Performance-Based Analytics-Driven Seismic Design of Steel Moment Frame Buildings (2018 - 2021)
Overview of Study
With the embrace of the performance-based seismic design as the state-of-the-art design method, recent emphasis has been placed on eliminating its drawbacks and facilitating its application in practice. This project aims to propose an alternative design method: performance-based analytics-driven seismic design, which is applied to steel moment resisting frame (SMRF) buildings. In this project, a Python-based computational platform was developed to automate the seismic design, structural modeling, and seismic response simulation. Then a comprehensive database including more than 600 SMRF designs and their responses are constructed. Using the database, three machine learning-based data-driven models are developed to estimate the seismic drift demand in SMRFs and the efficacy of newly-developed and existing model is investigated. Finally, a set of surrogate models are created to estimate the probabilistic distribution of engineering demand parameters, which are further adopted to evaluate the earthquake-induced economic losses.
