Answers are grounded in this paper and cite their sources.
In this study, we employ a recent variant of Particle Swarm Optimisation specifically for single objective numerical optimisation (PSO-sono) to pinpoint the optimal parameters of proton exchange membrane fuel cells (PEMFC) across certain operational scenarios. This research focuses on optimising seven parameters – ξ1,ξ2,ξ3,ξ4,λ,Rcand B – to replicate polarisation curves that align closely with those provided in manufacturers’ datasheets. The PSO-sono algorithm incorporates hybrid paradigms and adaptive parameter schemes, enhancing the traditional PSO algorithm's performance. The efficacy of PSO-sono was evaluated using six commercial PEMFC stacks: BCS 500-W PEM, BCS 250-W PEM, Nedstack PS6 PEM, 500W SR-12PEM, H-12 PEM and HORIZON 500W PEM, under varied operational conditions. The objective function for optimisation was the sum of squared errors (SSE) between the parameter-derived results and the actual experimental data from these fuel cell stacks. To establish the robustness of PSO-sono, its outcomes were benchmarked against results from other PSO variants, including PSO, CLPSO, DNLPSO, SLPSO, EPSO, PSO-DE, HFPSO, MPSO and HPSO. The I/V and P/V curves derived from PSO-sono showed a precise alignment with the datasheet specifications for all PEMFC models tested. Conclusively, the PEMFC model utilising the PSO-sono approach outperformed all other algorithms in terms of accuracy and convergence speed.
No takes yet. Share an insight, caveat, or question.
Jangir et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: