摘要
提出一种基于多层递归神经网络的自适应控制离散时间系统的方法．使用多层递归神经网络及新的动态ＢＰ算法（ＤＢＰ）描述未知系统的输入／输出关系．基于此神经网络模型，提出一种自适应控制方案，并对该方案的闭环稳定性进行了分析．
In this paper,an adaptive control method for nonlinear systems using a multilayered recurrent neural network is proposed.The multilayer recurrent neural network and new dynamic back propagation (DBP) algorithm are used to approximate the unknown nonlinear input output relationship.Based on the dynamic neural network model,an adaptive control scheme is proposed and the close loop stability of the system is analysed.
出处
《天津大学学报》
EI
CAS
CSCD
1998年第6期730-736,共7页
Journal of Tianjin University(Science and Technology)
关键词
神经网络
自适应控制
稳定性
DBP算法
multilayer recurrent neural network,dynamic BP algorithm (DBP),adaptive control,stability
