基于神经网络的蓄电池荷电状态估算  

Estimation of Battery State of Charge Based on Neural Network

作　　者：戴武昌[1] 王建国[1] 徐天锡[2] 

机构地区：[1]东北电力大学电气工程学院,吉林吉林132012 [2]国网淄博供电公司,山东淄博255000

出　　处：《东北电力大学学报》2016年第5期1-6,共6页Journal of Northeast Electric Power University

摘　　要：针对蓄电池荷电状态(SOC)的估算问题,将神经网络算法应用于此以估算蓄电池荷电状态。通过神经网络输入参数的选择建立了蓄电池SOC估算模型,并基于BP神经网络和RBF神经网络对蓄电池分别进行SOC的估算。结果表明:神经网络应用于蓄电池SOC估算所得的结果准确度高。通过比较可以得出,BP神经网络相对于RBF神经网络预测结果更准确,且具有相对较好的抗干扰能力,能够更加准确的估算出蓄电池SOC。For the estimation of the state of charge （SOC） of the battery, The neural network algorithm is ap- plied to estimate the residual capacity of the battery. In this paper, the selection of neural network input param- eters to establish a battery SOC estimation model, and based on the BP neural network and RBF neural network to estimate the SOC. The results show that the neural network is more accurate in estimating the SOC of the battery. By comparison,it can be known that the BP neural network is more accurate than the RBF neural net- work, and it has a relatively good anti-interference ability,can more accurately estimate the battery SOC.

关 键 词：荷电状态 神经网络 估算 BP神经网络 

分 类 号：TM912[电气工程—电力电子与电力传动]