Title :
Parameter estimation with missing input/output data
Author :
Fang, Huazhen ; Shi, Yang ; Wu, Jian
Author_Institution :
Dept. of Mech. Eng., Univ. of Saskatchewan, Saskatoon, SK, Canada
Abstract :
The problem of recursive parameter estimation with missing input/output data is studied in this paper. A fictitious measurement noise model is presented for missing data, and a noise-robust minimum component analysis based algorithm is developed to recursively estimate parameters from the new dasianoisypsila input/output data. Convergence properties of the proposed algorithm are analyzed. The simulation results verify the effectiveness of the proposed algorithm.
Keywords :
recursive estimation; statistical analysis; fictitious measurement noise model; noise-robust minimum component analysis based algorithm; recursive parameter estimation; Algorithm design and analysis; Control systems; Convergence; Maximum likelihood estimation; Noise measurement; Noise robustness; Parameter estimation; Recursive estimation; Signal processing algorithms; Spectral analysis;
Conference_Titel :
American Control Conference, 2009. ACC '09.
Conference_Location :
St. Louis, MO
Print_ISBN :
978-1-4244-4523-3
Electronic_ISBN :
0743-1619
DOI :
10.1109/ACC.2009.5160542
