Parameter optimization of PEMFC model using backtracking search algorithm

Proton Exchange Membrane Fuel Cell (PEMFC) is one of the promising alternative energy source that can decrease the adverse effect of greenhouse gas emissions. However, predicting the output voltage of PEMFC is difficult because of its non-linear characteristic. Thus, in this paper the modern backtracking search algorithm (BSA) is applied for modeling the PEMFC and extracting model parameters. Initially some experiments are performed on PEMFC system while changing its load linearly. The model parameters are optimized using BSA with root mean square error as an objective function. The final modeled voltage shows that the BSA provide better results than particle swarm optimization (PSO) in modelling PEMFC output voltage.