تشخیص ترک در سازه‌های بتنی با کاربرد شبکه عصبی کانولوشن

نوع مقاله : پژوهشی اصیل (کامل)

نویسندگان
مهران سیف‌الهی 1
سلیم عباسی 2
مازیار فهیمی فرزام 3
رسول دانشفراز 4
1 - کارشناسی ارشد عمران-سازه‌های هیدرولیکی، دانشگاه تبریز، تبریز
2 کارشناسی ارشد عمران-سازه‌های هیدرولیکی، دانشگاه محقق اردبیلی، اردبیل
3 گروه مهندسی عمران، دانشکده فنی و مهندسی، دانشگاه مراغه، مراغه، ایران
4 استاد بخش مهندسی عمران-سازه‌های هیدرولیکی، دانشگاه مراغه، مراغه
10.22034/23.5.2
چکیده
یکی از زمینه‌های فعال تحقیقاتی در بحث پایش‌ سلامت ‌سازه‌های بتنی تشخیص رخداد ترک در المان‌های سازه‌ای است. طبقه­بندی و تشخیص فنی براساس تصویر، روشی است که امروزه مورد توجه بسیاری از محققین قرار گرفته است. انجام روش مبتنی بر تصویر به دلیل پیشرفت فناوری تصویربرداری و پردازش سریع آن‌ها به سهولت صورت می‌گیرد، که این تشخیص توسط شبکه عصبی کانولوشن(CNN) انجام می‌شود. در این تحقیق تشخیص ترک در سازه­های بتنی با استفاده از شبکه عصبی کانولوشنی مطالعه شده است. مطالعه حاضر قابل تعمیم به تمام سازه­های بتنی برای نمونه سد، کانال، پل­ها، پوسته­ها، زیرسازی­های راه­ها و اسکلت­های بتنی می­باشد. بانک اطلاعاتی این پژوهش شامل 40.000 تصویر که، 20.000 تصویر بتن ترک­خورده و 20.000 بتن ترک­‌نخورده با ابعاد 3×227×227 پیکسل می‌باشد، 80 درصد تصاویر برای آموزش و 20 درصد باقیمانده برای صحت‌سنجی روش شبکه عصبی کانولوشن استفاده می‌شوند. دقت تشخیص بتن ترک‌ خورده از ترک‌ نخورده در حدود 16/98 درصد می‌باشد، که برای عملیاتی ‌شدن قابل قبول است و کاربردی محسوب می‌شود. همچنین طبق تحلیل ماتریس درهم‌ریختگی تعداد 147 تصویر از 8.000 تصویر داده­های صحت­سنجی به صورت اشتباه دسته‌بندی شده‌اند.

کلیدواژه‌ها

موضوعات

عنوان مقاله English

Crack Detection in Concrete Structures Using Convolutional Neural Network

نویسندگان English

M. Seifollahi 1
S. Abbasi 2
m. Fahimi Farzam 3
R. Daneshfaraz 4
1 M.Sc., Graduated of Civil-Hydraulic Structures Eng., Faculty of Civil Eng., Univ. of Tabriz, Tabriz, Iran
2 M.Sc., Graduated of Civil-Hydraulic Structures Eng., Faculty of Eng., Univ. of Mohaghegh Ardabili, Ardabil, Iran
3 Department of Civil Engineering, Faculty of Engineering, University of Maragheh, Maragheh, Iran
4 Professor of Civil Eng., Faculty of Eng., Univ. of Maragheh, Maragheh, Iran
چکیده English

One of the active areas of research in concrete structure health monitoring is the detection of cracking in structural elements. Image classification and diagnosis have attracted the attention of many researchers nowadays. Due to the advancement of artificial neural networks and their fast processing, a convolution neural network has been established to detect these cracks. In this study, crack detection in concrete structures has been studied using a convolutional neural network, which can be generalized to all concrete structures for example dams, canals, bridges, shells, road infrastructure, foundations and concrete frames. Convolution neural network training was performed by the SGDM method with the ReLU activator function. Also, 250 iterations were employed for convolution neural network training, which gradually reduced the error rate and increased the accuracy of detecting cracked and uneaten concrete. The convolutional neural network is trained and validated with these 250 iterations. First, images with 32-pixel window dimensions are converted and separated. Then, the 32-pixel window, the 16-pixel, and the 8-pixel windows filter the images. A total of 3 stages of 32, 16, and 8-pixel filter images are analyzed and interpreted. During the training process, validation is performed every 20 iterations, and a diagram related to the accuracy of convolution network estimation and data classification error is drawn and completed. In convolutional neural networks, where the output is in pairs, the cracked and uncracked images of the network architecture are almost identical, differing only in minor specifications. The database of this research includes 20,000 images of cracked concrete and 20,000 uncracked concrete with dimensions of 3×227×227 pixels, 80% of it is used for training and the remaining 20% is used for validation of the convolution neural network. The accuracy of distinguishing cracked concrete from uncracked ones is about 98.16%, which is acceptable for operation and is considered practical. To evaluate the accuracy and performance of the proposed algorithm, each classification was performed against the overall accuracy, the confusion matrix was used for the validation data. According to the clutter matrix, 3861 images, in other words, 48.3% have been predicted to be correctly cracked, and 3992 images, equivalent to 49.9%, have been predicted to be correctly uncracked, and a total of 147 incorrect images have been predicted, which is equivalent to 1.8 percent. Images that are cracked and not accidentally cracked are predicted. They had crack lines in the corner of the image or cracks with a very small width, which the proposed convolutional neural network was mistaken for due to a very small crack width or crack position. Also, the results of the present study showed that the accuracy of this research has the best accuracy in less analysis time compared to previous studies. It should be noted that this method and its associated database can be used to produce a crack detection application on a smartphone, to be able to make a good initial estimate of the structure in question, such as a bridge or building after an unusual loading event, such as an earthquake or explosion.

کلیدواژه‌ها English

Cracks in Concrete
Convolutional Neural Network
Structural health monitoring
Graphics Processing Unit
[1] ASCE. 2017. Infrastructure Report Card, Asce Reston. VA, USA.
[2] Cook, W., and Barr, P.J., 2017. Observations and trends among collapsed bridges in New York State. Journal of Performance of Constructed Facilities, 31 (4), pp.04017011.
[3] Bigdeli, N., Jabbari, H., and Shojaei, M., 2021. An Intelligent method for crack classification in concrete structures based on deep neural networks. Amirkabir Journal of Civil Engineering, 53(8), pp. 1-13. (DOI): 10.22060/CEEJ.2020.17738.6660.
[4] Xu, Y., Wei, S., Bao, Y., and Li, H., 2019. Automatic seismic damage identification of reinforced concrete columns from images by a region‐based deep convolutional neural network. Structural Control and Health Monitoring, 26 (3), pp.1-22.
[5] Valença, J., Puente, I., Júlio, E., González-Jorge, H., Arias-Sánchez, P., 2017. Assessment of cracks on concrete bridges using image processing supported by laser scanning survey. Construction and Building Materials, 146, pp.668-678.
[6] Cha, Y‐J., Choi, W., Suh, G., Mahmoudkhani, S., and Büyüköztürk, O., 2018. Autonomous structural visual inspection using region‐based deep learning for detecting multiple damage types. Computer‐Aided Civil and Infrastructure Engineering, 33(9), pp.731-747.
[7] Li, S., and Zhao, X., 2018. Convolutional neural networks-based crack detection for real concrete surface. In Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 10598 (105983). International Society for Optics and Photonics.
[8] Ryu, E., Kang, J., Lee, J., Shin, Y., and Kim, H., 2020. Automated detection of surface cracks and numerical correlation with thermal-structural behaviors of Fire damaged concrete beams. International Journal of Concrete Structures and Materials 14, pp.1-12.
[9] Edraki, A., and Razminia, A., 2018. Classification of white blood cells using convolutional neural network. ISMJ, 21(1), pp.65-80. (in persion)
[10] Koch, C., Georgieva, K., Kasireddy, V., Akinci, B., and Fieguth, P., 2015. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure. Advanced Engineering Informatics, 29 (2), pp.196-210.
[11] Kaseko, M.S., and Ritchie, S.G., 1993. A neural network-based methodology for pavement crack detection and classification. Transportation Research Part C: Emerging Technologies, 1(4), pp.275-291.
[12] Liu, Z., Suandi, S.A., Ohashi, T., Ejima, T., 2002. Tunnel crack detection and classification system based on image processing. in: Machine Vision Applications in Industrial Inspection X, International Society for Optics and Photonics, pp.145-152.
[13] Sato, Y., Bao, Y., Koya, Y.J., 2018. Crack detection on concrete surfaces using V-shaped features. World of Computer Science & Information Technology Journal, 8 (1).
[14] Davoudi, R. Miller, G.R. and Kutz, J.N. 2018. Structural load estimation using machine vision and surface crack patterns for shear-critical RC beams and slabs. Journal of Computing in Civil Engineering, 32(4), 04018024.
[15] Zhang, L., Yang, F., Zhang, Y.D., and Zhu, Y.J., 2016. Road crack detection using deep convolutional neural network. In 2016 IEEE international conference on image processing (ICIP), 3708-3712, IEEE.
[16] Moon, H., and Kim, J., 2011. Intelligent crack detecting algorithm on the concrete crack image using neural network. Proceedings of the 28th ISARC, pp.1461-1467.
[17] Yamaguchi, T., Nakamura, S., Saegusa, R., Hashimoto, S., 2008. Image‐based crack detection for real concrete surfaces. IEEJ Transactions on Electrical and Electronic Engineering, 3(1), pp.128-135.
[18] Cha, Y‐J., Choi, W., and Büyüköztürk. O. 2017. Deep learning‐based crack damage detection using convolutional neural networks. Computer‐Aided Civil and Infrastructure Engineering, 32(5), pp.361-378.
[19] Yeum, C.M., Dyke, S.J., 2015. Vision‐based automated crack detection for bridge inspection. Computer‐Aided Civil and Infrastructure Engineering, 30(10), pp.759-770.
[20] Liu, S.-W., Huang, J.H., Sung, J.-C., Lee, C., 2002. Detection of cracks using neural networks and computational mechanics. Computer methods in applied mechanics and engineering, 191 (25-26) pp.2831-2845.
[21] Moselhi, O., and Shehab-Eldeen, T., 2000. Classification of defects in sewer pipes using neural networks. Journal of infrastructure systems, 6(3), pp. 97-104.
[22] McClelland, C., 2017. The Difference between artificial intelligence, machine learning, and deep learning. Retrieved February 13, p.2018.
[23] Nhat-Duc, H., Nguyen, Q.-L., Tran, V.-D., 2018. Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network. Automation in Construction, 94, pp.203-213.
[24] Zhao, X., Han, R., Yu, Y., Hu, W., Jiao, D., Mao, X., Li, M., and Ou, J., 2017. Smartphone-based mobile testing technique for quick bridge cable–force measurement. Journal of Bridge Engineering, 22(4), 06016012.
[25] Li, S., and Zhao, X., 2019. Image-based concrete crack detection using convolutional neural network and exhaustive search technique. Advances in Civil Engineering, 2019.
[26] Chen, F.-C., and Jahanshahi, M.R., 2018. Video-based crack detection using deep learning and Nave Bayes data fusion. In Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018, p 105980J, International Society for Optics and Photonics.
[27] Cha, Y.-J., and Choi, W., 2017. Vision-based concrete crack detection using a convolutional neural network. In Dynamics of Civil Structures, 2, 71-73, Springer.
[28] Özgenel, Ç.F., 2019. Concrete crack images for classification. Mendeley Data, V2, DOI:10.17632/5y9wdsg2zt.2 or https://data.mendeley.com/datasets/5y9wdsg2zt/2.
[29] Lomonaco, V., 2015. Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks.
[30] McCann, M.T., Jin, K.H., Unser, M., 2017. Convolutional neural networks for inverse problems in imaging: A review. IEEE Signal Processing Magazine, 34(6), pp. 85-95.
[31] Romanuke, V.V., 2017. Appropriate number and allocation of ReLUs in convolutional neural networks sensors. Naukovi Visti NTUU KPI, 1, pp.69-78.
[32] Mohammadi-amin, F., Kouhestani, B., Dadashzadeh, B., 2017. Design and implementation of an improved deep learning system for image classification and comparison of its function with artificial neural network. 2nd International Conference on Knowledge-Based Research in Computer Engineering and Information Technology. (in persion)
[33] Moghasemi, H.R., Vasli, E., Manafi, S., 2018. Classify recorded images remotely using CNN deep learning algorithm. Congress of New Research Ideas in Engineering and Technology, Electrical and Computer Science. (in persion)
[34] Bai, X., Shi, B., Zhang, C., Cai, X., and Qi, L., 2017. Text/non-text image classification in the wild with convolutional neural networks. Pattern Recognition, 66, pp.437-446.
[35] Kim, J.H., Hong, G.H., and Park, K.R., 2017. Convolutional neural network-based human detection in nighttime images using visible light camera sensors. 17(5), 1065 (2017).
[36] Nawaz, W., Ahmed, S., Tahir, A., and Khan, H.A., 2018. Classification of breast cancer histology images using alexnet Recognition. in: International Conference Image Analysis and Recognition, Springer, pp.869-876.
[37] Dhakal, N., Zihan, Z.U.A., Elseifi, M.A., Mousa, M.R., Gaspard, K., and Fillastre. C.N., 2020. Surface identification of top-down, bottom-up, and cement-treated reflective cracks using convolutional neural network and
مهندسی عمران مدرس
دوره 23، شماره 5
مهر و آبان 1402
صفحه 21-34