• DocumentCode
    3261763
  • Title

    Support vector machines for fault detection

  • Author

    Batur, Celal ; Zhou, Ling ; Chan, Chien-Chung

  • Author_Institution
    Dept. of Mech. Eng., Akron Univ., OH, USA
  • Volume
    2
  • fYear
    2002
  • fDate
    10-13 Dec. 2002
  • Firstpage
    1355
  • Abstract
    Support vector machines (SVMs), based on Vapnik´s statistical learning theory is a new tool that can be used for fault detection and isolation in dynamic systems. This paper presents a new approach that combines the system identification technique and the SVM learning algorithm for fault detection and isolation in dynamic systems. A conventional heat exchanger dynamics is used to illustrate the technique.
  • Keywords
    fault location; heat exchangers; learning automata; statistical analysis; SVM learning algorithm; fault detection; fault isolation; heat exchanger dynamics; statistical learning theory; support vector machines; Condition monitoring; Fault detection; Fault diagnosis; Least squares methods; Machine learning; Statistical learning; Support vector machines; System identification; Technological innovation; Training data;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Decision and Control, 2002, Proceedings of the 41st IEEE Conference on
  • ISSN
    0191-2216
  • Print_ISBN
    0-7803-7516-5
  • Type

    conf

  • DOI
    10.1109/CDC.2002.1184704
  • Filename
    1184704