Development of an Intelligent Model for Predicting the Reduction in Load-Carrying Capacity of Urban Bridges under the Combined Effects of Earthquakes, Corrosion, and Structural Fatigue
Development of an Intelligent Model for Predicting the Reduction in Load-Carrying Capacity of Urban Bridges under the Combined Effects of Earthquakes, Corrosion, and Structural Fatigue
Orang Chaei Rassouli Tabrizi1
1) M.Sc. in Civil Engineering – Geotechnical Engineering, Tabriz Metropolitan Municipality, Tabriz, Iran Email:
IOI Code
:
ABZE-ABHGCD
Publication :
5th International Congress on Civil Engineering, Architecture, Building Materials and Environment(caucong.com)
Abstract :
Urban reinforced concrete bridges are exposed throughout their service life to the simultaneous effects of traffic loading, material deterioration, corrosion, and seismic hazards, which may lead to a gradual reduction in load-carrying capacity and increased structural vulnerability. This study aims to develop an intelligent model for predicting the reduction in the load-carrying capacity of reinforced concrete bridges under the combined effects of earthquakes, corrosion, and structural fatigue. The required data were generated using numerical simulations and physics-based models, and Random Forest, Gradient Boosting, and Artificial Neural Network algorithms were employed to predict the residual load-carrying capacity. The results demonstrated that the Random Forest model achieved the highest predictive accuracy, with a coefficient of determination (R²) of 0.96. Furthermore, Shapley value analysis identified reinforcement corrosion, shear span ratio, earthquake intensity, and fatigue cycles as the most influential factors affecting the residual load-carrying capacity. The proposed model can be effectively applied to intelligent bridge maintenance management and the prioritization of repair interventions for urban bridges.
Keywords : load carrying capacity reduction machine learning reinforcement corrosion structural fatigue earthquake