Detection of wind turbine blades damage by spectrum-recognition using Gaussian wavelet-entropy

Authors:
C. S. Tsai;C. T. Hsieh;K. L. Lew
Affiliations:
Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C.;Department of Electrical Engineering, Kun Shan University, Tainan, Taiwan, R.O.C.;Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kuala Lumpur, Malaysia
Venue:
ASID'09 Proceedings of the 3rd international conference on Anti-Counterfeiting, security, and identification in communication
Year:
2009

Citing 6
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Entropy and information theory

Entropy and information theory
Ten lectures on wavelets

Ten lectures on wavelets
Signal and image processing with neural networks: a C++ sourcebook

Signal and image processing with neural networks: a C++ sourcebook
On the digital filter associated with Daubechies' wavelets

IEEE Transactions on Signal Processing
Quantization

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a complex continuous wavelet transform (CWT)-based entropy method is proposed to enhance the damage-detection capability of wind turbine blades. By embedding the time-frequency localization features in wavelets, wavelet entropy of acquired signals can be readily computed. This approach can form a quantitative index systematically to detect the damage of blades, anticipating formulating a forewarning mechanism for wind power system. Test results demonstrated the practicality and advantages of the method for the application considered.