Parameters Optimization of PEMFC Model Based on Gazelle Optimization Algorithm

Fuel cells (FCs) play a crucial role in converting stored hydrogen energy into electricity. However, accurately modeling and optimizing their performance is challenging due to the lack of critical parameter data—specifically, seven key parameters including four semi-empirical coefficients (ξ1, ξ2, ξ3, ξ4), an adjusting parametric coefficient (β), a constant equivalent resistance (Rc), and an adjustable parameter (λ). These essential parameters are typically not provided in manufacturers' datasheets, creating a significant gap in the precise calibration and optimization of Proton Exchange Membrane Fuel Cells (PEMFCs).This study addresses this gap by applying seven population-based meta-heuristic algorithms to estimate and optimize these unknown parameters. Among these, the Gazelle Optimization Algorithm (GOA) is identified as particularly effective, offering superior precision and rapid convergence. Our research evaluates the performance of these algorithms using indicators such as Standard Deviation (StD) and Sum of Squared Errors (SSE). The GOA achieved exceptionally low SSE values of 7.637606 × 10^-3, 1.28694222 × 10−2, and 2.288128 for the Horizon 500W, BCS 500W, and NedStack PS6 stacks, respectively, along with corresponding StD values of 2.275703 × 10−9, 9.12077649 × 10−15, and 3.26518838 × 10−14. These results underscore the algorithm's accuracy and effectiveness in optimizing PEMFC parameters, closely aligning with the manufacturers' polarization curves.The study's findings, validated across these three different fuel cell stacks, highlight the GOA's superiority over other methods in terms of accuracy and convergence speed. This manuscript contributes to the field by providing a robust method for accurately optimizing PEMFC parameters, which are critical for enhancing the overall performance of fuel cells. The results also demonstrate the GOA's potential as a superior optimization tool in the field of fuel cell technology.