Putting the ‘train’ in training

Sebastian Moss

June 2, 2020

3 Min Read

Putting the ‘train’ in training

The Research Council of Norway has awarded Bane Nor and the Norwegian Computing Centre an NKr 4bn ($US 399.5m) contract to trial using artificial intelligence (AI) to undertake infrastructure inspections.

The state-owned company responsible for the Norwegian national railway infrastructure and the private non-profit research center will together develop the Image Analysis Railway Infrastructure (IARI) project.

The Computing Centre plans to develop the machine learning and artificial intelligence technology, based off of images and videos taken and annotated by Bane Nor staff.

Switching it up

The IARI system hopes to monitor key railway infrastructure components, including track, switches, and overhead contact lines. This should reduce the need to delay services for inspections, and increase the rate of inspections.

Norway's railways stretch over 3,000 kilometers (1,860 miles), across diverse landscapes from cities, to snowy mountains, to beside giant fjords.

“The solution will make it possible to inspect and analyze the railway infrastructure in a fast, secure, and objective manner without stopping traffic,” Jørgen Torgersen, project leader at Bane Nor, said.

“Pictures and video from measuring trains, passenger trains, work machines and drones in addition to fixed-mounted cameras, which Bane Nor has already installed, are examples of areas where automated image analysis can be useful.”

The $400m IARI project plans to initially focus on using existing general deep learning-based algorithms for rail uses and train them with the data.

“The use of modern technology such as AI and machine learning in traditional businesses such as railways is important to meet the future transport needs,” Sverre Kjenne, executive vice-president of digitalization and technology at Bane Nor, said.

“The railway is being developed and digitized to provide a better service for most people. We are grateful for the support from the Norwegian Research Council and proud that they are investing in this project.”

Further details about the costly project were not revealed. The Research Council's 2016 annual report (translated) reveals that private company SINTEF "has had a long-standing collaboration with the Bane NOR on analysis and visualization of traffic and punctuality data, in the form of a 3-year project on the development of an ICT tool for fact-based prioritization of maintenance, which will increase train punctuality, regularity and uptime."

Details on that project are also limited. A SINTEF 'Digital Open Day' presentation from 2019 makes mention of using drones to scan Bane Nor infrastructure for hazards.

The company is also collaborating with French company Certifier to help Bane NOR upgrade signalling equipment that, in some cases, dates back to the 1950s. 

Bane Nor plans to complete the digitalization of the Norwegian railway network by 2034.

Keep up with the ever-evolving AI landscape
Unlock exclusive AI content by subscribing to our newsletter!!

You May Also Like