To reduce wind turbine operations and maintenance costs, we present a machine learning framework for early damage detection in gearboxes based on the cyclostationary and kurtogram analysis of sensor data. The application focus is fault diagnostics in gearboxes under varying load conditions, particularly turbulent wind. Faults in the gearbox rotating components can leave their signatures in vibrations signals measured by accelerometers. We analyze data stemming from a simulated vibration response of a 5 MW multibody wind turbine model in a healthy and damaged scenarios and under different wind conditions. With cyclostationary and kurtogram analysis applied on acquired sensor data, we generate two types of 2D maps that highlight signatures related to the fault damage. Using these maps, convolutional neural networks are trained to identify faults, including those of small magnitude, in test data with a high accuracy. Benchmark test cases inspired by an NREL study are tested and faults successfully detected.
AntoniJ (2006) The spectral kurtosis: A useful tool for characterising non-stationary signals. Mechanical Systems and Signal Processing20(2): 282–307.
2.
AntoniJ (2007a) Cyclic spectral analysis in practice. Mechanical Systems and Signal Processing21(2): 597–630.
3.
AntoniJ (2007b) Fast computation of the kurtogram for the detection of transient faults. Mechanical Systems and Signal Processing21(1): 108–124.
4.
AntoniJXinGHamzaouiN (2017) Fast computation of the spectral correlation. Mechanical Systems and Signal Processing92: 248–277.
5.
BorghesaniPPennacchiPRandallRB, et al. (2013) Application of cepstrum pre-whitening for the diagnosis of bearing faults under variable speed conditions. Mechanical Systems and Signal Processing36(2): 370–384.
6.
ChebotarYHandaAMakoviychukV, et al. (2019) Closing the sim-to-real loop: Adapting simulation randomization with real world experience. In: 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 20–24 May 2019, pp.8973–8979. New York, NY: IEEE.
7.
ChoiHCrumpCDuriezC, et al. (2020) On the use of simulation in robotics: Opportunities, challenges, and suggestions for moving forward. Proceedings of the National Academy of Sciences of the United States of America118(1): e1907856118.
8.
GardnerWANapolitanoAPauraL (2006) Cyclostationarity: Half a century of research. Signal Processing86(4): 639–697.
9.
GuoSYangTGaoW, et al. (2018) A novel fault diagnosis method for rotating machinery based on a convolutional neural network. Sensors18(5): 1429.
10.
JingLWangTZhaoM, et al. (2017) An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox. Sensors17(2): 414.
11.
JonkmanBJ (2009) Turbsim user’s guide: Version 1.50. Technical report, National Renewable Energy Lab.(NREL), Golden, CO.
12.
JonkmanJButterfieldSMusialW, et al. (2009) Definition of a 5-mw reference wind turbine for offshore system development. Technical report, National Renewable Energy Lab.(NREL), Golden, CO.
13.
LuBLiYWuX, et al. (2009) A review of recent advances in wind turbine condition monitoring and fault diagnosis. In: 2009 IEEE power electronics and machines in wind applications, Lincoln, NE, USA, 24–26 June 2009, pp.1–7. New York, NY: IEEE.
14.
LuoHQiuHGhanimeG, et al. (2010) Synthesized synchronous sampling technique for differential bearing damage detection. Journal of Engineering for Gas Turbines and Power132(7): 072501.
15.
MauricioAQiJGrylliasK (2019) Vibration-based condition monitoring of wind turbine gearboxes based on cyclostationary analysis. Journal of Engineering for Gas Turbines and Power141(3): 031026.
16.
MauricioAShengSGrylliasK (2020) Condition monitoring of wind turbine planetary gearboxes under different operating conditions. Journal of Engineering for Gas Turbines and Power142(3): 031003.
17.
PeetersCGuillaumePHelsenJ (2018) Vibration-based bearing fault detection for operations and maintenance cost reduction in wind energy. Renewable Energy116: 74–87.
18.
QiaoWLuD (2015) A survey on wind turbine condition monitoring and fault diagnosis—part i: Components and subsystems. IEEE Transactions on Industrial Electronics62(10): 6536–6545.
19.
RaissiMYazdaniAKarniadakisGE (2020) Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations. Science367(6481): 1026–1030.
20.
RandallRBAntoniJ (2011) Rolling element bearing diagnostics—a tutorial. Mechanical Systems and Signal Processing25(2): 485–520.
21.
ShengS (2012) Wind turbine gearbox condition monitoring round robin study-vibration analysis. Technical report, National Renewable Energy Lab.(NREL), Golden, CO.
22.
VachonW (2002) Long-term o&m costs of wind turbines based on failure rates and repair costs. In: Proceedings WINDPOWER, American Wind Energy Association annual conference, Portland, OR, pp.2–5.
23.
VerbruggenT (2003) Wind turbine operation & maintenance based on condition monitoring wt. Final report, April.
24.
WangTHanQChuF, et al. (2019) Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: A review. Mechanical Systems and Signal Processing126: 662–685.
25.
WymoreMLVan DamJECeylanH, et al. (2015) A survey of health monitoring systems for wind turbines. Renewable and Sustainable Energy Reviews52: 976–990.
