摘要
锂离子电池荷电状态(SOC)估计在电池管理系统(BMS)尤为重要,由于SOC不可直接测量,因此估计精度很难保证。为提高电池荷电状态估计精度,采用通过最小二乘支持向量机(LSSVM)建立电压、电流和SOC之间的关系。不同的是,为了减小电压和电流因变化造成SOC估计精度低,提出了一种改进的LSSVM的锂离子电池SOC在线估计方法。将上一时刻的电压测量值、电流测量值以及上一时刻SOC的估计值,作为模型的反馈量,并和当前时刻的电压值和电流值,共同作为模型的输入量,来估计当前时刻的SOC。实验结果表明,与LSSVM相比,所提方法误差控制在1%以内,验证了所提方法的有效性。
The state-of-charge(SOC)estimation of a lithium-ion battery is very important with respect to a battery management system(BMS).It is difficult to ensure SOC estimation accuracy because it cannot be measured directly.To improve the SOC estimation accuracy,a least squares support vector machine(LSSVM)is used to establish a relation among voltage,current,and SOC.Further,an improved LSSVM method for SOC estimation is proposed to reduce the SOC estimation accuracy because of the changing voltage and current.The voltage measurement,current measurement,and SOC estimation values of the previous time are considered to be the feedback quantities of the model,and the voltage and current values of the present time are considered to be the input quantities that can be used to estimate the current SOC.The experimental results show that the error of the proposed method is less than 1%when compared with LSSVM,verifying the effectiveness of the proposed method.
作者
李嘉波
魏孟
李忠玉
叶敏
焦生杰
徐信芯
LI Jiabo;WEI Meng;LI Zhongyu;YE Min;JIAO Shengjie;XU Xinxin(Highway Maintenance Equipment National Engineering Laboratory,Changan University,Xi'an 710064,Shaanxi,China;Henan Gaoyuan Highway Maintenance Technology Co.Ltd.,Xinxiang 453000,Henan,China)
出处
《储能科学与技术》
CAS
CSCD
2020年第4期1200-1205,共6页
Energy Storage Science and Technology
基金
国家自然科学基金青年项目(51805041)
河南省交通运输厅科技计划项目(2019J3)。
