The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

A study on the improvement of concrete defect detection performance through the convergence of transfer learning and k-means clustering

전이학습과 k-means clustering의 융합을 통한 콘크리트 결함 탐지 성능 향상에 대한 연구

  • 윤영근 (인천대학교 안전공학과 ) ;
  • 오태근 (인천대학교 안전공학과)
  • Received : 2023.02.09
  • Accepted : 2023.03.10
  • Published : 2023.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Various defects occur in concrete structures due to internal and external environments. If there is a defect, it is important to efficiently identify and maintain it because there is a problem with the structural safety of concrete. However, recent deep learning research has focused on cracks in concrete, and studies on exfoliation and contamination are lacking. In this study, focusing on exfoliation and contamination, which are difficult to label, four models were developed and their performance evaluated through unlabelling method, filtering method, the convergence of transfer learning based k-means clustering. As a result of the analysis, the convergence model classified the defects in the most detail and could increase the efficiency compared to direct labeling. It is hoped that the results of this study will contribute to the development of deep learning models for various types of defects that are difficult to label in the future.

콘크리트 구조물은 대내외적 환경에 의해 다양한 결함이 발생한다. 결함이 있는 경우 콘크리트의 구조적 안전성에 문제가 있어 이를 효율적으로 파악하여 유지관리하는 것이 중요하다. 하지만, 최근 딥러닝 연구는 콘크리트의 균열에 초점이 맞추어져 있어, 박락과 오염 등에 대한 연구는 부족하다. 본 연구에서는 라벨링이 어려운 박락과 오염에 초점을 맞추어 언라벨 방법, 필터링 방법, 전이학습과 k-means cluster의 융합을 통한 4개의 모델을 개발하고 성능을 평가하였다. 분석결과, 융합모델이 결함을 가장 세밀하게 구분하였으며, 직접 라벨링을 하는 것보다 효율성을 증가시킬 수 있었다. 본 연구 결과가 향후 라벨링이 어려운 다양한 결함 유형에 대한 딥러닝 모델 개발에 기여할 수 있기를 기대한다.

Keywords

References

  1. K.F. Dunker, B.G. Rabbat, Performance of highway bridges. Concr. Int. 1990, 12, 40-42.
  2. J. Zhang, C. Lu, J. Wang, L. Wang, and X.-G. Yue, Concrete cracks detection based on fcn with dilated convolution, Applied Sciences, Vol.9, No.13, pp.2686, 2019.
  3. H. Yu, L. Zhu, D. Li, Q. Wang, X. Liu, C. Shen, Comparative Study on Concrete Crack Detection of Tunnel Based on Different Deep Learning Algorithms, Front. Earth Sci, Vol 9, pp.1452, 2022.
  4. A. Villanueva, J. K. B. Balba, C. D. Beceril, J. L. G. Belza, R. I. P. Tagle, M. C. A. Venal, M. M. Rosales, (2022, June). Crack Detection and Classification for Reinforced Concrete Structures using Deep Learning. In 2022 2nd International Conference on Intelligent Technologies (CONIT) (pp. 1-6). IEEE.
  5. V. P. Golding, Z. Gharineiat, H. S. Munawar, F. Ullah, Crack Detection in Concrete Structures Using Deep Learning. Sustainability, Vol 14, No 13, 8117. 2022.
  6. J.Y. Jung, S.K. Lee, C.I. Pa가, S.Y. Cho, J.H. Y, A Method for Detecting Concrete Cracks using Deep-Learning and Image Processing, JAIK, Vol, 35, No.11, pp.163-170, 2019. https://doi.org/10.5659/JAIK_SC.2019.35.11.163
  7. C.F. Ozgenel, A.G. Sorguc, Performance comparison of pretrained convolutional neural networks on crack detection in buildings. In: ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction, vol 35. IAARC Publications, pp 1-8, 2018.
  8. T. Defard, S. Aleksandr, L. Angelique, A. Romaric, "PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization." In Pattern Recognition. ICPR International Workshops and Challenges, 475-89. Lecture Notes in Computer Science. Cham, Switzerland: Springer International Publishing, 2021.
  9. Pan, S.J. and Yang, Q., 2010. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), pp.1345-1359. https://doi.org/10.1109/TKDE.2009.191