EV battery state of charge: neural network based estimation
Different electric vehicles (EV) types have beendeveloped with the aim of solving pollution problems caused by theemission of gasoline-powered engines. Environmental considerationspromote the adoption of EV for urban transportation. As it is wellknown one of the weakest points of electric vehicle is the batterysystem. Vehicle autonomy and therefore accurate detection ofbattery state of charge are among the main drawbacks that preventthe spread of electric vehicles in the consumer market. This paperdeals with the analysis of battery state of charge: performances ofa few sizes of batteries are analyzed and their state of charge isestimated with a neural network (NN) based system. The obtainedresults have been used to design a lithium-ion battery packsuitable for electric vehicles. The proposed system presents highcapability of energy recovering in braking conditions, togetherwith charge equalization, over and under voltage protection.Moreover a neural network based estimation of battery state ofcharge has been implemented in order to optimize autonomy insteadof performances or vice-versa depending on journey.
From: Electric Machines and Drives Conference,2003. IEMDC'03. IEEE International