AI used on the ECML to identify potential infrastructure issues

LNER, Network Rail, Hitachi Rail and CrossTech are trialling the use of Artificial Intelligence (AI) technology to identify potential infrastructure issues along the East Coast Main Line. 

Monitoring areas in real-time further enhances safety, helping detect potential hazards like overhanging or invasive tree species, leaves on the track, or embankment subsidence that could cause harm or delays. Network Rail previously estimated that vegetation-related incidents cost up to GBP 3 million annually in the Southern region alone.

AI technology from CrossTech

The new forward-facing CCTV camera (FFCCTV) has been installed inside the driver’s cabin of a LNER Azuma train for the 12-month trial, which started in May. The operational Azuma train now has a key role in digitising infrastructure monitoring and maintenance on the East Coast Main Line. This solution uses the very latest in Artificial Intelligence (AI) camera sensor technology.

Automating the detection of potential hazards, combined with pinpointing where maintenance is necessary, enables a proactive approach to infrastructure maintenance. Equally, the trial will provide insights and guidance to optimise when and where maintenance is needed on the East Coast Main Line.

Hitachi Rail is helping to convene the pilot project, using its digital supplier CrossTech. The UK SME is one of Network Rail’s AI technology success stories, using computer vision technology to live monitor tracks and the surrounding environment, via data that comes directly from the forward-facing video camera.

The FFCCTV monitoring solution was developed by combining CrossTech technology, with Hitachi Rail’s digital expertise to assist with integration, operations and customer interface. This is an excellent example of a global rail business incubating and supporting British SME innovation.

FFCCTV is the latest development in a wider suite of Hitachi digital asset monitoring solutions which can live-monitor tracks, overhead lines and the train itself. These digital solutions, working either independently or in combination, allow for automated and more accurate monitoring to help modernise the railways.

“Vegetation is the only living asset on the railway network and as such understanding the potential risk to trains is ever changing. Using forward facing footage allows us to ‘see’ from the driver’s perspective. We can use this technology to understand where vegetation is encroaching on the operational railway and at risk of making contact with either trains or fixed infrastructure such as overhead electrified wires. We can also identify where vegetation growth has compromised the driver’s view such as on the approach to signals or level crossings. This initiative will allow us to make passengers’ journeys more reliable and help minimise the risk of disruption on the network”, Johanna Priestley, Route Engineer at Network Rail, said.

The FFCCTV digital monitoring solution will be able to detect:

  • Leaves on track
  • Overhanging trees
  • Invasive and hazardous tree species
  • Low ballast signal and level crossing and signal sightings
  • Embankment and track condition, including subsidence

Share on:
Facebooktwitterlinkedinmail

 

RECOMMENDED EVENT: