Ramazan DUVAR, Oğuzhan URHAN, Mustafa BÖYÜK

Uçak Bakımında Görsel Muayene Yöntemleri Üzerine Bir İnceleme

Uçak bakımı sırasında çatlak, yanık, korozyon gibi hasarların kontrolü hassasiyetle yapılması gereken bir işlemdir. Bundan dolayı yapılan işlem uzun bir zaman alabilmektedir. Hızlı kontrol yapıldığı zamanlarda ise hataların takibi sağlıklı bir şekilde gerçekleştirilememektedir. Bununla birlikte kontrol işlemi genellikle göz ile gerçekleştirildiği için insan kaynaklı risklere oldukça açıktır. Son yıllarda yapay zekanın uygulama alanının genişlemesi ile birlikte hava taşıtları bakım ve arıza işlemlerinin gerçekleştirilmesinde modern tekniklerin kullanımı havacılık sektöründe giderek artmaktadır. Bu çalışmada, uçak bakım ve onarımında yer alan derin öğrenme tabanlı görsel inceleme yöntemleri incelenmiştir.

A Review on Visual Inspection Methods for Aircraft Maintenance

During aircraft maintenance, the control of damages such as crack, burn, corrosion should be done precisely. Therefore, the process can take a long time. In the case of rapid control, errors cannot be detected properly. However, since the control process is usually carried out by naked eye, it is quite open to human-induced risks. In recent years, with the expansion of the application area of artificial intelligence, the use of modern techniques in aircraft maintenance and breakdown operations has been increasing in the aviation industry. In this study, deep learning-based visual inspection methods involved in aircraft maintenance and repair are surveyed.

PDF

___

[1] K. A. Latorella and P. V. Prabhu, “A review of human error in aviation maintenance and inspection,” International Journal of Industrial Ergonomics, vol. 26, pp. 521-549, August 2000.
[2] Y.-H. Chang and Y.-C. Wang, “Significant human risk factors in aircraft maintenance technicians,” Safety Science, vol. 48, pp. 54–62, January 2010.
[3] U. Polimeno and M. Meo, “Detecting barely visible impact damage detection on aircraft composites structures,” Composite Structures, vol. 91, pp. 398–402, December 2009.
[4] R. Çoban, “Uçak Bakım Sektöründe İş Yükü ve Zaman Baskısı Üzerine Bir Örnek Olay Araştırması,” Journal of Aviation, vol. 3, June 2019.
[5] M. A. Kayrak, “Uçak Bakım Planlamasında Hata Analizi,” Mühendis ve Makina, vol. 53, pp.34-39, June 2012.
[6] T.-C. Wang and L.-H. Chuang, “Psychological and physiological fatigue variation and fatigue factors in aircraft line maintenance crews,” International Journal of Industrial Ergonomics, vol. 44, pp. 107– 113,January 2014.
[7] K. Yuan, Y. Yu, and X. Liu, “Aircraft cable fault location system based on principle of regression analysis,” in 2010 5th International Conference on Computer Science & Education, Hefei, China, August 24-27, 2010, pp.1226–1229.
[8] M. Boyuk, R. Duvar, and O. Urhan, “Deep Learning Based Vehicle Detection with Images Taken from Unmanned Air Vehicle,” in 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), Istanbul, Turkey, October 15-17, 2020, pp. 1– 4.
[9] K. Erdogan, O. Acun, A. Kucukmanisa, R. Duvar, A. Bayramoglu, and O. Urhan, “KEBOT: An Artificial Intelligence Based Comprehensive Analysis System for FUE Based Hair Transplantation,” IEEE Access, vol. 8, pp.200461–200476, 2020.
[10] Z. Jiao, G. Jia, and Y. Cai, “A new approach to oil spill detection that combines deep learning with unmanned aerial vehicles,” Computers & Industrial Engineering, vol. 135, pp. 1300–1311, September. 2019.
[11] Y. Wu, Y. Qin, Z. Wang, and L. Jia, “A UAV- Based Visual Inspection Method for Rail Surface Defects,” Applied Sciences, vol. 8, p. 1028, June 2018.
[12] “Aircraft Corrosion,” 2016. [Online]. Available: https://www.aopa.org/go-fly/aircraft-and- ownership/maintenance-and-inspections/aircraft- corrosion [Accessed Dec. 24, 2020].
[13] T. S. B. of C. Government of Canada, “Aviation Investigation Report A13C0105,”, 2015. [Online].Available:.https://www.bsttsb.gc.ca/eng/rapp ortsreports/aviation/2013/a13c0105/a13c0105.html [Accessed Dec. 24, 2020].
[14] Yu. B. Blokhinov, V. A. Gorbachev, A. D. Nikitin, and S. V. Skryabin, “Technology for the Visual Inspection of Aircraft Surfaces Using Programmable Unmanned Aerial Vehicles,” J. Comput. Syst. Sci. Int., vol. 58, pp. 960–968, November 2019.
[15] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” arxiv.org, April. 2018, [Online]. Available: http://arxiv.org/abs/1804.02767. [Accessed: Jun. 08, 2020].
[16] T. Malekzadeh, M. Abdollahzadeh, H. Nejati, and N.-M. Cheung, “Aircraft Fuselage Defect Detection using Deep Neural Networks,”,arxiv.org, December. 2017, [Online]. Available: http://arxiv.org/abs/1712.09213. [Accessed: Feb. 27, 2021].
[17] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, pp. 84–90, May 2017.
[18] K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman, “Return of the Devil in the Details: Delving Deep into Convolutional Nets,” arxiv.org, November. 2014, [Online]. Available: http://arxiv.org/abs/1405.3531. [Accessed: Oct. 03, 2020].
[19] Zhenhua Guo, Lei Zhang, and D. Zhang, “A Completed Modeling of Local Binary Pattern Operator for Texture Classification,” IEEE Trans. on Image Process., vol. 19, pp. 1657–1663, June 2010.
[20] B. Ramalingam., “Visual Inspection of the Aircraft Surface Using a Teleoperated Reconfigurable Climbing Robot and Enhanced Deep Learning Technique,” International Journal of Aerospace Engineering, vol. 2019, pp. 1–14, September 2019.
[21] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.&Y. Fu, A. C. Berg “SSD: Single Shot MultiBox Detector” arxiv.org, December 2015, [Online]. Available: https://arxiv.org/abs/1512.02325. [Accessed: Jun. 01,2020].
[22] S. Bouarfa, A. Doğru, R. Arizar, R. Aydoğan, and J. Serafico, “Towards automated aircraft maintenance inspection. A use case of detecting aircraft dents using mask r-cnn,” in AIAA Scitech 2020 Forum, vol. 1, January 2020.
[23] Y. Li, Z. Han, H. Xu, L. Liu, X. Li, and K. Zhang, “YOLOv3-Lite: A Lightweight Crack Detection Network for Aircraft Structure Based on Depthwise Separable Convolutions,” Applied Sciences, vol. 9, p. 3781, September 2019.
[24] S. Li, P. Zheng and L. Zheng, "An AR-Assisted Deep Learning-Based Approach for Automatic Inspection of Aviation Connectors," IEEE Transactions on Industrial Informatics, vol. 17, pp. 1721-1731, March 2021.
[25] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal Loss for Dense Object Detection,” arxiv.org, February. 2018 .[Online]. Available:http://arxiv.org/abs/1708.02002. [Accessed: Oct. 08,2020].
[26] W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, and A. Stolcke, “The Microsoft 2017 Conversational Speech Recognition System,” ,arXiv.org, August. 2017. [Online]. Available: http://arxiv.org/abs/1708.06073. [Accessed: Jun. 08, 2020].
[27] N. Çoruh, F. Aras, N. Kaya, and İ. Ciğerci, “Uçak Kablo Sisteminde Meydana Gelen Yaşlanma ve Bozulmaların Bakım Odaklı Değerlendirilmesi,” Mühendis ve Makina, vol. 60, pp. 1–9, June 2019.
[28] Z. An, Y. Wang, L. Zheng, and X. Liu, “Adaptive recognition of intelligent inspection system or cable brackets in multiple assembly scenes,” Int J Adv Manuf Technol, vol. 108, pp. 3373–3389, June 2020.
[29] M. Siegel, “Enhanced remote visual inspection of aircraft skin,” Proc. Intell. NDE Sci., February 2021. [Online].Available:https://www.academia.edu/100576 1/Enhanced_remote_visual_inspection_of_aircraft_ski n. [Accessed: Jun. 08, 2020].