| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 718207 | IFAC Proceedings Volumes | 2009 | 6 Pages |
Abstract
The paper outlines the development of time variable parameter (TVP) estimation as an approach to modelling time varying dynamic systems. It then describes one of the latest methods for estimating time variable parameters in transfer function models and shows how it overcomes problems associated with earlier methods based on the least squares estimation of time variable parameters in the more restricted auto-regressive, exogenous variables (ARX) model. This ‘dynamic transfer function’ (DTF) estimation methodology is a combination of recursive-iterative instrumental variable filtering and fixed interval smoothing algorithms.
Related Topics
Physical Sciences and Engineering
Engineering
Computational Mechanics
