Direct approaches to identification of continuous-time models from sampled data: what do they have to offer ?
with Hugues Garnier, Ph.D.
Visiting Professor, UCSD
Professor, University of Lorraine, France
February 22, 2013
10:30 am
GWC 465
abstract: The last decade has witnessed an increasing interest for direct identification methods of continuous-time models from sampled data. This talk will first give a review of the main aspects of the most efficient time-domain approaches including the iterative optimal instrumental variable method for identifying hybrid continuous-time Box-Jenkins transfer function models. Recent extensions to handle more complicated situations (closed-loop, LPV, non-uniformly sampled data) are briefly presented. The latest version of the CONTSID toolbox for Matlab which includes all the recent extensions is then described. The advantages and practical efficacy of these direct schemes to data-based continuous-time modelling are finally discussed and illustrated.
biosketch: Hugues Garnier received his Ph.D degree in 1995 from University of Lorraine, France, where he is a professor in Automatic Control. From Sept. 2003 to Aug. 2004, he visited the University of Newcastle, Australia. In 2006 and 2007, he held short visiting positions at different universities in Australia including the University of Newcastle, the Royal Melbourne Institute of Technology and the University of Technology in Sydney. His main research interest is related to data-based modelling of stochastic dynamical systems. This includes time series analysis and prediction, parameter estimation and system identification. He has been very active in the last decade to promote and develop new techniques for continuous-time model identification from sampled data. He is a member of the Editorial Board of International Journal of Control. He has been the (co)editor of two books (with Luiping Wang): ’Identification of Continuous-time Models from Sampled Data’, Springer Verlag, 2008 and ’System Identification, Environmetric Modelling and Control System Design’, Springer Verlag, 2012.
