Hybrid Beluga whale and jellyfish search optimizer for optimizing proton exchange membrane fuel cell parameter estimation

PEMFCs used in clean energy systems rely on accurate modeling to achieve optimal performance in addition to design optimization. The estimations of model parameters remain difficult due to PEMFC model complexity and nonlinearity alongside operating condition variations. A new Hybrid Beluga Whale Optimizer based on the Jellyfish Search Optimizer (HBWO-JS) serves as the proposed solution to handle these difficulties. The HBWO-JS combines vertical crossover and Gaussian variation elements from JS optimizer to improve both search effectiveness alongside solution precision and convergence acceleration. The research evaluated the proposed algorithm using six PEMFC models including Nedstack 600 W PS6, Horizon H- 12, Ballard Mark V, SR- 12 W, BCS 500 W, and STD 250 W Stack. The research compared results against Jellyfish Search (JS) Optimizer and Beluga Whale Optimization (BWO) as well as Artificial Hummingbird Algorithm (AHA) and Artificial Rabbits Optimization (ARO) and Dandelion Optimizer (DO) and White Shark Optimizer (WSO) and Grey Wolf Optimization (GWO). The HBWO-JS generated the most accurate curve fits through its consistent achievement of minimum sum of squared errors (SSE) for all tested methods. The research shows that HBWO-JS represents a powerful optimization framework for PEMFC parameter estimation which successfully manages exploration and exploitation to address existing optimization limitations. The results from this study will support future PEMFC model development for energy systems so they can be used in large-scale fuel cell systems and other applications like solid oxide fuel cells (SOFCs).