Journal of Korean Society of Disaster and Security (한국방재안전학회논문집)

Korean Society of Disaster & Security (한국방재안전학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Surface Damage Detection Method of the Main Tower of a Special Bridge Using Drones and A.I.

드론과 A.I.를 이용한 특수교 주탑부 표면 손상 탐지 방법 연구

  • Sungjin Lee (Department of Structural Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Bongchul Joo (Department of Structural Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Jungho Kim (Department of Structural Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Taehee Lee (R&D Institute, Infrastructure Engineering Team, LOTTE Engineering & Construction)
  • 이성진 (한국건설기술연구원 구조연구본부) ;
  • 주봉철 (한국건설기술연구원 구조연구본부) ;
  • 김정호 (한국건설기술연구원 구조연구본부) ;
  • 이태희 (롯데건설 기술연구원 토목기술연구팀)
  • Received : 2022.11.25
  • Accepted : 2023.12.18
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

A special offshore bridge with a high pylon has special structural features.Special offshore bridges have inspection blind spots that are difficult to visually inspect. To solve this problem, safety inspection methods using drones are being studied. In this study, image data of the pylon of a special offshore bridge was acquired using a drone. In addition, an artificial intelligence algorithm was developed to detect damage to the pylon surface. The AI algorithm utilized a deep learning network with different structures. The algorithm applied the stacking ensemble learning method to build a model that formed the ensemble and collect the results.

높은 주탑을 가지는 해상특수교량은 특수한 구조적 특징으로 인해 육안점검이 어려운 점검사각지대가 존재하게 되며, 이를 해결하기 위해 드론을 활용한 안전점검 방법들이 연구되고 있다. 본 연구에서는 드론을 이용하여 해상특수교량 주탑의 영상 데이터를 취득하고, 인공지능 알고리즘을 개발하여 주탑부 표면 손상에 대한 탐지를 수행하였다. 인공지능 알고리즘은 서로 다른 구조를 지닌 딥러닝 네트워크를 활용하여 앙상블을 형성한 모델을 구축하고 결과를 취합하는 스태킹 앙상블 학습법을 적용하였다.

Keywords

Acknowledgement

This work was supported by Korea Institute of Civil Engineering and Building Technology (Project Number: 20220183), granted financial resource from the Ministry of Science and ICT, Republic of Korea.

References

  1. Choi, Dae-Young, Seung-Hyun Paik, Young-Kyu Kim, Sang-Woo Jung, and Dae-Nyeon Kim. (2021). Deep-Learning Crack Analysis for Visual-Safety Inspection of Bridge by Drones. Journal of KIIT. 19(12): 115-121.
  2. Jung, Seo-Young, Seul-Ki Lee, Chan-Il Park, Soo-Young Cho, and Jung-Ho Yu. (2019). A Method for Detecting Concrete Cracks Using Deep-Learning and Image Processing. Journal of the Architectural Institute of Korea Structure & Construction. 35(11): 163-170.
  3. Korea Agency for Infrastructure Technology Advancement. (2020). Development of Rapid Diagnosis and Evaluation Technology for Bridge Structures Based on Unmanned Inspection Equipment (No. 19SCIP-C116873-04). Anyang: KAIA.
  4. Korea Institute of Civil Engineering and Building Technology. (2021). Inspection Technology at Blind Spot of SeaCrossing Bridge Utilizing Drone and A.I. (KICT 2021-104). Goyang: KICT.
  5. Lee, Suk-Bae, Ki-Hong Lee, Hyun-Min Choi and Chi-Sung Lim. (2022). Establishment of a Standard Procedure for Safety Inspections of Bridges Using Drones. Journal of Civil and Environmental Engineering Research. 42(2): 281-290.
  6. Lee, Teahee, Jung-Ho Kim, Sung-Jin Lee, Seung-Ki Ryu, and Bong-Chul Joo. (2023). Improvement of Concrete Crack Segmentation Performance Using Stacking Ensemble Learning. Applied Sciences. 13: 2367.
  7. National Geographic Information Institute. (2018). Guidelines for the Public Survey Using UAV (No. 2018-1075). Suwon: NGII.
  8. Park, Ho-Young, Gyeong-Min Lee, Myoung-Hwan Han and Si-Jun Kim. (2019). Structure Safety Inspection Using Drones. Journal of the Korean Association for Spatial Structure. 19(4): 8-13.
  9. Yeo, Chang-Jae and Jung-Ho Yu. (2018). A Present and Future: Facility Inspection Using Drone. Review of Architecture and Building Science. 63(06): 33-36.