Towards Multilevel Modelling of Train Passing Events on the Staffordshire Bridge

It is vital that we develop appropriate statistical models to represent and extract valuable insights from these large datasets, since the bridges constitute critical infrastructure within modern transportation networks. The process of monitoring engineered systems via streaming data is typically referred to as Structural Health Monitoring (SHM) and while successful applications have been emerging in recent years, a number of challenges remain for practical implementation [5]. During model design, these concerns usually centre around low variance data: that is, measurements are not available for the entire range of expected operational, environmental, and damage conditions. Consider a bridge following construction, this will have a relatively small dataset that should only be associated with normal operation. On the other hand, a structure with historical data might still not experience low-probability events - such as extreme weather or landslides. An obvious solution considers sharing data (or information) between structures; this has been the focus of a large body of recent work [6-8].