Existing reinforced concrete buildings with seismically deficient column details affect the overall behavior depending on the failure type of column. This study aims to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear, and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used, considering previously collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with simple column details.
As earthquakes have increased in Korea recently, people are paying attention to the seismic performance of buildings built in the past. Many school buildings in Korea were built based on standard drawings before the seismic design was applied. However, since school buildings are often designated as emergency evacuation facilities in case of disasters such as earthquakes, seismic evaluation and retrofit must be done quickly. This study investigated the failure modes among structural components (beams, columns, and joints), focusing on 1980s standard drawings for school buildings. The effects of column axial force, partial masonry infills, and different material strengths for concrete and rebar were considered for detailed evaluation. As a result, most of the joints were found to be the weakest among structural components. Column axial forces tended to make the joints more vulnerable, and partial masonry infills increased the possibility of joint failure and shear failure in columns.