Nonmodel rapid seismic assessment of eccentrically braced frames incorporating masonry infills using machine learning techniques

Abstract

This study investigates the seismic behavior of eccentrically braced frames (EBFs) taking into account the influence of masonry infill walls using a nonmodel scenario-based machine learning framework. Predicting engineering demand parameters (EDPs) by exploiting data-driven approaches and developing the associated fragility curves of infilled EBFs are the main objectives of this research. To this end, a set of 4- and 8-story archetype EBF structures considering 12 distinct infill properties, a total number of 4 bare and 48 infilled EBF models, are created in OpenSees software. A nonlinear pushover analysis is then conducted to assess the overall impact of infills on 4- and 8-story EBFs. Incremental dynamic analysis under 44 far-field ground motions is performed to collect an extensive raw database consisting of 37,164 and 461,480 data points for each variable of bare and infilled EBFs, respectively. It encompasses seismic intensity measure (Saavg), wavelet-based robust damage sensitive feature (rDSF), derived from roof absolute acceleration, frame geometric information, and infill parameter as input features and also EDPs containing peak and residual story drift ratios and peak floor accelerations (PFA) as response variables. After data preprocessing, both regression analysis and machine learning (ML) techniques are utilized to estimate EDPs under two scenarios of Input-Output and Output-Only based on the availability of Saavg. Comparing error measures, particularly in the Extreme Gradient Boosted Tree (ExGBT) algorithm, reveals strong observed-predicted EDP compatibility. Linear equations from bare frame data predict infilled frame EDPs without modification coefficients. Data preprocessing demonstrates that infills decrease drift-based EDPs due to stiffness improvement, while their impact on PFA remains inconclusive. Saavg and rDSF-based fragility curves at three damage states show accurate predictions and effectively reduce vulnerability in infilled 4-story EBFs. However, infills undesirably affect non-ductile behavior in 8-story EBFs, leading to increased global damage as supported by pushover analysis.