A health assessment and fault prediction method for wind turbine generators is proposed in this article. In health assessment module, considering generator status transferring along with environment and wind turbine–self operating, variables under wind turbine normal working are divided into two parameter spaces and recognized, namely operating conditions and status parameters. Then generator health benchmark models based on Gaussian mixture model are established in different operating condition sub-spaces after the data imbalance problem solved. For online health assessment, health deterioration index based on condition recognition models is calculated and a dual-threshold alarm scheme is proposed. When an alarm is raised by degraded health deterioration index, the program could access fault prediction module, where the generator rear bearing temperature trend and fault remaining time can be predicted through weights redistribution and hyper-parameter optimized support vector regression. In experiments, the proposed health assessment and fault prediction was verified in a real wind farm, and results showed this method could assess generator condition accurately and improve special fault prediction performance.
ZhaoYYLiDDongA, et al. Fault prediction and diagnosis of wind turbine generators using SCADA data. Energies2017; 108: 1210.
3.
CaoMNQiuYFengY, et al. Study of wind turbine fault diagnosis based on unscented Kalman filter and SCADA data. Energies2016; 9(10): 847.
4.
TidririKChattiNVerronS, et al. Model-based fault detection and diagnosis of complex chemical processes: a case study of the Tennessee Eastman process. Proc IMechE Part I: J Systems and Control Engineering2018; 232(6): 742–760.
5.
GeZQSongZHGaoFR.Review of recent research on data-based process monitoring. Ind Eng Chem Res2013; 52(10): 3543–3562.
6.
YangCLiuJZengY, et al. Real-time condition monitoring and fault detection of components based on machine-learning reconstruction model. Renew Energy2019; 133: 433–441.
7.
HuYLiHLiaoX, et al. A probability evaluation method of early deterioration condition for the critical components of wind turbine generator systems. Mech Syst Signal Process2016; 76–77: 729–741.
8.
ZhangJJiangNLiHK, et al. Online health assessment of wind turbine based on operational condition recognition. Trans Inst Measure Contr2018; 41: 2970–2981.
9.
JiaXJinCBuzzaM, et al. Wind turbine performance degradation assessment based on a novel similarity metric for machine performance curves. Renew Energy2016; 99: 1191–1201.
10.
DongYFangFGuY.Dynamic evaluation of wind turbine health condition based on Gaussian mixture model and evidential reasoning. J Renew Sustain Energy2013; 5(3): 033117.
11.
BangalorePTjernbergLB.An artificial neural network approach for early fault detection of gearbox bearings. IEEE Trans Smart Grid2015; 6(2): 980–987.
12.
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(8): 1421–1438.
13.
WangLZhangZXuJ, et al. Wind turbine blade breakage monitoring with deep autoencoders. IEEE Trans Smart Grid2018; 9: 2824–2833.
14.
JiangGQXiePHeHB, et al. Wind turbine fault detection using a denoising autoencoder with temporal information. IEEE/ASME Trans Mechatr2018; 23(1): 89–100.
15.
ZhaoHSZhangXT. Early fault prediction of wind turbine gearbox based on temperature measurement. In:
IEEE international conference on power system technology, Auckland, New Zealand, 30 October 2 November 2013. New York: IEEE.
16.
HuYLiHShiP, et al. A prediction method for the real-time remaining useful life of wind turbine bearings based on the Wiener process. Renew Energy2018; 127: 452–460.
17.
SaidiLBen AliJBechhoeferE, et al. Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR. Appl Acoustics2017; 120: 1–8.
18.
BenestyJChenJHuangY, et al. Pearson correlation coefficient. In: CohenIHuangYChenJ, et al. (eds) Noise reduction in speech processing. Berlin; Heidelberg: Springer, 2009, pp.14.
19.
KinneyJBAtwalGS.Equitability, mutual information, and the maximal information coefficient. Proc Nat Acad Sci2014; 111(9): 3354–3359.
20.
RokachL.A survey of clustering algorithms. In: MaimonORokachL (eds) Data mining and knowledge discovery handbook. Boston, MA: Springer, 2009, pp.269–298.
21.
ChenJZhangXGaoY.Fault detection for turbine engine disk based on an adaptive kernel principal component analysis algorithm. Proc IMechE Part I: J Systems and Control Engineering2016; 230(7): 651–660.
22.
MaulikUSanghamitraB.Performance evaluation of some clustering algorithms and validity indices. IEEE Trans Pattern Anal Machine Intell2002; 24(12): 1650–1654.
BilmesJA.A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Int Comp Sci Inst1998; 4(510): 126.
SheatherSJJonesMC.A reliable data-based bandwidth selection method for Kernel Density Estimation. J R Statist Soc1991; 53(3): 683–690.
30.
StatnikovAAliferisCFHardinDP, et al. Support Vector Regression (SVR). In: StatnikovAAliferisCFHardinDP, et al. (eds) A gentle introduction to support vector machines in biomedicine: theory and methods (vol. 1). Singapore: World Scientific; 2011; 97–118.
31.
KohaviR. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: International joint conference on artificial intelligence, Montreal, QC, Canada, 2025 August 1995. San Francisco, CA: Morgan Kaufmann Publishers.
32.
LavalleSMBranickyMS.On the relationship between classical grid search and probabilistic roadmaps. Int J Robot Res2003; 23(23): 673–692.
33.
KennedyJEberhartR. Particle swarm optimization. In: ICNN95-international conference on neural networks, Perth, WA, Australia, 27 November–1 December 2002. New York: IEEE.
34.
HuangGBZhuQYSiewCK.Extreme learning machine: theory and applications. Neurocomputing2006; 70(1): 489–501.
