<![CDATA[This paper presents a novel equivalent electrical circuit model for proton exchange membrane fuel cells (PEMFCs) and introduces a physics-informed neural network (PINN) algorithm for parameter identification. The proposed model provides a more accurate representation of the fuel cell’s dynamic behavior while maintaining computational efficiency. Unlike conventional methods, the PINN framework integrates physical constraints with data-driven learning, ensuring physically consistent parameter estimation. To validate its effectiveness, the proposed model is compared with the widely used RC equivalent circuit and a generic PEMFC model. Experimental data from a 1.2 kW PEMFC test bench serve as a benchmark for evaluating the transient and steady-state performance of each modeling approach. Results demonstrate that the proposed circuit, combined with PINN-based identification, yields enhanced accuracy in predicting voltage response under various operating conditions. Additionally, the model exhibits improved adaptability to transient phenomena compared to conventional equivalent circuits. These findings highlight the potential of physics-informed machine learning for advancing fuel cell modeling and control strategies.]]>
Copyrights © 2025
