This study aimed to develop a machine learning model to predict the damage state of reinforced concrete bridge columns after vehicle collisions. To achieve this, a numerical model of the columns was constructed in LS-DYNA to realistically simulate their lateral impact response through the calibration of concrete and steel material models under impact loads with the experimental results of column specimens available in the literature. The developed numerical model was then used to simulate vehicle collisions with full-scale bridge column, enabling a comprehensive analysis of column damage across diverse impact scenarios. Using design and vehicle parameters (input) used in the scenarios and post-collision damage state of the columns (output), five classification-based machine-learning models were developed. Among these models, the extreme gradient boosting (XGBoost) model with Bayesian optimization (accuracy of 92%) was selected as the optimal machine learning model based on feature selection, normalization, data splitting (training versus test), data balancing, and hyperparameter tuning. Shapley additive explanations were implemented to offer insights into the contribution of each input variable to the final prediction. The analysis showed that the column diameter, vehicle velocity, and longitudinal reinforcement ratio, in order of influence, significantly impacted the column damage state.
Selected Publications
This study aims to develop a computational fluid dynamics (CFD)-based framework to assess the thermal behavior of reinforced concrete structures with non-uniformly distributed fire damage. To achieve this, a CFD model that can predict fire-induced temperature was validated using experimental data of a reinforced concrete (RC) column obtained from an existing study. It was then extended to develop the CFD model of an RC building frame to investigate the extent and pattern of damage to its columns and beams under various fire scenarios, combinations of fire intensity, ventilation coefficient, and fire source locations. The non-uniform temperature distributions of the columns and beams were used to modify the stress–strain curve of concrete and rebar and to perform a moment–curvature analysis to evaluate their residual flexural strength. The computed flexural strengths were compared with those obtained from existing design guidelines. The guidelines were determined to be extremely cautious compared to the results of the proposed method.
Selected Publications
Jang Hyeok Yun and Jong-Su Jeon* (2023). Fire scenario-based damage assessment of ductile reinforced concrete buildings using computational fluid dynamics models. Journal of Building Engineering; 78: 107655, November 1.
Jang Hyeok Yun, Eunsoo Choi, and Jong-Su Jeon* (2024). CFD simulation-based fragility analysis of reinforced concrete buildings damaged by traveling fire. Engineering Structures; 317: 118644, October 15.
Non-ductile reinforced concrete building structures built before the 1970s have been significantly damaged and collapsed under man-made disasters (e.g., blast loads) due to their inadequate column details. The structural deficiencies can be mitigated by a fiber-reinforced polymer jacketing system. This research investigated the blast performance of a low-rise non-ductile building frame strengthened with the jacketing system. Based on the investigation, a retrofit scheme was established to mitigate the blast-induced damage and maximize the effectiveness of the retrofit system. The retrofitted models varied with the main parameters of the retrofit system associated with the confinement effect and flexural stiffness, and blast simulation was performed under various loading scenarios. The retrofit effect was examined in terms of confinement and stiffness ratios. Since the effects of the retrofit parameters on the blast performance depend on the blast loads, the retrofit scheme needs to be established in terms of expected blast loading scenarios.
Selected Publications
Bilal Ahmed, Taehyo Park, and Jong-Su Jeon* (2025). Blast response and damage assessment of reinforced concrete slabs using convolutional neural networks. International Journal of Damage Mechanics; 34(5): 771–797, May 1.
Jiuk Shin and Jong-Su Jeon* (2019). Retrofit scheme of FRP jacketing system for blast damage mitigation of non-ductile RC building frames. Composite Structures; 228: 111328, November 15.
To evaluate fire-induced damage to bridge structures, the thermal–structure interaction (TSI) fire analysis method is proposed, verified and applied to examine the behaviour of bridge superstructures with steel–concrete composite sections and prestressed concrete (PSC) exposed to fire loading. The proposed TSI fire analysis consists of two different modelling parts: thermal transfer analysis and thermodynamic structural analysis. The body temperature inside the structure is first calculated using fire curve boundary conditions in an overall non-linear transient thermal transfer analysis. Thermodynamic structural analysis is then performed based on the entire temperature and heat distribution in the structure. To validate the proposed method, comparisons are made with standard fire test results: the temperature distribution and the deflection of the steel–concrete composite superstructure agreed closely with the results of the standard fire test. The proposed fire analysis method is finally applied to two bridges with different superstructures (steel–concrete composite and PSC) damaged by recent fire events in Korea.
Selected Publications
Sung-Hwang Yun and Jong-Su Jeon* (2018). Post-fire damage assessment of Korean bridges using thermal–structure interaction fire analysis. Magazine of Concrete Research; 70(18): 938–953, September 15.