Drone in study.
Credit: Image courtesy of Luleå University of Technology
Wind turbines are getting bigger and bigger. The larger the wind turbines are, the more kilowatts they can produce. But larger wind turbines also imply increased difficulties in inspecting them. Usually cranes and people are used to inspect both the rotor blade and the overall structure. Maintenance and inspection are thus costly, time consuming and risky for those who carry out the inspection. The solution to this can be to let autonomous drones do the work.
“An autonomous aerial robot is programmed to analyze its surroundings and perform different tasks either towards inspection or interaction with the environment. It can work relatively independently and “make” autonomous decisions without any human interference, e.g. pilots.”
Last week’s field trials took place in norh Sweden. In the middle of the woods, an outdoor lab was set up. In focus was one of Skellefteå kraft’s wind turbines and of course, the autonomous drones. The drone’s task was to inspect the wind turbine and reconstruct a 3D model of it in order to detect faults and cracks. To perform this task outside is extremely more challenging compared to doing it indoors in a lab. Outside there are no reference points for the drone and the tricky part is to make the drone understand where it is.
“We managed to fly autonomous with great autonomy and precision in localization and this was an extremely successful and big step for us. The outcome makes our research group unique in Europe,” says George Nikolakopoulos.
The advances in computational power that can allow more complicated control algorithms to run on board the drones and hence perceive and process the surrounding environment much faster, is one reason to why this research leap is happening right now. But also, the improvement of the localization accuracy based on data fusion has played a major part.
“The main reason why we succeed is the use of the localization system that our group has developed based on fusion of Ultra Wide Band nodes and other onboard sensors. We can get an accuracy of a few centimeters and this is quite an outstanding result in the robotics area, especially while flying. Based on the results we got from this experiment, I’d say in two or three years it will be possible to use this technique for aerial inspection of wind turbines.”