ABSTRACT
Bridge Safety evaluation involves many uncertainties, such as the hydrodynamic drag force (demand) and the structural strength (capacity). Reliability analysis is necessary to provide a more precise safety index. Many factors have impact on the flood-resistant reliability of a bridge, such as the presence of a dam in the upstream direction and having protective facilities on the river bank or bed. Among all of the potential influencing factors, the reliability of the bridge itself plays a key role. Thus, this study aims to analyze the system reliability of a selected bridge that includes five limit states and that has random variables for the water surface elevation, water velocity, local scour depth, soil property and wind load. Monte Carlo Simulation (MCS) using a response surface built by a Least Square Support Vector Machine (LS-SVM) is proposed to enhance the efficiency. The accuracy and variation of our solutions were confirmed by direct MCS to ensure the applicability of the proposed approach.
