High-speed shaft bearing (HSSB) failure in wind turbines (WTs) is a major problem that can cause unexpected blackouts in the electricity generation. Research on naturally occurring, advanced faults in HSSBs is relatively scarce, and online damage severity assessments are rarely reported in published works. In this paper, two approaches are outlined to predict degradation in HSSBs (Kalman filter (KF) and artificial neural networks (ANNs)), specifically inner race failure, and to estimate the remaining useful life (RUL) of HSSB. The health indicators (HIs) are used to evaluate the degradation of HSSB, and the minimum redundancy maximum relevance (mRMR) method is used to extract the best suitable HI for HSSB prognosis purpose. Therefore, a single prognostic metric is employed to evaluate the RUL prediction outcomes. To validate the accuracy of the methods, experiments were conducted on an actual HSSB vibrations dataset. Comparing with current state-of-the-art methods on the same dataset demonstrates the performance of the proposed methods.
AmiratYBenbouzidMEHAl-AhmarE, et al. (2009) A brief status on condition monitoring and fault diagnosis in wind energy conversion systems. Renewable and Sustainable Energy Reviews13(9): 2629–2636.
2.
BechhoeferEDubéM (2020) Contending remaining useful life algorithms. Annual Conference of the PHM Society12(1): 9.
BechhoeferEXiaoLZhangX (2021) Remaining useful life calculation of a component using hybrid fatigue crack model. Annual Conference of the PHM Society13(1).
5.
Ben AliJChebel-MorelloBSaidiL, et al. (2015) Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mechanical Systems and Signal Processing56: 150–172.
6.
Ben AliJSaidiLHarrathS, et al. (2018) Online automatic diagnosis of wind turbine bearings progressive degradations under real experimental conditions based on unsupervised machine learning. Applied Acoustics132: 167–181.
7.
BoussebsiMMedouedASaidiL (2023) Data-driven and physics-based approaches for wind turbine high-speed shaft bearing prognostics. In: 2023 International Conference on Control, Automation and Diagnosis (ICCAD), pp. 1–6. IEEE.
8.
ChenWDingSXHaghaniA, et al. (2011) Observer based FDI schemes for wind turbine benchmark. IFAC Proceedings Volumes44(1): 7073–7078.
9.
ChoSChoiMGaoZ, et al. (2021) Fault detection and diagnosis of a blade pitch system in a floating wind turbine based on Kalman filters and artificial neural networks. Renewable Energy169: 1–13.
10.
ChoiYLiuCR (2007) Spall progression life model for rolling contact verified by finish hard machined surfaces. Wear262(1-2): 24–35.
11.
CobleJB (2010) Merging data sources to predict remaining useful life–an automated method to identify prognostic parameters. PhD diss., University of Tennessee, 2010. https://trace.tennessee.edu/utk_graddiss/683
12.
DingCPengH (2005) Minimum redundancy feature selection from microarray gene expression data. Journal of Bioinformatics and Computational Biology3(02): 185–205.
13.
DoucetAJohansenAM (2009) A tutorial on particle filtering and smoothing: fifteen years later. Handbook of nonlinear filtering12(656-704): 3.
14.
ElashaFShanbrSLiX, et al. (2019) Prognosis of a wind turbine gearbox bearing using supervised machine learning. Sensors19(14): 3092.
15.
IsmailASaidiLSayadiM (2019) Wind turbine power converter fault diagnosis using DC-link voltage time–frequency analysis. Wind Engineering43(4): 329–343.
16.
KamarzarrinMRefanMHAmiriP, et al. (2021) A new intelligent fault diagnosis and prognosis method for wind turbine doubly-fed induction generator. Wind Engineering46(1): 308–340.
17.
KimNHAnDChoiJH (2017) Prognostics and Health Management of Engineering Systems. Springer International Publishing.
18.
KongKDyerKPayneC, et al. (2023) Progress and trends in damage detection methods, maintenance, and data-driven monitoring of wind turbine blades–A review. Renewable Energy Focus44: 390–412.
19.
LaouafiA (2025) Towards efficient solutions for automatic recognition of complex power quality disturbances. Expert Systems with Applications286: 128077.
20.
LeahyKGallagherCO’DonovanP, et al. (2019) Issues with data quality for wind turbine condition monitoring and reliability analyses. Energies12(2): 201.
21.
LeiYLiNGuoL, et al. (2018) Machinery health prognostics: a systematic review from data acquisition to RUL prediction. Mechanical Systems and Signal Processing104: 799–834.
22.
LiYKurfessTRLiangSY (2000) Stochastic prognostics for rolling element bearings. Mechanical Systems and Signal Processing14(5): 747–762.
23.
MarugánAPMárquezFPGPerezJMP, et al. (2018) A survey of artificial neural network in wind energy systems. Applied Energy228: 1822–1836.
24.
MerainaniBRahmouneCBenazzouzD, et al. (2018) A novel gearbox fault feature extraction and classification using Hilbert empirical wavelet transform, singular value decomposition, and SOM neural network. Journal of Vibration and Control24(12): 2512–2531.
25.
MerainaniBLaddadaSBechhoeferE, et al. (2022) An integrated methodology for estimating the remaining useful life of high-speed wind turbine shaft bearings with limited samples. Renewable Energy182: 1141–1151.
26.
MoeiniREntezamiMRatkovacM, et al. (2018) Perspectives on condition monitoring techniques of wind turbines. Wind Engineering43(5): 539–555.
27.
NajdiBBenbrahimMKabbajMN (2025) Adaptive Res-LSTM attention-based remaining useful lifetime prognosis of rolling bearings. International Journal of Prognostics and Health Management16(1): 1–16. Available at: https://doi.org/10.36001/ijphm.2025.v16i1.4171
28.
QiuYChenLFengY, et al. (2017) An approach of quantifying gear fatigue life for wind turbine gearboxes using supervisory control and data acquisition data. Energies10(8): 1084.
29.
SaidiLBenbouzidM (2021) Prognostics and health management of renewable energy systems: state of the art review, challenges, and trends. Electronics10(22): 2732.
30.
SaidiLFnaiechFCapolinoGA, et al. (2012) Stator current bi-spectrum patterns for induction machines multiple-faults detection. In: IECON 2012–38th annual conference on IEEE industrial electronics society, pp. 5132–5137. IEEE.
31.
SaidiLAliJBBenbouzidM, et al. (2016) The use of SESK as a trend parameter for localized bearing fault diagnosis in induction machines. ISA Transactions63: 436–447.
32.
SaidiLAliJBBechhoeferE, et al. (2017a) Particle filter-based prognostic approach for high-speed shaft bearing wind turbine progressive degradations. In: IECON 2017-43rd annual conference of the IEEE industrial electronics society, pp. 8099–8104. IEEE.
33.
SaidiLAliJBBechhoeferE, et al. (2017b) Wind turbine high-speed shaft bearings health prognosis through a spectral Kurtosis-derived indices and SVR. Applied Acoustics120: 1–8.
34.
SaidiLAliJBBenbouzidM, et al. (2018) An integrated wind turbine failures prognostic approach implementing Kalman smoother with confidence bounds. Applied Acoustics138: 199–208.
35.
SaidiLHayderANSaidiM (2022) Remaining useful life prognosis for wind turbine using a neural network with a long-term prediction. Wind Engineering49(4): 857–870.
36.
ShanbrSElashaFElforjaniM, et al. (2017) Bearing fault detection within wind turbine gearbox. In: 2017 international conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), pp. 565–570. IEEE.
37.
SidhomJSaidiLGannounH (2025) AI-Driven prognostics for wind turbine bearings: predicting degradation with limited data. In 2025 International Conference on Control, Automation and Diagnosis (ICCAD), pp. 1–6. IEEE.
38.
WeiXVerhaegenMvan EngelenT (2010) Sensor fault detection and isolation for wind turbines based on subspace identification and Kalman filter techniques. International Journal of Adaptive Control and Signal Processing24(8): 687–707.
YangLLiTDongY, et al. (2024) A knowledge-data integration framework for rolling element bearing RUL prediction across its life cycle. ISA Transactions152: 331–357.
41.
ZhaoWSiegelDLeeJ, et al. (2013) An integrated framework of drivetrain degradation assessment and fault localization for offshore wind turbines. International Journal of Prognostics and Health Management4: 46.
