RBF network-aided adaptive unscented kalman filter for lithium-ion battery SOC estimation in electric vehicles

Abstract

An accurate battery State of Charge (SOC) estimation is very important for electric vehicles. In this paper, a method is proposed to estimate the SOC of the lithium-ion batteries using radial basis function (RBF) networks and the adaptive unscented Kalman filter (AUKF). The RBF networks are to model the battery-discharging process, then the AUKF is applied to estimate the SOC of the battery. Simulation results show that the proposed method has good performance in battery modeling and SOC estimation.