Fuzzy RBF Neural Network Control and New Smith Predictor for Hybrid Networked Control Systems

Wired and wireless network delays highly degrade the control performance of hybrid networked control systems(HNCS). In order to effectively restrain impact of network delay for the HNCS, a novel approach is proposed that new Smith predictor combined with fuzzy radial basis function neural network (FRBFNN), and comes true delay compensations. Because new Smith predictor does not include network delay model, network delay is no need to be measured, identified or estimated on line. It is applicable to some occasions that network delays are random, time-variant and uncertain, and possibly large compared to one, even tens sampling periods. Based on IEEE 802.15.4 (ZigBee) and CSMA/AMP (CAN bus), and there are some data packet dropouts in the inner and outer closed loops, the results of simulation show validity of the control scheme, and indicate that system has better dynamic performance, robustness, self-adaptability and disturbance rejection ability.