AN AUGMENTED UD IDENTIFICATION ALGORITHM

被引:26
作者
NIU, SH
FISHER, DG
XIAO, DY
机构
[1] UNIV ALBERTA,DEPT CHEM ENGN,EDMONTON T6G 2G6,ALBERTA,CANADA
[2] TSING HUA UNIV,DEPT AUTOMAT,BEIJING 100084,PEOPLES R CHINA
关键词
D O I
10.1080/00207179208934309
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
An augmented UD identification (AUDI) algorithm for system identification is developed by rearranging the data vectors and augmenting the covariance matrix of Bierman's UD factorization algorithm. The structure of the augmented information (covariance) matrix is particularly easy to interpret and it is shown that the AUDI algorithm is a direct extension of the familiar recursive least squares (RLS) algorithm. The proposed algorithm permits simultaneous identification of the model parameters plus loss functions for all orders from 1 to n at each time step with approximately the same calculation effort as nth order RLS. This provides a basis for simultaneous model order and parameter identification so that problems due to over- and under-estimation of model can be avoided. Based on its least-squares properties, numerical robustness, theoretical basis and the fact that it simultaneously estimates multiple models, the proposed AUDI algorithm is recommended for use in place of RLS and Bierman's UD factorization algorithms.
引用
收藏
页码:193 / 211
页数:19
相关论文
共 17 条
[1]   SELF-TUNING CONTROLLERS BASED ON POLE-ZERO PLACEMENT [J].
ASTROM, KJ ;
WITTENMARK, B .
IEE PROCEEDINGS-D CONTROL THEORY AND APPLICATIONS, 1980, 127 (03) :120-130
[2]  
Bierman G. J., 1977, FACTORIZATION METHOD
[3]  
Fang C.Z., 1988, PROCESS IDENTIFICATI
[4]  
FOLEY W, 1988, THESIS U ALBERTA CAN
[5]  
Isermann R, 1991, DIGITAL CONTROL SYST, V2
[6]  
JOHNSON CR, 1987, LECTURES ADAPTIVE PA
[7]  
Ljung L., 1999, SYSTEM IDENTIFICATIO
[8]  
Ljung L, 1983, THEORY PRACTICE RECU
[9]   ERROR PROPAGATION PROPERTIES OF RECURSIVE LEAST-SQUARES ADAPTATION ALGORITHMS [J].
LJUNG, S ;
LJUNG, L .
AUTOMATICA, 1985, 21 (02) :157-167
[10]  
LJUNG S, 1985, THESIS LINKOPING U S