Open AccessResidual signal feature extraction for gearbox planetary stage fault detection
Author(s) -
Skrimpas Georgios Alexandros,
Ursin Thomas,
Sweeney Christian,
Marhadi Kun,
Mijatovic Nenad,
Holboell Joachim
Publication year - 2017
Publication title -
wind energy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.743
H-Index - 92
eISSN - 1099-1824
pISSN - 1095-4244
DOI - 10.1002/we.2099
Subject(s) - residual , planet , bearing (navigation) , signal (programming language) , fault (geology) , feature extraction , fault detection and isolation , turbine , energy (signal processing) , resampling , frequency domain , process (computing) , engineering , computer science , algorithm , artificial intelligence , physics , geology , aerospace engineering , computer vision , seismology , actuator , programming language , quantum mechanics , astrophysics , operating system
Faults in planetary gears and related bearings, e.g. planet bearings and planet carrier bearings, pose inherent difficulties on their accurate and consistent detection associated mainly to the low energy in slow rotating stages and the operating complexity of planetary gearboxes. In this work, statistical features measuring the signal energy and Gaussianity are calculated from the residual signals between each pair from the first to the fifth tooth mesh frequency of the meshing process in a multi‐stage wind turbine gearbox. The suggested algorithm includes resampling from time to angular domain, identification of the expected spectral signature for proper residual signal calculation and filtering of any frequency component not related to the planetary stage. Two field cases of planet carrier bearing defect and planet wheel spalling are presented and discussed, showing the efficiency of the followed approach and the possibility of characterizing a fault as localized or distributed. Copyright © 2017 John Wiley & Sons, Ltd.