• DocumentCode
    2877078
  • Title

    Sequential prognosis of multiple failures for hybrid systems based on dynamic fault isolation and computational intelligence

  • Author

    Yu, Ming ; Wang, Danwei ; Luo, Ming

  • Author_Institution
    Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
  • fYear
    2011
  • fDate
    7-10 Nov. 2011
  • Firstpage
    2417
  • Lastpage
    2422
  • Abstract
    This work addresses prognosis of multiple failures for hybrid system using a dynamic fault isolation scheme. Multiple incipient faults may happen simultaneously at certain mode in which not all the faults can be detected. Decision making based on only one observation of inconsistency is not reliable under this condition. In order to carry out prognosis, a dynamic fault isolation method is developed in which a waiting time is set to observe all inconsistencies caused by these faults. The prognosis based on dynamic fault isolation is realized by computational intelligence. Simulation results illustrate the effectiveness of the proposed method.
  • Keywords
    bond graphs; evolutionary computation; fault tolerance; manufacturing systems; computational intelligence; decision making; dynamic fault isolation scheme; failure sequential prognosis; hybrid system; incipient fault; industrial systems; Circuit faults; Degradation; Fault diagnosis; Junctions; Monitoring; Vectors; Vehicle dynamics;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    IECON 2011 - 37th Annual Conference on IEEE Industrial Electronics Society
  • Conference_Location
    Melbourne, VIC
  • ISSN
    1553-572X
  • Print_ISBN
    978-1-61284-969-0
  • Type

    conf

  • DOI
    10.1109/IECON.2011.6119688
  • Filename
    6119688