Two-stage iterative estimation algorithm for systems with colored noises using the data filtering

Author

Ding, Feng

Author_Institution

Key Lab. of Adv. Process Control for Light Ind., Jiangnan Univ., Wuxi, China

fYear

2012

fDate

23-25 May 2012

Firstpage

2087

Lastpage

2092

Abstract

By means of the data filtering technique, this presents a two-stage least squares based iterative algorithm for systems with colored noises, i.e., controlled autoregressive autoregressive moving average (CARARMA) systems. The key is to obtain two identification models by using the decomposition technique, one including the parameters of the system model, and the other including the parameters of the noise model. Then we use the least squares principle to interactively estimate the parameters of two submodels. The proposed algorithm has lower computational cost and is effective for estimating the parameters of the CARARMA systems.

Keywords

autoregressive moving average processes; filtering theory; iterative methods; least squares approximations; parameter estimation; CARARMA systems; colored noises; computational cost; controlled autoregressive autoregressive moving average system; data filtering technique; decomposition technique; identification models; noise model parameters; submodel parameter estimation; system model parameters; two-stage iterative estimation algorithm; two-stage least squares based iterative algorithm; Computational modeling; Least squares approximation; Mathematical model; Parameter estimation; Signal processing algorithms; Stochastic processes; Vectors; Iterative identification; Least squares; Parameter estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (CCDC), 2012 24th Chinese

Conference_Location

Taiyuan

Print_ISBN

978-1-4577-2073-4

Type

conf

DOI

10.1109/CCDC.2012.6244336

Filename

6244336