Enhanced Osprey Optimization Algorithm for Global Optimization with Application to PEM Fuel Cell Parameter Identification

Bio-inspired metaheuristic algorithms, which emulate natural predatory and evolutionary behaviors, play a crucial role in solving complex engineering problems, such as the accurate parameter extraction of proton exchange membrane fuel cells (PEMFCs). However, many existing optimization algorithms suffer from premature convergence, premature stagnation in local minima, and limited accuracy. Among these algorithms, the Osprey Optimization Algorithm (OOA) has shown promising performance. In this paper, an Enhanced Osprey Optimization Algorithm (EOOA), an improved variant of the conventional OOA, is proposed. The performance of the proposed algorithm is first evaluated using the CEC2022 benchmark functions. Subsequently, the EOOA is applied to the problem of PEMFC parameter extraction for two commercial stacks, namely NedStack PS6 and Ballard Mark V. The results demonstrate that the EOOA outperforms the original OOA and four other metaheuristic algorithms, ranking first in 11 out of 12 CEC2022 benchmark functions. Furthermore, the EOOA shows superior performance in PEMFC parameter identification compared to the OOA and other methods reported in the literature. Specifically, the proposed algorithm achieves a sum of squared errors (SSE) of 2.065 for the NedStack PS6 and 0.81 for the Ballard Mark V. These results indicate that the EOOA has strong potential for application to other optimization problems beyond PEMFC parameter extraction.