New designs of large wind turbine blades have become increasingly flexible and thus need cost-efficient monitoring solutions. Hence, we investigate if aerodynamic pressure measurements from a low-cost sensing system can be used to detect structural damage. Our research is based on a wind tunnel study, emulating a simplified wind turbine blade under various conditions. We show that, when using a convolutional-neural-network-based method, structural damage can indeed be detected and its severity can be rated.

Movable surfaces on wind turbine (WT) blades, called active flaps, can reduce the cost of wind energy. However, they still need extensive testing. This study shows that the computer model used to design a WT with flaps aligns well with measurements obtained from a 3month test on a commercial WT featuring a prototype flap. Particularly during flap actuation, there were minimal differences between simulated and measured data. These findings assure the reliability of WT designs incorporating flaps.

This paper delves into the crucial task of transforming raw data into actionable knowledge which can be used by advanced artificial intelligence systems – a challenge that spans various domains, industries, and scientific fields amid their digital transformation journey. This article underscores the significance of cross-industry collaboration and learning, drawing insights from sectors leading in digitalisation, and provides strategic guidance for further development in this area.

Aerodynamic and acoustic field measurements on operating large-scale wind turbines are key for the further reduction in the costs of wind energy. In this work, a novel cost-effective MEMS (micro-electromechanical systems)-based aerodynamic and acoustic wireless measurement system that is thin, non-intrusive, easy to install, low power and self-sustaining is designed and tested.