Gearboxes are critical transmission components in the drivetrain of wind turbine, which have a dominant failure rate and the highest downtime loss in all wind turbine subsystems. However, load variations of wind turbine gearbox are far from smooth and usually nondeterministic, which result in inconsistent data distributions. To solve the problem, a novel performance degradation assessment and prognosis method based on maximum mean discrepancy is proposed to test the difference between data distributions and extract the characteristics of multi-source working conditions data. Besides, the increase in sensors will bring more difficulties to establish prediction models in real-world scenarios due to different installation locations. In view of this, a transfer learning strategy called joint distribution adaptation is utilized to adapt data distribution between multi-sensor signals. Nevertheless, the presence of background noise of wind turbine signals restricts the applicability of these algorithms in practice. To further reduce the distribution difference, a novel criterion is proposed to evaluate and measure the data distribution difference between known and tested working conditions based on the witness function of maximum mean discrepancy. The application and superiority of proposed methodology are validated using a wind turbine gearbox life-cycle test data set. Meanwhile, model comparison and cross-verification are conducted between conventional and proposed prediction models. The results indicate that the proposed method has a better performance in performance degradation assessment for wind turbine gearbox.
SchröderKGebhardtCRolfesR. A two-step approach to damage localization at supporting structures of offshore wind turbines. Struct Health Monit2018; 17: 1313–1330.
2.
LeeJWuFZhaoW, et al. Prognostics and health management design for rotary machinery systems—reviews, methodology and applications. Mech Syst Signal Pr2014; 42: 314–334.
3.
PanYHongRChenJ, et al. Incipient fault detection of wind turbine large-size slewing bearing based on circular domain. Measurement2019; 137: 130–142.
4.
WuRJahanshahiM. Data fusion approaches for structural health monitoring and system identification: past, present, and future. Struct Health Monit2020; 19: 552–586.
5.
American Gear Manufacturer Association. Standard for design and specification of gearboxes for wind turbines. Alexandria, VA: American Gear Manufacturer Association, 2004.
6.
WangDMiaoQZhouQ, et al. An intelligent prognostic system for gear performance degradation assessment and remaining useful life estimation. J Vib Acoust2015; 137(2): 021004.
7.
NiXZhaoJHuQ, et al. A new improved Kurtogram and its application to planetary gearbox degradation feature analysis. J Vibroeng2017; 19(5): 3413–3428.
8.
LiuXJiaYHeZ, et al. Application of EMD-WVD and particle filter for gearbox fault feature extraction and remaining useful life prediction. J Vibroeng2017; 19(3): 1793–1808.
9.
MusialWButterfieldSMcNiffB. Improving wind turbine gearbox reliability. In: 2007 European wind energy conference, Milan, 7–10 May 2007.
10.
IgbaJAlemzadehKDurugboC, et al. Performance assessment of wind turbine gearboxes using in-service data: current approaches and future trends. Renew Sust Energ Rev2015; 50: 144–159.
11.
IgbaJAlemzadehKDurugboC, et al. Analysing RMS and peak values of vibration signals for condition monitoring of wind turbine gearboxes. Renew Energ2016; 91(3): 90–106.
12.
SkrimpasGAUrsinTSweeneyC, et al. Residual signal feature extraction for gearbox planetary stage fault detection. Wind Energy2017; 20: 1389–1404.
WuXWangHJiangG, et al. Monitoring wind turbine gearbox with echo state network modeling and dynamic threshold using SCADA vibration data. Energies2019; 12: 982.
SiegelDZhaoWLapiraE, et al. A comparative study on vibration-based condition monitoring algorithms for wind turbine drive trains. Wind Energy2014; 17: 695–714.
17.
SaidiLAliBJBechhoeferE, et al. Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR. Appl Acoust2017; 120: 1–8.
18.
TengWDingXZhangX, et al. Multi-fault detection and failure analysis of wind turbine gearbox using complex wavelet transform. Renew Energ2016; 93: 591–598.
19.
FengZLiangM. Fault diagnosis of wind turbine planetary gearbox under nonstationary conditions via adaptive optimal kernel time-frequency analysis. Renew Energ2014; 66: 468–477.
20.
ElashaFGreavesMMbaD. Planetary bearing defect detection in a commercial helicopter main gearbox with vibration and acoustic emission. Struct Health Monit2018; 17: 1192–1212.
21.
FengZLiangMZhangY, et al. Fault diagnosis for wind turbine planetary gearboxes via demodulation analysis based on ensemble empirical mode decomposition and energy separation. Renew Energ2012; 47: 112–126.
22.
KarCMohantyA. Technical note: gearbox health monitoring through multiresolution Fourier transform of vibration and current signals. Struct Health Monit2006; 13: 195–200.
23.
SequeiraCPachecoAGalegoP, et al. Analysis of the efficiency of wind turbine gearboxes using the temperature variable. Renew Energ2019; 135: 465–472.
24.
ChengFQuLQiaoW. Fault prognosis and remaining useful life prediction of wind turbine gearboxes using current signal analysis. IEEE T Sustain Energ2017; 9: 157–167.
25.
CoronadoDWenskeJ. Monitoring the oil of wind-turbine gearboxes: main degradation indicators and detection methods. Machines2018; 6(2): 25.
26.
WangLZhangZLongH, et al. Wind turbine gearbox failure identification with deep neural networks. IEEE T Ind Inform2016; 13(3): 1360–1368.
27.
AdelDHosseinR. Wind turbine gearbox condition monitoring and fault diagnosis based on multi-sensor information fusion of SCADA and DSER-PSO-WRVM method. Int J Model Simul2018; 39: 48–72.
28.
AngelGMiguelSMiguelR. Behavior anomaly indicators based on reference patterns-application to the gearbox and electrical generator of a wind turbine. Energies2018; 11(1): 87.
29.
GuoPBaiN. Wind turbine gearbox condition monitoring with AAKR and moving window statistic methods. Energies2011; 4(12): 2077–2093.
30.
BangalorePLetzgusSKarlssonD, et al. An artificial neural network-based condition monitoring method for wind turbines, with application to the monitoring of the gearbox. Wind Energy2017; 20: 1421–1438.
31.
CuiYBangalorePTjernbergL. An anomaly detection approach using wavelet transform and artificial neural networks for condition monitoring of wind turbines’ gearboxes. In: Proceedings of the 2018 power systems computation conference (PSCC), Dublin, 11–15 June 2018, pp. 1–7. New York: IEEE.
32.
QianPMaXCrossP. Integrated data-driven model-based approach to condition monitoring of the wind turbine gearbox. IET Renew Power Gen2017; 11(9): 1177–1185.
CarrollJKoukouraSMcDonaldA, et al. Wind turbine gearbox failure and remaining useful life prediction using machine learning techniques. Wind Energy2019; 22(3)): 360–375.
35.
GrettonABorgwardtKRaschM, et al. A kernel method for the two-sample-problem. Adv Neural Inf Process Syst2006; 19: 513–520.
36.
SawalhiNRallRForresterD. Separation and enhancement of gear and bearing signals for the diagnosis of wind turbine transmission systems. Wind Energy2014; 17: 729–743.
37.
RandallRSawalhiNCoatsM. Separation of gear and bearing fault signals from a wind turbine transmission under varying speed and load. In: FakhfakhTBartelmusWChaariF, et al. (eds) Condition monitoring of machinery in non-stationary operations. Berlin: Springer, 2012, pp. 3–12.
38.
ErrichelloRMullerJ. Application requirements for wind turbine gearboxes. NREL/TP-442-7076, September1994. Golden, CO: National Renewable Energy Lab.
39.
LuYTangJLuoH. Wind turbine gearbox fault detection using multiple sensors with features level data fusion. J Eng Gas Turbine Power2012; 134: 042501.
40.
DempseyPJShengS. Investigation of data fusion applied to health monitoring of wind turbine drivetrain components. Wind Energy2013; 16: 479–489.
41.
DhamiSPablaB. Hybrid data fusion approach for fault diagnosis of fixed-axis gearbox. Struct Health Monit2018; 17: 936–945.
42.
PanYHongRChenJ, et al. Performance degradation assessment of a wind turbine gearbox based on multi-sensor data fusion. Mech Mach Theory2019; 137: 509–526.
43.
ZhaoHXuFLiangB, et al. A condition-based opportunistic maintenance strategy for multi-component system. Struct Health Monit2019; 18: 270–283.
44.
LongMWangJDingG, et al. Transfer feature learning with joint distribution adaptation. In: Proceedings of the 2013 IEEE international conference on computer vision, Sydney, NSW, Australia, 1–8 December 2013, pp. 2200–2207. New York: IEEE.
45.
WangJXieJZhangL, et al. A factor analysis based transfer learning method for gearbox diagnosis under various operating conditions. In: Proceedings of the international symposium on flexible automation, Cleveland, OH, 1–3 August 2016.
46.
CaoPZhangSTangJ. Pre-processing-free gear fault diagnosis using small datasets with deep convolutional neural network-based transfer learning. IEEE Access2018; 6: 26241–26253.
47.
HanTLiuCYangW, et al. Deep transfer network with joint distribution adaptation: a new intelligent fault diagnosis framework for industry application. ISA T2020; 97: 269–281.
48.
ChenCLiZYangJ, et al. A cross domain feature extraction method based on transfer component analysis for rolling bearing fault diagnosis. In: Proceedings of the control & decision conference, Chongqing, China, 28–30 May 2017. New York: IEEE.
49.
GrettonABorgwardtKRaschM, et al. A kernel two-sample test. J Mach Learn Res2012; 13(1): 723–773.
CobleJ. Merging data sources to predict remaining useful life-an automated method to identify prognostic parameters. Knoxville, TN: The University of Tennessee, 2010.
56.
SunSShiHWuY. A survey of multi-source domain adaptation. Inform Fusion2015; 24: 84–92.
