Implementation of Battery Management Systems Using Adaptive Modeling for Electric Vehicles Applications

Abstract

This paper proposes and implements a new method for the estimation of the state of charge (soc) and state of health for the electric vehicles (EVs). The key of the proposed method is to model the EV battery by using the neuro-fuzzy inference system. This paper describes about different Adaptive   system for SOC estimation in Electric vehicle applications. Due to the increasing concern of fossil fuels and toxic gases, Environmental conditions and higher capacity accumulators transformation method has been changing day by day. In order to get safe and reliable operation, the battery should be protected. Battery properties such as state of charge and state of Health have been analyzed by using different algorithms. As batteries have been affected by many chemical factors and have non-linear state of charge (SOC) Adaptive systems offer good solution for SOC estimation. In recent years with the development Artificial Intelligence various new adaptive systems for SOC estimation have been developed. Among all the methods, neural network, radial basis function (RBF) neural network, Fuzzy logic methods, support vector machine, Fuzzy neural network and kalman filter are produced good results. In this work comparative solution is implemented using neural network method. Finally, the investigations of selected drive performances such as Battery voltage, current, ultra capacitor voltage evaluation parameters are presented. Matlab coding using simulation results is analyzed here.