Model reductions of high-order estimated models: the asymptotic ML approach
1989 (English)In: International Journal of Control, ISSN 0020-7179, E-ISSN 1366-5820, Vol. 49, no 1, 169-192 p.Article in journal (Refereed) Published
The reduction of order of high-order models obtained from an identification experiment is discussed from a statistical point of view. The asymptotic maximum likelihood (ML) approach is defined to reduce the order of an estimated model. This approach considers the maximum likelihood criterion given the asymptotic statistics of the estimated model, and corresponds to frequency weighted L2-norm model reduction. By using the insight from the asymptotic ML approach, an identification algorithm is proposed based on a high-order ARX estimate and model reduction via a frequency weighted balanced realization. The advantage of this algorithm is that iterative minimization methods are not required to find the estimate.
Place, publisher, year, edition, pages
1989. Vol. 49, no 1, 169-192 p.
Statistical Methods--Estimation, High-Order Models, Identification Algorithm, Maximum Likelihood, Model Reductions, Control Systems
IdentifiersURN: urn:nbn:se:kth:diva-55453DOI: 10.1080/00207178908559628ISI: A1989T275500014OAI: oai:DiVA.org:kth-55453DiVA: diva2:471558
QC 201201042012-01-022012-01-022013-09-05Bibliographically approved