期刊
ENERGY CONVERSION AND MANAGEMENT
卷 53, 期 1, 页码 33-39出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.enconman.2011.06.003
关键词
Electric vehicles; Battery pack; State of charge (SOC); Stochastic fuzzy neural network; Extended Kalman filter (EKF)
资金
- National Natural Science Foundation of China [11072183, 21106113]
- State Key Laboratory of Automobile Safety and Energy Conservation [KF10092]
- Jiangsu Provincial Natural Science Foundation of China [BK2009144]
- Application Foundation [SYG201138]
Extended Kalman filtering is an intelligent and optimal means for estimating the state of a dynamic system. In order to use extended Kalman filtering to estimate the state of charge (SOC), we require a mathematical model that can accurately capture the dynamics of battery pack. In this paper, we propose a stochastic fuzzy neural network (SFNN) instead of the traditional neural network that has filtering effect on noisy input to model the battery nonlinear dynamic. Then, the paper studies the extended Kalman filtering SOC estimation method based on a SFNN model. The modeling test is realized on an 80 Ah Ni/MH battery pack and the Federal Urban Driving Schedule (FUDS) cycle is used to verify the SOC estimation method. The maximum SOC estimation error is 0.6% compared with the real SOC obtained from the discharging test. (C) 2011 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据