Practical Energy Management Control of Fuel Cell Hybrid Electric Vehicles Using Artificial-Intelligence-Based Flatness Theory

This paper proposes a practical solution to address the energy management issue in fuel cell hybrid electric vehicles (FCHEVs). revolves around powertrain system that contains (FC) as main supply, photovoltaic (PC) secondary source, and battery bank (Batt) backup storage compensate for FC’s low response rate. The this alternated between designated elements load via DC bus, maintain stable output voltage, link was adjusted using nonlinear approach is based on flatness theory autoregressive moving average (NARMA-L2) neuro-controller. As current regulation loops, sliding mode technique employed attain high dynamic of reference signals produced by manager loop. To validate accuracy proposed (EMA), test bench equipped with digital, electronic circuits dSPACE DS-1104 unit. experimental contained emulator FC 1200 W 46 A, lithium-ion batteries 24 V, solar source capable 400 W. obtained results, indeed, attested validity used, yielding notable performance during multiple charge variations. ultimately demonstrated enhanced efficiency powertrain.