Neural Network Based Drive Cycle Analysis for Parallel Hybrid Electric Vehicle

The progress of automobiles for transportation has been intimately associated with the progress of civilization. The main aim of this article is to develop a vehicle that can run on internal combustion engine (ICE) and electric motor efficiently and lower the fuel usage for a trip. The goal of this article is to analyze the driving speed of a vehicle and switch the energy sources based on the prediction given by a neural network. This ultimately reduces the fuel consumption when compared with a regular vehicle that is powered entirely by fuel. The neural network used in this paper is built using TensorFlow, which is considered one of fastest machine-learning libraries ever, which in turn helps in switching, thus leading to efficiency. The outcome of progress in the automobile sector in the present day is the accumulation of many years of pioneering research development. The usage of battery during low torque helps in reducing the heat dissipation in peak times; furthermore, the usage of ICE during high torque balances the economy of the vehicle.