Title :
Improving RELS local convergence via long-range predictive identifiers
Author :
Chisci, L. ; Giarré, L. ; Mosca, E.
Author_Institution :
Dipartimento di Sistemi e Inf., Firenze Univ., Italy
Abstract :
A recursive autoregressive moving-average (ARMA) identifier based on multistep prediction error minimization is considered in order to sidestep the positive realness conditions of recursive extended least squares (RELS). For a single-step prediction horizon, the algorithm reduces to RELS while, as shown by local convergence analysis, it tends to be a local approximation of the recursive maximum likelihood (RML) algorithm as the prediction horizon increases
Keywords :
adaptive control; convergence of numerical methods; identification; predictive control; RELS local convergence; local approximation; long-range predictive identifiers; multistep prediction error minimization; recursive autoregressive moving-average; recursive extended least squares; recursive maximum likelihood; single-step prediction horizon; Algorithm design and analysis; Approximation algorithms; Convergence; Least squares approximation; Least squares methods; Maximum likelihood estimation; Parameter estimation; Polynomials; Prediction algorithms; Recursive estimation;
Conference_Titel :
Decision and Control, 1992., Proceedings of the 31st IEEE Conference on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-0872-7
DOI :
10.1109/CDC.1992.371678
