• DocumentCode
    142234
  • Title

    Fault prediction of wind turbine by using the SVM method

  • Author

    Jun-Hyun Shin ; Yun-Seong Lee ; Jin-O Kim

  • Author_Institution
    Dept. of Electr. Eng., Hanyang Univ., Seoul, South Korea
  • Volume
    3
  • fYear
    2014
  • fDate
    26-28 April 2014
  • Firstpage
    1923
  • Lastpage
    1926
  • Abstract
    Wind power is one of the fastest growing renewable energy sources. Wind turbine blades and heights have been increased steadily in the last 10 years in order to increase the capacity of wind power generator. So, the amount of wind turbine energy is increased by increasing the capacity of wind turbine generator, but the preventive, corrective and replacement maintenance cost is increased by that´s reasons. Recently, Condition Monitoring System (CMS) can repair the fault and diagnose of wind turbine that introduce to solve these problems. However, these systems have a problem that cannot predict and diagnose of the wind turbine faults. In this paper, wind turbine fault prediction methodology is proposed by using the SVM method. In the case study, wind turbine fault and external environmental factors are analysed by using the SVM method.
  • Keywords
    condition monitoring; fault diagnosis; maintenance engineering; power engineering computing; support vector machines; wind turbines; CMS; SVM method; condition monitoring system; corrective maintenance cost; fault prediction; preventive maintenance cost; replacement maintenance cost; wind power generator; wind turbine blades; wind turbine energy; wind turbine fault prediction methodology; Environmental factors; Generators; Kernel; Maintenance engineering; Support vector machines; Temperature; Wind turbines; Fault; Maintenance planning; Support Vector Machine; Wind turbine;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Science, Electronics and Electrical Engineering (ISEEE), 2014 International Conference on
  • Conference_Location
    Sapporo
  • Print_ISBN
    978-1-4799-3196-5
  • Type

    conf

  • DOI
    10.1109/InfoSEEE.2014.6946258
  • Filename
    6946258