Journal Search Engine

to

Search Advanced Search Adode Reader(link)
Download PDF Export Citation Korean Bibliography
ISSN : 1226-525X(Print)
ISSN : 2234-1099(Online)
Journal of the Earthquake Engineering Society of Korea Vol.29 No.3 pp.203-215
DOI : https://doi.org/10.5000/EESK.2025.29.3.203

Machine Learning-Based Allowable Axial Loading Estimation for RC Moment Frames

Hwang Heejin1), Oh Keunyeong2), Lee Kihak3), Shin Jiuk4)*
1)Ph.D. Student, Department of Architectural Engineering, Gyeongsang National University, 2)Senior Researcher, Department of Building Research, Korea Institute of Civil Engineering and Building Technology, 3)Professor (PhD), Department of Architectural Engineering, Sejong University, 4)Associate Professor (PhD), Department of Architectural Engineering, Gyeongsang National University

Abstract

Seismically deficient reinforced concrete(RC) structures experience reduced structural capacity and lateral resistance due to the increased axial loads resulting from green retrofitting and vertical extensions. To ensure structural safety, traditional performance assessment methods are commonly employed. However, the complexity of these evaluations can act as a barrier to the application of green retrofitting and vertical extensions. This study proposes a methodology for rapidly calculating the allowable axial force range of RC buildings by leveraging simplified structural details and seismic wave information. The methodology includes three machine-learning-based models: (1) predicting column failure modes, (2) assessing seismic performance under current conditions, and (3) evaluating seismic performance under amplified mass conditions. A machine learning model was specifically developed to predict the seismic performance of an RC moment frame building using structural details, gravity loads, failure modes, and seismic wave data as input variables, with dynamic response-based seismic performance evaluations as output data. Classifiers developed using various machine learning methodologies were compared, and two optimal ensemble models were selected to effectively predict seismic performance for both current and increased mass scenarios.

초록

     

    Figure

    Table

    Reference

    Journal Abbreviation J. Earthq. Eng. Soc. Korea
    Frequency Bimonthly
    Doi Prefix 10.5000/EESK
    Year of Launching 1997
    Publisher Earthquake Engineering Society of Korea
    Indexed/Tracked/Covered By