Title :
Recursive parameter estimation with bounded noises in the presence of missing outputs and outliers
Author :
Wen Xie ; Yuanqing Xia
Author_Institution :
Key Lab. of Intell. Control & Decision of Complex Syst., Beijing Inst. of Technol., Beijing, China
Abstract :
In this paper, the problem of parameter estimation is investigated for a class of discrete-time linear systems with missing outputs and outliers. It is assumed that the unknown parameters are constant and the evolution of the systems is subject to some unknown but bounded noises. To solve such a problem, a recursive algorithm based on set membership identification is proposed and employed. Besides, the data validation is processed and outliers are set aside. The effectiveness of the algorithm is verified by performing some numerical simulations.
Keywords :
discrete time systems; linear systems; recursive estimation; set theory; bounded noise; data validation; discrete-time linear system; recursive algorithm; recursive parameter estimation; set membership identification; Ellipsoids; Linear systems; Noise; Noise measurement; Numerical simulation; Parameter estimation; Vectors; Parameter estimation; bounded noise; missing output; outlier; set membership identification;
Conference_Titel :
Control Conference (CCC), 2014 33rd Chinese
Conference_Location :
Nanjing
DOI :
10.1109/ChiCC.2014.6895820
