A Novel Joint Support Vector Machine - Cubature Kalman Filtering Method for Adaptive State of Charge Prediction of Lithium-Ion Batteries

Accurate estimation of SOC lithium-ion batteries has always been an important work in the battery management system. However, it is often very difficult to accurately estimate batteries. Therefore, a novel joint support vector machine - cubature Kalman filtering (SVM-CKF) method proposed this paper. SVM used train output data CKF algorithm obtain model. Meanwhile, model compensate original SOC, more accurate SOC. After SVM-CKF introduced, amount needed for prediction reduced. By using Beijing Bus Dynamic Stress Test (BBDST) and (DST) condition verify training model, results show that can significantly improve accuracy Lithium-ion maximum error BBDST 0.800%, which reduced by 0.500% compared with algorithm. The under DST about 0.450%, 1.350% less than overall great improvement generalization ability, lays foundation subsequent research on prediction.