System parameter estimation with input/output noisy data and missing measurements

被引:38
作者
Chen, JM [1 ]
Chen, BS
机构
[1] St Johns & St Marys Inst Technol, Dept Elect Engn, Tamsui, Taiwan
[2] Natl Tsing Hua Univ, Dept Elect Engn, Hsinchu, Taiwan
关键词
input/output noisy data; l(p)-norm iterative algorithm; missing measurement; parameter estimation;
D O I
10.1109/78.845914
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, an investigation is undertaken to examine the parameter estimation problem of linear systems when some of the measurements are unavalaible (i.e,, missing data) and the probability of occurrence of missing data is unknown a priori. The system input and output data are also assumed to be corrupted by measurement noise, and the knowledge of noise distribution is unknown. Under the unknown noise distribution and missing measurements, a consistent parameter estimation algortihm [which is based on an I, norm iterative estimation algorithm-iteratively reweighted least squares (IRLS)] is proposed to estimate the system parameters, We show that if the probability of missing measurement is less than one half, the parameter estimates via the proposed estimation algorithm will converge to the true parameters as the number of data tends to infinity. Finally, several simulation results are presented to illustrate the performance of the proposed l(p) norm iterative estimation algorithm. Simulation results indicate that under input/output missing data and noise environment, the proposed parameter estimation algorithm is an efficient approach toward the system parameter estimation problem.
引用
收藏
页码:1548 / 1558
页数:11
相关论文
共 20 条
[1]   AN ARMA ROBUST SYSTEM-IDENTIFICATION USING A GENERALIZED LP NORM ESTIMATION ALGORITHM [J].
CHEN, BS ;
CHEN, JM ;
SHERN, SC .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1994, 42 (05) :1063-1073
[2]   PARAMETER-ESTIMATION OF LINEAR-SYSTEMS WITH INPUT-OUTPUT NOISY DATA - A GENERALIZED LP NORM APPROACH [J].
CHEN, JM ;
CHEN, BS ;
CHANG, WS .
SIGNAL PROCESSING, 1994, 37 (03) :345-356
[3]   IDENTIFICATION OF LINEAR-SYSTEMS WITH INPUT AND OUTPUT NOISE - THE KOOPMANS-LEVIN METHOD [J].
FERNANDO, KV ;
NICHOLSON, H .
IEE PROCEEDINGS-D CONTROL THEORY AND APPLICATIONS, 1985, 132 (01) :30-36
[4]   PROPERTIES OF SOME ESTIMATORS FOR THE ERRORS-IN-VARIABLES MODEL [J].
FULLER, WA .
ANNALS OF STATISTICS, 1980, 8 (02) :407-422
[5]   LEAST ABSOLUTE VALUES ESTIMATION - INTRODUCTION [J].
GENTLE, JE .
COMMUNICATIONS IN STATISTICS PART B-SIMULATION AND COMPUTATION, 1977, 6 (04) :313-328
[6]   NONLINEAR LP-NORM ESTIMATION .2. THE ASYMPTOTIC-DISTRIBUTION OF THE EXPONENT, P, AS A FUNCTION OF THE SAMPLE KURTOSIS [J].
GONIN, R ;
MONEY, AH .
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 1985, 14 (04) :841-849
[7]   1972 WALD LECTURE - ROBUST STATISTICS - REVIEW [J].
HUBER, PJ .
ANNALS OF MATHEMATICAL STATISTICS, 1972, 43 (04) :1041-&
[8]   MAXIMUM-LIKELIHOOD FITTING OF ARMA MODELS TO TIME-SERIES WITH MISSING OBSERVATIONS [J].
JONES, RH .
TECHNOMETRICS, 1980, 22 (03) :389-395
[9]  
MILOSAVLJEVIC M, 1996, P IEEE TENCON DIG SI, P200
[10]   THE LINEAR-REGRESSION MODEL - LP NORM ESTIMATION AND THE CHOICE OF P [J].
MONEY, AH ;
AFFLECKGRAVES, JF ;
HART, ML ;
BARR, GDI .
COMMUNICATIONS IN STATISTICS PART B-SIMULATION AND COMPUTATION, 1982, 11 (01) :89-109