网络控制系统的时延估计和自适应预测控制  

Time Delay Estimation and Adaptive Control of Networked Control Systems

作　　者：李春茂[1] 肖建[1] 张玥 

机构地区：[1]西南交通大学电气工程学院,四川成都610031

出　　处：《西南交通大学学报》2007年第2期175-180,共6页Journal of Southwest Jiaotong University

基　　金：国家自然科学基金资助项目(60674057);教育部博士点基金资助项目(20040613013)

摘　　要：提出了基于最小二乘支持向量机(LS-SVM)的网络时延预估网络控制系统(NCS)的自适应预测控制方法．先将网络时延转化为非线性时间序列,再用径向基函数(RBF)作为LS-SVM的核函数,建立NCS的时延预测模型．用通过该模型预测的时延设计自适应控预测制器,补偿和控制NCS的时延．仿真结果表明,该时延预测方法对NCS的随机时变时延有较高的预测精度,根据预测的时延设计的控制器能使系统的输出很好地跟踪期望的输出．A novel approach for predictive control of an NCS （networked control system ） was proposed. To derive the model for prediction of time delays in an NCS, the time delays were transformed into a nonlinear time series, and a RBF （radial basis function） was taken as the kernel function of LS-SVM （least square support vector machine）. An adaptive predictive control algorithm was designed according to the delays predicted with the model to compensate the time delays. Simulation results show that the proposed method has good performances in time delay prediction of the NCS, and the output of the controller designed based on the predicted time delay can trace the desired output precisely.

关 键 词：网络控制系统 最小二乘 支持向量机 时延估计 自适应控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]