Search

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). [ABSTRACT FROM AUTHOR]

Non-ductile reinforced concrete frames have seismic vulnerabilities due to inadequate reinforcing details. Adequately characterizing the performance of these details is critical to the development of analytical models. This study presents a methodology to simulate the response of such frames with and without fiber-reinforced polymer column jackets. The bond-slip effects between reinforcing bars and surrounding concrete, observed in column lap-splice and beam–column joints, are modeled with one-dimensional slide line models in LS-DYNA. The model is defined from failure modes and bonding conditions observed in full-scale dynamic tests and can predict story displacements, inter-story drifts, and damage mechanisms. [ABSTRACT FROM AUTHOR]

Piloti-type reinforced concrete building structures have vertically irregular configurations composing a moment frame for parking spaces in the lower story and heavy-weight shear wall system for residential spaces in the upper stories. Due to these vertically irregular configurations, such building structures are governed by a soft-story mechanism, damage concentration on the first story. Since the 2017 Pohang earthquake led to severe damage to the piloti-type building structures on a regional level, a decision-making tool mitigating the seismic damage for future events is needed. This paper aimed to propose a rapid decision-making tool promptly estimating seismic damage with simple information and determining a retrofit scheme using a pre-developed extensive database, i.e., multi-dimensional structural parameter surfaces. The multi-dimensional surfaces were created using a simplified modeling approach with five structural parameters: period, strength ratio, and ductility controlling failure modes as the input, and peak inter-story drift ratio and demand-to-capacity ratio as the output. The proposed methodology was validated using a finite element model for the piloti-type building structure with a soft-story mechanism. The seismic responses detected from the multi-dimensional surfaces have a slight difference from those of the numerical model. Nevertheless, the rapid tool predicted a reasonable agreement with performance evaluation from the finite element simulation. In addition, the rapid tool provided feasible retrofit options to meet target performance using brief structural information. Due to its simplified process, the proposed tool can be implemented to the regional seismic assessment for the residential areas where the piloti-type building structures were highly concentrated. • Seismic vulnerabilities to piloti-type buildings highly concentrated in urban areas due to their vertical irregularities. • Extensive database from simplified numerical models reproducing the seismic vulnerabilities of the piloti-type structures. • Development of a database-based tool for regional seismic damage assessment of the piloti-type buildings. • Validation of the proposed tool with finite element simulation of a vertically-irregular building structure. • Establishment of retrofit schemes for piloti-type building structures with brief structural information. [ABSTRACT FROM AUTHOR]