• DocumentCode
    2283039
  • Title

    Arithmetic and experiment research on ultrasonic detection of partial discharge for switchboard

  • Author

    Zhang, Rencheng ; Liu, Erli ; Xie, Li ; Yang, Jianhong

  • Author_Institution
    Coll. of Mech. Eng. & Autom., Huaqiao Univ., Xiamen, China
  • Volume
    4
  • fYear
    2011
  • fDate
    10-12 June 2011
  • Firstpage
    330
  • Lastpage
    334
  • Abstract
    Partial discharge detection for switchboard is effective method in insulation fault diagnosing. In this paper, different kinds of typical partial discharge for switchboard based on ultrasonic method is studied. Partial discharge detection system simulation model is established, including partial discharge model, measuring system for ultrasonic signals. Numerous figures of domain and frequency about ultrasonic signals are obtained and analyzed. Two ultrasonic bands of 20 k~40 kHz and 80 k~140 kHz for the partial discharge detection are chosen as characteristic parameters and input of support vector machine (SVM). SVM is used to recognize the discharge models and the recognition rate can reach up to 100%. The results prove that this method can recognize partial discharge effectively, which provides a new arithmetic for detecting ultrasonic signals.
  • Keywords
    partial discharges; power apparatus; power engineering computing; signal detection; support vector machines; ultrasonic applications; electric equipment; frequency 20 kHz to 40 kHz; frequency 80 kHz to 140 kHz; partial discharge detection; partial discharge model; support vector machine; switchboard; system simulation model; ultrasonic detection method; ultrasonic signal detection; ultrasonic signals; Acoustics; Kernel; Partial discharges; Pattern recognition; Support vector machines; Switches; Training; SVM; partial discharge; switchboard; ultrasonic;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science and Automation Engineering (CSAE), 2011 IEEE International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-8727-1
  • Type

    conf

  • DOI
    10.1109/CSAE.2011.5952862
  • Filename
    5952862