Model order selection criterion with application to physical systems

Rajamani Doraiswami*, Lahouari Cheded, Haris M. Khalid

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

In this paper, it is shown that poles of the discretetime equivalent of continuous system will lie in the right-half of the complex plane if the sampling rate is chosen to be more than twice the Nyquist rate. This new criterion allows for a quick and reliable separation between the system's poles and any extraneous poles emanating from a variety of artifacts such as high frequency noise and nonlinearities in the system. The system is identified for different model orders and only those for which the poles lie in the right-half plane are chosen. Then using a conventional scheme such as Akaike Information Criterion (AIC), the correct order is chosen from the selected model set. The proposed model order selection criterion has been evaluated on a physical system.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Automation Science and Engineering, CASE 2010
Pages393-398
Number of pages6
DOIs
StatePublished - 2010

Publication series

Name2010 IEEE International Conference on Automation Science and Engineering, CASE 2010

Keywords

  • Akaike information criterion
  • Identification
  • Model-based fault diagnosis
  • Model-order selection
  • Modelbased control design

ASJC Scopus subject areas

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Model order selection criterion with application to physical systems'. Together they form a unique fingerprint.

Cite this