ALGORITHMS FOR GLOBAL TOTAL LEAST-SQUARES MODELING OF FINITE MULTIVARIABLE TIME-SERIES

被引：21

作者：

ROORDA, B ^{[1
]}

机构：

[1] ERASMUS UNIV ROTTERDAM,INST ECONOMETR,3000 DR ROTTERDAM,NETHERLANDS

来源：

AUTOMATICA | 1995年 / 31卷 / 03期

关键词：

IDENTIFICATION LEAST SQUARES APPROXIMATIONS; LINEAR SYSTEMS; STATE SPACE METHODS; KALMAN FILTERS;

D O I：

10.1016/0005-1098(94)00114-X

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we present several algorithms related to the global total least squares (GTLS) modelling of multivariable time series observed over a finite time interval. A GTLS model is a linear, time-invariant finite-dimensional system with a behaviour that has minimal Frobenius distance to a given observation. The first algorithm determines this distance. We also give a recursive version of this, which is comparable to Kalman filtering. Necessary conditions for optimality are described in terms of state space representations. Further we present a Gauss-Newton algorithm for the construction of GTLS models. An example illustrates the results.

引用

页码：391 / 404

页数：14