Rail Safety and Standards Board to use AI
04/04/2023
The Rail Safety and Standards Board (RSSB) in the UK has partnered with the University of Sheffield to develop a tool that will help to predict low-adhesion track conditions using artificial intelligence (AI).
This research project is exploring how detailed information on local conditions can be used to reduce seasonal train delays caused by ‘leaves on the line’.
Particularly in autumn, temperature, humidity and the presence of leaves or other contaminants can impact the level of adhesion between the train wheel and the rail.
Low-adhesion track conditions can cause delays and result in station and signal overruns. This is thus a safety and operational issue that currently costs the rail industry around £350 million each year.
RSSB’s project will use AI to analyse data and high-resolution video footage. This process then aims to deliver more accurate predictions regarding friction at the wheel-rail interface.
An online tool will be created in time for autumn 2023, to allow users to enter data that will generate friction predictions for any location on the rail network.
Roger Lewis, Professor of Mechanical Engineering at the University of Sheffield, said: “It is very exciting for the team at Sheffield and the Rail Safety and Standards Board that our fundamental analysis of the causes of low adhesion and extensive collection of data from track are now coming together to enable the development of the AI friction prediction tool that will help the railway industry with performance and safety issues around autumn.”
