FAULT DIAGNOSIS OF PLANETARY GEARBOX OF WIND TURBINES BY DIGITAL-MODEL HYBRID DRIVATION

Zeng Qingtao; Tang Guihua; Zhang Xuan; Cheng Jijie; Ma Ping

doi:10.19912/j.0254-0096.tynxb.2025-0589

PDF(2715 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (8) : 737-746. DOI: 10.19912/j.0254-0096.tynxb.2025-0589

FAULT DIAGNOSIS OF PLANETARY GEARBOX OF WIND TURBINES BY DIGITAL-MODEL HYBRID DRIVATION

Zeng Qingtao¹, Tang Guihua², Zhang Xuan², Cheng Jijie², Ma Ping³

Author information +

History +

Abstract

In response to the problems that it is difficult to collect a large amount of high-quality fault data during the operation of the planetary gearbox of wind turbines and that the diagnostic accuracy of intelligent diagnostic models is low under the scarcity of fault samples, a fault diagnosis method for the planetary gearbox of wind turbines driven by a combination of numerical and physical models is proposed. First, a high-fidelity dynamic model of the planetary gearbox of wind turbines is constructed based on the lumped parameter method to generate pseudo-fault data. Second, a domain-shared residual network feature extractor incorporating a convolutional block attention mechanism is designed to extract the key physical features of the pseudo-data and the measured data. The local maximum mean discrepancy is introduced to align the feature distributions of the pseudo-fault data and the real fault data at the fault category level. By adopting the Kolmogorov-Arnold network module, the network’s learning ability for complex data relationships is enhanced to achieve the classification and identification of different types of faults. Finally, the proposed method is verified on the fault diagnosis test bench of the planetary gearbox of wind turbines. The experimental results show that compared with other classic methods, the proposed method has a good diagnostic effect under the condition of scarce fault samples.

Key words

wind turbines / fault diagnosis / planetary gear box / dynamic model / domain adaptation / transfer learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zeng Qingtao, Tang Guihua, Zhang Xuan, Cheng Jijie, Ma Ping. FAULT DIAGNOSIS OF PLANETARY GEARBOX OF WIND TURBINES BY DIGITAL-MODEL HYBRID DRIVATION[J]. Acta Energiae Solaris Sinica. 2026, 47(8): 737-746 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0589

References

[1] 吴宣勇, 黄忠全, 李琪康, 等. 无源数据约束下多源域自适应的风电齿轮箱故障诊断方法[J]. 太阳能学报, 2024, 45(4): 238-246.
Wu X Y, Huang Z Q, Li Q K, et al.Multi-source domain adaptive fault diagnosis method of wind turbine gearbox under no-accessing source data constraints[J]. Acta Energiae Solaris Sinica, 2024, 45(4): 238-246.
[2] 王城宇, 万书亭, 王萱, 等. 基于转子绕组电流的双馈风电机组齿轮箱阶次跟踪与故障诊断[J]. 太阳能学报, 2025, 46(2): 556-564.
Wang C Y, Wan S T, Wang X, et al.Order tracking and fault diagnosis of doubly-fed wind turbine gearbox based on rotor winding current[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 556-564.
[3] Xu Z F, Li C, Yang Y.Fault diagnosis of rolling bearings using an improved multi-scale convolutional neural network with feature attention mechanism[J]. ISA Transactions, 2021, 110: 379-393.
[4] 张亚洲, 赵小强, 惠永永, 等. 基于多传感器数据融合的SA-DACNN齿轮箱故障诊断方法[J]. 控制与决策, 2024, 39(11): 3699-3708.
Zhang Y Z, Zhao X Q, Hui Y Y, et al.SA-DACNN gearbox fault diagnosis method based on multi-sensor data fusion[J]. Control and Decision, 2024, 39(11): 3699-3708.
[5] 梁舒曼, 谷艳玲, 罗园庆, 等. 基于增强型卷积神经网络的风力发电机行星齿轮箱故障诊断方法[J]. 太阳能学报, 2023, 44(2): 146-152.
Liang S M, Gu Y L, Luo Y Q, et al.Fault diagnosis method of wind turbine planetary gearbox based on enhanced convolutional neural network[J]. Acta Energiae Solaris Sinica, 2023, 44(2): 146-152.
[6] Wang Z Y, Liu T, Wu X, et al.A diagnosis method for imbalanced bearing data based on improved SMOTE model combined with CNN-AM[J]. Journal of Computational Design and Engineering, 2023, 10(5): 1930-1940.
[7] Chen H, Li C S, Yang W X, et al.Deep balanced cascade forest: an novel fault diagnosis method for data imbalance[J]. ISA Transactions, 2022, 126: 428-439.
[8] Liu S W, Jiang H K, Wu Z H, et al.Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis[J]. Measurement, 2021, 168: 108371.
[9] 许小伟, 韦道明, 严运兵, 等. 基于改进ACGAN的永磁同步电机数据扩张方法[J]. 哈尔滨工业大学学报, 2023, 55(10): 114-121.
Xu X W, Wei D M, Yan Y B, et al.Data expansion method of permanent magnet synchronous motor based on improved ACGAN[J]. Journal of Harbin Institute of Technology, 2023, 55(10): 114-121.
[10] Jia F, Lei Y G, Lu N, et al.Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J]. Mechanical Systems and Signal Processing, 2018, 110: 349-367.
[11] Xu J, Li Y X, Meng F J, et al.Fault diagnosis on imbalanced data using an adaptive cost-sensitive multiscale attention network[C]//2021 International Conference on Intelligent Technology and Embedded Systems (ICITES). Chengdu, China, 2021: 77-82.
[12] Fernando K R M, Tsokos C P. Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(7): 2940-2951.
[13] Yu K, Fu Q, Ma H, et al.Simulation data driven weakly supervised adversarial domain adaptation approach for intelligent cross-machine fault diagnosis[J]. Structural Health Monitoring, 2021, 20(4): 2182-2198.
[14] Yan S, Zhong X, Shao H D, et al.Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization[J]. Reliability Engineering & System Safety, 2023, 239: 109522.
[15] 王冉, 韩海保, 颜福成, 等. 条件分布域适应下数模混动齿轮箱故障诊断[J]. 振动与冲击, 2025, 44(3): 182-190, 209.
Wang R, Han H B, Yan F C, et al.Fault diagnosis of digital-analog hybrid transmission gearbox under conditional distribution domain adaptation[J]. Journal of Vibration and Shock, 2025, 44(3): 182-190, 209.
[16] Yang Y, Hu N Q, Li Y H, et al.Dynamic modeling and analysis of planetary gear system for tooth fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 207: 110946.
[17] 莫帅, 胡庆森, 王檑, 等. 考虑齿根裂纹的传动系统动力学特性研究[J]. 华中科技大学学报(自然科学版), 2023, 51(12): 66-72.
Mo S, Hu Q S, Wang L, et al.Research on dynamic characteristics of transmission system considering tooth root crack[J]. Journal of Huazhong University of Science and Technology(nature science edition), 2023, 51(12): 66-72.
[18] He K M, Zhang X Y, Ren S Q, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 2016: 770-778.
[19] Woo S, Park J, Lee J Y, et al.CBAM: convolutional block attention module[M]. Cham: Springer International Publishing, 2018: 3-19.
[20] Zhu Y C, Zhuang F Z, Wang J D, et al.Deep subdomain adaptation network for image classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(4): 1713-1722.
[21] Liu Z, Wang Y, Vaidya S, Et Al.KAN: Kolmogorov-arnold networks[C]//International Conference on Learning Representations. 2025, 2025: 70367-70413.
[22] Liu D D, Cui L L, Cheng W D.Fault diagnosis of wind turbines under nonstationary conditions based on a novel tacho-less generalized demodulation[J]. Renewable Energy, 2023, 206: 645-657.
[23] Maaten L, Hinton G.Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9: 2579-2605.