Title :
On the use of compensated total least squares in system identification
Author :
Vandersteen, Gerd
Author_Institution :
Vrije Univ., Brussels, Belgium
Abstract :
A bias compensated total least squares estimator is proposed for models linear-in-the-parameters and nonlinear in the perturbed input and output signals. The estimates are obtained using a non-iterative and numerically stable method, strong consistency of both generalized and compensated total least squares estimates are proven. Theoretical properties are confirmed by simulation
Keywords :
compensation; least squares approximations; matrix algebra; nonlinear systems; parameter estimation; stochastic processes; compensated total least squares; least squares estimates; matrix algebra; nonlinear systems; parameter estimation; stochastic process; strong consistency; system identification; Additive noise; Covariance matrix; Ear; Least squares approximation; Least squares methods; Maximum likelihood estimation; OWL; Polynomials; Stochastic processes; System identification;
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.1995.480403
