한국지진공학회논문집 (Journal of the Earthquake Engineering Society of Korea)

  • 제28권4호
  • /
  • Pages.193-203
  • /
  • 2024
  • /
  • 1226-525X(pISSN)
  • /
  • 2234-1099(eISSN)
한국지진공학회 (Earthquake Engineering Society of Korea)
권호 표지
DOI QR코드

DOI QR Code

기계학습 기반 지진 취약 철근콘크리트 골조에 대한 신속 내진성능 등급 예측모델 개발 연구

Machine Learning-based Rapid Seismic Performance Evaluation for Seismically-deficient Reinforced Concrete Frame

  • 강태욱 (경상국립대학교 건축공학과) ;
  • 강재도 (서울연구원 안전인프라연구실) ;
  • 오근영 (한국건설기술연구원 건축연구본부) ;
  • 신지욱 (경상국립대학교 건축공학과)
  • Kang, TaeWook (Department of Architecture Engineering, Gyeongsang National University) ;
  • Kang, Jaedo (Division of Safety and Infrastructure Research, The Seoul Institute) ;
  • Oh, Keunyeong (Department of Building Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Shin, Jiuk (Department of Architecture, Gyeongsang National University)
  • 투고 : 2024.02.23
  • 심사 : 2024.04.01
  • 발행 : 2024.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Existing reinforced concrete (RC) building frames constructed before the seismic design was applied have seismically deficient structural details, and buildings with such structural details show brittle behavior that is destroyed early due to low shear performance. Various reinforcement systems, such as fiber-reinforced polymer (FRP) jacketing systems, are being studied to reinforce the seismically deficient RC frames. Due to the step-by-step modeling and interpretation process, existing seismic performance assessment and reinforcement design of buildings consume an enormous amount of workforce and time. Various machine learning (ML) models were developed using input and output datasets for seismic loads and reinforcement details built through the finite element (FE) model developed in previous studies to overcome these shortcomings. To assess the performance of the seismic performance prediction models developed in this study, the mean squared error (MSE), R-square (R2), and residual of each model were compared. Overall, the applied ML was found to rapidly and effectively predict the seismic performance of buildings according to changes in load and reinforcement details without overfitting. In addition, the best-fit model for each seismic performance class was selected by analyzing the performance by class of the ML models.

키워드

과제정보

본 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원 (RS-2024-00348713) 및 과학기술정보통신부의 재원으로 수행된 한국건설기술연구원 주요사업의 결과물임(No.20230146-001).

참고문헌

  1. Bracci JM, Reinhom AM, Mander JB, Seismic resistance of concrete frame structures designed for gravity loads: performance of structural system. ACI Struct J. 1995;92(5):597-609. https://doi.org/10.14359/909
  2. Sause R, Herries KA, Walkup SL, Pessiki Sm Ricles JM. Flexural behavior of concrete columns retrofitted with carbon fiber reinforced polymer jackets. ACI Sturct J. 2004;101(5):708-716.
  3. Jeon J-S, DesRoches R, Lowes LN, Brilakis I. Framework of aftershock fragility assessment-case studies: older Califronia Reinforced concrete building frames. Earthquake Eng. Struct. Dyn. 2015;44(15):2617-2636. https://doi.org/10.1002/eqe.2599
  4. Wright TR. Full-scale seismic testing of a reinforced concrete moment frame using mobile shakers. Atlanta, GA (US): Georgia Institute of Technology, PhD Thesis.
  5. Ministry of the Interior and Safety (MOIS), Pohang Earthquake White Paper, 2018: 144-163, 209-213, 227-241.
  6. Aschheim M, Gulkan P, Sezen H, Bruneau M, Elnashai AS, Halling M, et al. Performance of buildings. Earthquake Spectra. 2000; 16(S1):237-279. https://doi.org/10.1193/1.1586155
  7. Gulen O, Robert KD, Tugce B, Jui‑Liang L, Tunc Deniz Uludag et al., Field reconnaissance and observations from the February 6, 2023, Turkey earthquake sequence, Original Paper 2023;119:663-700. https://doi.org/10.1007/s11069-023-06143-2
  8. Sause R, Harries KA, Walkup SL, Pessiki S, Ricles JM, Felxural behavior of concrete columns retrofittedd with carbon fiber reinforced polymer jackets. ACI Structural J. 2004;101(5):708-716. https://doi.org/10.14359/13393
  9. Harries K, Ricles J, Pissiki S, Sause R, Seismic retrofit of lap splices in nonductile columns using CFRP jackets. ACI Struct J. 2006;103(6):226-236. https://doi.org/10.14359/18242
  10. Haroun MA, Mossalam AS, Feng Q, Elsanadedy Hm. Experimental investigation of seismic repair and retrofit of bridge columns by composite jackets. J Reinforced Plastics and Composites. 2003; 22(4):1243-1268. https://doi.org/10.1177/0731684403035573
  11. Lan YM, Sotelino ED, Chen WF. State of the art review of highway bridge columns retrofitted with FRP jackets. Department Report CE -STR-98-5; School of Civil Engineering Purdue University; West Lafatette (IN); c1998.
  12. Seible F, Prisetley MJN, Innamorato D, Weeks J, Policelli F. Carbon firber jacket retrofit test of circular shear bridge column. CRC-2. advanced Composites Technology Transfer Consortium Rep. No. ACTT-94/02, University of California, San Diego, La Jolla, California; c1994.
  13. Seible F, Hegemier GA, Priestley MJN, Ho F, Innamorato D. Rectan- gular carbon jacket retrofit of flexural column with 5% continuous reinforcement. Advanced Composites Technology Transfer Consortium Report No. ACTT-95/03, University of California, San Diego, La Jolla, California; c1995.
  14. Seible F, Hegemier GA, Priestley MJN, Innamorato D, Ho F. Carbon fiber jacket retrofit test of circular flexural columns with lap spliced rein- forcement. Advanced Composites Technology Transfer Consortium Report No. ACTT-95/04, University of California, San Diego, La Jolla, California; c1995.
  15. Seible F, Priestley MJN, Hegemier GA, Innamorato, Seismic retrofit of RC Columns with continuous carbon fiber jackets. J Composites for Construction. 1997;1(2):52-62. https://doi.org/10.1061/(ASCE)1090-0268(1997)1:2(52)
  16. Ministry of Land, Infrastructure and Transport (MOLIT), Korea Authority of Land & Infrastructure Safety (KALIS), Guidelines for Seismic Performance Evaluation of Existing Structures (Buildings), 2021:2-4.
  17. Lee SC. Prediction of concrete strength using artificial neural networks. Eng Struct. 2003;25(7):849-57. https://doi.org/10.1016/S0141-0296(03)00004-X
  18. Inel M. Modeling ultimate deformation capacity of RC columns using artificial neural networks. Eng Struct. 2007;29(3):329-335. https://doi.org/10.1016/j.engstruct.2006.05.001
  19. Stewart LK, Morrill KB, Residual capacity prediction of blast-looaded steel columns using physics-based fast running models. Int J Safety Security Eng. 2015;5(4):289-303. https://doi.org/10.2495/SAFE-V5-N4-289-303
  20. Shin J, Scott DW, Stewart LK, Jeon J. Multi-hazard assessment and mitigartion for seismically-deficient RC building frames using artificial neural network models. Engineering Structures. 2020; 207: 110204. Available from: https://doi.org/10.1016/j.engstruct.2020.110204
  21. Pham K, Kim D, Park S, Choi H. Ensemble learning-based classification models for slope stability analysis. Catena. 2021;196: 104886. Available from: https://doi.org/10.1016/j.catena.2020.104886
  22. Shin J, Scott DW, Stewart LK, Yang CS, Wright RT, DesRoches R. Dynamic response of a full-scale reinforced concrete building frame retrofitted with FRP column jackets. Eng Struct. 2016; 125:244-53. https://doi.org/10.1016/j.engstruct.2016.07.016
  23. Livermore Software Technology Corporation. LS-DYNA Keyword User's Manual Version 971/R7.0. Livermore, CA (US); c2013.
  24. FEMA-P695. Quantification of building seismic performance factors Rep. No. FEMA-P695, Federal Emergency Management Agency (FEMA): Washington, DC (US); c2009.
  25. Shin J, Stewart LK, Yang CS, Scott DW. Implementation of bondslip performance models in analyses of non-ductile reinforced concrete frames under dynamic loads. J Earthquake Eng. 2020; 24(1):129-154. https://doi.org/10.1080/13632469.2017.1401565
  26. Shin, J. Multi-hazard performance ctiteraia for non-ductile reinforced concrete frame buildings retrofitted with an FRP column jacketing system. PhD thesis, Georgia Institute of Technology, Atlanta, GA (US); c2017.
  27. FEMA-356. Pre-standard and commentart for the seismic rehabilita-tion of buildings, prepared by ASCE. Rep. No. FEMA356, Federal Emergency Management Agency (FEMA): Washington, DC (US); c2000.
  28. FEMA-P695. Quantification of building seismic performance factors Rep. No. FEMA-P695, Federal Emergency Management Agency (FEMA): Washington, DC (US); c2009.
  29. FEMA-356. Pre-standard and commentart for the seismic rehabilita- tion of buildings, prepared by ASCE. Rep. No. FEMA-356, Federal Emergency Management Agency (FEMA): Washington, DC (US); c2000.