Starfish Optimization Algorithm for Enhanced Parameter Identification of Proton Exchange Membrane Fuel Cell Models

This study evaluates the performance of the starfish optimization algorithm (SFOA) for parameter identification in Proton Exchange Membrane Fuel Cells (PEMFCs). SFOA, inspired by the decentralized movement and regeneration behavior of starfish, combines global exploration and local exploitation strategies to efficiently estimate unknown PEMFC parameters. Four different PEMFC stacks, namely, 250W, BCS 500W, SR-12 500W, and NetStack_PS6, are analyzed using SFOA, with results benchmarked against state-of-the-art optimization techniques. The optimization is executed 50 times on each PEMFC. Statistical measurements have been conducted, and the statistical results confirm that SFOA yields the minimum total squared deviation (TSD) for all the four PEMFCs studied. The results of convergence characteristics identify that optimum results are achieved within 200 iterations and 30 agents. In addition, the proposed algorithm is capable of capturing the PEMFC performance under varying temperatures and gas pressure and is applicable in real-world situations. The results confirm the better precision, rate of convergence, and efficiency of SFOA and conclude that it is a valuable tool in PEMFC simulation and optimization.