RBF Neural Network Control and Novel Smith Predictor for Networked Control Systems

This paper aims to the random and uncertain network delays, a novel approach is proposed that new Smith predictor combined with adaptive PID control with RBF neural network for networked control systems (NCS). This novel Smith predictor comes true to hide predictor models of the network delays into real network data transmission processes, therefore network delays donpsilat need to be measured, identified or estimated on-line. Based on CSMA/CD (Ethernet), the results of simulation show validity of this control scheme, and indicate that system has better dynamic performance and strong robustness.