ORDER TRACKING TEMPORAL–FREQUENCY HYPERGRAPH FOR MULTI SENSOR FAULT DIAGNOSIS OF OFFSHORE WIND TURBINE MAIN BEARINGS. 1-15. SI

Lingling Yang

View Full Paper

References

  1. [1] Y. Zhang, C. Li, H. Wang, et al., “A dynamic graph attentionnetwork for multi-sensor fault diagnosis of offshore wind turbinebearings,” IEEE Transactions on Industrial Electronics, vol. 70,no. 5, pp. 5210–5220, 2023.
  2. [2] X. Yan, Z. Shi, J. Liu, et al., “Multisensor fusion on hypergraphfor fault diagnosis of rotating machinery,” IEEE Transactionson Industrial Informatics, vol. 20, no. 8, pp. 8123–8132, 2024.
  3. [3] T. Yu, Z. Jiang, Y. Zhang, et al., “Diffusion model-based multi-sensor time-frequency fusion for gearbox fault diagnosis underimbalanced conditions,” Mechanical Systems and Signal Pro-cessing, vol. 201, p. 110897, 2025.
  4. [4] M. Liu, L. Zhang, W. Chen, et al., “Attention-aware temporal-spatial graph neural network for multi-sensor fusion in windturbine diagnosis,” IEEE Sensors Journal, vol. 24, no. 7,pp. 10234–10243, 2024.
  5. [5] Q. Wang, J. Zhao, J. Lee, et al., “Semi-supervised open-set faultdiagnosis for marine machinery using graph neural networks,”IEEE Journal of Oceanic Engineering, vol. 50, no. 1, pp. 289–300, 2025.
  6. [6] J. Chen, H. Li, S. Zhang, et al., “Multi-channel hypergraphconvolutional network for few-shot fault diagnosis of helicoptertail-drive systems,” Chinese Journal of Aeronautics, vol. 37,no. 4, pp. 345–356, 2024.
  7. [7] Z. Ren, S. Gao, H. Kim, et al., “Multimodal knowledge graphfor rolling bearing fault diagnosis under variable speeds,” IEEETransactions on Industrial Informatics, vol. 21, no. 2, pp. 1567–1576, 2025.
  8. [8] S. Park, D. Lee, J. Kim, et al., “Dygat-ftnet: Dynamic graphattention network for time-frequency data fusion in fault diag-nosis,” Measurement Science and Technology, vol. 36, no. 1,p. 015102, 2025.
  9. [9] J. Chen, Y. Li, S. Zhang, et al., “Physical information-enhancedlstm with hyperparameter optimization for bearing fault diag-nosis,” Control Engineering Practice, vol. 126, p. 105189, 2022.
  10. [10] G. Khoury, Z. Alomar, M. Sabat, et al., “Improving the effi-ciency of savonius wind turbine through shielding: Numericaland experimental study,” International Journal of Power andEnergy Systems, vol. 45, no. 10, 2025.
  11. [11] H. Han, X. Wang, B. Mao, et al., “A real-time monitoringsystem for gearwear evaluation of wind turbine,” InternationalJournal of Power and Energy Systems, vol. 45, no. 10, 2025.
  12. [12] D. Lee, S. Park, J. Kim, et al., “Order tracking-based time-frequency analysis for non-stationary bearing fault diagnosis,”Mechanical Systems and Signal Processing, vol. 195, p. 110286,2023.
  13. [13] J. Kim, D. Lee, M. Park, et al., “Multi-resolution time-frequency transformation for non-stationary vibration signals,”Mechanical Systems and Signal Processing, vol. 198, p. 110356,2024.
  14. [14] Y. Shao, J. Hu, F. Liu, et al., “Cross-sensor asynchrony cor-rection for multi-sensor fusion in fault diagnosis,” Journal ofVibration and Control, vol. 29, no. 11-12, pp. 2789–2801, 2023.
  15. [15] L. Zhang, M. Li, H. Wang, et al., “Order tracking and waveletdenoising for offshore wind turbine bearing signal processing,”IEEE Transactions on Energy Conversion, vol. 38, no. 4,pp. 2876–2885, 2023.
  16. [16] H. Zhang, L. Wang, G. Chen, et al., “Deep graph convolutionalnetwork for roller bearing diagnosis based on acoustic signalmapping,” Journal of Sound and Vibration, vol. 550, p. 116878,2023.
  17. [17] S. Zhang, J. Chen, H. Li, et al., “1d-cnn combined with hyper-graph for multi-sensor feature extraction,” IEEE Sensors Jour-nal, vol. 23, no. 12, pp. 14023–14032, 2023.
  18. [18] H. Kim, K. Lee, M. Park, et al., “Hypergraph convolution withattention for cross-sensor feature fusion,” IEEE Transactionson Cybernetics, vol. 54, no. 3, pp. 1890–1901, 2024.
  19. [19] Y. Liu, Z. Wang, L. Chen, et al., “Hypergraph constructionbased on k-nearest neighbors for multi-sensor fault diagnosis,”IEEE Transactions on Reliability, vol. 73, no. 2, pp. 890–901,2024.
  20. [20] J. Lee, H. Kim, S. Park, et al., “Few-shot fault diagnosis us-ing meta-learning for wind turbine bearings,” Renewable andSustainable Energy Reviews, vol. 178, p. 113389, 2025.
  21. [21] Z. Wang, Y. Liu, L. Chen, et al., “Amplitude coherence andmutual information for hypergraph weight calculation,” Mea-surement, vol. 221, p. 113456, 2024.
  22. [22] X. Wang, Y. Chen, L. Davis, et al., “Lightweight 1d-cnn forshort-term dynamic feature extraction in bearing diagnosis,”IEEE Access, vol. 11, pp. 78945–78954, 2023.
  23. [23] K. Lee, H. Kim, S. Park, et al., “Operating condition-gatedfusion for fault diagnosis under variable loads,” IEEE Transac-tions on Cybernetics, vol. 55, no. 2, pp. 1234–1245, 2025.
  24. [24] W. Chen, S. Zhang, J. Liu, et al., “Attention mechanism-enhanced hypergraph convolution for multi-sensor fusion,” Neu-ral Computing and Applications, vol. 36, no. 15, pp. 11234–11245, 2024.
  25. [25] M. Park, J. Kim, D. Lee, et al., “Performance evaluation ofgraph vs. hypergraph modeling in multi-sensor diagnosis,” IEEETransactions on Reliability, vol. 74, no. 1, pp. 567–578, 2025.
  26. [26] J. Liu, L. Zhang, W. Chen, et al., “Digital twin integration forreal-time bearing fault diagnosis,” Journal of ManufacturingSystems, vol. 71, pp. 345–356, 2024.
  27. [27] Y. Shao, J. Hu, F. Liu, et al., “Stacked wavelet autoencoderfor multi-sensor data fusion in collaborative fault diagnosis,”Neurocomputing, vol. 489, pp. 187–198, 2022.
  28. [28] C. Li, Y. Zhang, H. Wang, et al., “Comparative study of baselinemethods for multi-sensor fault diagnosis,” IEEE Access, vol. 11,pp. 98765–98774, 2023.
  29. [29] J. Zhao, Q. Wang, J. Lee, et al., “Online fault diagnosis proto-type system for offshore wind turbines,” IEEE Transactions onIndustrial Informatics, vol. 20, no. 10, pp. 8901–8910, 2024.

Important Links:

Go Back