DocumentCode :
1868789
Title :
LiFePO4 battery capacity prediction based on support vector machine
Author :
Liu, Deming ; Liu, Xindong ; ZHU, Z. Q. ; Sun, J.W. ; Zhang, Ye
Author_Institution :
School of Electrical Engineering and Automation, Harbin Institute of Technology, China
fYear :
2012
fDate :
3-5 March 2012
Firstpage :
1302
Lastpage :
1305
Abstract :
Capacity character is one of the most important parameters to reflect the basis performance of secondary battery, whose precise measurement is of great significance in the aspects of safety and efficiency of battery usage. The law between capacity, ambient temperature and charge-discharge rate are studied in this paper, and a novel method of capacity prediction is presented to apply to LiFePO4 battery. Furthermore, battery capacity prediction experiments are respectively carried out for charging and discharging process in case of small sample, and the corresponding relative errors are lesser than 4.45% and 3.72%. In addition, this paper also conducts a subdivided prediction of battery capacity, which elaborates the validity of the proposed method from the global perspective.
Keywords :
Capacity prediction; LiFePO4 battery; Support Vector Machine;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Automatic Control and Artificial Intelligence (ACAI 2012), International Conference on
Conference_Location :
Xiamen
Electronic_ISBN :
978-1-84919-537-9
Type :
conf
DOI :
10.1049/cp.2012.1218
Filename :
6492825
Link To Document :
بازگشت