Electrical Engineering

Jingwei Yang1This email address is being protected from spambots. You need JavaScript enabled to view it., Xiaocong Chen2, Shengxian Cao3, Bo Zhao3, Zhenhao Tang3, Gong Wang3, Xingyu Li3, and Han Gao3

1Zhongdian Huachuang Electric Power Technology Research Co., Ltd., 215123, Suzhou, China.

2Hubei Zhongdian Chunyangshan wind power Co., LTD., 430040, Wuhan, China.

3Northeast Electric Power University, 132012, Jilin, China.

 

 

Received: December 30, 2024
Accepted: February 25, 2025
Publication Date: March 28, 2025

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.


Download Citation: ||https://doi.org/10.6180/jase.202512_28(12).0002  


Wind turbine generators operate in harsh areas for a long time, resulting in frequent problems such as blade breakage, and traditional blade defect detection methods have low detection accuracy. In this paper, an end-to end target detection algorithm FRE-DETR based on wind turbine blade defects is designed, and the detection speed and detection accuracy of the end-to-end detection model are further improved by redesigning the feature extraction location in the backbone network and proposing a feature selection and fusion module. FRE-DETR is tested on a wind turbine blade defect dataset, and the results show that the model improves the detection accuracy by 2% compared with RTDETR-R18. The inference speed is already higher than RTDETR-R18 when the step size is larger than 2. The Gflops of the model is only 66.8% of that of RTDETR-R18, which also greatly reduces the computational requirements of the hardware when deployed. FRE-DETR meets the requirements of real-time detection.


Keywords: Integrated energy system; End-to-end algorithm; Wind Turbine Blade Defect; Target Detect; Computer Vision


  1. [1] F. Jaramillo, J. M. Gutiérrez, M. Orchard, M. Guar ini, and R. Astroza, (2022) “A Bayesian approach for fatigue damage diagnosis and prognosis of wind turbine blades" Mechanical Systems and Signal Processing 174: 109067. DOI: 10.1016/j.ymssp.2022.109067.
  2. [2] K. Kong, K. Dyer, C. Payne, I. Hamerton, and P. M. Weaver, (2023) “Progress and trends in damage detec tion methods, maintenance, and data-driven monitoring of wind turbine blades–A review" Renewable Energy Focus 44: 390–412. DOI: 10.1016/j.ref.2022.08.005.
  3. [3] Y.Wang,T.Peng,W.Wang,andM.Luo,(2023)“High efficient view planning for surface inspection based on parallel deep reinforcement learning" Advanced Engi neering Informatics 55: 101849. DOI: 10.1016/j.aei.2022.101849.
  4. [4] L. Wang and Z. Zhang, (2017) “Automatic detection of wind turbine blade surface cracks based on UAV-taken images" IEEE Transactions on Industrial Electronics 64(9): 7293–7303. DOI: 10.1109/tie.2017.2682037.
  5. [5] J. Zhu, C. Wen, and J. Liu, (2022) “Defect identification of wind turbine blade based on multi-feature fusion resid ual network and transfer learning" Energy Science & Engineering 10(1): 219–229. DOI: 10.1002/ese3.1024.
  6. [6] J. Zhang, G. Cosma, and J. Watkins, (2021) “Image enhanced mask R-CNN: A deep learning pipeline with new evaluation measures for wind turbine blade defect detection and classification" Journal of Imaging 7(3): 46. DOI: 10.3390/jimaging7030046.
  7. [7] Y.-h. Liu, Y.-q. Zheng, Z.-f. Shao, T. Wei, T.-c. Cui, and R. Xu, (2024) “Defect detection of the surface of wind turbine blades combining attention mechanism" Advanced Engineering Informatics 59: 102292. DOI: 10.1016/j.aei.2023.102292.
  8. [8] X.Ran, S. Zhang, H. Wang, and Z. Zhang, (2022) “An improved algorithm for wind turbine blade defect detec tion" IEEE Access 10: 122171–122181. DOI: 10.1002/adts.202100631.
  9. [9] L. Liu, P. Li, D. Wang, and S. Zhu, (2024) “A wind turbine damage detection algorithm designed based on YOLOv8"Applied Soft Computing 154: 111364. DOI: 10.1016/j.asoc.2024.111364.
  10. [10] H.Yu, J. Wang, Y. Han, B. Fan, and C. Zhang, (2024) “Research on an intelligent identification method for wind turbine blade damage based on CBAM-BiFPN-YOLOV8" Processes 12(1): 205. DOI: 10.3390/pr12010205.
  11. [11] Y. Yao, G. Wang, and J. Fan, (2023) “WT-YOLOX: An efficient detection algorithm for wind turbine blade damage based on YOLOX" Energies 16(9): 3776. DOI: 10.3390/en16093776.
  12. [12] Y. Liu, Z. Wang, X. Wu, F. Fang, and A. S. Saqlain, (2022) “Cloud-edge-end cooperative detection of wind tur bine blade surface damage based on lightweight deep learning network" IEEE internet computing 27(1): 43–51. DOI: 10.1109/mic.2022.3175935.
  13. [13] Y.Zhang, Y. Yang, J. Sun, R. Ji, P. Zhang, and H. Shan, (2023) “Surface defect detection of wind turbine based on lightweight YOLOv5s model" Measurement 220: 113222. DOI: 10.1016/j.measurement.2023.113222.
  14. [14] C. Zhang, T. Yang, and J. Yang, (2022) “Image recogni tion of wind turbine blade defects using attention-based MobileNetv1-YOLOv4 and transfer learning" Sensors 22(16): 6009. DOI: 10.3390/s22166009.
  15. [15] W. Chen, G. Zhu, M. Mao, X. Xi, W. Xiong, L. Liu, S. Wang, and Y. Chen. “Defect detection method of wind turbine blades based on improved YOLOv4”. In: 2022 International Conference on Sensing, Measure ment & Data Analytics in the era of Artificial Intelligence (ICSMD). IEEE. 2022, 1–4. DOI: 10.1109/ICSMD57530.2022.10058380.
  16. [16] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo. “Swin transformer: Hierarchical vision transformer using shifted windows”. In: Proceedings of the IEEE/CVF international conference on computer vision. 2021, 10012–10022. DOI: 10.48550/arXiv.2103.14030.
  17. [17] X. Liu, H. Peng, N. Zheng, Y. Yang, H. Hu, and Y. Yuan. “Efficientvit: Memory efficient vision trans former with cascaded group attention”. In: Proceed ings of the IEEE/CVF conference on computer vision and pattern recognition. 2023, 14420–14430. DOI: 10.48550/arXiv.2305.07027.
  18. [18] Y. Zhao, W. Lv, S. Xu, J. Wei, G. Wang, Q. Dang, Y. Liu, and J. Chen. “Detrs beat yolos onreal-time object detection”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024, 16965–16974. DOI: 10.48550/arXiv.2304.08069.
  19. [19] X. Liu, Z. Rao, Y. Zhang, and Y. Zheng. “UAVs Im ages Based Real-Time Insulator Defect Detection with Transformer Deep Learning”. In: 2023 IEEE In ternational Conference on Robotics and Biomimetics (RO BIO). IEEE. 2023, 1–6. DOI: 10.1109/ROBIO58561.2023.10354816.
  20. [20] E. Guemas, B. Routier, T. Ghelfenstein-Ferreira, C. Cordier, S. Hartuis, B. Marion, S. Bertout, E. Varlet Marie, D. Costa, and G. Pasquier, (2024) “Automatic patient-level recognition of four Plasmodium species on thin blood smear by a real-time detection transformer (RT DETR) object detection algorithm: a proof-of-concept and evaluation" Microbiology Spectrum 12(2): e01440–23. DOI: 10.1128/spectrum.01440-23.
  21. [21] H.Ouyang,(2023)“Deyov3: Detr with yolo for real-time object detection" arXiv preprint arXiv:2309.11851: DOI: 10.48550/arXiv.2309.11851.
  22. [22] J. Chen, S.-h. Kao, H. He, W. Zhuo, S. Wen, C.-H. Lee, and S.-H. G. Chan. “Run, don’t walk: chasing higher FLOPS for faster neural networks”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023, 12021–12031.
  23. [23] J. Hu, L. Shen, and G. Sun. “Squeeze-and-excitation networks”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, 7132 7141. DOI: 10.1109/tpami.2019.2913372.
  24. [24] D. Wan, R. Lu, S. Shen, T. Xu, X. Lang, and Z. Ren, (2023) “Mixedlocal channel attention for object detection" Engineering Applications of Artificial Intelligence 123: 106442. DOI: 10.1016/j.engappai.2023.106442.
  25. [25] Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu. “ECA-Net: Efficient channel attention for deep con volutional neural networks”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020, 11534–11542.
  26. [26] G. Wang, Y. Chen, P. An, H. Hong, J. Hu, and T. Huang,(2023) “UAV-YOLOv8:Asmall-object-detection model based on improved YOLOv8 for UAV aerial photog raphy scenarios" Sensors 23(16): 7190. DOI: 10.3390/s23167190.
  27. [27] X. Jiang, X. Zhuang, J. Chen, J. Zhang, and Y. Zhang, (2024) “YOLOv8-MU: an improved YOLOv8 underwa ter detector based on a large kernel block and a multi branch reparameterization module" Sensors 24(9): 2905. DOI: 10.3390/s24092905.
  28. [28] A. K. Aggarwal, (2023) “A review on genomics data analysis using machine learning" Wseas Trans. Biol. Biomed 20: 119–131. DOI: 10.37394/23208.2023.20.12.
  29. [29] A.K. Aggarwal, (2014) “Rehabilitation of the blind us ing audio to visual conversion tool" Journal of Biomed ical Engineering and Medical Imaging 1(4): 24–31.
  30. [30] S. J. Mambou, P. Maresova, O. Krejcar, A. Selamat, and K. Kuca, (2018) “Breast cancer detection using in frared thermal imaging and a deep learning model" Sen sors 18(9): 2799. DOI: 10.3390/s18092799.
  31. [31] A.Foster,O.Best,M.Gianni,A.Khan,K.Collins,and S. Sharma. “Dronefootage windturbinesurface dam age detection”. In: 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). IEEE. 2022, 1–5. DOI: 10.1109/IVMSP54334.2022.9816220.
  32. [32] A. Shihavuddin, X. Chen, V. Fedorov, A. Nymark Christensen, N. Andre Brogaard Riis, K. Branner, A. Bjorholm Dahl, and R. Reinhold Paulsen, (2019) “Wind turbine surface damage detection by deep learning aided drone inspection analysis" Energies 12(4): 676. DOI: 10.3390/en12040676.
  33. [33] X.Wang,J. Xia, J. H. Park, X. Xie, and G. Chen, (2022) “Event-triggered adaptive tracking with guaranteed tran sient performance for switched nonlinear systems under asynchronous switching" IEEE Transactions on Cy bernetics 54(1): 496–505. DOI: 10.1109/tcyb.2022.3223983.
  34. [34] X.Wang,J. Xia, J. H. Park, X. Xie, and G. Chen, (2022) “Intelligent control of performance constrained switched nonlinear systems with random noises and its applica tion: An event-driven approach" IEEE Transactions on Circuits and Systems I: Regular Papers 69(9): 3736 3747. DOI: 10.1109/tcsi.2022.3175748.

Latest Articles

Hummingbird-Inspired Modified Particle Swarm Optimization for Efficient Task Scheduling in Cloud Computing
Hummingbird-Inspired Modified Particle Swarm Optimization for Efficient Task Scheduling in Cloud ComputingVolume 28, Issue 12 (In Press)

Read more: ...

MPTTF-BERT: Multi-Prefix-Tuning Template Fusion by BERT for Zero-shot English Text Relation Extraction Model
MPTTF-BERT: Multi-Prefix-Tuning Template Fusion by BERT for Zero-shot English Text Relation Extraction ModelVolume 28, Issue 12 (In Press)

Read more: ...

Advancing Pile-Bearing Capacity Prediction with Meta-Heuristic Enhanced Specific ANFIS strategys
Advancing Pile-Bearing Capacity Prediction with Meta-Heuristic Enhanced Specific ANFIS strategysVolume 28, Issue 12 (In Press)

Read more: ...

Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR network
Research on surface loss detection algorithm of wind turbine blade based on FRE-DETR networkVolume 28, Issue 12 (In Press)

Read more: ...

Dynamic Soft Sensor Modeling and Its Application Using TCN-CBAM-LSTM Method
Dynamic Soft Sensor Modeling and Its Application Using TCN-CBAM-LSTM MethodVolume 28, Issue 12 (In Press)

Read more: ...

Employment of a Radial Basis Function Model for Predicting the Heating Load of Construction
Employment of a Radial Basis Function Model for Predicting the Heating Load of ConstructionVolume 28, Issue 12 (In Press)

Read more: ...

Study on the Compounding of Xanthan Gum and Guar Gum and Joint Soil Consolidation Performance with Roots
Study on the Compounding of Xanthan Gum and Guar Gum and Joint Soil Consolidation Performance with RootsVolume 28, Issue 11 (In Press)

Read more: ...

Mining Data Patterns in Chinese-English Translation via Multi-granularity Contrastive Learning
Mining Data Patterns in Chinese-English Translation via Multi-granularity Contrastive LearningVolume 28, Issue 11 (In Press)

Read more: ...

Mobile robot visual image hierarchical matching algorithm based on deep reinforcement learning and orthogonal matching pursuit
Mobile robot visual image hierarchical matching algorithm based on deep reinforcement learning and orthogonal matching pursuitVolume 28, Issue 11 (In Press)

Read more: ...