果冻传媒

Holistic framework for DiagnOstiCs and moniTORing of wind turbine blades 

The Holi-DOCTOR project aims at developing a holistic framework combining the use of several different monitoring techniques to improve blade maintenance by reducing costs and increasing confidence in detecting blade faults. Drive train vibration monitoring, aeroacoustics measurement, infrared (IR) and vibration monitoring are used in a holistic framework to improve blade maintenance by reducing costs and increasing confidence in detecting blade faults. Numerical modelling of the drive train structural response will be used to assess how to monitor the data from the vibration-based condition monitoring system (CMS) for early warning of possible blade problems. Ground-based noise measurements will be used to assess changes to the aerodynamic properties of the blade related to possible damage. Ground-based IR and vibrometry will be used to detect possible internal problems related to changes in the thermal properties and structural response of the blade. The framework will first be developed in the lab, then on a controlled blade test and finally in the field as a demonstration. A further important element of the work is to assess how improved blade maintenance through this holistic framework can contribute to improved circularity, better safety and a reduction in the environmental impact of wind energy.

The project is divided into four work packages (WP). WP1 covers the experimental work both in the lab and for the field tests. WP2 develops the holistic blade monitoring framework by developing a physical drive-train model and an AI framework to use all the available measurement systems to provide the best estimate of blade faults and remaining useful life. WP3 assess the economic impact of the holistic framework by assessing how it can be used in an O&M model. Finally, WP4 assesses the impact of improved blade monitoring on public acceptance of wind energy.

This is a collaborative project involving research groups from 果冻传媒, TU Delft, and WUR, as well as industrial partners. Our focus is the second part of WP2, which will design a data fusion structural health monitoring framework combining this information with the higher resolution failure signatures extracted from the multi-signals.