Title :
State of Charge Estimation for Electric Vehicle Batteries Based on LS-SVM
Author :
Hui Bao ; Yang Yu
Author_Institution :
Dept. of Electron. & Commun. Eng., North China Electr. Power Univ., Baoding, China
Abstract :
For the study of optimal control problems of battery power in electric vehicle, accurately estimating the state of charge (SOC) of the battery is a non-negligible part. This paper proposes a prediction model for state of charge of batteries Based on least squares support vector machine. It was with battery terminal voltage, temperature, electric current as inputs, state of charge as output. After gaining data samples through experiment platform, least squares support vector machine was established, and state of charge can be predicted by the model. The experimental results show that the prediction accuracy of the method Based on LS - SVM significantly better than BP neural network, so it can be used to predict battery SOC values.
Keywords :
battery powered vehicles; electrical engineering computing; least squares approximations; secondary cells; support vector machines; BP neural network; LS-SVM method; SOC estimation; battery power; battery terminal voltage; electric current; electric vehicle batteries; least square support vector machine; optimal control problem; prediction model; state-of-charge estimation; Batteries; Electric vehicles; Kernel; Predictive models; Support vector machines; System-on-chip; Training; Battery; Electric vehicle; Least squares support vector machine; Prediction model; State of charge; prediction accuracy;
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2013 5th International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-0-7695-5011-4
DOI :
10.1109/IHMSC.2013.112