摘要
针对Elman动态递归神经网络的特点,在现有结构的基础上提出一种隐层包含径向基函数的混合Elman神经网络,给出了网络结构和训练算法,并将其应用于非线性自适应逆控制系统中。仿真实验表明该动态神经网络自适应性强,动态特性优异。此方法为实现非线性系统自适应逆控制提供了理想的途径。
Based on the properties of Elman dynamical recursive neural network,a hybrid Elman network containing radial basis function in its hidden layer is suggested,the structure of network and the learning method are given,then it is used in adaptive inverse control for nonlinear system.The simulation experiment shows that the network has higher control accuracy and adaptive learning ability.This method offers and ideal way of adaptive inverse control for nonlinear system.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2005年第z2期349-351,共3页
Chinese Journal of Scientific Instrument
关键词
ELMAN网络
径向基函数
自适应逆控制
Elman neural network Radial basis function Adaptive inverse control
