FRBF Neural Network and New Smith Predictor for Wireless Networked Control Systems
Wireless network delay is the main factor that deteriorates the performance of the wireless networked control systems (WNCS). In order to effectively restrain the impact of network delay, as well as controlled plant might be time-variant or nonlinear, a novel approach is proposed that new Smith predictor combined with fuzzy radial basis function neural network (FRBFNN) for the WNCS. Because new Smith predictor hides predictor model of the network delay into real network data transmission process, further the network delay no longer need to be measured, identified or estimated on-line. Simultaneously this new Smith predictor doesnt include the prediction model of the controlled plant, thus it doesnt need to know the exact mathematical model of the controlled plant beforehand. It is applicable to some occasions that network delay is random, time-variant or uncertain, larger than one, even tens of sampling periods, and there are some data dropouts in closed loop. Based on IEEE 802.15.4 (ZigBee), the results of simulation show that this approach is effective.
Fuzzy radial basis function neural network (FRBFNN) Wireless networked control systems (WNCS) Network delay Smith predictor
Feng Du Wencai Du
College of Information Sciences & Technology, Hainan University, Haikou 570228
国际会议
2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)
广西桂林
英文
3689-3694
2009-06-17（万方平台首次上网日期，不代表论文的发表时间）