Open AccessApplication of the multi‐scale enveloping spectrogram to detect weak faults in a wind turbine gearbox
Author(s) -
Ma Zhiyong,
Teng Wei,
Liu Yibing,
Wang Dameng,
Kusiak Andrew
Publication year - 2017
Publication title -
iet renewable power generation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.005
H-Index - 76
eISSN - 1752-1424
pISSN - 1752-1416
DOI - 10.1049/iet-rpg.2016.0722
Subject(s) - spectrogram , turbine , fault (geology) , vibration , demodulation , wind power , envelope (radar) , signal (programming language) , condition monitoring , fault detection and isolation , scale (ratio) , computer science , engineering , acoustics , pattern recognition (psychology) , automotive engineering , speech recognition , artificial intelligence , geology , seismology , mechanical engineering , electrical engineering , physics , telecommunications , quantum mechanics , channel (broadcasting) , radar , actuator , programming language
The gearbox of a wind turbine involves multiple rotating components, each having a potential to be affected by a fault. Detecting weak faults of these components with traditional demodulation analysis is challenging. Multi‐scale enveloping spectrogram (MuSEnS) decomposes a vibration signal into different frequency bands while simultaneously generating the corresponding envelope spectra. In this study, a MuSEnS‐based diagnosis approach is applied to detect faults affecting the intermediate stage of a gearbox installed in an operating wind turbine. The MuSEnSs of 12 vibration channels have allowed to identify multiple fault features, including the weak fault of the big gear on the sun shaft. The effectiveness of the proposed fault diagnosis approach has been tested with industrial data and the faults themself have been confirmed with the disassembled gears.