Asymptotic variance expressions for closed-loop identification英语教案.pdfVIP

Automatica 37 (2001) 781}786 Technical Communique Asymptotic variance expressions for closed-loop identication Michel Gevers , Lennart Ljung , Paul Van den Hof * CESAME, BaL timent Euler, Louvain University, B-1348 Louvain-la-Neuve, Belgium Department of Electrical Engineering, Linko(ping Uni versity, S-581 83 Linko(ping, Sweden Signals, Systems and Control Group, Department of A lied Physics, Delft University of Technology, Lorentzweg 1, 2628 CJ Delft, Netherlands Received 12 May 2000; received in revised form 15 November 2000 Abstract Asymptotic variance expressions are analyzed for models that are identied on the basis of closed-loop data. The considered methods comprise the classical direct method, as well as the more recently developed indirect methods, employing coprime factorized models, dual Youla/Kucera parametrizations and the two-stage approach. The variance expressions are compared with the open-loop situation, and evaluated in terms of their relevance for subsequent model-based control design. 2001 Elsevier Science Ltd. All rights reserved. Keywords: System identication; Closed-loop identication; Asymptotic variance expressions, Prediction error methods; Model-based control design 1. Introduction Hof Schrama, 1995). Later it has been shown in Hjal- marsson, Gevers, and De Bruyne (1996) that, for a When identifying dynamic models for th