How artificial intelligence is improving Network Rail track worker safety
Network Rail is improving its track worker safety, with artificial intelligence software helping to find and remove scrap materials from the side of the railway.
The rail operator is spearheading a trial of One Big Circle’s video and AI technology to locate old railway kit that can either be re-used or recycled but that is also creating obstructions for track workers. This will reduce the risk of injury to colleagues from slips, trips and falls, while also tidying up the railway Network Rail has said.
The technology captures high-definition train’s-eye-view video – known as Automated Intelligent Video Review (AIVR) – from across the rail network, with the footage instantly accessible in the cloud. The footage is then analysed by AI to find scrap rail, sleepers and bags of ballast and map their locations using GPS, enabling maintenance teams to plan how and when to safely remove the items.
Network Rail senior innovations engineer Wayne Cherry said the technology is “a brilliant opportunity to improve how efficient we are as a business”.
He added: “While AIVR is already in use across other parts of Network Rail, this will be the first time this technology has been used in this way with AI and could be a real game-changer. Not only is scrap on the side of the railway unsightly, but it can also become an obstacle during planned engineering work, block safe walkways or delay our teams accessing part of the railway infrastructure to make repairs during disruption.
“If we can become safer and more efficient with identifying and removing scrap material, it will not only help our colleagues stay safe, but benefit the wider rail industry, passengers and the taxpayer.”
AI specialist nPlan chief executive Dev Amratia emphasised that “AI can make railways safer, services more reliable and costs lower”.
He added: “Network Rail’s video analysis trial shows what is possible – as does its use of nPlan’s AI to forecast and de-risk its large-scale construction projects. Wider use of AI will be transformative, ultimately allowing Network Rail to gain a real-time, data-driven view of infrastructure, foresee problems, enhance strategic planning and optimise project delivery.
“Network Rail is clearly making some very smart choices about deploying what are still fairly cutting-edge technologies right now and we’re excited to see how they’re going to use these to benefit passengers, industry and taxpayers in the near future.”
The project is currently being trialled on the Wessex route, one of the busiest on the rail network, taking in all or part of the counties of Surrey, Berkshire, Hampshire, Dorset, Devon, Somerset and Wiltshire. After this Network Rail will look to roll it out more widely.
On the Wessex route, slips, trips and falls are the largest causes of injury and scrap on the side of the track is a significant hazard, particularly as most work happens during darkness.
Network Rail Wessex route health and safety advisor Martyn Shaftoe, who is leading this project, said he believes the technology “will play an important role in helping keep our front-line colleagues safe, help us become more efficient in locating and removing scrap, as well as improving the overall condition of the railway for the benefit of our passengers and local residents”.
He added: “Unfortunately, over recent years, the railway has become somewhat of a dumping ground for discarded railway sleepers, scrap rail, redundant ballast bags and many other assets. The challenge we face is there is no definitive list of where these materials or assets are.
“The prospect of accurately locating scrap material using high-definition video footage and AI without the need for colleagues to walk along the railway is a huge safety improvement opportunity.”
Financially, not only can some of the scrap material be recycled and any money accrued used to support running the railway, but some of the leftover materials are also reusable. For example, Bomac concrete sleepers are no longer manufactured, but there is still a demand for them as replacements on sidings and on some stretches of track. As a result of this technology, 40 of these sleepers have been identified on a site between Yeovil and Weymouth where they can be recovered and stored for future use across the business, preventing the need to buy costly new equivalents.
Shaftoe added: “To be able to help the industry potentially save money by reusing or recycling this treasure-trove of scrap materials is a brilliant prospect and we look forward to hopefully rolling it out more widely across the business later in the year.”
One Big Circle co-founder and director Emily Kent described the work as “a really exciting application of AI”.
She said: “The AIVR system collects high quality lineside imagery from across the whole of the UK to help many different engineers and disciplines see what they need to see without attending site.
“Adding further intelligence to that data – as with this automatic detection and location of scrap rail and other lineside hazards – really enables you to hone in on specific issues and respond to them quickly and safely.”
Like what you’ve read? To receive New Civil Engineer’s daily and weekly newsletters click here.