Digital Twin of Hydrogen Fuel Cell Hybrid Electric Vehicle using Laboratory and Drive Cycle Data

Abstract:
Nowadays, there is a noticeable shift in mobility from combustion engines toward electric and hybrid vehicles. Unlike conventional electric vehicles (EVs), fuel cell vehicles (FCVs) have an electric powertrain powered by a proton exchange membrane fuel cell (PEMFC) and a battery, such as a nickel-metal hydride battery. To predict energy exchange and vehicle behavior, a digital twin (DT) based on an equivalent circuit model (ECM) is developed using empirical data, as detailed internal specifications are often not available. Parameters such as membrane resistance and activation polarization are derived from current-voltage curves and step responses. This study involves the creation of a DT of the fuel cell and storage system using laboratory data and its validation with driving data from a laboratory-scale tested FCV in a temperature-controlled environment. The results show that the DT accurately predicts the vehicle's performance and energy exchange, as reflected by a mean absolute error (MAE) of 0.686 W for the PEMFC, 0.261 W for the battery, and 0.975 W for the overall system. These results validate its suitability for further development and real-world applications.