Comparative analysis on parametric estimation of a PEM fuel cell using metaheuristics algorithms

Tabbi Wilberforce*, Hegazy Rezk, A.G. Olabi*, Emmanuel I. Epelle, Mohammad Ali Abdelkareem*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

One of the primary issues in the modelling of fuel cell is the determination of specific boundary conditions often deduced from the manufacturer of the fuel cell. Realistically, not all data is available from the manufacturer's data sheet; hence, to improve the accuracy as well as predict the performance of the cell, all these information need to be determined. This investigation however advanced the concept of using five different algorithms (Grey Wolf Optimization(GWO), Particle Swarm Optimization(PSO), Slime Mould Algorithm(SMA), Harris Hawk Optimiser (HHO), artificial ecosystem-based algorithm(AEO)) to ascertaining seven (ξ 1234,R,B,λ) unknow parameters that affect the mathematical modelling of the cell. The unknown parameters were used as the modelling variables. A minimum fitness function implied a good correlation between the measured/experimental data and the predicted/modelled data. The study had to rank the performance of the algorithms from the best value to the worse value, average and standard deviation. The artificial ecosystem-based algorithm showed the best results compared to the PSO, SMA, GWO and HHO algorithms.

Original languageEnglish
Article number125530
Number of pages16
JournalEnergy
Volume262
Issue numberPart B
Early online date27 Sep 2022
DOIs
Publication statusE-pub ahead of print - 27 Sep 2022

Keywords

  • Fuel cell
  • Meta-heuristic algorithms
  • Modelling
  • Optimization
  • PEMFC
  • Parameter estimation

Fingerprint

Dive into the research topics of 'Comparative analysis on parametric estimation of a PEM fuel cell using metaheuristics algorithms'. Together they form a unique fingerprint.

Cite this