Pruning LS-SVM Based Battery Model for Electric Vehicles

This paper presents a new method to estimate the battery state of charge (SOC) in electric vehicles (EVs). The key of the proposed method is to establish the relationship of the SOC to the battery current, voltage and temperature by using least squares support vector machine (LS-SVM). For ease of practical application, the pruning procedure is developed to reduce the number of support vectors in terms of their significance. The results show that the proposed method can simulate the battery dynamics for the accurate estimation of the SOC in EVs.