Reformulation of parameter identification with unknown-but-bounded errors

✍ Scribed by Thierry Clement; Sylviane Gentil

• Publisher: Elsevier Science
• Year: 1988
• Tongue: English
• Weight: 802 KB
• Volume: 30
• Category: Article
• ISSN: 0378-4754
• DOI: 10.1016/0378-4754(88)90005-5

✦ Synopsis

In this paper a new formulation of the problem of identification of discrete-time linear models in the case of Unknown-But-Bounded errors is proposed. The bounds of the error at each sampling time are specified over a measurement noise rather than over an equation error, which is mainly motivated by experimental considerations. The method is particularly suitable for ARMAX models, as it accounts for the presence of uncertainties in the autoregressive terms.

It provides parameter uncertainty intervals using an off-line procedure. Simulations provide results that favourably compare with those of three classical identification methods (Simple-Least-Squares, Output-Error method, Maximum-Likelihood method) and those of the equation error based U.B.B. approach.