Effective methodology based on neural network optimizer for extracting model parameters of PEM fuel cells

I/V polarization curves of proton-exchange membrane fuel cells (PEMFCs) are used to characterize the performance of single cells and stacks. Numerous semi-empirical models are presented to predict such polarization curves by determining the unknown parameters of mathematical model of the PEMFCs stack. In this paper, a novel optimization approach, namely neural network algorithm (NNA) is applied for an estimation of the unknown PEMFC model parameters. The NNA is employed to minimize adopted objective function, which is formulated as the sum of squared deviations (SSD) between the actual data and estimated voltage points subjects to set of inequality constraints are satisfied. Three commercial types of PEMFCs stack namely Ballard Mark V, BCS-500 W, and Nedstack PS6 are numerically simulated to show the effectiveness of the proposed NNA-based tool for parameter identification. The minimum values of SSD are 0.8536 V-2 for Ballard Mark V, 0.011698 V-2 for BCS-500 W stack, and 2.14487 V-2 for Nedstack PS6, respectively. The obtained results of the NNA are compared with other optimizers recently published in the literature such as flower pollination algorithm, slap swarm optimizer, grey wolf algorithm, grasshopper optimization algorithm, and shark smell algorithm under the same conditions. The comparisons and other performance tests indicate the robustness and the competition of the adopted NNA-based method for producing accurate I/V polarization curves under different operating scenarios.