Based on the simulation results, the I-GWO algorithm can improve the optimization efficiency to 99.96931463 for the 250 W stack while the efficiency with GWO and SOGWO are 98.83244042 and 98.84297862, respectively for 250 W stack case study.
Data of three commercial PEMFC stacks: BCS 500W-PEM, 500W-SR-12PEM and 250W-stack.