Probabilistic machine learning approach to bridge fatigue failure analysis due to vehicular overloading

Abstract

With the rapid development of freight transportation, truck overloading becomes very common and severe, posing a great threat to the safety of bridges, and it can even result in bridge failure. Traditional approaches investigating the overloading-induced fatigue damage on bridges, such as finite element analysis (FEA) and reliability analysis, have proven to be computationally expensive and model dependent. In this study, the prediction of fatigue failure probability of bridges due to traffic overloading was investigated by using the feedforward neural network and the Monte Carlo method. Our results show that based on a finite set of training data for the bridge under consideration, the proposed machine-learning-based approach can assist in providing an instantaneous assessment of the fatigue failure probability with high accuracy.