Wenzhe Wang, HuaSu, Xinliang Liu, Jawad Munir, and Jingqiu WangThis email address is being protected from spambots. You need JavaScript enabled to view it.
National Key Laboratory of Helicopter Aeromechanics, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China
Received: July 24, 2024 Accepted: September 12, 2024 Publication Date: November 16, 2024
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.
To address the large number of parameters and the computational complexity of deep learning models in the f ield of borescope detection, we propose a lightweight blade damage detection model LSSD using a knowledge distillation algorithm. First, the inverse residual structure is used to lightweight the backbone network of the classic SSD model. Then, the K-means clustering algorithm is used to optimize the scale and number of anchor boxes to reduce the parameters and computational complexity of the proposed model. Second, to ensure that the lightweight model has a certain level of detection accuracy, a feature fusion module CA-FPN combined with coordinate attention and a small damage detection enhancement module W-Inception are embedded. Finally, the knowledge distillation algorithm is used to further improve the detection accuracy of the model. The number of parameters of the LSSD model is 4.99M, the MACs is 3.541G, and the detection speed reaches 32FPS. Compared with the SSD model, the LSSD model reduces the number of parameters by 79.3% and the computational complexity by 88.42%, resulting in a 2-fold increase in the detection speed.
[1] K. G. Harding, J. Gu, L. Tao, G. Song, and J. Han. “Blade counting tool with a 3D borescope for tur bine applications”. In: Interferometry XVII: Advanced Applications. 9204. SPIE. 2014, 143–152.
[2] Z. Yuan. “Borescope inspection for HPT blade of CFM56-7B engine”. In: IOP Conference Series: Materi als Science and Engineering. 382. IOP Publishing. 2018, 032028.
[3] D.Zhang, N. Zeng, and L. Lin. “Detection of blades damages in aero engine”. In: 2020 Chinese Automation Congress (CAC). IEEE. 2020, 6129–6134.
[4] J. Aust and D. Pons, (2019) “Taxonomy of gas turbine blade defects" Aerospace 6(5): 58.
[5] R. Mishra, J. Thomas, K. Srinivasan, V. Nandi, and R. R. Bhatt, (2017) “Failure analysis of an un-cooled turbine blade in an aero gas turbine engine" Engineering Failure Analysis 79: 836–844.
[6] J. Aust and D. Pons, (2019) “Bowtie methodology for risk analysis of visual borescope inspection during aircraft engine maintenance" Aerospace 6(10): 110.
[7] J. Aust and D. Pons, (2020) “A systematic methodology for developing bowtie in risk assessment: application to borescope inspection" Aerospace 7(7): 86.
[8] M.Li-Yong,H.Chun-Sheng,andH.Yu-Qing.“Defect detection of the irregular turbine blades based on edgepixel direction information”. In: 2018 4th Annual International Conference on Network and Information Systems for Computers (ICNISC). IEEE. 2018, 165–170.
[9] S. Shao and W.Lin. “Compressor Blade Fault Diag nosis Based on Image Processing”. In: 2018 IEEE 4th International Conference on Control Science and Systems Engineering (ICCSSE). IEEE. 2018, 467–471.
[10] C. Y. Wong, P. Seshadri, and G. T. Parks. “Auto matic borescope damage assessments for gas turbine blades via deep learning”. In: AIAA Scitech 2021 Fo rum. 2021, 1488.
[11] C. Cai, Y. Ziyan, and S. Lizhong, (2023) “Aeroengine damage detection method based on improved YOLOv4" Modern Manufacturing Engineering: 99–108. DOI: 10.16731/j.cnki.1671-3133.2023.02.014.
[12] H. Yuhao, C. Xueguo, L. Xinliang, J. Haokun, and W. Jingqiu, (2024) “Real time detection of aircraft engine blade damage based on SW-YOLO model" Journal of Propulsion Technology 45: 197–203. DOI: 10.13675/j.cnki.tjjs.2302058.
[13] X. Li, W. Wang, L. Sun, B. Hu, L. Zhu, and J. Zhang, (2022) “Deep learning-based defects detection of certain aero-engine blades and vanes with DDSC-YOLOv5s" Scientific Reports 12(1): 13067.
[14] H.Shang, C. Sun, J. Liu, X. Chen, and R. Yan, (2022) “Deep learning-based borescope image processing for aero engine blade in-situ damage detection" Aerospace Sci ence and Technology 123: 107473.
[15] W. Yongchao, L. Tao, and D. Yi, (2022) “Research on Intelligent Detection Method of Engine Hole Detection Defects Based on Raspberry PI" Modern Computer 28(8): 100–103+108. DOI: 10.3969/j.issn.1007-1423.2022.08.018.
[16] A. G. Howard, (2017) “Mobilenets: Efficient convolu tional neural networks for mobile vision applications" arXiv preprint arXiv:1704.04861:
[17] X. Zhang, X. Zhou, M. Lin, and J. Sun. “Shufflenet: Anextremely efficient convolutional neural network for mobile devices”. In: Proceedings of the IEEE confer ence on computer vision and pattern recognition. 2018, 6848–6856.
[18] 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 learn ing network" IEEE Internet Computing 27(1): 43–51.
[19] W.Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg. “Ssd: Single shot multibox detector”. In: Computer Vision–ECCV 2016: 14th Euro pean Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer. 2016, 21–37.
[20] S. Ren, K. He, R. Girshick, and J. Sun, (2016) “Faster R-CNN: Towards real-time object detection with region proposal networks" IEEE transactions on pattern anal ysis and machine intelligence 39(6): 1137–1149.
[21] J. Redmon. “You only look once: Unified, real-time object detection”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
[22] M.Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen. “Mobilenetv2: Inverted residuals and lin ear bottlenecks”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, 4510–4520.
[23] T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie. “Feature pyramid networks for ob ject detection”. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017, 2117–2125.
[24] Q. Hou, D. Zhou, and J. Feng. “Coordinate attention for efficient mobile network design”. In: Proceedings of the IEEE/CVF conference on computer vision and pat tern recognition. 2021, 13713–13722.
[25] G.Hinton, (2015) “Distilling the Knowledge in a Neural Network" arXiv preprint arXiv:1503.02531:
[26] A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta, and Y. Bengio, (2014) “Fitnets: Hints for thin deep nets" arXiv preprint arXiv:1412.6550:
We use cookies on this website to personalize content to improve your user experience and analyze our traffic. By using this site you agree to its use of cookies.
