Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (16): 150-152.DOI: 10.3778/j.issn.1002-8331.2010.16.044

• 数据库、信号与信息处理 • Previous Articles     Next Articles

Novel approach to parameter estimation for linear system

YANG Wei-feng,ZENG Fang-ling   

  1. Key Laboratory of Electronic Restriction,Anhui Province,Electronic Engineering Institute,PLA,Hefei 230037,China
  • Received:2008-11-24 Revised:2009-02-16 Online:2010-06-01 Published:2010-06-01
  • Contact: YANG Wei-feng



  1. 解放军电子工程学院 安徽省电子制约技术重点实验室,合肥 230037
  • 通讯作者: 杨卫锋

Abstract: The reasons why interval analysis is used in parameter estimation are discussed,then the interval algorithm is presented for parameter estimation of a linear system in the Unknown-But-Bounded(UBB) error context.The basic contents of the Matlab toolbox—INTLAB are introduced,and the INTLAB is applied to the numerical example which based on the presented algorithm.The simulation results show the effectiveness and feasibility of the algorithm compared with Fogel’s algorithm and the least squares algorithm.

Key words: interval analysis, AR model, parameter estimation, Unknown-But-Bounded(UBB), INTLAB

摘要: 分析了使用区间分析进行参数估计的原因,由此在未知但有界(UBB)误差假设下,提出了线性系统模型参数估计的区间分析方法,同时,对Matlab区间算法工具箱INTLAB进行了简介,并将INTLAB应用于使用所提算法的算例中。通过数值算例,将此算法与Fogel椭球算法和最小二乘算法进行了比较,算例结果表明了所提算法的有效性和可行性。

关键词: 区间分析, AR模型, 参数估计, 未知但有界, INTLAB工具箱

CLC Number: