Title :
Discarding data to perform more accurate system identification
Author :
Carrette, P. ; Bastin, G. ; Genin, Y. ; Gevers, M.
Author_Institution :
CESAME, Louvain-la-Neuve, Belgium
Abstract :
Presents results concerning the parameter estimates obtained by prediction error methods in the case of system input signals that are insufficiently rich. Such input signals are typical of industrial measurements where occasional stepwise reference changes occur. Using singular value decomposition techniques, the authors propose a new data selection criterion that discards the poorly informative data in order to decrease the total mean square error (MSE) of the estimated parameters
Keywords :
parameter estimation; singular value decomposition; data selection criterion; industrial measurement; parameter estimates; prediction error methods; singular value decomposition techniques; stepwise reference changes; system identification; total mean square error; Colored noise; Delay; Matrix decomposition; Mean square error methods; Parameter estimation; Performance analysis; Predictive models; Singular value decomposition; System identification; Vectors;
Conference_Titel :
Decision and Control, 1995., Proceedings of the 34th IEEE Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-2685-7
DOI :
10.1109/CDC.1995.480605
