The seismically deficient column details in existing reinforced concrete buildings affect the overall behavior of the building depending on the failure type of the column. The purpose of this study is 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 the 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 the accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model has the highest average value for the classification model performance measurements among the considered learning methods and can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with the simple column details. Additionally, it was demonstrated that the predicted failure modes from the selected model were exactly same as the failure mode determined from a code-defined equation (traditional method).
Existing reinforced concrete building structures have low lateral resistance capacities due to seismically deficient details. Since these building structures suffer an increase in axial loads to the main structural elements due to green retrofits (e.g., installation of energy equipment/devices, roof gardens) as one of the sustainable building solutions and/or vertical extensions, their capacities can be reduced. This paper aims to propose a rapid estimation method incorporating a previously developed machine-learning model to find an allowable range of axial loads for reinforced concrete columns using simple structural details for enhancement in the sustainability performance of existing buildings in structural and energy fields. The methodology consists of two steps: (1) a machine-learning-based failure detection model, and (2) column damage limits proposed by previous researchers. To demonstrate this proposed method, an existing building structure built in the 1990s was selected, and the allowable range for the target structure was computed for both exterior and interior columns. A machine-learning-based method showed that axial loading could be increased by a factor of 1.35. Additionally, nonlinear time-history analysis for the target structure was performed to compare the seismic responses before and after applying the maximum allowable axial load. Based on the dynamic responses, the increased axial loads from green retrofits and/or vertical extensions could degrade structural performance and change its failure mode. The proposed methodology can rapidly estimate the allowable axial load range for existing reinforced concrete buildings without repeated modeling and computing processes. In addition, nonlinear time-history analysis is needed to accurately evaluate the impact of the increased axial loads from green retrofits/vertical extensions on structural performance.
Existing reinforced concrete buildings with seismically-deficient column details affect the overall behavior depending on the failure type of column. The purpose of this study is 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 the simple column details. Additionally, it was demonstrated that the predicted failure modes from the selected model were exactly same as the failure mode determined from a code-defined equation (traditional method)