Journal of Korean Association for Spatial Structures (한국공간구조학회논문집)

Korean Association for Spatial Structures (한국공간구조학회)
권호 표지
DOI QR코드

DOI QR Code

Application Verification of AI&Thermal Imaging-Based Concrete Crack Depth Evaluation Technique through Mock-up Test

Mock-up Test를 통한 AI 및 열화상 기반 콘크리트 균열 깊이 평가 기법의 적용성 검증

  • Jeong, Sang-Gi (School of Civil, Environ.&Arch. Eng., Korea Univ.) ;
  • Jang, Arum (School of Civil, Environ.&Arch. Eng., Korea Univ.) ;
  • Park, Jinhan (Smart Construction team, Smart Technology Center, Hyundai Engineering Co., Ltd) ;
  • Kang, Chang-hoon (Smart Construction team, Smart Technology Center, Hyundai Engineering Co., Ltd) ;
  • Ju, Young K. (Dept. of Civil, Environ.&Arch. Eng., Korea Univ.)
  • 정상기 (고려대 건축사회환경공학과) ;
  • 장아름 (고려대 건축사회환경공학과) ;
  • 박진한 (현대엔지니어링(주) 스마트기술센터) ;
  • 강창훈 (현대엔지니어링(주) 스마트기술센터) ;
  • 주영규 (고려대 건축사회환경공학부)
  • Received : 2023.08.03
  • Accepted : 2023.09.04
  • Published : 2023.09.15
Download PDF
⟨ Previous Next ⟩

Abstract

With the increasing number of aging buildings across Korea, emerging maintenance technologies have surged. One such technology is the non-contact detection of concrete cracks via thermal images. This study aims to develop a technique that can accurately predict the depth of a crack by analyzing the temperature difference between the crack part and the normal part in the thermal image of the concrete. The research obtained temperature data through thermal imaging experiments and constructed a big data set including outdoor variables such as air temperature, illumination, and humidity that can influence temperature differences. Based on the collected data, the team designed an algorithm for learning and predicting the crack depth using machine learning. Initially, standardized crack specimens were used in experiments, and the big data was updated by specimens similar to actual cracks. Finally, a crack depth prediction technology was implemented using five regression analysis algorithms for approximately 24,000 data points. To confirm the practicality of the development technique, crack simulators with various shapes were added to the study.

Keywords

Acknowledgement

이 논문은 (주)현대엔지니어링 스마트기술센터와 한국연구재단 과학기술정보통신부의 재원으로 연구비 지원을 받아 수행된 연구입니다. (NRF-2020R1A2C3005687, 2021R1A5A1032433)

References

  1. KOSIS KOrean Statistical Information Service, "Scale status by year of completion" 2023.4.15. https://kosis.kr/index/index.do
  2. Park Yong-seok, a researcher at the Construction Industry, "The Prospects and Policy Tasks of the Building Remodeling Market", 2020.9.
  3. Sony, S., Laventure, S. and Sadhu, A. (2019), "A literature review of next-generation smart sensing technology in structural health monitoring", Structural Control and Health Monitoring, 26(3), e2321. DOI:https://doi.org/10.1002/stc.2321
  4. Mader, D., Blaskow, R., Westfeld, P., & Maas, H. G. (2015). UAV-based acquisition of 3D point cloud-a comparison of a low-cost laser scanner and SFM-tools. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 40, 335-341. DOI:https://doi.org/10.5194/isprsarchives-XL-3-W3-335-2015
  5. Jang, A., Ju, Y.K. and Park, M.J. (2022), "Structural stability evaluation of existing buildings by reverse engineering with 3D laser scanner", Remote Sensing, 14(10), 2325. DOI:https://doi.org/10.3390/rs14102325
  6. Bae, J., Lee, J., Jang, A., Ju, Y.K. and Park, M.J. (2022), "SMART SKY Eye system for preliminary structural safety assessment of buildings using unmanned aerial vehicles", Sensors, 22(7), 2762. DOI:https://doi.org/10.3390/s22072762
  7. Khaloo, A., Lattanzi, D., Cunningham, K., Dell'Andrea, R., & Riley, M. (2018), "Unmanned aerial vehicle inspection of the Placer River Trail Bridge through imagebased 3D modelling", Structure and Infrastructure Engineering, 14(1), 124-136. DOI:https://doi.org/10.1080/15732479.2017.1330891
  8. Omar, T., Nehdi, M. L., & Zayed, T. (2018). Infrared thermography model for automated detection of delamination in RC bridge decks. Construction and Building Materials, 168, 313-327. DOI:https://doi.org/10.1016/j.conbuildmat.2018.02.126
  9. Watase, A., Birgul, R., Hiasa, S., Matsumoto, M., Mitani, K., & Catbas, F. N. (2015). Practical identification of favorable time windows for infrared thermography for concrete bridge evaluation. Construction and Building Materials, 101, 1016-1030. DOI:https://doi.org/10.1016/j.conbuildmat.2015.10.156
  10. Bae, J., Jang, A., Park, M. J., Lee, J. and Ju, Y.K. (2022), "Assessment of concrete macrocrack depth using infrared thermography", Steel and Composite Structures, 43(4), 501-509. DOI:https://doi.org/10.12989/scs.2022.43.4.501
  11. Park, M.J., Kim, J., Jeong, S., Jang, A., Bae, J. and Ju, Y.K. (2022), "Machine learning-based concrete crack depth prediction using thermal images taken under daylight conditions", Remote Sensing, 14(9), 2151. DOI:https://doi.org/10.3390/rs14092151
  12. Mohan, A., & Poobal, S. (2018). Crack detection using image processing: A critical review and analysis. alexandria engineering journal, 57(2), 787-798. DOI:https://doi.org/10.1016/j.aej.2017.01.020
  13. Chen, C., Chandra, S., Han, Y., & Seo, H. (2021). Deep learning-based thermal image analysis for pavement defect detection and classification considering complex pavement conditions. Remote Sensing, 14(1), 106. DOI:https://doi.org/10.3390/rs14010106
  14. Rhim, H. C., Kim, Y. S., Woo, S. K., & Song, Y. C. (2002). "Measurement of crack depth located under steel reinforcement in reinforced concrete specimens using ultrasonic method", Journal of the Korea institute for structural maintenance and inspection, 6(4), 181-188.
  15. Jang, A., Jeong, S., Park J., Kang C. and Ju, Y.K. (2022). "Crack Detection Technology Based on Ortho-image Using Convolutional Neural Network", Journal of Korean Association for Spatial Structures, 22(2), 19-27. DOI:https://doi.org/10.9712/KASS.2022.22.2.19