Posters
Come meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics and provide an opportunity for delegates to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please, join us at the conference and take advantage of this opportunity to learn and engage with your peers in the academic community. We look forward to seeing you there!
PO249: Development of deep learning model for damage equivalent load estimation of wind turbine blades
Sungmok Hwang, Senior Researcher, Korea Institute of Energy Research
Abstract
The blade of a wind power generator is a key component that converts kinetic energy in the wind into mechanical rotational energy. Blades are designed to withstand loads acting on various operating and environmental conditions throughout their design life. In order to evaluate the structural safety or remaining useful life (RUL) of the blade, it is necessary to monitor the actual load applied to the blade during operation. Although the load applied to the blade can be measured directly using a load measurement system installed at the relevant location, such as the blade root, it is practically difficult to continuously operate and maintain the load measurement system throughout the design life of the blade. The SCADA system can monitor and emergency control wind turbine in real time by measuring and collecting operational data and environmental information of key components. However, even the SCADA system does not provide direct information about the load applied to the blade. This study proposes a deep learning model that predicts the 1Hz damage equivalent load (DEL) applied to each blade using the data provided by the SCADA system. As a result of verification using the measured data, it was confirmed that the proposed model showed more than 90% prediction accuracy. The DEL of blade can be calculated from the SCADA data alone using the proposed model, even if the blade load measurement system is not operated during the design life. Thus, the accumulated fatigue load of the blade can be easily obtained, and the RUL also can be predicted through comparison with the design fatigue load.
Follow the event on: