System identification using Laguerre models
1991 (English)In: IEEE Transactions on Automatic Control, ISSN 0018-9286, E-ISSN 1558-2523, Vol. 36, no 5, 551-562 p.Article in journal (Refereed) Published
The traditional approach of expanding transfer functions and noise models in the delay operator to obtain linear-in-the-parameters predictor models leads to approximations of very high order in cases of rapid sampling and/or dispersion in time constants. By using prior information about the time constants of the system more appropriate expansions, related to Laguerre networks, are introduced and analyzed. It is shown that the model order can be reduced, compared to ARX (FIR, AR) modeling, by using Laguerre models. Furthermore, the numerical accuracy of the corresponding linear regression estimation problem is improved by a suitable choice of the Laguerre parameter. Consistency (error bounds), persistance of excitation conditions, and asymptotic statistical properties are investigated. This analysis is based on the result that the covariance matrix of the regression vector of a Laguerre model has a Toeplitz structure.
Place, publisher, year, edition, pages
1991. Vol. 36, no 5, 551-562 p.
Mathematical Techniques - Transfer Functions, Signal Filtering and Prediction, Statistical Methods - Regression Analysis, ARX Models, Laguerre Models, Linear Regression Models, Predictor Models, Control Systems, Predictive
IdentifiersURN: urn:nbn:se:kth:diva-55437DOI: 10.1109/9.76361ISI: A1991FH78200005OAI: oai:DiVA.org:kth-55437DiVA: diva2:471586
QC 201201042012-01-022012-01-022013-09-05Bibliographically approved