A Nonlinear Time Series Approach for Time Delay Estimation and Adaptive Control of Networked Control Systems

摘要

An LS-SVM (Least Square Support Vector Machines) based algorithm is introduced in this paper to estimate random communication time delay in Networked Control Systems (NCS).By modelling the time delay of NCS as a nonlinear time series, the algorithm updates the delay estimate using an online LS-SVM, and identifies plant parameters by a modified RLS. Through an adaptive algorithm based on muti-step regressive prediction, future control sequences are generated to compensate for the communication time delay when control signals are delayed or missed. To illustrate the improvement in control performance of the proposed approach, simulation results are presented, and show that the method is superior to the standard networked predictive control.