Probabilistic machine learning approach to bridge fatigue failure analysis due to vehicular overloading. (15th August 2019)

• Record Type: Journal Article
• Authors: Yan, Wangchen; Deng, Lu; Zhang, Feng; Li, Tiange; Li, Shaofan
• Is Part Of: Engineering structures. Volume 193(2019)
• Page Start: 91
• Page End: 99
• Publication Date: 2019-08-15
• Subjects: Fatigue damage -- Machine learning -- Probabilistic analysis -- Steel girder bridge -- Vehicle overloading; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2019.05.028
• Languages: English
• ISSNs: 0141-0296

Abstract

Highlights: We have developed a machine learning based probabilistic fatigue analysis method. We have investigated the fatigue failure probability of the bridge due to overloaded truck traffic by using the Monte Carlo method. It is demonstrated that the proposed approach can predict the fatigue failure probability accurately and efficiently. 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.