Fault diagnosis based on black-box models with application to a liquid-level system

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

6 Citations (Scopus)

Abstract

This paper proposes an on-line robust approach to fault detection and isolation (FDI) of dynamic systems. This FDI approach is based on black-box models: artificial neural networks (ANNs) and the autoregressive with exogenous input (ARX) models. ANNs are used as observers and pattern classifiers, and adaptive ARX models are used as observers. The generalized likelihood ratio (GLR) algorithm is used for change detection. Process faults are considered, and the robust FDI problem is also addressed. The approach is applied to a laboratory set-up tank system under closed-loop control.

Original languageEnglish
Title of host publicationETFA 2003
Subtitle of host publication2003 IEEE Conference on Emerging Technologies and Factory Automation : proceedings : September 16-19, 2003, Lisbon, Portugal
Place of PublicationPiscataway
PublisherIEEE
Pages739-746
Number of pages8
Volume2
ISBN (Print)0-7803-7937-3
DOIs
Publication statusPublished - 2003
Event2003 IEEE Conference on Emerging Technologies and Factory Automation, ETFA 2003 - Lisbon, Portugal
Duration: 16 Sep 200319 Sep 2003

Publication series

NameIEEE International Conference on Emerging Technologies and Factory Automation, ETFA
ISSN (Print)1946-0740

Conference

Conference2003 IEEE Conference on Emerging Technologies and Factory Automation, ETFA 2003
CountryPortugal
CityLisbon
Period16/09/0319/09/03

Keywords

  • Fault diagnosis
  • Fault detection
  • Neural networks
  • Robustness
  • Mathematical model
  • Power system modeling
  • Automatic control
  • Control systems
  • Manufacturing automation
  • Isolation technology

Fingerprint

Dive into the research topics of 'Fault diagnosis based on black-box models with application to a liquid-level system'. Together they form a unique fingerprint.

Cite this