This is the authors' abstract. We don't add key points for this paper.
Accurate parameter identification of proton exchange membrane fuel cells (PEMFCs) is essential for model-based control and health management. However, the complex parameter semi-empirical model exhibits strong and significant parameter coupling, sensitivity, and non-convex multimodal characteristics, which can lead to premature convergence of traditional metaheuristic algorithms. This paper proposes an event-triggered and dimension-weighted-based Whale Migration Algorithm–Particle Swarm Optimization (WMA–PSO) for the PEMFC semi-empirical model. Firstly, a scale-normalized progress indicator is introduced to address the issue of premature convergence. Additionally, sequential smoothing and bounded normalization are proposed to enhance global search stability. Through numerical experiments compared with commonly used algorithms, the proposed WMA–PSO demonstrates superior search performance. Furthermore, convergence analysis and computational complexity analysis are conducted from a theoretical perspective for verification. Finally, PEMFC parameters are effectively identified on three publicly available PEMFC stack datasets. Experimental results show that the method exhibits excellent versatility in identifying complex parameters in the PEMFC model.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Bi et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: