Volume 7, Issue 4 (12-2025)
sjis 2025, 7(4): 1-7 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Alavi F, Sharifzadeh M. Hybrid Deep Learning for Wind Turbine Fault Detection. sjis 2025; 7 (4) :1-7
URL: http://sjis.srpub.org/article-5-262-en.html
URL: http://sjis.srpub.org/article-5-262-en.html
1- Sharif Energy, Water and Environment Institute (SEWEI), Sharif University of Technology, Tehran, Iran.
2- Sharif Energy, Water and Environment Institute (SEWEI), Sharif University of Technology, Tehran, Iran. & Imperial College London: London, London, GB ,m.sharifzadeh@ucl.ac.uk
2- Sharif Energy, Water and Environment Institute (SEWEI), Sharif University of Technology, Tehran, Iran. & Imperial College London: London, London, GB ,
Abstract: (67 Views)
Wind turbine fault detection is crucial for maintaining efficient and reliable renewable energy systems. This paper introduces a novel hybrid deep learning architecture, LSTM-Attention-CapsNet, which combines Long Short-Term Memory networks, attention mechanisms, and Capsule Networks for time series-based fault detection in wind turbines. Our proposed model achieved unprecedented performance metrics when tested on a wind turbine dataset, attaining 1 accuracy, F1 score, precision, and recall. This exceptional performance marks a significant advancement in fault detection capabilities, potentially revolutionizing predictive maintenance strategies in the wind energy sector. Our findings herald a new era in wind turbine fault detection and condition monitoring, promising substantial improvements in the efficiency and reliability of wind energy production.
Keywords: Wind Turbine, Fault Detection, Deep Learning, LSTM, Attention Mechanism, Capsule Neural Networks
Type of Study: Research |
Subject:
Energy Engineering and Power Technology
Received: 2025/10/5 | Revised: 2025/11/18 | Accepted: 2025/12/3 | Published: 2025/12/25
Received: 2025/10/5 | Revised: 2025/11/18 | Accepted: 2025/12/3 | Published: 2025/12/25
References
1. Long, X. F., Yang, P., Guo, H. X., & Wu, X. W. (2017). Review of fault diagnosis methods for large wind turbines. Power system technology, 41(11), 3480-3490.
2. Lebranchu, A., Charbonnier, S., Bérenguer, C., & Prévost, F. (2019). A combined mono-and multi-turbine approach for fault indicator synthesis and wind turbine monitoring using SCADA data. ISA transactions, 87, 272-281. [DOI:10.1016/j.isatra.2018.11.041] [PMID]
3. Yu, D., Chen, Z. M., Xiahou, K. S., Li, M. S., Ji, T. Y., & Wu, Q. H. (2018). A radically data-driven method for fault detection and diagnosis in wind turbines. International Journal of Electrical Power & Energy Systems, 99, 577-584. [DOI:10.1016/j.ijepes.2018.01.009]
4. Laouti, N., Sheibat-Othman, N., & Othman, S. (2011). Support vector machines for fault detection in wind turbines. IFAC Proceedings Volumes, 44(1), 7067-7072. [DOI:10.3182/20110828-6-IT-1002.02560]
5. Qiu, Y., Jiang, H., Feng, Y., Cao, M., Zhao, Y., & Li, D. (2016). A new fault diagnosis algorithm for PMSG wind turbine power converters under variable wind speed conditions. Energies, 9(7), 548. [DOI:10.3390/en9070548]
6. Simani, S., & Castaldi, P. (2014). Active actuator fault‐tolerant control of a wind turbine benchmark model. International Journal of Robust and Nonlinear Control, 24(8-9), 1283-1303. [DOI:10.1002/rnc.2993]
7. Mojallal, A., & Lotfifard, S. (2017). Multi-physics graphical model-based fault detection and isolation in wind turbines. IEEE transactions on smart grid, 9(6), 5599-5612. [DOI:10.1109/TSG.2017.2691782]
8. Lei, J., Liu, C., & Jiang, D. (2019). Fault diagnosis of wind turbine based on Long Short-term memory networks. Renewable energy, 133, 422-432. [DOI:10.1016/j.renene.2018.10.031]
9. Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory. Neural computation, 9(8), pp.1735-1780. [DOI:10.1162/neco.1997.9.8.1735] [PMID]
10. Chen, J., Li, J., Chen, W., Wang, Y., & Jiang, T. (2020). Anomaly detection for wind turbines based on the reconstruction of condition parameters using stacked denoising autoencoders. Renewable Energy, 147, 1469-1480. [DOI:10.1016/j.renene.2019.09.041]
11. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł. and Polosukhin, I., 2017. Attention is all you need. Advances in neural information processing systems, 30.
12. Sabour, S., Frosst, N. and Hinton, G.E., 2017. Dynamic routing between capsules. Advances in neural information processing systems, 30.
13. Ahmed, S. F., Alam, M. S. B., Hassan, M., Rozbu, M. R., Ishtiak, T., Rafa, N., ... & Gandomi, A. H. (2023). Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artificial Intelligence Review, 56(11), 13521-13617. [DOI:10.1007/s10462-023-10466-8]
14. Boudiaf, A., Moussaoui, A., Dahane, A., & Atoui, I. (2016). A comparative study of various methods of bearing faults diagnosis using the case Western Reserve University data. Journal of Failure Analysis and Prevention, 16(2), 271-284. [DOI:10.1007/s11668-016-0080-7]
15. Smith, W. A., & Randall, R. B. (2015). Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mechanical systems and signal processing, 64, 100-131. [DOI:10.1016/j.ymssp.2015.04.021] [PMCID]
16. Zhang, X., Zhao, B., & Lin, Y. (2021). Machine learning based bearing fault diagnosis using the case western reserve university data: A review. Ieee Access, 9, 155598-155608. [DOI:10.1109/ACCESS.2021.3128669]
17. J. Platt, et al., Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods, Advances in large margin classifiers 10 (3) (1999) 61-74. [DOI:10.7551/mitpress/1113.003.0008] [PMID]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |