Technology AI to monitor cracks on the Zermatt-Brig railroad line

The train line between Zermatt and Brig in the canton of Valais will in future be monitored using artificial intelligence (AI). A Lausanne research team is testing an AI-supported method for monitoring cracks on this route.

This will make inspections of the train line more efficient, the Swiss Federal Institute of Technology in Lausanne (EPFL) wrote in a press release on Wednesday.

Until now, railroad lines have mostly been inspected manually by experts who assess the condition of infrastructure such as retaining walls or concrete sleepers based on defined criteria. However, according to the university, this method carries the risk of subjective assessments, as different inspectors may assess the damage differently at different times.

Trained with crack images

To solve this problem, the EPFL research team has trained an AI algorithm to differentiate between images with cracks and those without cracks.

This trained algorithm can now be fed with images taken over several years of a railroad section and quantify the severity of cracks in the walls and sleepers over time. In a study published in the journal "Automation in Construction", the researchers showed that this method of monitoring cracks works.

In the next tests, the AI will be tested on the railroad lines between Zermatt and Brig and between Brig and Disentis. These sections of track contain a number of retaining walls with different shapes and materials, which makes the task very challenging for the algorithm, according to the EPFL.