Development of a probabilistic model for fatigue analysis of railway bridges using dynamic bayesian networks

• Grant number: 23/09449-2
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: December 01, 2023
• End date: November 30, 2027
• Field of knowledge: Engineering - Civil Engineering - Structural Engineering
• Principal Investigator: Tulio Nogueira Bittencourt
• Grantee: Caroline Correa de Faria
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

Railway bridges are considered Structural Arts, due to their impressive dimensions, ability to span obstacles, and transport people and goods within a country. Due to the cyclic nature of the loads acting on these structures, their structural elements and connections are subjected to fatigue, which can compromise their performance and even their safety. Therefore, it is important to develop an efficient monitoring system with effective inspection and repair actions that ensure proper structural performance throughout the service life of the structure. Thus, assessing deterioration mechanisms is essential for making accurate predictions. However, in addition to the high costs involved in these activities, bridge management in Brazil has been carried out empirically, based on the experience of inspectors and managers who may be subjectively evaluating these structures. To overcome this situation, probabilistic deterioration models for real structures can be used to improve the accuracy of the prediction of the deterioration rate over time, optimize inspection intervals and intervention actions, as well as control the life-cycle cost of the structure. Therefore, this project aims to develop a probabilistic deterioration model to evaluate fatigue in railway bridges using Dynamic Bayesian Networks, trained and capable of classifying and characterizing a large amount of data obtained from real-time structural monitoring. The ultimate goal of this project is to optimize the planning of inspections and repair of the structural components, thereby minimizing the associated costs.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BEN SEGHIER, MOHAMED EL AMINE; ELSHABOURY, NEHAL; ABDELKADER, ESLAM MOHAMMED; CARVALHO, HERMES; DE FARIA, CAROLINE CORREA; MIGUEL, LEANDRO FADEL. Two-stage framework for lateral-torsional buckling resistance prediction of cellular steel beams under fire conditions. STRUCTURES, v. 68, p. 17-pg., 2024-09-10. (23/09449-2)