A 12-month research project launched by Norwegian accreditation society DNV aims to develop automated inspection solutions for offshore wind turbines.
The Innovate UK supported project, which also includes the University of Bristol and Perceptual Robotics, will trial the use of UAVs to detect blade defects.
Focusing on automated verification, validation and processing of inspection data, collected by the UAVs, the project aims to improve inspection quality and performance.
According to the team, the UAVs, developed by Perceptual Robotics based at the Bristol Robotics Laboratory, can collect rich and extensive data sets. This includes high-definition video, images, geo-positioning and sensor data, which can provide integrity information about the installed structures without personnel having to access these dangerous locations.
Elizabeth Traiger, a DNV senior researcher in digital assurance, said: “With many inspections still being carried out manually, visual inspection of offshore wind turbines, is expensive, labour intensive, and hazardous. Automatic visual inspections can address these issues.
“This collaboration will develop and demonstrate an automated processing pipeline alongside a general framework with the aim of generating broader acceptance across the industry and informing future regulation. This project should provide a stepping-stone to the growth of the automated inspection industry.”
As part of the project, the Visual Information Lab at the University of Bristol will create algorithms for automated localisation of inspection images and defects using SLAM and 3-D tracking technology.
While DNV will work to verify data collected, validate the methodology and performance of the AI algorithms. The company will also provide guidance as to existing DNV and IEC recommend practices, regulations and industry networks.
Pierre C. Sames, group research and development director at DNV, added: “With the number of installed wind turbines worldwide increasing, including those in remote and harsh environments, the volume of inspection data collected is quickly outpacing the capacity of skilled inspectors who can competently review it.
“This research project will develop means to tackle this challenge through machine learning algorithms and process automation.”
