Title :
State-of-charge estimation for lithium-ion battery using AUKF and LSSVM
Author :
Jinhao Meng ; Guangzhao Luo ; Fei Gao
Author_Institution :
Sch. of Autom., Northwestern Polytech. Univ., Xi´an, China
fDate :
Aug. 31 2014-Sept. 3 2014
Abstract :
A new method based on adaptive unscented Kalman filter (AUKF) is proposed to improve the SOC estimation accuracy of lithium-ion battery in this paper. The noise covariance in AUKF is adaptively adjusted. To improve the accuracy of the AUKF-based method, least squares support vector machine (LSSVM) is used to establish measurement equation. A comparison with unscented Kalman filter shows that the proposed method has a better accuracy. Simulation data indicates a better SOC estimation result and a faster convergence can be obtained by using the AUKF-based method.
Keywords :
adaptive Kalman filters; least squares approximations; nonlinear filters; power engineering computing; secondary cells; support vector machines; AUKF; LSSVM; SOC estimation accuracy; adaptive unscented Kalman filter; least squares support vector machine; lithium-ion battery; measurement equation; noise covariance; state-of-charge estimation; Accuracy; Batteries; Battery charge measurement; Equations; Estimation; Mathematical model; System-on-chip; Battery; adaptive unscented Kalman filter (AUKF); least squares support vector machine (LSSVM); state of charge (SOC);
Conference_Titel :
Transportation Electrification Asia-Pacific (ITEC Asia-Pacific), 2014 IEEE Conference and Expo
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-4240-4
DOI :
10.1109/ITEC-AP.2014.6940680
