Plastic hinge length of rectangular RC columns using ensemble machine learning model

Abstract It is critical to properly define the plastic hinge region (the region that is exposed to maximum plastic deformation) of reinforced concrete (RC) columns to assess their performances in terms of ductility and energy dissipation capacity, implement retrofitting techniques, and control damages under lateral loads. The plastic hinge length (PHL) is used to define the extent of damages/plastic deformation in a structural element. However, accurate determination of the plastic hinge length remains a challenge. This study leveraged the power of ensemble machine learning algorithms by combining the performances of different base models and proposed a robust ensemble learning model to predict the PHL. The prediction of the proposed model is compared with those of existing empirical models and guideline equations for the PHL. The proposed model outperformed the predictions of all models and resulted in a superior prediction with a coefficient of determination ( R 2 ) between the experimental and predicted values for PHL of 98 % . Furthermore, the SHapley Additive exPlanations (SHAP) approach is used to explain the predictions of the model and highlight the most significant factors that influence the PHL of rectangular RC columns.