Most reinforced concrete (RC) school buildings constructed in the 1980s have seismic vulnerabilities due to low transverse reinforcement ratios in columns and beam-column joints. In addition, the building structures designed for only gravity loads have the weak-columnstrong- beam (WCSB) system, resulting in low lateral resistance capacity. This study aims to investigate the lateral resistance capacities of a two-story, full-scale school building specimen through cyclic loading tests. Based on the experimental responses, load-displacement hysteresis behavior and story drift-strain relationship were mainly investigated by comparing the responses to code-defined story drift limits. The test specimen experienced stress concentration at the bottom of the first story columns and shear failure at the beam-column joints with strength degradation and bond failure observed at the life safety level specified in the code-defined drift limits for RC moment frames with seismic details. This indicates that the seismically vulnerable school building test specimen does not meet the minimum performance requirements under a 1,400-year return period earthquake, suggesting that seismic retrofitting is necessary.

Existing reinforced concrete (RC) building frames constructed before the seismic design was applied have seismically deficient structural details, and buildings with such structural details show brittle behavior that is destroyed early due to low shear performance. Various reinforcement systems, such as fiber-reinforced polymer (FRP) jacketing systems, are being studied to reinforce the seismically deficient RC frames. Due to the step-by-step modeling and interpretation process, existing seismic performance assessment and reinforcement design of buildings consume an enormous amount of workforce and time. Various machine learning (ML) models were developed using input and output datasets for seismic loads and reinforcement details built through the finite element (FE) model developed in previous studies to overcome these shortcomings. To assess the performance of the seismic performance prediction models developed in this study, the mean squared error (MSE), R-square (R2), and residual of each model were compared. Overall, the applied ML was found to rapidly and effectively predict the seismic performance of buildings according to changes in load and reinforcement details without overfitting. In addition, the best-fit model for each seismic performance class was selected by analyzing the performance by class of the ML models.