Wind turbine gearbox planet bearing failure prediction using vibration data

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a methodology for predicting planet bearing failures utilising vibration data acquired through accelerometers installed on the gearbox surface. The proposed methodology applies certain signal pre-processing techniques in order to remove the speed variations of the turbine and separate the stochastic bearing components from the deterministic gear ones. Then, spectral kurtosis is used to enhance the impulsiveness of the bearing fault signatures and envelope analysis is used to demodulate the signal. Features are extracted from the envelope spectrum and are used as an input to a classification model. The classification labelling is performed based on the time before failure. The methodology is tested on real offshore wind turbine vibration data collected at various times before failure. The performance of the classifier is assessed using k-fold cross validation. The results are compared with methods of classic envelope analysis that uses a constant demodulation band.
LanguageEnglish
Article number012016
Number of pages10
JournalJournal of Physics: Conference Series
Volume1104
Early online date6 Nov 2018
DOIs
Publication statusE-pub ahead of print - 6 Nov 2018

Fingerprint

transmissions (machine elements)
wind turbines
planets
envelopes
methodology
vibration
predictions
kurtosis
demodulation
turbines
accelerometers
preprocessing
classifiers
marking
signatures

Keywords

  • wind turbines
  • planetary gearboxes
  • wind power
  • reliability and maintenance modelling
  • vibration signals

Cite this

@article{efc31c2186154cf39e33aa6a797af147,
title = "Wind turbine gearbox planet bearing failure prediction using vibration data",
abstract = "This paper presents a methodology for predicting planet bearing failures utilising vibration data acquired through accelerometers installed on the gearbox surface. The proposed methodology applies certain signal pre-processing techniques in order to remove the speed variations of the turbine and separate the stochastic bearing components from the deterministic gear ones. Then, spectral kurtosis is used to enhance the impulsiveness of the bearing fault signatures and envelope analysis is used to demodulate the signal. Features are extracted from the envelope spectrum and are used as an input to a classification model. The classification labelling is performed based on the time before failure. The methodology is tested on real offshore wind turbine vibration data collected at various times before failure. The performance of the classifier is assessed using k-fold cross validation. The results are compared with methods of classic envelope analysis that uses a constant demodulation band.",
keywords = "wind turbines, planetary gearboxes, wind power, reliability and maintenance modelling, vibration signals",
author = "S Koukoura and J Carroll and A McDonald and S Weiss",
year = "2018",
month = "11",
day = "6",
doi = "10.1088/1742-6596/1104/1/012016",
language = "English",
volume = "1104",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",

}

TY - JOUR

T1 - Wind turbine gearbox planet bearing failure prediction using vibration data

AU - Koukoura, S

AU - Carroll, J

AU - McDonald, A

AU - Weiss, S

PY - 2018/11/6

Y1 - 2018/11/6

N2 - This paper presents a methodology for predicting planet bearing failures utilising vibration data acquired through accelerometers installed on the gearbox surface. The proposed methodology applies certain signal pre-processing techniques in order to remove the speed variations of the turbine and separate the stochastic bearing components from the deterministic gear ones. Then, spectral kurtosis is used to enhance the impulsiveness of the bearing fault signatures and envelope analysis is used to demodulate the signal. Features are extracted from the envelope spectrum and are used as an input to a classification model. The classification labelling is performed based on the time before failure. The methodology is tested on real offshore wind turbine vibration data collected at various times before failure. The performance of the classifier is assessed using k-fold cross validation. The results are compared with methods of classic envelope analysis that uses a constant demodulation band.

AB - This paper presents a methodology for predicting planet bearing failures utilising vibration data acquired through accelerometers installed on the gearbox surface. The proposed methodology applies certain signal pre-processing techniques in order to remove the speed variations of the turbine and separate the stochastic bearing components from the deterministic gear ones. Then, spectral kurtosis is used to enhance the impulsiveness of the bearing fault signatures and envelope analysis is used to demodulate the signal. Features are extracted from the envelope spectrum and are used as an input to a classification model. The classification labelling is performed based on the time before failure. The methodology is tested on real offshore wind turbine vibration data collected at various times before failure. The performance of the classifier is assessed using k-fold cross validation. The results are compared with methods of classic envelope analysis that uses a constant demodulation band.

KW - wind turbines

KW - planetary gearboxes

KW - wind power

KW - reliability and maintenance modelling

KW - vibration signals

U2 - 10.1088/1742-6596/1104/1/012016

DO - 10.1088/1742-6596/1104/1/012016

M3 - Article

VL - 1104

JO - Journal of Physics: Conference Series

T2 - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

M1 - 012016

ER -