http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
지붕층 가속도를 활용한 비모델 기반 최대층간변위비 추정
오미드야즈단파나 ( Omid Yazdanpanah ),장민우 ( Minwoo Chang ) 한국구조물진단유지관리공학회 2022 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.26 No.1
In this paper, a nonmodel-based procedure incorporating machine learning techniques is introduced to estimate the peak story drift ratios (SDR) of buildings with eccentrically braced frames. The database includes average spectral acceleration intensity measure, wavelet-based refined damage-sensitive feature (rDSF), assembled only by the roof absolute acceleration response, geometric information, as predictor variables, and peak story drift ratios for the prototype models, as the target. Random forest machine learning regression is employed to predict the peak SDR. To compute the improved wavelet-based rDSF and promote a nonmodel-based approach, the first mode frequency, estimated numerically using Auto-Regressive model with exogenous input, is employed.