Enhanced Accuracy in PEM Fuel Cell Modeling Using Load‐Dependent Semiempirical Approaches

ABSTRACT Proton exchange membrane fuel cells (PEMFCs) play a central role in the transition to clean hydrogen‐based energy systems. However, conventional models with fixed empirical parameters often fail to predict performance under variable operating conditions accurately. This paper introduces two novel PEMFC models with load‐dependent formulations of the activation overpotential constant and its temperature coefficient, parameters shown to have the greatest sensitivity to load variation. Using the artificial hummingbird algorithm (AHA) for parameter optimization, the models were tested on four representative PEMFC configurations (Ballard‐Mark‐V 5 kW PEMFC, BCS 500 W, NedStack PS6 6 kW PEMFC, and Horizon 500 W). The results demonstrate a consistent reduction in prediction error compared with state‐of‐the‐art models, with an improvement of up to 89.97% in RMSE for the Horizon cell. Sensitivity and robustness analyses further confirm stable performance under varying temperature and pressure conditions. These findings suggest that the proposed models offer a reliable and computationally efficient foundation for advanced simulation, control, and optimization of PEMFC systems in real‐world applications.