한국전산구조공학회논문집 (Journal of the Computational Structural Engineering Institute of Korea)

  • 제36권1호
  • /
  • Pages.1-7
  • /
  • 2023
  • /
  • 1229-3059(pISSN)
  • /
  • 2287-2302(eISSN)
한국전산구조공학회 (Computational Structural Engineering Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

구조형상 공간상관을 고려한 인공지능 기반 변위 추정

Estimation of Displacements Using Artificial Intelligence Considering Spatial Correlation of Structural Shape

  • 신승훈 (한국해양대학교 해양건축공학과) ;
  • 김지영 ((주)씨앤피동양 기술연구소) ;
  • 우종열 ((주)힐엔지니어링) ;
  • 김대건 (동서대학교 건축공학과) ;
  • 진태석 (동서대학교 매카트로닉스 융합공학부)
  • Seung-Hun Shin (Department of Oceanic Architectural Engineering, Korea Maritime and Ocean University) ;
  • Ji-Young Kim (Technology Research Institute, CNP Dongyang) ;
  • Jong-Yeol Woo (Hill Engineering) ;
  • Dae-Gun Kim (Department of Architectural & Civil Engineering, DongSeo University) ;
  • Tae-Seok Jin (Department of Mechatronis Engineering, DongSeo University)
  • 투고 : 2022.04.29
  • 심사 : 2023.01.10
  • 발행 : 2023.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 구조물의 부분 변위값으로 전체 구조물의 변위 형상을 예측할 수 있는 인공지능 학습기법을 개발하였으며, 개발된 기술의 성능을 실험을 통해 평가하였다. 3차원 공간에서 변위 형상 및 노드 위치 좌표의 특성을 학습에 반영할 수 있는 Image-to-Image 변위 형상 학습과 위치 특징을 결합한 변위 상관 학습 방법을 제시하였다. 개발된 인공지능 학습방법의 성능을 평가하기 위해 목업 구조 실험을 진행하였고, 3D 스캔으로 측정한 변위값과 인공지능으로 예측한 결과를 비교하였다. 비교 결과 인공지능 예측 결과는 3D 스캔 측정 결과에 비해 5.6~5.9%의 오차율을 보여 적정 성능을 보였다.

An artificial intelligence (AI) method based on image deep learning is proposed to predict the entire displacement shape of a structure using the feature of partial displacements. The performance of the method was investigated through a structural test of a steel frame. An image-to-image regression (I2IR) training method was developed based on the U-Net layer for image recognition. In the I2IR method, the U-Net is modified to generate images of entire displacement shapes when images of partial displacement shapes of structures are input to the AI network. Furthermore, the training of displacements combined with the location feature was developed so that nodal displacement values with corresponding nodal coordinates could be used in AI training. The proposed training methods can consider correlations between nodal displacements in 3D space, and the accuracy of displacement predictions is improved compared with artificial neural network training methods. Displacements of the steel frame were predicted during the structural tests using the proposed methods and compared with 3D scanning data of displacement shapes. The results show that the proposed AI prediction properly follows the measured displacements using 3D scanning.

키워드

과제정보

본 성과물은 중소벤처기업부에서 지원하는 2021년도 산학연 Collabo R&D사업(No. S3115914)의 연구수행으로 인한 결과물임을 밝힙니다.

참고문헌

  1. Kim, J.Y. (2012) Application of ANN (Artificial Neural Network)-based Field Measurement System for Launching of Floating Structures, J. KASS, 12(1), pp.14~19.
  2. Kim, J.Y., Jeon, H.S. (2015) Structural Safety and Disaster Management Technologies Applied in Songdo Campus Town, J. KASS., 15(1), pp.30~35.
  3. Kim, J.Y., Yu, E., Kim, D.Y., Kim, S.D. (2009) Calibration of Analytical Models to Assess Wind-induced Acceleration Responses of Tall Buildings in Serviceability Level, Eng. Struct., 31(9), pp.2086~2096. https://doi.org/10.1016/j.engstruct.2009.03.010
  4. Kim, J.Y., Yu, E., Kim, D.Y., Tamura, Y. (2011) Long-term Monitoring of Wind-Induced Responses of a Large-Spanroof Structure, J. Wind Eng. Ind. Aerodyn., 99, pp.955~963. https://doi.org/10.1016/j.jweia.2011.06.008
  5. LeCun, Y., Bottou, L., Benjio, Y., Haffner, B. (1998) Graient-based Learning Applied to Document Recognition, Proc. of THE IEEE, pp.1~45.
  6. Ronneberger, O., Fis cher, P., Brox, T. (2015) U-net: Convolutional Networks for Biomedical Image Segmentation, In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, Springer International Publishing, pp.234~241.
  7. Yu, E., Chung, L. (2012) Seismic Damage Detection of a Reinforced Concrete Structure by Finite Element Model Updating, Smart Struct. & Syst., 9(3), pp.253~271. https://doi.org/10.12989/sss.2012.9.3.253
  8. Yu, E., Kim, S.N., Lee, H.K., Choi, H. (2009) Damage Detection of a Frame Structure Using Finite Element Model Updating, J. Comput. Struct. Eng. Inst. Korea, 22(5), pp.445~452.