电动汽车锂电池SOC预测方法研究  

Research on Forcasting Method of Lithium Battery SOC

作　　者：李国康[1] 段玲玲[1] 王幼兰[2] 

机构地区：[1]沈阳理工大学机械工程学院,辽宁沈阳110159 [2]东风汽车有限公司,湖北十堰442001

出　　处：《沈阳理工大学学报》2011年第2期5-7,19,共4页Journal of Shenyang Ligong University

摘　　要：为有效地对电动汽车锂电池荷电分布状态(SOC)进行预测,在分析与电池剩余电量相关因数,对动力电池组进行不同工况充放电试验的基础上,建立电池组的神经网络仿真模型。提出基于BP神经网络的电池剩余电量预测模型,利用模型可逼近任何多输入输出参数函数的性能,系统通过样本训练达到较好的仿真结果。与实验结果对比,仿真结果与实验基本吻合,验证了该方法的正确性.In order to predict the state of charge（SOC） of batteries for electric vehicle（EV）,by analyzing the factors influencing the SOC of batteries,on the basis of charge and discharge test experiments of battery packs in different operating cases,an artificial neural network simulation model was set up.The author proposed a predictive SOC model based on BP neural network.The model can approach the non-linear function with many input/output parameters.By comparing simulation results with experimental results,simulation results are verified by experimental results,which can prove the correctness of the simulation method.

关 键 词：荷电分布状态 电动汽车 神经网络 锂电池 预测 

分 类 号：TM912[电气工程—电力电子与电力传动]