用含动态隐层的前馈网辨识非线性系统

NONLINEAR SYSTEM IDENTIFICATION USING FEEDFORWARD NEURAL NETWORKS WITH RECURRENT HIDDEN LAYER

用含动态隐层的前馈网对非线性系统建立全局成立的输入输出模型，证明了这种辨识结构的可行性，网络学习算法为动态ＢＰ法．

This paper presents a feedforward neural network which contains a dynamic hidden layer (RHNN) for the modeling of a nonlinear system and the feasibility of this approach is proved. The learning algorithm is the dynamic BP. In the simulation a comparison between RHNN and RFNN for modeling a nonlinear system is made.