Abstract:

This paper includes an overview of electric vehicle design and an artificial neural network application for energy consumption prediction in all-electric cars. In this study, several forms of electrified cars were referred to as "electric vehicles" (EVs). The technologies behind these electric vehicles were also discussed. The survey focuses on hybrid electric vehicles (HEVs), pure electric vehicles (PEVs), and plug-in hybrid electric vehicles (PHEVs). The study also presented the design simulation of a typical hybrid electric vehicle. A hybrid electric vehicle was designed using ADVISOR, and it was compared with another car known as the targeted car. The fuel consumption of the designed car was found to be lower than that of the targeted car. The study also introduced a multifunctional artificial neural network model for predicting electrical energy consumption in all-electric vehicles. The proposed model has nine input variables, which are virtual functions calculated from the nine selected parameters using a virtual function formula. The number of input variables was made to be equal to the number of output variables so that the artificial neural network could simulate a unique solution. The proposed model was compared with a multi-output inverse function model of an artificial neural network. The accuracy of the proposed model was 1.23–6.85 times higher than that of the inverse function model for the nine case studies considered in terms of mean square error.