SOC estimation of lithium-ion power battery for HEV based on advanced wavelet neural network

基于先进小波神经网络的HEV动力锂离子电池SOC估计(英文)

In order to improve the estimation accuracy of the battery＇s state of charge（SOC） for the hybrid electric vehicle（HEV）,the SOC estimation algorithm based on advanced wavelet neural network（WNN） is presented.Based on advanced WNN,the SOC estimation model of a lithium-ion power battery for the HEV is first established.Then,the convergence of the advanced WNN algorithm is proved by mathematical deduction.Finally,using an adequate data sample of various charging and discharging of HEV batteries,the neural network is trained.The simulation results indicate that the proposed algorithm can effectively decrease the estimation errors of the lithium-ion power battery SOC from the range of ±8% to ±1.5%,compared with the traditional SOC estimation methods.

为了提高混合动力汽车(HEV)电池荷电状态(SOC)的估计精度,提出了一种基于先进小波神经网络的HEV动力电池SOC估计算法.首先,建立了基于先进小波神经网络的电池SOC估计模型.然后,通过数学推导证明了先进小波神经网络的收敛性.最后,利用大量HEV动力电池在行驶过程中充放电的数据样本,对神经网络进行网络训练.仿真结果表明,所提出的估计算法与传统SOC估计算法相比,提高了电池SOC的估计精度,有效地将估计误差从±8%减小到±1.5%.