• DocumentCode
    1710746
  • Title

    HV Power Equipment Diagnosis Based on Infrared Imaging Analyzing

  • Author

    Li, Baoshu ; Zhu, Xiaohui ; Zhao, Shutao ; Niu, Wendong

  • Author_Institution
    Key Lab. of Power Syst. Protection & Dynamic Security Monitoring & Control under Minist. of Educ., North China Electr. Power Univ., Baoding
  • fYear
    2006
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    Infrared imaging detection is an important method detecting the high-voltage(HV) power equipments running state. It is a kinds of non-contact on-line measurement that can determine the HV power equipment running state, find the fault position and predictive its future state. In the process of the infrared images analyzing, the computer captures remote equipments images, calculates images´ moment invariants as characteristic vector of recognition, recognizes power equipments by support vector machine (SVM). The system further analyzes images and find if images has convex hull, intensive stochastic noise, or false edges, sequently make a conclusion whether the running state of equipments is in order. Replace of scouting by people themselves, the use of image recognition in power system can timely find troubles and potential troubles of power equipments.
  • Keywords
    infrared imaging; power apparatus; power engineering computing; support vector machines; convex hull; fault position; high voltage power equipment diagnosis; image recognition; infrared imaging detection; intensive stochastic noise; noncontact online measurement; power system; support vector machine; Character recognition; Image analysis; Image recognition; Infrared detectors; Infrared imaging; Optical computing; Position measurement; Power measurement; Stochastic systems; Support vector machines; Neutral nets; Recognition; feature extraction; infrared image; power equipment;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Power System Technology, 2006. PowerCon 2006. International Conference on
  • Conference_Location
    Chongqing
  • Print_ISBN
    1-4244-0110-0
  • Electronic_ISBN
    1-4244-0111-9
  • Type

    conf

  • DOI
    10.1109/ICPST.2006.321512
  • Filename
    4116320