摘要
本文将多层前向传递神经网络应用于非线性系统控制,通过对神经网络的训练,实现非线性系统的状态反馈控制。本文还介绍了用神经网络控制一类非线性系统的学习控制算法,该算法对对象的数学模型依赖程度较低,为非线性系统的学习控制提供了一种有效的研究方法。另外还给出了该算法应用于几个不同非线性对象的学习控制仿真结果。
A back-propagation neural network is applied to learning control of nonlinear control system, By. By training the neural networks using back-propagation algorithm, optimal state feedback control of nonlinear systems can be realized. This paper presents a novel learning control mechanism for a class of nonlinear systems, which does not depend the model of nonlinear control system. Simulation results show that the new scheme is efficient for large unknown nonlinearity.
出处
《自动化学报》
EI
CSCD
北大核心
1993年第3期307-315,共9页
Acta Automatica Sinica
关键词
神经网络
学习系统
非线性系统
Neural network
back-propagation
nonlinear control
learning control.
