기계학습 기반 철근콘크리트 기둥에 대한 신속 파괴유형 예측 모델 개발 연구
Machine Learning-Based Rapid Prediction Method of Failure Mode for Reinforced Concrete Column
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Existing reinforced concrete buildings with seismically deficient column details affect the overall behavior depending on the failure type of column. This study aims to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear, and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used, considering previously collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with simple column details.
Abstract
Existing reinforced concrete buildings with seismically deficient column details affect the overall behavior depending on the failure type of column. This study aims to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear, and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used, considering previously collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with simple column details.
참고문헌 (20)
- Mo YL, "Seismic behavior of RC columns with various tie configurations", Journal of Structural Engineering, 126(10), pp.1122~1130 (2000)
- Lynn AC, "Seismic evaluation of existing reinforced concrete building columns", Earthquake Spectra, 12(4), pp.715~739 (1996)
- Sezen H, "Seismic behavior of shear-critical reinforced concrete building columns", Seventh US National Conference on Earthquake Engineering (2002), Earthquake Engineering Research Institute
- Zhu L, "Classification and seismic safety evaluation of existing reinforced concrete columns", J Struct Eng, 133(9), pp.1316~1330 (2007)[DOI]
- Qi Yl, "Failure mode classification of reinforced concrete column using Fisher method", Journal of Central South University, 20(10), pp.2863~2869 (2013)[DOI]
- Naderpour H, "Proposed soft computing models for moment capacity prediction of reinforced concrete columns", Soft Comput, 24(15), pp.11715~11729 (2020)[DOI]
- Mirrashid M, "Innovative Computational Intelligence-Based Model for Vulnerability Assessment of RC Frames Subject to Seismic Sequence", J Struct Eng, 147(3), pp.04020350~ (2021)[DOI]
- Alibrandi U, "A new sampling strategy for SVM-based response surface for structural reliability analysis", Probab Eng Mech, 41, pp.1~12 (2015)[DOI]
- Mangalathu S, "Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques", Eng Struct, 160, pp.85~94 (2018)[DOI]
- Naderpour H, "Classification of failure modes in ductile and non-ductile concrete joints", Eng Fail Anal, 103, pp.361~375 (2019)[DOI]
- Alcantara PA, "Failure mode classification of reinforced concrete columns by the analysis of the strain distribution in the main reinforcement", Proceedings of the 12th World Conference on Earthquake Engineering (2000), New Zealand Society for Earthquake Engineering
- Ying M, "Seismic failure modes and deformation capacity of reinforced concrete columns under cyclic loads", Periodica Polytechnica Civil Engineering, 62(1), pp.80~91 (2018)
- Mangalathu S, "Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations(SHAP)approach", Eng Struct, 219, pp.110927~ (2020)
- Feng DC, "Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm", Adv Eng Inf, 45, pp.101126~ (2020)
- Berry M, "PEER structural performance database user’s manual (version 1.0)", University of California, ~ (2004)
- Yoshikawa H, "Ductility and failure modes of single reinforced concrete columns", Nippon Konkurito Kogaku Kyokai Ronbunshu, 51(1), pp.229~224 (1999)
- Naderpour H, "Failure mode prediction of reinforced concrete columns using machine learning methods", Engineering Structures, 248, pp.113263~ (2021)
- Choi JS, "Shear Strength Evaluation of Reinforced Concrete Columns 1 : Variable Analysis for Code Method", Journal of the Architectural Institute of Korea(JAIK), 37(1), pp.687~688 (2017)
- Bažant ZP, "Failure of slender and stocky reinforced concrete columns : Tests of size effect", Materials and Structures, 27, pp.79~90 (1994)
- Shi Q, "Structures", pp.1955~1970 (2021), Elsevier