摘要
针对一类非线性动态系统,提出了一种新的基于多层神经网络的自适应预测器,并对基于神经网络的预测机理进行了分析。该预测器由两个同构的多层神经网络实现,其中一个称为学习网络(LN),另一个称为预测网络(PN)。彷真结果表明,速种基于多层神经网络的预测嚣对于恒定参数的非线性系统是有效的,从而为解决非线性系统预测问题提供了一条可行的途径。
This paper develops a novel multilayer neural networks based on adaptive prediction technique for a class of nonlinear dynamical systems, and the prediction mechanism is analyzed . Two isomorphic multilayer nets are used together to implement the proposed predictor. One is called learning network while the other is called prediction network. Simulation results show that this neural nets based on adaptive predictor is applicable for a class of nonlinear systems with constant parameters, which may involve a large time delay and stochastic disturbances, so that it provides a new way to deal with nonlinear prediction problems.
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
1992年第3期247-252,共6页
Journal of University of Electronic Science and Technology of China
基金
国家教委优秀青年教师基金
关键词
神经网络
非线性系统
系统仿真
multilayer neural networks
nonlinear systems
adaptive prediction
isomorphic networks
system simulation
