A levy chaotic horizontal vertical crossover based artificial hummingbird algorithm for precise PEMFC parameter estimation

Abstract In this research, enhanced versions of the Artificial Hummingbird Algorithm are used to accurately identify unknown parameters in Proton Exchange Membrane Fuel Cell (PEMFC) models. In particular, we propose a multi strategy variant, the Lévy Chaotic Artificial Hummingbird Algorithm (LCAHA), which combines sinusoidal chaotic mapping, Lévy flights and a new cross update foraging strategy. The combination of this method with PEMFC parameters results in a significantly improved performance compared to traditional methods, such as Particle Swarm Optimization (PSO), Differential Evolution (DE), Grey Wolf Optimizer (GWO), and Sparrow Search Algorithm (SSA), which we use as baselines to validate PEMFC parameters. The quantitative results demonstrate that LCAHA attains a minimum Sum of Squared Errors (SSE) of 0.0254 and standard deviation of 4.59E−08 for the BCS 500W PEMFC model, which is much lower than the SSE values obtained for PSO (0.1924) and GWO (0.0364), thereby validating the superior accuracy and stability of LCAHA. Moreover, LCAHA converges faster than DE and SSA, reducing runtime by about 47%. The robustness and reliability of LCAHA-simulated and actual I–V curves across six PEMFC stacks are shown to be in close alignment.