Integrating Novel Circuit Design with Optimization Algorithms for Advanced Parameter Identification in PEM Fuel Cells

This paper investigates the Proton Exchange Membrane (PEM) fuel cell as a potential alternative energy source for applications including transportation and emergency power systems. It introduces a novel circuit model for a PEM fuel cell that can be used to design and analyze fuel-cell power system. An optimization algorithm is used to identify key parameters, not typically found in manufacturers datasheets, for developing a precise and accurate model to predict fuel cell performance. A new algorithm based on differential evolution (DE) is utilized to compute five previously unknown parameters of a PEMFC. In the optimization process, these parameters are treated as decision variables, and the objective is to minimize the sum square error (SSE) between the estimated and the actual measured cell voltage. The SSE achieved by the DE algorithm was found to be 0.313, demonstrating its effectiveness in accurately predicting fuel cell performance. This precision makes DE particularly suitable for the development of digital twins for fuel-cell applications and control systems in the automotive industry. The study underscores the potential of metaheuristic algorithms like DE in predicting fuel-cell performance, aiding in the development and commercialization of digital twins within the automotive sector.