Norway-based professional services company DNV yesterday announced a research project aimed at the development of an automated data processing procedure for verification of detected wind turbine blade defects.
It is partnering with the University of Bristol and Percepetual Robotics on the research, which will be conducted over 12 months from April 2021 and is supported by a grant from Innovate UK.
Asset inspections in the harsh environments of offshore wind farms are often done with autonomous and remote-controlled vehicles and drones, but the processing of the data collected is currently semi-automated with the need for trained experts to visually inspect images, the company explains.
The project will explore the automated verification, validation and processing of inspection data, gathered by drones, to the end of improving inspection quality and performance. It will also seek to create greater acceptance across the industry of automated data processing methods.
"With many inspections still being carried out manually, visual inspection of offshore wind turbines is expensive, labour intensive, and hazardous," commented Elizabeth Traiger, DNV senior researcher in digital assurance.
"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," Pierre Sames, DNV group research and development director, said and added that the project will develop means to address this through machine learning algorithms and process automation.
Choose your newsletter by Renewables Now. Join for free!