Skip to the content

Rail researchers develop risk tool with big data



Institute of Railway Research uses live feeds from Network Rail in development of RAATS to estimate frequency of trains passing signals at danger level

Researchers at the University of Huddersfield have created a software tool that uses big data to help rail operators cut the likelihood of incidents known as SPADs – Signals Passed at Danger.

The project by the Institute of Railway Research (IRR), part of the university’s School of Computing and Engineering, and the rail industry body RSSB indicates the potential of using large volumes of data from live feeds to improve the operation of public infrastructure.

The tool, named RAATS (Red Aspect Approach to Signals), can be used to help rail operators focus on individual signals and the number of occasions on which they have been red when been approached by a train. According to Julian Stow, the institute’s assistant director, this will have implications for driver training over specific routes and be used in timetable planning and dealing with other strategic issues.

Until the development of RAATS – derived from live feeds provided by Network Rail – information from driver surveys was used for an overall estimate for the number of occasions on which trains approached signals at red.

Enormous variation

“But actually it varies enormously between individual signals,” said Stow. “What our work allows operators to do is to look not only at the overall red approach rate for the system but to query individual signals, looking at factors such as time of the day or week, so you can start exploring how the red approach rate is influenced by how the railway is running.

“That has the potential for a much better estimation of SPAD risk at individual signals.”

Network rail provided a year’s worth of data covering about 137 million situations in which trains approached signals. An initial study of seven signalling areas showed that 3.3% of all approaches are to red signals – when the train should have stopped – but there was a large variation in the approach rates between areas and between individual signals.

This makes it possible to estimate red approach rates for individual signals and improve the SPAD risk assessment.

The project is an outcome of the £5 million strategic partnership formed between the Huddersfield’s IRR and RSSB.

Reducing risk

Director of system safety and health, Professor George Bearfield, said: “The risk from signals passed at danger has reduced substantially since the turn of the millennium so the rail industry is keen to understand where to turn to now, to make the next step change in risk management. 

“The revolution in big data offers us that opportunity to explore risk in more depth, and we’re looking forward to continuing the work with Huddersfield to enhance and then promote the RAATS tool more widely.”

RAATS is now being made freely available online to UK rail operators.

Image from University of Huddersfield

Register For Alerts

Keep informed - Get the latest news about the use of technology, digital & data for the public good in your inbox from UKAuthority.