Beton duvar, köprü tabliyesi ve kaldırım yapılarında otonom çatlak tespiti için derin öğrenme yaklaşımları

Year 2024, Volume: 15 Issue: 2, 503 - 513, 30.06.2024

Fethi Şermet , Ishak Pacal

https://doi.org/10.24012/dumf.1450640

Cited By: 1

Abstract

Çatlakların tespiti, beton yapıların incelenmesi ve bakımı, erken müdahalenin sağlanması ve olası hasarların önlenmesi açısından hayati öneme sahiptir. İnşaat mühendisliğinde bilgisayarlı görme ve görüntü işlemenin ortaya çıkışı, geleneksel görsel incelemelerin yerini alarak derin öğrenmeye dayalı yarı otomatik/otomatik tekniklerin yolunu açtı. Otonom teşhisle yönlendirilen bu yöntemlerin çeşitli sektörlerde uygulamaları vardır ve inşaat mühendisliğinde hızlı ilerlemeyi teşvik eder. Bu çalışmada köprüler, yollar ve duvarlardaki çatlakları bağımsız olarak teşhis etmek için görüş transformatörlerini ve evrişimli sinir ağlarını (CNN) birleştiren bir yaklaşım sunulmuştur. Popüler CNN ve ViT mimarileri kullanılarak transfer öğrenimi, veri artırma ve optimize edilmiş hiper parametreler yoluyla performans iyileştirmesi sağlandı. Önerilen yöntem, 56.000'den fazla görüntü içeren SDNET2018 veri kümesi üzerinde test edildi. Deneysel sonuçlar, yaklaşımın etkinliğini gösterdi; yol çatlaklarını %96,41, duvar çatlaklarını %92,76 ve köprü çatlaklarını %92,81 tespit etmede yüksek doğruluk elde etti. Bu bulgular, bu alanda derin öğrenmenin umut verici potansiyelini ortaya çıkarmaktadır.

Keywords

Çatlak tespiti, yapısal çatlaklar, derin öğrenme, görüntü işleme, CNN

Ethical Statement

Çalışmanın yayına kabul edilmesi halinde Dicle Üniversitesi Mühendislik Dergisi'nde (DUJE) yayınlanacaktır. Makalede ismi bulunan yazarlar, Çalışmanın yayınlanması halinde, Çalışmaya ait ve Çalışmaya ilişkin her türlü şekil ve ortamda tüm telif hakkı mülkiyetini Dicle Üniversitesi Mühendislik Dergisi'ne (DUJE) devretmektedir. Ancak Çalışmanın Dergide yayınlanmaması durumunda bu sözleşme geçersiz olacaktır. Makalede ismi bulunan yazarlar, Çalışmanın orijinal olduğunu, başka bir dergi tarafından değerlendirme aşamasında olmadığını ve daha önce yayınlanmadığını garanti eder.

Deep learning approaches for autonomous crack detection in concrete wall, brick deck and pavement

Abstract

Detecting cracks is vital for inspecting and maintaining concrete structures, enabling early intervention and preventing potential damage. The advent of computer vision and image processing in civil engineering has ushered in deep learning-based semi-automatic/automatic techniques, replacing traditional visual inspections. These methods, driven by autonomous diagnosis, have applications across various sectors, fostering rapid progress in civil engineering. In this study, we present an approach that combines vision transformers and convolutional neural networks (CNN) for autonomously diagnosing cracks in bridges, roads, and walls. Performance enhancement was achieved through transfer learning, data augmentation, and optimized hyperparameters, utilizing popular CNN and ViT architectures. The proposed method was tested on the SDNET2018 dataset, comprising over 56,000 images. Experimental results demonstrated the approach's effectiveness, achieving high accuracy in detecting road cracks at 96.41%, wall cracks at 92.76%, and bridge cracks at 92.81%. These findings highlight the promising potential of deep learning in this field.

Keywords

Crack detection, structural cracks, deep learning, image processing, CNN

References

• [1] Kovler, K., & Chernov, V. (2009). Types of damage in concrete structures. In N. Delatte, Failure, distress and repair of concrete structures (pp. 32-56). Boca Raton: Woodhead Publishing Limited.
• [2] Larosche, C. J. (2009). Types and causes of cracking in concrete structures. In N. Delatte, Failure, distress and repair of concrete structures (pp. 57-83). Boca Raton: Woodhead Publishing Limited.
• [3] Ghali, A., Favre, R., & Elbadry, M. (2002). Concrete Structures- Stresses and Deformation. Spon Press.
• [4] ACI Committee 201. (2001). Guide to Durable Concrete. In ACI Manual of Concrete Practrice Part 1 -Materials and General Properties of Concrete (pp. 20 1.2Rl-20 1.2R41). Farmington Hills: American Concrete Institute.
• [5] Daghighi, A. (2020). Full-Scale Field Implementation of Internally Cured Concrete Pavement Data Analysis for Iowa Pavement Systems. Creative Components. 638. https:// lib. dr. iasta te. edu/ creat iveco mpone nts/ 638.
• [6] Hosseini, S., & Smadi, O. (2020). How prediction accuracy can affect the decision-making process in pavement management system. Infrastructures. https:// doi. org/ 10. 31224/ osf. io/ t28ue.
• [7] Abukhalil, Y. B. (2019). Cross asset resource allocation framework for pavement and bridges in Iowa. Graduate Theses and Dissertations. 16951. https:// lib. dr. iasta te. edu/ etd/ 16951.
• [8] N. F. Hawks, and T. P. Teng. (2014). Distress identi_cation manual for the long-term pavement performance project. National academy of sciences.
• [9] R. Amhaz, S. Chambon, J. Idier, and V. Baltazart. (2016). Automatic crack detection on two-dimensional pavement images: an algorithm based on minimal path selection," IEEE Trans. Intell. Transp. Syst., vol. 17, no. 10, pp. 2718-2729.
• [10] I. Abdel, O. Abudayyeh, and M. E. Kelly. (2003). Analysis of edge-detection techniques for crack identi_cation in bridges," J. Computer Civil Eng., vol. 17, no. 4, pp. 255-263.
• [11] P. Lad, and M. Pawar. (2016). Evaluation of railway track crack detection system," in Proc., IEEE ROMA, pp. 1-6.
• [12] E. Aslan ve Y. Özüpak, “Classification of Blood Cells with Convolutional Neural Network Model”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, c. 13, sy. 1, ss. 314–326, 2024, doi: 10.17798/bitlisfen.1401294.
• [13] Lubbad, M. A., Kurtulus, I. L., Karaboga, D., Kilic, K., Basturk, A., Akay, B., ... & Pacal, I. (2024). A Comparative Analysis of Deep Learning-Based Approaches for Classifying Dental Implants Decision Support System. Journal of Imaging Informatics in Medicine, 1-22.
• [14] Kunduracioglu, I., & Pacal, I. (2024). Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases. Journal of Plant Diseases and Protection, 1-20.
• [15] Pacal, I. (2024). A novel Swin transformer approach utilizing residual multi-layer perceptron for diagnosing brain tumors in MRI images. International Journal of Machine Learning and Cybernetics, 1-19.
• [16] Loverdos, D., & Sarhosis, V. (2022). Automatic image-based brick segmentation and crack detection of masonry walls using machine learning. Automation in Construction 140, 104389.
• [17] Ali, R., Chuah, J-H., Abu Talip, M-S., Mokhtar, N., Shoaib, M-A. (2022). Structural crack detection using deep convolutional neural networks. Automation in Construction 133, 103989.
• [18] Xu, Z., Guan, H., Kang, J, Xiangda, L., Ma, L., Yu, Y., Chen, Y., Li, J. (2022). Pavement crack detection from CCD images with a locally enhanced transformer network. International Journal of Applied Earth Observations and Geoinformation, 110,102825.
• [19] Chaiyasarn, K., Buatik, A., Mohamad, H., Zhou, M., Kongsilp, S., Poovarodom, N. (2022). Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures. Automation in Construction, 140, 104388 Available.
• [20] Yu, Y., Samali, B., Rashidi, M., Mohammadi, M., Nguyen, T.N., Zhang, G. (2022). Vision-based concrete crack detection using a hybrid framework considering noise effect. Journal of Building Engineering, 61, 105246.
• [21] Duo Ma, Hongyuan Fang, Niannian Wang, Binghan Xue, Jiaxiu Dong & Fu Wang (2022). A real-time crack detection algorithm for pavement based on CNN with multiple feature layers. Road Materials and Pavement Design, 23:9, 2115-2131, DOI: 10.1080/14680629.2021.1925578.
• [22] Müller, A., Karathanasopoulos, N., Roth, C.C., Mohr, D. (2021). Machine Learning Classifiers for Surface Crack Detection in Fracture Experiments. International Journal of Mechanical Sciences 209, 106698.
• [23] Fang, X., Liu, G., Wang, H., Xie, Y., Tian, X., Leng, D., Mu, W., Ma, P., Li, G. (2022). Fatigue crack growth prediction method based on machine learning model correction. Ocean Engineering 266, 112996.
• [24] Hamidia, M., Mansourdehghan, S., Asjodi, A-H., Dolatshahi, K-M. (2022). Machine learning-based seismic damage assessment of non-ductile RC beam-column joints using visual damage indices of surface crack patterns. Structures 45, 2038–2050.
• [25] Aravind, N., Nagajothi, S., Elavenil, S. (2021). Machine learning model for predicting the crack detection and pattern recognition of geopolymer concrete beams. Construction and Building Materials 297, 123785.
• [26] Han, X., Zhao, Z., Chen, L., Hu, X., Tian, Y., Zhai, C., Wang, L., Huang, X. (2022). Structural damage-causing concrete cracking detection based on a deep-learning method. Construction and Building Materials 337, 127562.
• [27] Laxman, K. C., Tabassum, N., Ai, L., Cole, C., Ziehl, P. (2023). Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning. Construction and Building Materials 370, 130709.
• [28] Zhang, J., Cai, Y-Y., Yang, D., Yuan, Y., He, W-Y., Wang, Y-J. (2023). MobileNetV3-BLS: A broad learning approach for automatic concrete surface crack detection. Construction and Building Materials 392, 131941.
• [29] Martinez-Ríos, E.A., Bustamante-Bello, R., Navarro-Tuch, S.A. (2023). Generalized Morse Wavelets parameter selection and transfer learning for pavement transverse cracking detection. Engineering Applications of Artificial Intelligence 123, 106355.
• [30] Xu, G., Yue, Q., Liu, X. (2023). Deep learning algorithm for real-time automatic crack detection, segmentation, qualification. Engineering Applications of Artificial Intelligence 126, 107085.
• [31] Yuan, X., Cao, Q., Amin, M-N., Ahmad, A., Ahmad, W., Althoey, F., Deifalla, A-F. (2023). Predicting the crack width of the engineered cementitious materials via standard machine learning algorithms. Journal of Materials Research and Technology, 24: 6187 – 6200.
• [32] Iraniparast, M., Ranjbar, S., Rahai, M., Nejad, F-M. (2023). Surface concrete cracks detection and segmentation using transfer learning and multi-resolution image processing. Structures 54, 386–398.
• [33] Katsigiannis, S., Seyedzadeh, S., Agapiou, A., Ramzan, N. (2023). Deep learning for crack detection on masonry façades using limited data and transfer learning. Journal of Building Engineering 76, 107105.
• [34] Pacal, I. (2024). Enhancing crop productivity and sustainability through disease identification in maize leaves: Exploiting a large dataset with an advanced vision transformer model. Expert Systems with Applications, 238, 122099.
• [35] E. Aslan, M.A. Arserim, A Uçar. (2023). Development of Push-Recovery control system for humanoid robots using deep reinforcement learning. Ain Shams Engineering Journal. doi: https://doi.org/10.1016/j.asej.2023.102167.
• [36] Lubbad, M., Karaboga, D., Basturk, A., Akay, B. A. H. R. İ. Y. E., Nalbantoglu, U., & Pacal, I. (2024). Machine learning applications in detection and diagnosis of urology cancers: a systematic literature review. Neural Computing and Applications, 1-25.
• [37] Lecun, Y., Bottou, L., Bengio, Y., Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proc. IEEE, 86, 2278–2324.
• [38] Kurtulus, I. L., Lubbad, M., Yilmaz, O. M. D., Kilic, K., Karaboga, D., Basturk, A., ... & Pacal, I. (2024). A robust deep learning model for the classification of dental implant brands. Journal of Stomatology, Oral and Maxillofacial Surgery, 101818.
• [39] Karaman, A., Pacal, I., Basturk, A., Akay, B., Nalbantoglu, U., Coskun, S., ... & Karaboga, D. (2023). Robust real-time polyp detection system design based on YOLO algorithms by optimizing activation functions and hyper-parameters with artificial bee colony (ABC). Expert systems with applications, 221, 119741.
• [40] Pacal, I. (2024). MaxCerVixT: A Novel Lightweight Vision Transformer-Based Approach for Precise Cervical Cancer Detection. Knowledge-Based Systems: 111482.
• [41] Dorafshan, S., Thomas, R.J., Maguire, M. (2018). SDNET2018: An Annotated İmage Data Set for non-contact concrete crack detection using deep convolutional neural networks. Data in Brief, 21,1664–1668.
• [42] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
• [43] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
• [44] Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., ... & Adam, H. (2019). Searching for mobilenetv3. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 1314-1324).
• [45] Mehta, S., & Rastegari, M. (2021). Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178.
• [46] Li, Y., Wu, C. Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., & Feichtenhofer, C. (2022). Mvitv2: Improved multiscale vision transformers for classification and detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4804-4814).