Deep neural network-based modeling and optimization methodology of fuel cell electric vehicles considering power sources and electric motors

Abstract

This study proposes a modeling and optimization methodology for fuel cell electric vehicles (FCEVs). Among FCEV components, the traction motor, lithium-ion battery, fuel cell stack, and air supply system are mainly investigated. The FCEV modeling is performed based on the vehicle specifications, electromagnetic finite element analysis, and experimental data. To conduct design optimization, deep neural networks (DNNs) are adopted and trained to predict vehicle performance considering the fluctuation of applied direct current voltage. At this stage, the adaptive layering and sampling algorithm was suggested, which enables efficient DNN construction. To confirm the feasibility of the suggested training algorithm, the number of hidden layers and sampling points of constructed DNNs are investigated. Finally, DNN-based fuel economy optimization is performed considering the driving performance. The effectiveness of the proposed optimization methodology is validated by additional optimization results.