Search
Abstract
The unique characteristics of earthquakes prevent the use of a single formula for predicting seismic responses of Reinforced Concrete (RC) buildings. Therefore, the objective of this study is to utilize widely recognized Machine Learning (ML) techniques in Python software to propose a solution for addressing this challenge. In order to develop data-driven methods, training and testing datasets were prepared through Incremental Dynamic Analyses (IDAs). The IDAs focused on RC buildings with elevations ranging from two to nine stories, considering near-fault seismic excitations as defined by FEMA P695. Subsequently, the datasets were enriched with significant structural features to train and evaluate ML-based models, aiming to identify the most accurate algorithms for probabilistic seismic prediction. The findings indicate that the improved algorithms as stacked ensemble ML models exhibit higher R2 values in predicting the maximum Interstory Drift Ratio (IDR) of RC buildings compared to the conventional ML algorithms.
Authors (4)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language:
- English
- Publication year:
- 2024
- Bibliographic description:
- Kazemi F., Asgarkhani N., Lasowicz N., Jankowski R.: MACHINE LEARNING-BASED SEISMIC RESPONSE AND PERFORMANCE ASSESSMENT OF REINFORCED CONCRETE FRAMES// / : , 2024,
- Sources of funding:
-
- Free publication
- Verified by:
- Gdańsk University of Technology
seen 0 times