Autonomous drone inspections of offshore oil and gas infrastructure have moved a step closer after a successful test that used artificial intelligence to analyse live video.
In the test, video shot by a drone was interpreted in real-time by an algorithm to detect cracks in a 19.4 metre high oil tank on board a Floating Production, Storage and Offloading vessel.
Norway-based quality assurance and risk management company DNV GL has been working with Scout Drone Inspection to develop an autonomous drone system that can overcome the common challenges of tank inspections.
The cost of these inspections can run into hundreds of thousands of dollars as the tank is taken out of service for days to ventilate and construct scaffolding, DNV GL explained. The tanks are also tough work environments, with surveyors often having to climb or raft into hard to reach corners. Using a drone in combination with an algorithm to gather and analyse video footage can significantly reduce survey times and staging costs, while also improving surveyor safety.
GPS reception is not available in the enclosed space, so the drone uses LiDAR to navigate inside the tank. It creates a 3D map of the tank and all images and video are accurately geo-tagged with position data.
During the test, the drone was controlled by a pilot but as the technology matures it will be able to navigate more and more autonomously. In the future the camera and algorithm will also be able to detect anomalies below the surface, such as corrosion and structural deformations.
“This is another important step towards autonomous drone inspections,” said Nicolai Husteli, CEO of Scout Drone Inspection. “Up until now the process has been completely analogue but technology can address the urgent need to make the process more efficient and safer.”
Advanced technologies enabled by the next wave of internet connectivity will transform sectors ranging from energy and utilities to financial services. To read more, download your free copy of Osborne Clarke’s Next-generation connectivity report.
Tags: AI, Artificial Intelligence, drones
