Data-Driven Substructuring Technique for Pseudo-Dynamic Hybrid Simulation of Steel Braced Frames

TL;DR

This paper introduces a novel data-driven hybrid simulation method using machine learning to accurately predict the hysteretic response of steel braces in seismic structural analysis.

Contribution

It develops a new machine learning-based model, PI-SINDy, for hybrid simulation of steel braced frames, enhancing prediction accuracy of hysteretic responses under seismic loads.

Findings

PI-SINDy accurately predicts hysteretic behavior.

DDHS matches nonlinear response history analysis results.

Model improves simulation efficiency and reliability.

Abstract

This paper proposes a new substructuring technique for hybrid simulation of steel braced frame structures under seismic loading in which a new machine learning-based model is used to predict the hysteretic response of steel braces. Corroborating numerical data is used to train the model, referred to as PI-SINDy, developed with the aid of the Prandtl-Ishlinskii hysteresis model and sparse identification algorithm. By replacing a brace part of a prototype steel buckling-restrained braced frame with the trained PI-SINDy model, a new simulation technique referred to as data-driven hybrid simulation (DDHS) is established. The accuracy of DDHS is evaluated using the nonlinear response history analysis of the prototype frame subjected to an earthquake ground motion. Compared to a baseline pure numerical model, the results show that the proposed model can accurately predict the hysteretic response of steel buckling-restrained braces.