ZEBRA battery SOC estimation using PSO-optimized hybrid neural model considering aging effect

Abstract

The state of charge (SOC) estimation for electric vehicles (EVs) is important and helps to optimize the utilization of the battery energy storage in EVs. In this way, aging is also a key parameter impacting the performance of batteries. In this paper, a hybrid neural model is proposed for the SOC estimation of ZEBRA (Zero Emission Battery Research Activities) battery considering the aging effect through the state of health (SOH) and the discharge efficiency (DE) parameters. The number of hidden nodes in neural modules is also optimized using particle swarm optimization (PSO) algorithm. The SOC estimation error of the proposed system is 1.7% when compared with the real SOC obtained from a discharge test. © IEICE 2012.