Danish holding firm Sund & Bælt, construction company BAM Infra Nederland and software integrator OrangeNXT are all using innovative technologies such as artificial intelligence (AI), drones and Microsoft Azure to ensure the safety of roads and bridges.
Europe has some of the safest roads in the world. However, according to a recent Microsoft article, 25,300 people lost their lives in 2017 as a result of human error, weather conditions or damaged surfaces. While the former causes cannot be controlled, damaged road surfaces can be.
The Great Belt Bridge is a suspension bridge which connects the Danish islands of Zealand and Funen. Sund & Bælt is responsible for the structure’s maintenance and has worked with Microsoft to create a solution to predict where cracks and faults will occur which uses drones and AI.
The drones fly around and take hundreds of pictures of the concrete structure, a safer and faster alternative to a human carrying out the task in a harness. Instead, workers use their expertise to train a machine learning algorithm to detect cracks in the surface of the concrete, once the photos have been uploaded to Microsoft Azure. The AI solution then creates a list of concerning areas and workers then select the ones in need of maintenance and repair.
“Concrete does not simply degrade overnight – it is a slow process,” says Mikkel Hemmingsen, CEO of Sund & Bælt. “Therefore, being able to detect and predict potential points of damage in advance is extremely useful.”
BAM Infra Nederland and OrangeNXT have also developed an Azure-based system to train algorithms to detect and classify various types of damage on paved surfaces. Previously BAM sent out drivers to take photos of the road surface which were then inspected to identify damaged areas and fix them.
“This process was time-consuming, costly and tedious,” says Kitting Lee, director of Commerce and Innovation at BAM Infra Nederland. “We needed a smarter solution.”
The new solution uses vehicles with 360-degree cameras record video footage from every angle. This is then uploaded to Azure, where algorithms flag up areas in need of work. The process improves the speed, quality and efficiency of visual road checks, enabling predictive asphalt maintenance and reducing costs.
“Most roads were being checked just once per year,” said Lee. “We knew that if we could check more frequently, we could prevent small defects from becoming big holes, which would improve public safety, enable predictive maintenance and reduce emergency repairs that shut down roads and cause traffic jams.”
Share this story