Title :
Identification of errors-in-variables model with observation outlier based on MCD
Author_Institution :
Dept. of Appl. Math. & Phys., Kyoto Univ., Kyoto, Japan
Abstract :
In this paper, we develop a subspace system identification algorithm for the Errors-In-Variables (EIV) model subject to observation noise with outliers. To this end, we proposed the random search algorithm in order to solve the Minimum-Covariance-Determinant (MCD) problem. By using the MCD, we identify and delete the outliers, and then we apply the classical EIV subspace system identification algorithms to get state space model. In addition, we show that the problem of detecting the outliers in the closed loop systems is especial case of the EIV model. The propose algorithm has been applied to heat exchanger data.
Keywords :
closed loop systems; identification; observers; search problems; closed loop systems; errors-in-variables model identification; minimum covariance determinant problem; observation outliers; random search algorithm; Closed loop systems; Computational modeling; Covariance matrix; Data models; Linear regression; White noise; Minimum-Covariance-Determinant; Subspace system identification; errors-in-variables model; outliers; random search algorithm;
Conference_Titel :
GCC Conference (GCC), 2006 IEEE
Conference_Location :
Manama
Print_ISBN :
978-0-7803-9590-9
Electronic_ISBN :
978-0-7803-9591-6
DOI :
10.1109/IEEEGCC.2006.5686225
