首页 | 本学科首页   官方微博 | 高级检索  
     

基于支持向量机N4SID辨识模型的非线性预测控制
引用本文:向立志,史运涛,高东杰.基于支持向量机N4SID辨识模型的非线性预测控制[J].控制与决策,2007,22(5):549-553.
作者姓名:向立志  史运涛  高东杰
作者单位:中国科学院,自动化研究所综合自动化工程研究中心,北京,100080
基金项目:中科院知识创新工程重大项目(KGCX-SW-15).
摘    要:针对工业控制领域中非线性系统的模型辨识与预测控制问题,采用最小二乘支持向量机回归方法构造非线性函数,运用状态子空间(N4SID)模型辨识方法辨识非线性状态空间模型.在此基础上建立非线性预测控制器,利用拟牛顿算法进行非线性预测控制律的求解,从而实现了一种新的基于支持向量机N4SID辨识模型的非线性预测控制算法.仿真实验验证了该算法的有效性和可行性.

关 键 词:最小二乘支持向量机  N4SID模型辨识  非线性状态空间模型  非线性预测控制  拟牛顿算法
文章编号:1001-0920(2007)05-0549-05
收稿时间:2006-01-10
修稿时间:2006-03-31

Nonlinear model predictive control based on N4SID model identification using support vector machines
XIANG Li-zhi,SHI Yun-tao,GAO Dong-jie.Nonlinear model predictive control based on N4SID model identification using support vector machines[J].Control and Decision,2007,22(5):549-553.
Authors:XIANG Li-zhi  SHI Yun-tao  GAO Dong-jie
Affiliation:1. Engineering Research Center of Integrated Automation Technology, Institute of Automation, Chinese Academy of Science, Beijing 100080, China
Abstract:To the problems of the model identification and predictive control of nonlinear systems in the domain of industry control,a nonlinear model predictive control algorithm is presented.The nonlinear function is constructed by least squares support vector machines regression.A numerical algorithm for subspace state space system identification is utilized to identify a nonlinear stat-space model,which is used to construct a nonlinear model predictive controller.In deriving the control law,a quasi-Newton algorithm is applied to implement the nonlinear model predictive control(NMPC) algorithm.The simulation result shows the validity and feasibility of the NMPC algorithm.
Keywords:Least square support vector machines  N4SID identification  Nonlinear state space model  Nonlinear predictive control  Quasi-Newton algorithm
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《控制与决策》浏览原始摘要信息
点击此处可从《控制与决策》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号