An Enhanced Empirical Wavelet Transform for Features Extraction from Wind Turbine Condition Monitoring Signals

Abstract

Feature extraction from nonlinear and non-stationary (NNS) wind turbine (WT) condition monitoring (CM) signals is challenging. Previously, much effort has been spent to develop advanced signal processing techniques for dealing with CM signals of this kind. The Empirical Wavelet Transform (EWT) is one of the achievements attributed to these efforts. The EWT takes advantage of Empirical Mode Decomposition (EMD) in dealing with NNS signals but is superior to the EMD in mode decomposition and robustness against noise. However, the conventional EWT meets difficulty in properly segmenting the frequency spectrum of the signal, especially when lacking pre-knowledge of the signal. The inappropriate segmentation of the signal spectrum will inevitably lower the accuracy of the EWT result and thus raise the difficulty of WT CM. To address this issue, an enhanced EWT is proposed in this paper by developing a feasible and efficient spectrum segmentation method. The effectiveness of the proposed method has been verified by using the bearing and gearbox CM data that are open to the public for the purpose of research. The experiment has shown that, after adopting the proposed method, it becomes much easier and more reliable to segment the frequency spectrum of the signal. Moreover, benefitting from the correct segmentation of the signal spectrum, the fault-related features of the CM signals are presented more explicitly in the time-frequency map of the enhanced EWT, despite the considerable noise contained in the signal and the shortage of pre-knowledge about the machine being investigated.

Keywords

• wind turbine
• drive train
• condition monitoring
• empirical wavelet transform