Optimal parameters of PEM fuel cells using chaotic binary shark smell optimizer

Abstract

Proton Exchange Membrane Fuel Cells (PEMFCs) are regarded as a promising system for power generation and energy sources in recent years. PEMFCs exhibit various advantages in comparison to other traditional energy sources especially due to their requirement for Hydrogen and air for operation while the final product is only water. Thus, the PEMFCs have received great attention for investigation of the operation under various conditions. In recent years, many researchers have done lots of mathematical modeling, but because of exact modeling absence, evolutionary optimization methods are used to adopt for parameter estimation of PEMFCs. This paper suggested a novel optimization scheme, namely, chaotic binary shark smell optimization (CBSSO), to optimize unknown parameters of PEMFC model. The CBSSO is a Meta-Heuristic algorithm which is introduced newly and has shown an appropriate ability in parameter identification and optimization cases. Moreover, the results of this proposed method are compared with some other results including typical SSO, Hybrid Artificial Bee Colony, Adaptive RNA Genetic Algorithm, Real-coded GA, Modified Particle Swarm Optimization, and Artificial Immune System. Based on the obtained results, this proposed method is very efficient in convergence and accuracy aspects compared to other famous methods.