基于混沌免疫网络的镍氢电池建模研究

摘要

Corresponding to modeling of Ni- MH Battery pack used in electric vehicle, computational algorithm is used to train RBF network to model the Ni -MH battery. In this paper, RBF network centre is identified by the artificial immune data clustering method. Parallel chaos immune evolutionary programming (PCIEP) is used to train RBF network, and then RBFNN training steps is designed. Finally, under the state of constant current discharging and FUDS discharging, validity of the battery model is verified.%针对电动汽车用镍氢电池组,提出利用计算智能算法训练的RBF网络实现电池组建模;首先采用免疫聚类的方法,通过对样本径基进行成分提取,并与并行免疫进化规划(PCEIP)相结合,形成一种更有效的RBF网络构造策略,然后基于PCIEP设计了改进的RBF网络的训练步骤;最后,在镍氢电池恒流放电和变功率放电工况下,以改进的RBF网络实现镍氢电池建模,验证建模的精度.