Identification and Control of Multi-variables Discrete-time Input-affine Nonlinear System Based on Recurrent Neural Network

摘要

The architecture of identification and control of multi-variables discrete-time input-affine nonlinear system based on recurrent neural network is put forth. The system is identified using a three layers recurrent neural network. A model reference adaptive controller is presented. At last the closed loop system is globally exponentially stable is proven.