DocumentCode
2124241
Title
Data-driven SOH prediction for EV batteries
Author
Gae-won You ; Sangdo Park ; Sunjae Lee
Author_Institution
Samsung Adv. Inst. of Technol., Samsung Electron., Yongin, South Korea
fYear
2015
fDate
9-12 Jan. 2015
Firstpage
577
Lastpage
578
Abstract
As electric vehicles (EVs) have been popularized, research on battery management system (BMS) of EVs´ core technology has considerably drawn attention. Among various functions of BMS, predicting state-of-health (SOH) that indexes batteries´ aging is the most crucial to determine replacement time of the battery or to estimate driving mileage. This paper studies how to predict SOH in practical EV environments where the batteries are charged and discharged dynamically.
Keywords
battery management systems; battery powered vehicles; BMS; EV batteries; battery management system; data-driven SOH prediction; electric vehicles; state-of-health prediction; Aging; Artificial neural networks; Batteries; Data models; Pattern recognition; Predictive models; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Consumer Electronics (ICCE), 2015 IEEE International Conference on
Conference_Location
Las Vegas, NV
Print_ISBN
978-1-4799-7542-6
Type
conf
DOI
10.1109/ICCE.2015.7066533
Filename
7066533
Link To Document