GoSAFE RAIL project has provided a means of virtually eradicating sudden failure on railway transport network by moving from considering critical infrastructure as inert objects to being intelligent (self-learning objects). The Safety framework for railways was developed in the project and implemented at two demonstration projects, one in Ireland and onein Croatia.

The safety framework allows the integration of data on transport network performance (e.g. visual inspection data, historic failure information, traffic data etc.) into a decision support tool (DST). DST is supporting decisions for emergency safety measures and maintenance scheduling. Algorithms at an object level (e.g. a level crossing,

bridge/earthwork or tunnel) and at a network level (traffic flow model and DST) are incorporating machine learning to train the system to evolve with time using available monitoring data. Historical and forecast climate data are used as input to the system. The precision of monitoring and predictions areimproving with time as the model predictions are compared to the object and network performance.

The application of the safety framework developed in the project and implemented within a decision support tool was demonstrated on a section of the TEN-T network in Ireland. This has included two of the main assets, also considered as critical infrastructure on the network, which are a major railway bridge, the Boyne Viaduct and railwayembankments along the network. (Figure Boyne Viaduct - drone inspection and 2 figures from DST risk mapping of railway embankments).

Our tasks:

●       Identification of railway hazards, development of Global Safety KPIs

●       Development of Decision Support Tool (DST)

●       Demonstration of the DST implementation in case studies in Ireland and Croatia

●       Railway safety management processes