Fault Diagnosis of Wind Turbine Bearings Using SwinT-CBAM-BiGRU
DOI:
https://doi.org/10.71222/phh5hc13Keywords:
wind turbine, bearing fault diagnosis, multimodal fusionAbstract
To address the challenge that traditional diagnostic models struggle to simultaneously capture local impacts and global features due to background noise interference under the complex operating conditions of wind turbine bearings, this study proposes a novel multimodal fusion fault diagnosis model based on SwinT-CBAM-BiGRU. Specifically, the Gramian Angular Difference Field (GADF) encoding technique is employed to transform 1D vibration signals into 2D feature images. A Swin Transformer integrated with the Convolutional Block Attention Module (CBAM) is utilized to extract deep spatial features and precisely pinpoint core fault regions. Concurrently, a Bidirectional Gated Recurrent Unit (BiGRU) is combined to mine the long-range temporal evolution patterns of the signals. Through comparative and ablation experiments conducted on the Case Western Reserve University (CWRU) bearing dataset, the results demonstrate that the proposed fusion model exhibits superior diagnostic capabilities. Ultimately, this method effectively breaks the constraints of single-dimensional features, demonstrating stronger discriminative stability and robustness in multi-class bearing fault diagnosis tasks.References
1. E. Hart, A. Turnbull, J. Feuchtwang, et al., "Wind turbine main‐bearing loading and wind field characteristics," Wind Energy, vol. 22, no. 11, pp. 1534-1547, 2019.
2. Z. Liu and L. Zhang, "A review of failure modes, condition monitoring and fault diagnosis methods for large-scale wind turbine bearings," Measurement, vol. 149, p. 107002, 2020.
3. X. Chen, R. Yang, Y. Xue, et al., "Deep transfer learning for bearing fault diagnosis: A systematic review since 2016," IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-21, 2023.
4. W. Qiao and D. Lu, "A survey on wind turbine condition monitoring and fault diagnosis---Part I: Components and subsystems," IEEE Transactions on Industrial Electronics, vol. 62, no. 10, pp. 6536-6545, 2015.
5. T. Sun, G. Yu, M. Gao, et al., "Fault diagnosis methods based on machine learning and its applications for wind turbines: A review," IEEE Access, vol. 9, pp. 147481-147511, 2021.
6. Z. Chen, A. Mauricio, W. Li, et al., "A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks," Mechanical Systems and Signal Processing, vol. 140, p. 106683, 2020.
7. W. Lu and F. Chu, "Condition monitoring and fault diagnostics of wind turbines," in Proc. 2010 Prognostics and System Health Management Conference, IEEE, 2010, pp. 1-11.
8. D. Liu, W. Cheng, and W. Wen, "Rolling bearing fault diagnosis via STFT and improved instantaneous frequency estimation method," Procedia Manufacturing, vol. 49, pp. 166-172, 2020.
9. P. K. Kankar, S. C. Sharma, and S. P. Harsha, "Rolling element bearing fault diagnosis using wavelet transform," Neurocomputing, vol. 74, no. 10, pp. 1638-1645, 2011.
10. D. Meng, H. Wang, S. Yang, et al., "Fault analysis of wind power rolling bearing based on EMD feature extraction," Computer Modeling in Engineering & Sciences, vol. 130, no. 1, p. 543, 2022.
11. S. Maurya, V. Singh, and N. K. Verma, "Condition monitoring of machines using fused features from EMD-based local energy with DNN," IEEE Sensors Journal, vol. 20, no. 15, pp. 8316-8327, 2019.
12. C. Hu, M. Huang, Q. Yang, et al., "On the use of EEMD and SVM based approach for bearing fault diagnosis of wind turbine gearbox," in Proc. 2016 Chinese Control and Decision Conference (CCDC), IEEE, 2016, pp. 3472-3477.
13. D. T. Hoang and H. J. Kang, "A survey on deep learning based bearing fault diagnosis," Neurocomputing, vol. 335, pp. 327-335, 2019.
14. A. U. Rehman, W. Jiao, Y. Jiang, et al., "Deep learning in industrial machinery: A critical review of bearing fault classification methods," Applied Soft Computing, vol. 171, p. 112785, 2025.
15. D. Wang, Q. Guo, Y. Song, et al., "Application of multiscale learning neural network based on CNN in bearing fault diagnosis," Journal of Signal Processing Systems, vol. 91, no. 10, pp. 1205-1217, 2019.
16. C. Guo, V. V. Potekhin, P. Li, et al., "MDFT-GAN: A Multi-Domain Feature Transformer GAN for Bearing Fault Diagnosis Under Limited and Imbalanced Data Conditions," Applied Sciences, vol. 15, no. 11, p. 6225, 2025.
17. K. Yeshun, W. Puzhou, and G. Yingkui, "Toward efficient and interpretative rolling bearing fault diagnosis via quadratic neural network with Bi-LSTM," IEEE Internet of Things Journal, vol. 11, no. 13, pp. 23002-23019, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fei Li, Xueming Zhai (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
