Estimation of Proton Exchange Membrane Fuel Cell Parameters via Enhanced Artificial Bee Colony Optimization

ABSTRACT Proton Exchange Membrane Fuel Cells (PEMFCs) play a crucial role in energy transition owing to their efficiency and eco‐friendly nature. However, precise parameter estimation plays a critical role in effective modeling and control of PEMFC systems. In this study, the enhanced artificial bee colony (E‐ABC) algorithm is proposed for the accurate estimation of model parameters. The random scout phase of the ABC algorithm is replaced by a guided search using sine and cosine functions to enable more efficient and balanced exploration of the solution space in the developed approach. Two commercial PEMFC stacks, BCS 500 W and NedStack PS6, are considered for performance evaluation. The effectiveness of the proposed E‐ABC algorithm in PEMFC parameter estimation was analyzed through comparison with several algorithms. E‐ABC successfully estimated the parameters of the BCS 500 W and NedStack PS6 PEMFC systems with sum of squared errors values of 0.01191 and 2.14895, respectively. Results from comparative analysis clearly indicate that the E‐ABC algorithm outperforms other methods by achieving significantly lower estimation errors. Reduced median and standard deviation values serve as evidence of greater performance stability and consistency. Also, nonparametric statistical analyses further verify the statistical significance of the superiority of the proposed E‐ABC algorithm.