一种电动汽车电池SOC软测量方法研究  

Method for SOC soft measurement of battery for electric vehicles

作　　者：孙正凤[1] 苏磊[1] SUN Zheng-feng;SU Lei(School of Electronic and Electrical Engineering,Taizhou Institute of Sci.&Tech.,Nanjing University of Science&Technology, Taizhou Jiangsu 225300,China)

机构地区：[1]南京理工大学泰州科技学院电子电气工程学院,江苏泰州225300

出　　处：《电源技术》2018年第7期987-989,1088,共4页Chinese Journal of Power Sources

基　　金：国家自然科学基金(51377074);江苏省自然科学基金青年基金(BK20150246)

摘　　要：针对电动汽车电池荷电状态(state of charge,SOC)不可直接测量这一问题,引入基于减法聚类和自适应模糊神经网络的SOC软测量方法。首先,利用减法聚类确定自适应模糊神经网络的结构;然后,将反向传播算法与最小二乘算法混合使用,对网络的前件参数和结论参数分别进行优化,提高了参数的学习效率;最后,将神经网络自动生成的模糊隶属函数和规则集应用于电动汽车电池SOC的软测量中。在CYC-HWFET工况下,取电池的电压、电流和温度参数来实现SOC的软测量,仿真结果表明:基于减法聚类和自适应模糊神经网络方法的电动汽车电池SOC软测量模型精度较高,真实值与软测量值误差较小。Aiming at the problem that the state of charge(SOC)can not be directly measured,the SOC soft sensing method based on subtractive clustering and adaptive fuzzy neural network was introduced.Firstly,the structure of AFNN was decided by SC;secondly,by adopting the back-propagation algorithm and least square method respectively,the front and back parameters of AFNN were optimized,and the study efficiency of the parameters was raised;finally,the fuzzy membership functions and rules were used,which generated automatically by AFNN in the control of HES for HEV.Under the CYC-HWFET working conditions,the working voltages,currents and surface temperature of battery were used to predict the value of SOC.The results indicate that the prediction model possesses higher predicted accuracy,and the errors between the real value and the soft measurement value are small.

关 键 词：电动汽车 SOC 软测量 减法聚类 自适应模糊神经网络 

分 类 号：TM912.9[电气工程—电力电子与电力传动]