Eulerian motion magnification applied to structural health monitoring of wind turbines

Abstract

Several types of defects may occur in wind turbines, as physical damage of blades or gearbox malfunction. A wind farm monitoring and damage prediction system is built to observe abnormal vibrations of elements of wind turbine: blades, nacelle, and tower. Contactless methods are developed which do not require turbine stopping. In this work, structural health monitoring of a wind turbine is evaluated using a conversion from the captured and processed video to the acoustic signal, employing the method of Eulerian motion magnification in video. It was assumed that this task can be achieved using a stabilized high-speed video camera only, directed at the wind turbine without any additional sensors mounted on windmill blades or on its body. Moreover, the developed vector sound intensity probe was used for spatial measurements in order to recover the vibration modes of wind turbines. Finally, statistical methods were applied to the processing of computed features reflecting vibrations in order to determine wind turbine technical condition. The developed method was evaluated empirically in real wind farm. [Research was subsidized by the Polish National Centre for Research and Development within the grant “STEO—System for Technical and Economic Optimization of Distributed Renewable Energy Sources,” No. POIR.01.02.00-00-0357/16.]