«Previous Article|Table of Contents|Next Article»

¡¶½¨Öþ¿ÆѧÓ빤³Ìѧ±¨¡·[ISSN:1673-2049/CN:61-1442/TU]

Issue:

2026Äê01ÆÚ

Page:

41-55

Research Field:

ÖÇÄܼì²âÓ뽨Ôì¼¼ÊõרÀ¸

Publishing date:

Info

Title:

Study on surface damage detection of RC frame joints based on deep-learning and image recognition

Author(s):

YANG Shuo¹; 2;  LENG Yubing³;  XU Qingfeng³

1. School of Civil Engineering, Tianjin Chengjian University, Tianjin 300384, China; 2. Tianjin Key Laboratory of? Civil Structure Protection and Reinforcement, Tianjin Chengjian University, Tianjin 300384, China; 3. Shanghai Key ª¤Laboratory of Engineering Structure Safety, Shanghai Research Institute of Building Sci. Co., Ltd,? Shanghai 200032, China

Keywords:

reinforced concrete frame joint;  deep learning;  Mask R-CNN;  surface damage detection

PACS:

TU375

DOI:

10.19815/j.jace.2024.06089

Abstract:

In order to improve the efficiency of surface damage detection of reinforced concrete (RC) structures and to realize the integration of RC component surface damage localization, fine measurement and evaluation, a damage detection and assessment method based on the deep learning and image recognition was proposed for the scenario of detection of surface damage for RC frame structures. The surface damage detection model of RC frame members was established based on the mask region convolutional neural network (Mask R-CNN) model and image processing. Based on the images of damage and destruction in previous RC component tests, the surface damage dataset of RC components including six types of damage, i.e. crack, spalling, crushing, rebar exposure, rebar buckling and rebar fracture, was established after cropping and data augmentation to train the model. Based on the 3D reconstruction and the damage detection model, an inspection program, which could simultaneously locate the surface damage of RC components and analyze the damage geometric parameters, was made and integrated the criteria for classifying the damage level and judging the damage pattern of RC components to quantitatively assess the damage degrees and judge the damage patterns for RC components. Two fullª²scale RC beamª²column joint specimens were designed, fabricated, and used to conduct an experimental test. The damaged joint specimens were photographed with a smart phone and a small unmanned aerial vehicle (UAV) to detect the surface damage of the beams for validation of the above damage detection method. The results show that the detection results based on the smart phone are better than those based on UAV digital zoom shooting. The accuracy of the rebar buckling and fracture is poor due to the fewer training samples. When the lens is about 200 mm from the surface of the members, the measurement accuracy of crack width can reach 0.1 mm. If the measured crack width is greater than 0.5 mm, the crack width detection accuracy of the above method is higher. The damage grades (degrees) and failure patterns of components analyzed by the detection program are consistent with the observation. The damage detection method based on the deep learning and image recognition can support quantitative surface damage rapid detection and assessment for damaged or postª²earthquake RC frame components.

References:

£Û 1 £Ý³ÂÕØÔª , ÐìÓÐÁÚ , Ç®¼ÚÈã . ÍÁ½¨½á¹¹¹¤³ÌµÄ°²È«ÐÔÓëÄ;ÃÐÔ£Û J £Ý . ½¨Öþ¼¼Êõ ,2002,33(4):248 - 253.

ª¤ CHEN Zhaoyuan, XU Youlin, QIAN Jiaru. Safety and durability of structural works in civil engineering £Û J £Ý . Architecture Technology, 2002, 33(4): 248 - 253.

£Û 2 £Ý»ôÁÖÉú , ÀîºêÄÐ , ФʫÔÆ , µÈ . ãë´¨µØÕð¸Ö½î»ìÄýÍÁ¿ò¼Ü½á¹¹Õ𺦵÷²éÓëÆôʾ£Û J £Ý . ´óÁ¬Àí¹¤´óѧѧ±¨ ,2009,49(5):718 - 723.

ª¤ HUO Linsheng, LI Hongnan, XIAO Shiyun, et al. Earthquake damage investigation and analysis of reinforced concrete frame structures in Wenchuan earthquake £Û J £Ý . Journal of Dalian University of Technology, 2009, 49(5): 718 - 723.

£Û 3 £Ý½¨ÖþÕðºóÓ¦¼±ÆÀ¹ÀºÍÐÞ¸´¼¼Êõ¹æ³Ì :JGJ/T 415 ¡ª 2017 £Û S £Ý . ±±¾© : Öйú½¨Öþ¹¤Òµ³ö°æÉç ,2017.

ª¤ Technical specification for post - earthquake urgent assessment and repair of buildings: JGJ/T 415 ¡ª 2017 £Û S £Ý . Beijing: China Architecture & Building Press, 2017.

£Û 4 £Ý GRAYBEAL B A, PHARES B M, ROLANDER D D, et al. Visual inspection of highway bridges £Û J £Ý . Journal of Nondestructive Evaluation, 2002, 21(3): 67 - 83.

£Û 5 £Ýº«Ïþ½¡ , ÕÔÖ¾³É . »ùÓÚ¼ÆËã»úÊÓ¾õ¼¼ÊõµÄ½á¹¹±íÃæÁÑ·ì¼ì²â·½·¨Ñо¿£Û J £Ý . ½¨Öþ½á¹¹Ñ§±¨ ,2018,39( Ôö 1):418 - 427.

ª¤ HAN Xiaojian, ZHAO Zhicheng. Research on detection method of structural surface cracks based on computer vision technology £Û J £Ý . Journal of Building Structures, 2018, 39(S1): 418 - 427.

£Û 6 £Ý ZAKERI H, NEJAD F M, FAHIMIFAR A. Image based techniques for crack detection, classification and quantification in asphalt pavement: a review £Û J £Ý . Archives of Computational Methods in Engineering, 2017, 24(4): 935 - 977.

£Û 7 £Ý HAN X J, ZHAO Z C, CHEN L K, et al. Structural damage - causing concrete cracking detection based on a deep - learning method £Û J £Ý . Construction and Building Materials, 2022, 337: 127562.

£Û 8 £ÝÖÜÓ± , ÁõÍ® . »ùÓÚ¼ÆËã»úÊÓ¾õµÄ»ìÄýÍÁÁÑ·ìʶ±ð£Û J £Ý . ͬ¼Ã´óѧѧ±¨ ( ×ÔÈ»¿Æѧ°æ ),2019,47(9):1277 - 1285.

ª¤ ZHOU Ying, LIU Tong. Computer vision - based crack detection and measurement on concrete structure £Û J £Ý . Journal of Tongji University (Natural Science), 2019, 47(9): 1277 - 1285.

£Û 9 £ÝÑî¹ú¿¡ , ÆëÑÇ»Ô , ʯÐãÃû . »ùÓÚÊý×ÖͼÏñ¼¼ÊõµÄÇÅÁºÁÑ·ì¼ì²â×ÛÊö£Û J £Ý . ¼ªÁÖ´óѧѧ±¨ ( ¹¤Ñ§°æ ),2024, ª© 54(2) ªª :313 - 332.

ª¤ YANG Guojun, QI Yahui, SHI Xiuming. Review of bridge crack detection based on digital image technology £Û J £Ý . Journal of Jilin University (Engineering and Technology Edition), 2024, 54(2): 313 - 332.

£Û 10 £Ý ALI L, ALNAJJAR F, KHAN W, et al. Bibliometric analysis and review of deep learning - based crack detection literature published between 2010 and 2022 £Û J £Ý . Buildings, 2022, 12(4): 432.

£Û 11 £ÝÑîîå , ÐíÇå·ç , Íõ׿ÁÕ . »ùÓÚ¾í»ýÉñ¾­ÍøÂçµÄ½á¹¹ËðÉËʶ±ðÑо¿½øÕ¹£Û J £Ý . ½¨Öþ¿ÆѧÓ빤³Ìѧ±¨ ,2022, ª© 39(4) ªª :38 - 57.

ª¤ YANG Shuo, XU Qingfeng, WANG Zhuolin. Research progress on structural damage detection based on convolutional neural networks £Û J £Ý . Journal of Architecture and Civil Engineering, 2022, 39(4): 38 - 57.

£Û 12 £Ý DOGAN G, HAKAN ARSLAN M, ILKI A. Detection of damages caused by earthquake and reinforcement corrosion in RC buildings with deep transfer learning £Û J £Ý . Engineering Structures, 2023, 279: 115629.

£Û 13 £ÝÁõÓî·É , ·®½¡Éú , Äô½¨¹ú , µÈ . ½á¹¹±íÃæÁÑ·ìÊý×ÖͼÏñ·¨Ê¶±ðÑо¿×ÛÊöÓëÇ°¾°Õ¹Íû£Û J £Ý . ÍÁľ¹¤³Ìѧ±¨ ,2021,54(6):79 - 98.

ª¤ LIU Yufei, FAN Jiansheng, NIE Jianguo, et al. Review and prospect of digital - image - based crack detection of structure surface £Û J £Ý . China Civil Engineering Journal, 2021, 54(6): 79 - 98.

£Û 14 £Ý BAI Z L, LIU T J, ZOU D J, et al. Image - based reinforced concrete component mechanical damage recognition and structural safety rapid assessment using deep learning with frequency information £Û J £Ý . Automation in Construction, 2023, 150: 104839.

£Û 15 £Ý CHEN L K, CHEN W X, WANG L, et al. Convolutional neural networks (CNNs) - based multi - category damage detection and recognition of high - speed rail (HSR) reinforced concrete (RC) bridges using test images £Û J £Ý . Engineering Structures, 2023, 276: 115306.

£Û 16 £Ý MENG S Q, GAO Z Y, ZHOU Y, et al. Real - time automatic crack detection method based on drone £Û J £Ý . Computer - aided Civil and Infrastructure Engineering, 2023, 38(7): 849 - 872.

£Û 17 £Ý LIU Y F, NIE X, FAN J S, et al. Image - based crack assessment of bridge piers using unmanned aerial vehicles and three - dimensional scene reconstruction £Û J £Ý . Computer - aided Civil and Infrastructure Engineering, 2020, 35(5): 511 - 529.

£Û 18 £Ý ZHAO S Z, KANG F, LI J J. Concrete dam damage detection and localisation based on YOLOv5s - HSC and photogrammetric 3D reconstruction £Û J £Ý . Automation in Construction, 2022, 143: 104555.

£Û 19 £Ý¹úÎñÔº£¬ÖÐÑë¾üί . ÎÞÈ˼ÝÊ»º½¿ÕÆ÷·ÉÐйÜÀíÔÝÐÐÌõÀý£Û EB/OL £Ý . £¨ 2023 - 06 - 28 £©£Û 2024 - 04 - 15 £Ý .https://www.gov.cn/zhengce/zhengceku/202306/content_6888800.htm.

ª¤ State Council, Central Military Commission. Regulations on the administration of unmanned aerial vehicle £Û EB/OL £Ý . £¨ 2023 - 06 - 28 £©£Û 2024 - 04 - 15 £Ý . https://www.gov.cn/zhengce/zhengceku/202306/content_6888800.htm.

£Û 20 £ÝÑîÄÈ , ÕÅÁˆ , ÀîÌìê» . »ùÓÚÎÞÈË»úÓë¼ÆËã»úÊÓ¾õµÄÖйú¹Å½¨Öþľ½á¹¹ÁÑ·ì¼à²âϵͳÉè¼Æ£Û J £Ý . ¹¤³ÌÁ¦Ñ§ ,2021,38(3):27 - 39.

ª¤ YANG Na, ZHANG Chong, LI Tianhao. Design of crack monitoring system for Chinese ancient wooden buildings based on UAV and CV £Û J £Ý . Engineering Mechanics, 2021, 38(3): 27 - 39.

£Û 21 £Ý¹¤³Ì½á¹¹Êý×ÖͼÏñ·¨¼ì²â¼¼Êõ¹æ³Ì :T/CECS 1114 ¡ª 2022 £Û S £Ý . ±±¾© : Öйú½¨Öþ¹¤Òµ³ö°æÉç ,2022.

ª¤ Technical specification for digital image inspection of engineering structures: T/CECS 1114 ¡ª 2022 £Û S £Ý . Beijing: China Architecture & Building Press, 2022.

£Û 22 £Ý CHOW J K, LIU K F, TAN P S, et al. Automated defect inspection of concrete structures £Û J £Ý . Automation in Construction, 2021, 132: 103959.

£Û 23 £Ý HARTLEY R, ZISSERMAN A. Multiple view geometry in computer vision £Û M £Ý . Cambridge: Cambridge University Press, 2004.

£Û 24 £Ý KIM B, CHO S. Image - based concrete crack assessment using mask and region - based convolutional neural network £Û J £Ý . Structural Control and Health Monitoring, 2019, 26(8): e2381.

£Û 25 £ÝËÎ³ÉºÆ , ³ÂÊé³É , ºúÏþ±ó , µÈ . »ùÓÚ¼ÆËã»úÊÓ¾õµÄÍù¸´ºÉÔØ×÷ÓÃϸֽî»ìÄýÍÁÖùÁÑ·ì¼à²â£Û J £Ý . ¹¤Òµ½¨Öþ ,2022,52(10):53 - 60.

ª¤ SONG Chenghao, CHEN Shucheng, HU Xiaobin, ª© et al ªª . Crack monitoring of RC columns under cyclic loading based on computer vision £Û J £Ý . Industrial Construction, 2022, 52(10): 53 - 60.

£Û 26 £Ý REN S Q, HE K M, GIRSHICK R, et al. Faster R - CNN: towards real - time object detection with region proposal networks £Û J £Ý . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137 - 1149.

£Û 27 £Ý HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition £Û C £Ý //IEEE. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770 - 778.

£Û 28 £Ý LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection £Û C £Ý // IEEE. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017:936 - 944.

£Û 29 £Ý KALFARISI R, WU Z Y, SOH K. Crack detection and segmentation using deep learning with 3D reality mesh model for quantitative assessment and integrated visualization £Û J £Ý . Journal of Computing in Civil Engineering, 2020, 34(3): 04020010.

£Û 30 £ÝÕÂع½ú . ¼ÆËã»úÊÓ¾õ½Ì³Ì£Û M £Ý .2 °æ . ±±¾© : ÈËÃñÓʵç³ö°æÉç ,2017.

ª¤ ZHANG Yujin. A course of computer vision £Û M £Ý . 2nd ed. Beijing: Posts & Telecom Press, 2017.

£Û 31 £Ý OTSU N. A threshold selection method from gray - level histograms £Û J £Ý . IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62 - 66.

£Û 32 £ÝªªPAYAB M, ABBASINA R, KHANZADI M. A brief review and a new graph - based image analysis for concrete crack quantification £Û J £Ý . Archives of Computational Methods in Engineering, 2019, 26(2): 347 - 365.

£Û 33 £Ý½¨Öþ¿¹ÕðÊÔÑé¹æ³Ì :JGJ/T 101 ¡ª 2015 £Û S £Ý . ±±¾© : Öйú½¨Öþ¹¤Òµ³ö°æÉç ,2015.

ª¤ Specification for seismic test of buildings: JGJ/T 101 ¡ª 2015 £Û S £Ý . Beijing: China Architecture & Building Press, 2015.

£Û 34 £Ý½¨ ( ¹¹ ) ÖþÎïµØÕðÆÆ»µµÈ¼¶»®·Ö :GB/T 24335 ¡ª 2009 £Û S £Ý . ±±¾© : Öйú±ê×¼³ö°æÉç ,2009.

ª¤ Classification of earthquake damage to buildings and special structures: GB/T 24335 ¡ª 2009 £Û S £Ý . Beijing: Standards Press of China, 2009.

£Û 35 £Ýªª OHKUBO M. Current Japanese system on seismic capacity and retrofit techniques for existing reinforced concrete buildings and post - earthquake damage inspection and restoration techniques £Û R £Ý . San Diego: Department of Applied Mechanics and Engineering Sciences, University of California, 1991.

£Û 36 £Ý SINHA R, GOYAL A. A national policy for seismic vulnerability assessment of buildings and procedure for rapid visual screening of buildings for potential seismic vulnerability £Û R £Ý . Hindistan: Ministry of Home Affairs, Government of India, 2004.

£Û 37 £Ý·¿ÎÝÍêËðµÈ¼¶ÆÀ¶¨±ê×¼£¨ÊÔÐУ© : ³Çס×Ö£¨ 1984 £©µÚ 678 ºÅ£Û S £Ý . ±±¾© : ³ÇÏ罨Éè»·¾³±£»¤²¿ , 1984.

ª¤ Standard for assessing the level of housing deterioration(trial): Cheng Zhuzi (1984) No.678 £Û S £Ý . Beijing: Ministry of Urban and Rural Construction and Environmental Protection, 1984.

£Û 38 £Ý ZOU D J, ZHANG M, BAI Z L, et al. Multicategory damage detection and safety assessment of post - earthquake reinforced concrete structures using deep learning £Û J £Ý . Computer - aided Civil and Infrastructure Engineering, 2022, 37(9): 1188 - 1204.

Memo

Memo:

-

Common functions

Last Update: 2026-01-20