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
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
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.
Abstract
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.
참고문헌 (29)
- Bracci JM, "Seismic resistance of concrete frame structures designed for gravity loads: performance of structural system", ACI Struct J, 92(5), pp.597~609 (1995)
- Sause R, "Flexural behavior of concrete columns retrofitted with carbon fiber reinforced polymer jackets", ACI Sturct J, 101(5), pp.708~716 (2004)
- Jeon J-S, "Framework of aftershock fragility assessment-case studies: older Califronia Reinforced concrete building frames", Earthquake Eng. Struct. Dyn, 44(15), pp.2617~2636 (2015)
- Wright TR, "Full-scale seismic testing of a reinforced concrete moment frame using mobile shakers", PhD
- Ministry of the Interior and Safety (MOIS), "Pohang Earthquake White Paper", 144~241 (2018)
- Aschheim M, "Performance of buildings", Earthquake Spectra, 16(S1), pp.237~279 (2000)
- Gulen O, "Field reconnaissance and observations from the February 6, 2023, Turkey earthquake sequence", Original Paper, 119, pp.663~700 (2023)
- Sause R, "Felxural behavior of concrete columns retrofittedd with carbon fiber reinforced polymer jackets", ACI Structural J, 101(5), pp.708~716 (2004)
- Harries K, "Seismic retrofit of lap splices in nonductile columns using CFRP jackets", ACI Struct J, 103(6), pp.226~236 (2006)
- Haroun MA, "Experimental investigation of seismic repair and retrofit of bridge columns by composite jackets", J Reinforced Plastics and Composites, 22(4), pp.1243~1268 (2003)
- State of the art review of highway bridge columns retrofitted with FRP jackets, "Lan YM", School of Civil Engineering Purdue University, ~, pp.Department Report CE –STR-98-5 (1998)
- Carbon firber jacket retrofit test of circular shear bridge column, "Seible F", University of California, ~, pp.CRC-2. advanced Composites Technology Transfer Consortium Rep. No. ACTT-94 (1994), 02
- Rectan- gular carbon jacket retrofit of flexural column with 5%continuous reinforcement, "Seible F", University of California, ~, pp.Advanced Composites Technology Transfer Consortium Report No. ACTT-95 (1995), 03
- Carbon fiber jacket retrofit test of circular flexural columns with lap spliced rein- forcement, "Seible F", University of California, ~, pp.Advanced Composites Technology Transfer Consortium Report No. ACTT-95 (1995), 04
- Seible F, "Innamorato, Seismic retrofit of RC Columns with continuous carbon fiber jackets", J Composites for Construction, 1(2), pp.52~62 (1997)
- Ministry of Land, Infrastructure and Transport (MOLIT), "Guidelines for Seismic Performance Evaluation of Existing Structures (Buildings)", 2~4 (2021)
- Lee SC, "Prediction of concrete strength using artificial neural networks", Eng Struct, 25(7), pp.849~857 (2003)
- Inel M, "Modeling ultimate deformation capacity of RC columns using artificial neural networks", Eng Struct, 29(3), pp.329~335 (2007)
- Stewart LK, "Residual capacity prediction of blastlooaded steel columns using physics-based fast running models", Int J Safety Security Eng, 5(4), pp.289~303 (2015)
- Shin J, "Multi-hazard assessment and mitigartion for seismically-deficient RC building frames using artificial neural network models", Engineering Structures, 207, pp.110204~ (2020)[DOI]
- Pham K, "Ensemble learning-based classification models for slope stability analysis", Catena, 196, pp.104886~ (2021)[DOI]
- Shin J, "Dynamic response of a full-scale reinforced concrete building frame retrofitted with FRP column jackets", Eng Struct, 125, pp.244~253 (2016)
- Livermore Software Technology Corporation, "LS-DYNA Keyword User’s Manual Version 971", R7.0, 2013
- FEMA-P695. Quantification of building seismic performance factors, , Federal Emergency Management Agency (FEMA), ~, pp.Rep. No. FEMA-P695 (2009)
- Shin J, "Implementation of bondslip performance models in analyses of non-ductile reinforced concrete frames under dynamic loads", J Earthquake Eng, 24(1), pp.129~154 (2020)
- Shin, J, "Multi-hazard performance ctiteraia for non-ductile reinforced concrete frame buildings retrofitted with an FRP column jacketing system", PhD, pp.2017
- FEMA-356. Pre-standard and commentart for the seismic rehabilita–tion of buildings, prepared by ASCE, , Federal Emergency Management Agency (FEMA), ~, pp.Rep. No. FEMA-356 (2000)
- FEMA-P695. Quantification of building seismic performance factors, , Federal Emergency Management Agency (FEMA), ~, pp.Rep. No. FEMA-P695 (2009)
- FEMA-356. Pre-standard and commentart for the seismic rehabilita–tion of buildings, prepared by ASCE, , Federal Emergency Management Agency (FEMA), ~, pp.Rep. No. FEMA-356 (2000)