eprintid: 566
rev_number: 8
eprint_status: archive
userid: 7
dir: disk0/00/00/05/66
datestamp: 2011-07-27 08:53:49
lastmod: 2011-08-04 07:29:08
status_changed: 2011-07-27 08:53:49
type: book_section
metadata_visibility: show
contact_email: alberto.bemporad@imtlucca.it
item_issues_count: 0
creators_name: Bemporad, Alberto
creators_name: Garulli, Andrea
creators_name: Paoletti, Simone
creators_name: Vicino, Antonio
creators_id: alberto.bemporad@imtlucca.it
creators_id: 
creators_id: 
creators_id: 
title: Data classification and parameter estimation for the identification of piecewise affine models
ispublished: pub
subjects: QA
subjects: TA
divisions: CSA
full_text_status: none
keywords: data classification; greedy algorithm; identification; multiclass linear separation technique; nonlinear dynamic system; parameter estimation; piece wise affine auto regressive exogenous model; autoregressive processes; greedy algorithms; nonlinear dynamical systems; parameter estimation; pattern classification; piecewise constant techniques
abstract: This paper proposes a three-stage procedure for parametric identification of piece wise affine auto regressive exogenous (PWARX) models. The first stage simultaneously classifies the data points and estimates the number of submodels and the corresponding parameters by solving the MIN PFS problem (partition into a minimum number of feasible subsystems) for a set of linear complementary inequalities derived from input-output data. Then, a refinement procedure reduces misclassifications and improves parameter estimates. The last stage determines a polyhedral partition of the regressor set via two-class or multi-class linear separation techniques. As a main feature, the algorithm imposes that the identification error is bounded by a fixed quantity δ. Such a bound is a useful tuning parameter to trade off between quality of fit and model complexity. Ideas for efficiently addressing the MIN PFS problem, and for improving data classification are also discussed in the paper. The performance of the proposed identification procedure is demonstrated on experimental data from an electronic component placement process in a pick-and-place machine.
date: 2004
date_type: published
publication: Proc. 43th IEEE Conf. on Decision and Control
volume: 43
publisher: IEEE
place_of_pub: 14-17 December 2004 
pagerange: 20-25
event_dates: Paradise Island, Bahamas
id_number: 10.1109/CDC.2004.1428600
refereed: TRUE
isbn: 0-7803-8682-5 
book_title: Decision and Control Conference
official_url: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1428600&isnumber=30836
citation:   Bemporad, Alberto and Garulli, Andrea and Paoletti, Simone and Vicino, Antonio  Data classification and parameter estimation for the identification of piecewise affine models.   In:  Decision and Control Conference.   IEEE, 14-17 December 2004 , pp. 20-25.  ISBN 0-7803-8682-5       (2004)