A research team from the University of Klagenfurt is collaborating with industry partner AIR6 SYSTEMS on the FFG-funded DORBINE project to create a novel technology that employs artificial intelligence to manage swarms of drones that monitor wind turbines while in operation.
Image Credit: Yousuk Yang/Shutterstock.com
Traditionally, to check wind turbines for damage, they must be turned off. This indicates that these wind turbines are not producing any energy during the shutdown time. Moreover, wind turbine inspections are typically expensive.
To do their job, the drone swarms must be precisely positioned about the turbine. So, even under complex operating conditions, we must always know what the distance and angle are between the drone and the respective component of the turbine. This allows the drones to collect comprehensive data.
Farzad Tashtarian, Study Co-Leader, University of Klagenfurt
Farzad Tashtarian (Department of Information Technology), co-leads the project with Jan Steinbrener (Department of Smart Systems Technologies, Control of Networked Systems) at the University of Klagenfurt.
The drone swarms must be able to identify any flaws that may emerge in a turbine. To achieve this, scientists are trying to put AI-assisted picture analysis into practice that can identify even the smallest flaws. Drones with high-resolution cameras and sensors like LiDAR, radar, and ultrasonic sensors are used to gather the data.
With DORBINE, the research team is working toward the following objectives: Wind turbines should no longer need to be turned off for inspections. Sturdy, AI-powered navigation systems must allow the drone swarms to be precisely positioned and guarantee effective data gathering. Advanced AI and machine learning systems should optimize maintenance procedures and inspection schedules by precisely identifying cracks, erosion, and structural deformations in the captured photos.
To date, wind turbines have been inspected using helicopters and work boats – which generates significant CO2 emissions. By using drone swarms, we can achieve significant reductions in emissions.
Farzad Tashtarian, Study Co-Leader, University of Klagenfurt
AIR6 SYSTEMS is DORBINE's project partner. The Austrian Research Promotion Agency (FFG) is providing funding for the study.