Interstory Drift Ratio Prediction of Steel Frames via Interpretable Machine Learning and Systematic Ground Motion Augmentation

Abstract

To overcome the dual bottlenecks of scarce actual strong earthquake records and high computational costs of nonlinear time history analysis, this study proposes a fast prediction method for structural nonlinear response that integrates systematic seismic sample expansion and machine learning technology by studying mature methods in the industry. A total of 500 ground motion records were created through the application of the amplitude scaling approach. Subsequently, the development of the steel frame structure was carried out through the application of the Abaqus software(Abaqus 2021 Edition) for the purpose of carrying out the nonlinear time history analysis to obtain the maximum interstory drift ratio (IDR) as the target response parameter. The XGBoost model was optimized to obtain improved results through the application of various evaluation criteria. Subsequently, the Shapley Additive exPlanations (SHAP) tool was applied to “open the black box” model to obtain the coupled effect of the various parameters, including displacement-related intensity measures such as RMSD and PGD on the maximum IDR during significant structure deformations. The method developed within this research has the potential to be a powerful tool for the prediction of the seismic responses. The method can be used in many areas, including probabilistic seismic demand, fragility assessment, and rapid evaluation of earthquake damage.