Addressing the challenges of extracting fault features from non-stationary and noisy vibration signals in wind turbines, this paper proposes a novel wind turbine fault diagnosis method based on the Red-Tailed Hawk (RTH) algorithm and a lightweight ShuffleNet with a dense structure, which can realize rapid and accurate fault identification for wind turbine bearing during its operation and maintenance. The proposed method first employs RTH-optimized Variational Mode Decomposition (VMD) to adaptively decompose the original signal, decoupling fault features from irrelevant components. Subsequently, a weighted Intrinsic Mode Function (IMF) evaluation metric is introduced to filter out irrelevant feature components and reconstruct the signal. Bispectrum transformation is then applied to capture nonlinear phase coupling, further enhancing fault characterization. Finally, a lightweight Dense-ShuffleNet (DS) model is utilized to significantly reduce runtime without compromising accuracy. After denoising the signal using VMD optimized by the RTH algorithm, the model accuracy improved from approximately 90% to around 98.0%. In comparison with alternative data transformation approaches, the Bispectrum method enabled the model to attain the optimal classification performance. Through analysis and validation via t-SNE visualization and Friedman test, the proposed method exhibited significant advantages over other models in terms of both runtime efficiency and prediction accuracy. Experimental results under high-noise conditions and on additional datasets further demonstrated the generality and robustness of the method presented in this study.
ZhuYXieBWangA, et al. Fault diagnosis of wind turbine gearbox under limited labeled data through temporal predictive and similarity contrast learning embedded with self-attention mechanism. Expert Syst Appl2024; 245: 123080. https://doi.org/10.1016/j.eswa.2023.123080
2.
LiuDCuiLChengW. Fault diagnosis of wind turbines under nonstationary conditions based on a novel tacho-less generalized demodulation. Renew Energy2023; 206: 645–657. https://doi.org/10.1016/j.renene.2023.01.056
3.
ZhaoDShaoDCuiL. CTNet: a data-driven time-frequency technique for wind turbines fault diagnosis under time-varying speeds. ISA Trans2024; 154: 335–351. https://doi.org/10.1016/j.isatra.2024.08.029
4.
MaZZhaoMDaiX, et al. Compound fault diagnosis of wind turbine bearing under ultra-low speed operations using generalized sparse spectral coherence. Mech Syst Signal Process2024; 208: 111027. https://doi.org/10.1016/j.ymssp.2023.111027
5.
SunSWangTChuF. A multi-learner neural network approach to wind turbine fault diagnosis with imbalanced data. Renew Energy2023; 208: 420–430. https://doi.org/10.1016/j.renene.2023.03.097
6.
ZhangYLiuWWangX, et al. A novel hierarchical hyper-parameter search algorithm based on greedy strategy for wind turbine fault diagnosis. Expert Syst Appl2022; 202: 117473. https://doi.org/10.1016/j.eswa.2022.117473
7.
ZhongJLiuWSongD, et al. A novel rolling bearing fault diagnosis method based on E-RTH multi-parameter optimization of LSSVM. J Vib Eng Technol2026; 14(1): 23. https://doi.org/10.1007/s42417-025-02225-6
8.
LiuWRenHShaheerMA, et al. A novel wind turbine health condition monitoring method based on correlative features domain adaptation. Int J Precis Eng Manuf Technol2022; 9(1): 191–200. https://doi.org/10.1007/s40684-020-00293-5
9.
LiuYWangYWangZ, et al. Early fault diagnosis of transformers based on relative deterioration analysis. Expert Syst Appl2025; 279: 127437. https://doi.org/10.1016/j.eswa.2025.127437
10.
DibajAEttefaghMMHassannejadR, et al. A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults. Expert Syst Appl2021; 167: 114094. https://doi.org/10.1016/j.eswa.2020.114094
11.
HeXZhouXYuW, et al. Adaptive variational mode decomposition and its application to multi-fault detection using mechanical vibration signals. ISA Trans2021; 111: 360–375. https://doi.org/10.1016/j.isatra.2020.10.060
12.
JinZHeDWeiZ. Intelligent fault diagnosis of train axle box bearing based on parameter optimization VMD and improved DBN. Eng Appl Artif Intell2022; 110: 104713. https://doi.org/10.1016/j.engappai.2022.104713
13.
MiaoYZhaoMLinJ. Identification of mechanical compound-fault based on the improved parameter-adaptive variational mode decomposition. ISA Trans2019; 84: 82–95. https://doi.org/10.1016/j.isatra.2018.10.008
14.
KangJZhuXShenL, et al. Fault diagnosis of a wave energy converter gearbox based on an adam optimized CNN-LSTM algorithm. Renew Energy2024; 231: 1210 22. https://doi.org/10.1016/j.renene.2024.121022
15.
AttallahOIbrahimRAZakzoukNE. CAD system for inter-turn fault diagnosis of offshore wind turbines via multi-CNNs & feature selection. Renew Energy2023; 203: 870–880. https://doi.org/10.1016/j.renene.2022.12.064
16.
LiuXXiaLShiJ, et al. Fault diagnosis of rolling bearings based on the improved symmetrized dot pattern enhanced convolutional neural networks. J Vib Eng Technol2024; 12(2): 1897–1908. https://doi.org/10.1007/s42417-023-00949-x
17.
FanCWangPMaH, et al. Performance degradation assessment of rolling bearing cage failure based on enhanced CycleGAN. Expert Syst Appl2024; 255: 12 4697. https://doi.org/10.1016/j.eswa.2024.124697
18.
JinZSunY. Bearing fault diagnosis based on VMD fuzzy entropy and improved deep belief networks. J Vib Eng Technol2023; 11(2): 577–587. https://doi.org/10.1007/s42417-022-00595-9
19.
ShiMDingCWangR, et al. Deep hypergraph autoencoder embedding: an efficient intelligent approach for rotating machinery fault diagnosis. Knowl Based Syst2023; 260: 110172. https://doi.org/10.1016/j.knosys.2022.110172
20.
PichikaSVVSNKasamVRajasekharanSG, et al. Automatic signal denoising and multi-component fault classification based on deep learning using integrated condition monitoring in a wind turbine gearbox. J Vib Eng Technol2024; 12(7): 8623–8637. https://doi.org/10.1007/s42417-024-01380-6
21.
LuoSHuangXWangY, et al. Transfer learning based on improved stacked autoencoder for bearing fault diagnosis. Knowl Based Syst2022; 256: 109846. https://doi.org/10.1016/j.knosys.2022.109846
22.
ChenHMengWLiY, et al. An anti-noise fault diagnosis approach for rolling bearings based on multiscale CNN-LSTM and a deep residual learning model. Meas Sci Technol2023; 34(4): 045013. https://doi.org/10.1088/1361-6501/acb074
23.
TangHHZhangKWangB, et al. Early bearing fault diagnosis for imbalanced data in offshore wind turbine using improved deep learning based on scaled minimum unscented kalman filter. Ocean Eng2024; 300: 117392. https://doi.org/10.1016/j.oceaneng.2024.117392
24.
JianTCaoJLiuW, et al. A novel wind turbine fault diagnosis method based on compressive sensing and lightweight SqueezeNet model. Expert Syst Appl2025; 260: 125440. https://doi.org/10.1016/j.eswa.2024.125440
25.
ChengFWangJQuL, et al. Rotor-current-based fault diagnosis for DFIG wind turbine drivetrain gearboxes using frequency analysis and a deep classifier. IEEE Trans Ind Appl2018; 54(2): 1062–1071. https://doi.org/10.1109/tia.2017.2773426
26.
DuYGengXZhouQ, et al. A fault diagnosis method for offshore wind turbine bearing based on adaptive deep echo state network and bidirectional long short term memory network in noisy environment. Ocean Eng2024; 312: 119101. https://doi.org/10.1016/j.oceaneng.2024.119101
27.
ZhaoZYunSJiaL, et al. Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features. Eng Appl Artif Intell2023; 121: 105982. https://doi.org/10.1016/j.engappai.2023.105982
28.
YangMZhangKShengZ, et al. The amplitude modulation bispectrum: a weak modulation features extracting method for bearing fault diagnosis. Reliab Eng Syst Saf2024; 250: 110241. https://doi.org/10.1016/j.ress.2024.110241
29.
ZhaoHGaoYDengW. Defect detection using shuffle Net-ca-ssd lightweight network for turbine blades in IoT. IEEE Internet Things J2024; 11(20): 32804–32812. https://doi.org/10.1109/jiot.2024.3409823
30.
FerahtiaSHouariARezkH, et al. Red-tailed hawk algorithm for numerical optimization and real-world problems. Sci Rep2023; 13(1): 12950. https://doi.org/10.1038/s41598-023-38778-3
31.
RathodAASB. Optimization of stand-alone hybrid renewable energy system based on techno-socio-enviro-financial perspective using improved red-tailed hawk algorithm. Appl Energy2024; 376: 124137. https://doi.org/10.1016/j.apenergy.2024.124137
32.
SeyyedabbasiAKianiF. I-GWO and Ex-GWO: improved algorithms of the Grey Wolf Optimizer to solve global optimization problems. Eng Comput2021; 37(1): 509–532. https://doi.org/10.1007/s00366-019-00837-7
33.
GuHLiuWZhangY, et al. A novel fault diagnosis method of wind turbine bearings based on compressed sensing and AlexNet. Meas Sci Technol2022; 33(11): 115011. https://doi.org/10.1088/1361-6501/ac8276
34.
TangHTangYSuY, et al. Feature extraction of multi-sensors for early bearing fault diagnosis using deep learning based on minimum unscented kalman filter. Eng Appl Artif Intell2024; 127: 107138. https://doi.org/10.1016/j.engappai.2023.107138
35.
XuKKongXWangQ, et al. A bearing fault diagnosis method without fault data in new working condition combined dynamic model with deep learning. Adv Eng Inform2022; 54: 101795. https://doi.org/10.1016/j.aei.2022.101795
36.
BaiRMengZXuQ, et al. Fractional Fourier and time domain recurrence plot fusion combining convolutional neural network for bearing fault diagnosis under variable working conditions. Reliab Eng Syst Saf2023; 232: 109076. https://doi.org/10.1016/j.ress.2022.109076
37.
XiaSHuangWZhangJ. A novel fault diagnosis method based on nonlinear-CWT and improved YOLOv8 for axial piston pump using output pressure signal. Adv Eng Inform2025; 64: 103041. https://doi.org/10.1016/j.aei.2024.103041
38.
HuYLuoPLiuH, et al. Open-circuit fault diagnosis method of inverter in wind turbine yaw system based on GADF image coding. Comput Electr Eng2024; 117: 109252. https://doi.org/10.1016/j.compeleceng.2024.109252
39.
DibajAGaoZNejadAR. Fault detection of offshore wind turbine drivetrains in different environmental conditions through optimal selection of vibration measurements. Renew Energy2023; 203: 161–176. https://doi.org/10.1016/j.renene.2022.12.049
