The frequent occurrence of major earthquakes highlights the structural challenges posed by long-period ground motions (LPGMs). This study investigates the seismic performance and resilience of five reinforced concrete (RC) columns with different high-strength steel bars under LPGM-induced cyclic loading, both experimentally and numerically. The results show that low-bond and debonded high-strength steel bars significantly enhance self-centering capabilities and reduce residual drift, with lateral force reductions of 7.6% for normal cyclic loading and 19.2% for multiple reversed cyclic loading. The concrete damage in the hinge zone of the columns was increased; however, the significant inside damage of the concrete near the steel bars made it easier to restore the columns for the damage accumulation caused by multiple loading. Based on the experiment, a numerical model was developed for the columns, and a simplified model was proposed to predict energy dissipation capacity, providing practical design methods for resilient RC structures that may be attacked by LPGMs.

The application of machine learning (ML) in structural engineering is receiving increasing attention recently. This paper experimentally studies three self-restoring reinforced concrete (SRRC) columns reinforced with low-bond ultra-high strength rebars, to first discuss the reliability and evaluation of the SRRC columns under multiple reversed cyclic (MRC) loads induced by strong earthquakes, and to also first introduce the Transformer method into the analysis and discussion of structural tests. The tests confirmed the superior seismic behavior and high self-centering performance of the columns and presented how MRC loads affect the seismic performance of SRRC columns in terms of the lateral load-carrying capacity and energy dissipation capacity. Superior to conventional methods, a high-accuracy Transformer-based model is proposed to evaluate the plastic hinge height (PHL) of the tested SRRC columns compared with the other three algorithms (MLP, KNN, and XGBoost). Furthermore, the Shapley Additive exPlanations (SHAP) approach is adopted to explain the insight relationship between the structural parameters and PHL of the columns.