Uçuşa Elverişlilik İçin Derin Öğrenme Tabanlı Pist Yüzeyi Çatlak Tespiti Yaklaşımı
Uçuş emniyeti, havacılık endüstrisindeki önemli konulardan biridir. Uçuş emniyetini doğrudan etkileyen hususlardan biri ise uçuş pistlerinin yüzey şartlarıdır. Pistlerin yüzey şartlarının denetim ve kontrolleri güvenli bir uçuş için büyük önem arz eder. Pist yüzeylerinde denetlenen başlıca durumlar, çatlama, kırılma, kopma, açılma ve kabarma gibi zemin hasarlarıdır. İlgili denetimsel işlemler zaman alıcı süreçler olup, alanında eğitim almış uzman personel tarafından yapılmaktadır. Derin öğrenme, son yıllarda popülerliği oldukça artan bir makine öğrenmesi yaklaşımıdır. Bu çalışmada, uçuş pistlerinin yüzeylerindeki çatlaklıkların tespitini yapmak amacıyla iki farklı derin öğrenme modeli geliştirilmiştir. İlk model bu çalışmaya yönelik baştan tasarlanan ve sıfırdan eğitilen özgün bir evrişimli sinir ağı iken; ikinci model AlexNet mimarisinin aktarmalı öğrenme yoluyla bu çalışmaya özgü eğitilmiş sürümüdür. Modeller, veriler üzerinde test edilmiş ve elde ettikleri başarı oranları raporlanmıştır.
___
- [1] Sivil Havacılık Genel Müdürlüğü. 2016. Havaalanı Pistleri, HAD/T-283-37.
- [2] Zhang, J., Qian, S., Tan, C., 2022. Automated Bridge Surface Crack Detection And Segmentation Using Computer
Vision-Based Deep Learning Model, Engineering Applications of Artificial Intelligence, 115(1-13).
- [3] Yazgan, E., Yılmaz, A.K., 2019. Prioritization of Factors Contributing to Human Error for Airworthiness
Management Strategy with ANP. Aircraft Engineering and Aerospace Technology, 91(78-93).
- [4] Tatlı, A., 2016. Uçuşa Elverişliliğin Meteorolojik Açıdan İncelenmesi ve Kısa Vadeli Kestirim Modeli İçin
Zaman Serilerinde Yapay Sinir Ağları Yaklaşımı: Hasan Polatkan Havaalanı Örneği. Anadolu Üniversitesi,
Yüksek Lisans Tezi, Eskişehir.
- [5] Wang, H., vd., 2019. Civil Aviation Safety Evaluation Based on Deep Belief Network and Principal Component
Analysis. Elsevier Safety Science, 112(90-95).
- [6] Inacio, F.R., vd., 2008. Object Detection and Identification Applied to Planes and Aircraft for Airport
Surveillance, 2008 23rd International Conference Image and Vision Computing New Zealand.
- [7] Tsai, Y. vd., 2015. Innovative Crack Sealing Analysis and Cost Estimation for Airport Runway Shoulders Using
3D Laser Technology and Automatic Crack Detection Algorithms. Airfield and Highway Pavements, 652-661.
- [8] Yang, F., Zhang, L., Yu, S., 2019. Feature Pyramid and Hierarchical Boosting Network for Pavement Crack
Detection. IEEE Transactions on Intelligent Transportation Systems, 21(1525-1535).
- [9] Jiang, L., Xie, Y., Ren, T., 2020. Deep Neural Networks Approach for Pixel-Level Runway Pavement Crack
Segmentation Using Drone-Captured Images, arXiv, 2001.03257.
- [10] Peng, L. vd., 2015. Research on Crack Detection Method of Airport Runway Based on Twice-Threshold
Segmentation. 2015 Fifth International Conference on Instrumentation and Measurement, Computer,
Communication and Control, 1716-1720.
- [11] Jo, J., Jadidi, Z., 2020. A High Precision Crack Classification System Using Multi-Layered İmage Processing and
Deep Belief Learning. Structure And Infrastructure Engineering, 16(297-305).
- [12] Gopalakrishnan, K. vd., 2017. Deep Convolutional Neural Networks with Transfer Learning For Computer
Vision-Based Data-Driven Pavement Distress Detection. Construction and Building Materials, 157(322–330).
- [13] Qurishee, M.A. vd., 2020. Bridge Girder Crack Assessment Using Faster RCNN Inception V2 and Infrared
Thermography. Journal of Transportation Technologies, 10(110-127).
- [14] Gopalakrishnan, K., 2018. Deep Learning in Data-Driven Pavement Image Analysis and Automated Distress
Detection: A Review, Data, 3(28), 2-19.
- [15] Gopalakrishnan, K. vd., 2018. Crack Damage Detection in Unmanned Aerial Vehicle Images of Civil
Infrastructure Using Pre-Trained Deep Learning Model. International Journal for Traffic and Transport
Engineering, 8(1-14).
- [16] Cha, Y.-J., Choi, W., Büyüköztürk, O., 2017. Deep Learning-Based Crack Damage Detection Using Convolutional
Neural Networks. Computer-Aided Civil and Infrastructure Engineering, 32(361-378).
- [17] Coca, Georgiana Lucia vd., 2020. Crack Detection System in AWS Cloud Using Convolutional Neural Networks.
Procedia Computer Science, 176(400-409).
- [18] Ha, J., Park, K. ve Kim, M., 2021. A Development of Road Crack Detection System Using Deep Learning-based
Segmentation and Object Detection. The Journal of Society for e-Business Studies, 26(93-106).
- [19] Yang, X., Li, H., Yu, Y., Luo, X., Huang, T. and Yang, X., 2018. Automatic Pixel-Level Crack Detection and
Measurement Using Fully Convolutional Network, Computer-Aided Civil and Infrastructure Engineering,
33(12), 1090-1109.
- [20] Ni, F. and Zhang, J., 2018. Pixel-Level Crack Delineation in Images with Convolutional Feature Fusion,
Structural Control and Health Monitoring, e2286, 26(1–18).
- [21] Ronneberger, O., Fischer, P. and Brox, T., 2015. U-net: Convolutional Networks for Biomedical Image
Segmentation, International Conference on Medical image computing and computer-assisted intervention,
234–241.
- [22] Cha, Y.J., Choi, W., Büyüköztürk, O., 2017. Deep Learning-Based Crack Damage Detection Using Convolutional
Neural Networks. Computer-Aided Civil and Infrastructure Engineering, 5(361–378).
- [23] Zhang, L., Yang, F., Daniel Zhang, Y., Zhu, Y.J., 2016. Road Crack Detection Using Deep Convolutional Neural
Network, 2016 IEEE International Conference on Image Processing (ICIP), 3708–3712.
- [24] Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., Omata, H., 2018. Road Damage Detection Using Deep Neural
Networks with Images Captured Through a Smartphone, arXiv preprint, arXiv:1801.09454
- [25] Makantasis, K., Protopapadakis, E., Doulamis, A., Doulamis, N., Loupos, C., 2015. Deep Convolutional Neural
Networks for Efficient Vision Based Tunnel Inspection, Proceedings-2015 IEEE 11th International
Conference on Intelligent Computer Communication and Processing, ICCP 2015, 335–342.
- [26] Stentoumis, C., Protopapadakis, E., Doulamis, A. and Doulamis, N., 2016. A Holistic Approach for Inspection of
Civil Infrastructures Based on Computer Vision Techniques, International Archives of the Photogrammetry,
Remote Sensing and Spatial Information Sciences- ISPRS Archives, 131–138.
- [27] Sevinç, A., Özyurt, F., 2022. Beton Yüzey Çatlaklarının Tespitinde Derin Öğrenme Mimarilerin Kullanılması,
International Journal of Innovative Engineering Applications , 6(318-325).
- [28] McCulloch, W.S., Pitts, W. 1943. A Logical Calculus of The Ideas Immanent in Nervous Activity. The Bulletin of
Mathematical Biophysics, 5(115-133).
- [29] Yakıt, O., Özkan, Y., 2017. Kurumsal Kaynak Planlama Sistemlerinde Yapay Sinir Ağlarının Değerlendirilmesi
Yaklaşımı. Siyaset, Ekonomi ve Yönetim Araştırmaları Dergisi, 5(287-296).
- [30] Karpathy, A., Stanford University CS231n Convolutional Neural Networks for Visual Recognition Course
Notes, 2019, (http://cs231n.github.io/), (Ağustos 2022)
- [31] Bengio, Y., 2009. Learning deep architectures for AI. Foundations and Trends in Machine Learning, 2(1-127).
- [32] Deng, L., Yu, D. 2013. Deep Learning: Methods and Applications. Found. Trends Signal Process. 7(197-387).
- [33] LeCun, Y., Bengio, Y., Hinton, G., 2015. Deep Learning. Nature. 521(436-444).
- [34] Brownlee, J., 2019, What is Deep Learning?, (https://machinelearningmastery.com/what-is-deep-learning/),
(Mayıs 2022)
- [35] Akmeşe, Ö.F., Erbay, H., Kör, H., 2018. Derin Öğrenme ile Görüntü Kümeleme. 5th International Management
Information Systems Conference, 108-110.
- [36] Ferentinos, K.P. 2018. Deep Learning Models for Plant Disease Detection and Diagnosis. Computers and
Electronics in Agriculture,145(311-318).
- [37] N. Kruger vd., 2013. Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1847-1871).
- [38] Introducing Deep Learning with MATLAB, https://www.mathworks.com/campaigns/offers/next/deeplearning-ebook.html, (Erişim Tarihi: Ağustos 2022).
- [39] Brownlee, J., A Gentle Introduction to Dropout for Regularizing Deep Neural Networks, 2018,
(https://machinelearningmastery.com/dropout-for-regularizing-deep-neural-networks/) (Erişim Tarihi:
Ağustos 2022)
- [40] Geetharamani, G., Arun Pandian, J., 2019. Identification of Plant Leaf Disease Using A Nine Layer Deep
Convolutional Neural Network. Computers and Electrical Engineering, 76(323-338).
- [41] Shi, Y., Cui, L., Qi, Z., Meng, F. and Chen, Z., 2016. Automatic Road Crack Detection Using Random Structured
Forests. IEEE Transactions on Intelligent Transportation Systems, 17(3434–3445).
- [42] Zou, Q., Cao, Y., Li, Q., Mao, Q. and Wang, S., 2012. Cracktree: Automatic Crack Detection from Pavement
Images. Pattern Recognition Letters, 33(227–238).
- [43] Eisenbach, M., Stricker, R., Seichter, D., Amende, K., Debes, K., Sesselmann, M., Ebersbach, D., Stoeckert, U.,
Gross, H.-M., 2017. How to Get Pavement Distress Detection Ready for Deep Learning? A Systematic
Approach, International Joint Conference on Neural Networks, 2039–2047.
- [44] Amhaz, R., Chambon, S., Idier, J. and Baltazart, V., 2016. Automatic Crack Detection on Two-Dimensional
Pavement Images: An Algorithm Based on Minimal Path Selection, IEEE Transactions on Intelligent
Transportation Systems, 17(2718–2729).