• DocumentCode
    694278
  • Title

    Fault classification on high voltage power lines using principal component analysis and feed-forward artificial neural networks

  • Author

    Govender, Poobalan ; Pillay, Narushan ; Moorgas, Kevin Emanuel

  • Author_Institution
    Dept. of Electron. Eng., Durban Univ. of Technol., Durban, South Africa
  • fYear
    2013
  • fDate
    10-13 Dec. 2013
  • Firstpage
    1550
  • Lastpage
    1554
  • Abstract
    Overhead high voltage power transmission lines are affected by various external factors that result in faults and power outages. Most faults on overhead high voltage power transmission lines are due to factors such a lightning, fire, birds, pollution and other faults. The managing utility has to take the appropriate mitigating action in order to reduce the recurrence of line faults. This is possible if the exact cause of the fault is known. This paper examines the impact of lightning, fire and birds on the power line and proposes a simple artificial neural network based system to identify the exact cause of a transmission line failure.
  • Keywords
    neural nets; power engineering computing; power overhead lines; principal component analysis; fault classification; feedforward artificial neural networks; high voltage power lines; overhead high voltage power transmission lines; principal component analysis; transmission line failure; Artificial neural networks; Birds; Circuit faults; Fires; Lightning; Power transmission lines; Principal component analysis; artificial neural network; classification; power line fault; principle component analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Industrial Engineering and Engineering Management (IEEM), 2013 IEEE International Conference on
  • Conference_Location
    Bangkok
  • Type

    conf

  • DOI
    10.1109/IEEM.2013.6962670
  • Filename
    6962670