Networked control systems with RBF neural network control and new Smith predictor

This paper aims to random, time-variant and uncertain network delay in the networked control systems (NCS), a new approach is proposed that radial basis function neural network (RBFNN) control combined with new Smith predictor for the NCS. This approach can identify the controlled plant and adaptively adjusts weights of the controller. Because new Smith predictor does not include network delay models, therefore network delays no longer need to be measured, identified or estimated on line. Simultaneously, this new Smith predictor doesn´t include the prediction model of the controlled plant, thus it doesn´t need to know the exact mathematical model of the controlled plant beforehand. Thereby it is applicable to some occasions that network delays are the random, time-variant or uncertain. Based on CSMA/AMP (CAN bus), the results of the simulation show the validity of the control scheme.