电源技术2012，Vol.36Issue(3)：349-351,370,4.
基于LS-SVM算法动力电池SOC估计方法的研究
Estimating method for power battery state of charge based on LS-SVM
摘要
Abstract
It is crucial for the research of battery management system (BMS) to improve the estimating veracity of state of charge (SOC) determination of battery for electric vehicle (EV). According to the historical data analysis on battery voltage, current, power factors of total discharge battery influence, a novel way to estimate SOC on-line by least squares support vector machine ( LS-SVM )was presented, which had good nonlinear approximation ability, quick convergence rate and global optimal solution. Comparing with the BP neural network algorithm, the proposed method has more exact results in approaching actual results and its maximum error is reduced to 0.02 which reaches the demands of electric vehicle.关键词
电动汽车/动力电池/荷电状态/最小二乘支持向量机/BP神经网络Key words
electric vehicle/power battery/state of charge/least squares support vector machine/BP neural network分类
信息技术与安全科学引用本文复制引用
于洋,纪世忠,魏克新..基于LS-SVM算法动力电池SOC估计方法的研究[J].电源技术,2012,36(3):349-351,370,4.基金项目
国家自然科学基金(50977063) （50977063）
国家“863”高技术研究发展计划项目(2008AA11A145) （2008AA11A145）
天津市科技支撑重点项目(09ZCKFGX01800) （09ZCKFGX01800）
