A hybrid slime mold enhanced convergent particle swarm optimizer for parameter estimation of proton exchange membrane fuel cell.

High efficiency and eco friendliness, proton exchange membrane fuel cells (PEMFCs) have become a good solution to cleaner energy solutions. However, due to the electrochemical complexity of PEMFCs and the limitations of existing optimization methods, accurately estimating PEMFC parameters to achieve optimal performance is still challenging. In this work, we propose a hybrid optimization algorithm, SCPSO, combining Particle Swarm Optimization with Mixed Mutant Slime Mold to improve precision, consistency, and computational efficiency in PEMFC parameter optimization. Six PEMFC types, BCS 500 W, Nedstack 600 W PS6, SR-12 W, Horizon H-12, Ballard Mark V, and STD 250 W Stack were applied to SCPSO and compared with seven state-of-the-art algorithms, FLA, HFPSO, PSOLC, ESMA, LSMA, DETDO, and EGJO. In all cases, SCPSO consistently outperformed all competitors with the lowest mean sum of squared error (SSE) and minimal standard deviation (e.g., [10, 10]), thus confirming its robustness and reliability. Additionally, it demonstrated the lowest number of iterations to reach the optimal solution (less than 200 iterations) and best Friedman Rank (FR = 1), signifying the best optimization to the customer. For instance, in PEMFC1, SCPSO achieved minimal SSE of 0.02549 with negligible variability (Std. = 1.05958E-15) as compared to HFPSO (Std. = 0.001998568) and DETDO (FR = 4). SCPSO's rapid convergence curves, narrow box plot spreads, and precise polarization curves were further validated across all fuel cells. SCPSO was experimentally validated and proved to be reliable with minimal deviations between predicted and experimental voltage and power outputs (e.g., RE = 0.052587% for PEMFC1 and RE = 0.016537% for PEMFC2). The average runtime of SCPSO was 3.05 s, which is faster than alternatives, and still maintains its unparalleled precision. The results of the analyses, fitting the datasets and the convergence curves confirm that the adaptive parameter tuning of SCPSO has significantly improved its performance, resulting in the highest consistency and accuracy with the fastest convergence speed. For PEMFC parameter optimization, results from SCPSO have established it as the algorithm with the strongest precision and stability and fastest computational efficiency. The extension to other energy systems and dynamic real time scenarios will be investigated in future research to enable wider adoption in sustainable energy management.