Quantifying the error in estimated transfer functions with application to model order selection
- 1 July 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 37 (7) , 913-928
- https://doi.org/10.1109/9.148344
Abstract
Previous results on estimating errors or error bounds on identified transfer functions haverelied upon prior assumptions about the noise and the unmodelled dynamics. This prior informationtook the form of parameterized bounding functions or parameterized probability densityfunctions, in the time or frequency domain, with known parameters. Here we show that theparameters that quantify this prior information can themselves be estimated from the data usinga Maximum Likelihood technique. This...Keywords
This publication has 13 references indexed in Scilit:
- System identification using Laguerre modelsIEEE Transactions on Automatic Control, 1991
- Adaptive quantification of model uncertainties by rational approximationIEEE Transactions on Automatic Control, 1991
- Laguerre series approximation of infinite dimensional systemsAutomatica, 1990
- Approximation of stable systems by laguerre filtersAutomatica, 1990
- Deterministic adaptive control based on Laguerre series representationInternational Journal of Control, 1988
- Adaptive control via parameter set estimationInternational Journal of Adaptive Control and Signal Processing, 1988
- Identification of parameter bounds for ARMAX models from records with bounded noiseInternational Journal of Control, 1987
- Design variables for bias distribution in transfer function estimationIEEE Transactions on Automatic Control, 1986
- On the value of information in system identification—Bounded noise caseAutomatica, 1982
- System identification via membership set constraints with energy constrained noiseIEEE Transactions on Automatic Control, 1979