Towards a real-time Structural Health Monitoring of railway bridges

More than 350,000 railway bridges are present on the European railway network, making them a key infrastructure of the whole railway network. Railway bridges are continuously exposed to changing environmental threats, such as wind, floods and traffic load, which can affect safety and reliability of the bridge. Furthermore, a problem on a bridge can affect the whole railway network by increasing the vulnerability of the geographic area, served by the railway network. In this paper a Bayesian Belief Network (BBN) method is presented in order to move from visual inspection towards a real time Structural Health Monitoring (SHM) of the bridge. It is proposed that the health state of a steel truss bridge is continuously monitored by taking account of the health state of each bridge element. In this way, levels of bridge deterioration can be identified before they become critical, the risk of direct and indirect economic losses can be reduced by defining optimal bridge maintenance works, and the reliability of the bridge can be improved by identifying possible hidden vulnerabilities among different bridge elements