Advertisement

Implementation of Automatic Failure Diagnosis for Wind Turbine Monitoring System Based on Neural Network

  • Ming-Shou An
  • Sang-June Park
  • Jin-Sup Shin
  • Hye-Youn Lim
  • Dae-Seong Kang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 240)

Abstract

The global action began to resolve the problem of global warming. Thus, the wind power has been emerged as an alternative energy of existing fossil fuel energy. The existing wind power has limitation of location requirements and noise problems. In case of Korea, the existing wind power has difficulties on limitation of location requirements and the noise problems. The wind power turbine requires bigger capacity to ensure affordability in the market. Therefore, expansion into sea is necessary. But due to the constrained access environment by locating sea, the additional costs are occurred by secondary damage. In this paper, we suggest automatic fault diagnosis system based on CMS (Condition Monitoring System) using neural network and wavelet transform to ensure reliability. In this experiment, the stator current of induction motor was used as the input signal. Because there was constraint about signal analysis of large wind turbine. And failure of the wind turbine is determined through signal analysis based wavelet transform. Also, we propose improved automatic monitoring system through neural network of classified normal and error signal.

Keywords

Wavelet transform Neural network Automatic failure diagnosis CMS Wind turbine monitoring system 

Notes

Acknowledgments

This work was supported by the Human Resources Development of the Korea Institute of Energy Technology Evaluation and planning (KETEP) grant funded by the Ministry of knowledge Economy, Republic of Korea (No. 20114010203060).

References

  1. 1.
    Robi P The wavelet tutorial-fundamental concepts and an overview of the wavelet theory, 2nd editionGoogle Scholar
  2. 2.
    Park JY (2012) Development of wind power integrated condition monitoring system, Korea Electrical Contractors Association, pp 56–63, Feb 2012Google Scholar
  3. 3.
    Kim CH, Kim H, Ko YH, Byun SH, Aggarwal RK, Allan TJ (2002) A novel fault-detection technique of high-impedance arcing faults in transmission lines using the wavelet transform. IEEE Trans Power Deliv 17(4):921–929Google Scholar
  4. 4.
    Mallat S (1991) Zero crossings of a wavelet transform. IEEE Trans Inf Theory 37(4):1019–1033CrossRefMathSciNetGoogle Scholar
  5. 5.
    Wenxian Y, Tavner PJ, Michael W (2008) Wind Turbine condition monitoring and fault diagnosis using both mechanical and electrical signatures. In: Proceedings of the 2008 IEEE/ASME international conference on advanced intelligent mechatronics, pp 1296–1301, July 2008Google Scholar
  6. 6.
    He Q, Du DM (2007) Fault diag -nosis of induction motor using neural networks. In: Proceedings of the 6th international conference on machine learning and cybernetics. vol 2, pp 1090–1095, Aug 2007Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht(Outside the USA) 2013

Authors and Affiliations

  • Ming-Shou An
    • 1
  • Sang-June Park
    • 1
  • Jin-Sup Shin
    • 1
  • Hye-Youn Lim
    • 1
  • Dae-Seong Kang
    • 1
  1. 1.Department of Electronics EngineeringDong-A UniversityBusanKorea

Personalised recommendations