Design optimization and parameter estimation of a PEMFC using nature-inspired algorithms

Numerical simulation of proton-exchange membrane fuel cells (PEMFCs) requires an adequate model and precise parameters for reproducing their operational performance quantified by the polarization curve. Bioinspired algorithms are well-suited optimization. The simulator is stressed inputting thousands randomly generated parameters, hence, a robust numerical required. Once proper reproduce experimental data, they can be used design improvement. This article proposes reformulation macrohomogeneous mathematical to provide higher stability solutions. We introduce optimization problems parameter estimation applying three bioinspired maximize its minimize platinum mass loading $$m_\mathrm{{Pt}}$$ . results validated comparing curves with those simulated from estimated parameters. compare base design’s optimized maximum performance. also minimum show that particle swarm lowest computational cost performs best in most cases, fitting data errors lesser than $$10^{-17}$$ minimization reduces amount 42% compared case.