Multiple fault detection based on wavelet denoising: Application on wind turbine system

Abstract

This paper deals with an application of wavelets denoising for residual signal in a wind turbine system. We have utilized wavelet denoising to generate denoised residual signal and used it for detection. The objective of the experiment was to evaluate the performance of the wavelet denoising algorithm for the accuracy of fault detection results using a simple fixed threshold and to examine to what extent the results were influenced by different false alarms. Accuracy of fault detection results as related to the appearance of false alarms is also discussed in the paper.