The state of charge (SOC) is a key parameter in battery management systems (BMSs). As an indirectparameter, accurately estimating the SOC has been an area of interest in battery research. To achieveonline SOC estimation under variable temperature and discharge rate conditions, this paper proposes anovel modeling methodology for battery online SOC estimation based on an extended Kalman filter(EKF) and a backpropagation (BP) neural network and a method for calculating the true value of thebattery SOC under these varying conditions for model validation. Three types of SOC estimation modelsare established and compared, involving an EKF model based on a second-order equivalent circuitmodel, a data-driven BP neural network model, and a fusion of the two models. Ultimately, the validityand rationality of the fusion modeling methodology for SOC online estimation proposed in this paper isverified by experimental data.
展开▼
