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!
PO018: Validation of a digital twin to predict fatigue life from SCADA data
Edoardo Cicirello, Wind Domain Expert at GreenPowerMonitor, a DNV company, DNV
Abstract
Life assessment of wind turbines is becoming increasingly important as the global operating fleet is ageing and approaching its useful design life . An accurate estimate of the consumed life of the main structural components is a powerful tool to guide operators' decisions and to inform operating strategies. We present a method to assess fatigue life from commonly available operational signals. The tool that powers the calculation, called LoadsPredict+, relies on 10-minute SCADA data to predict fatigue loads and to calculate fatigue life. The algorithm is based on a combination of data analysis, physical modelling, and machine learning (ML). Here, we report the results of a validation of LoadsPredict+ on a 3MW onshore turbine, against loads measurements at the tower base. The model was able to predict the consumed fatigue life with a 2.3% error. LoadsPredict+ was built on the experience of LoadsPredict and WindGEMINI. The former is a ML model that can predict loads directly from strain gauge measurements. The latter is a digital twin that combines traditional aeroelastic modelling and wind measurements from the site. The main step forward of LoadsPredict+ over these solutions is that it eliminates the need for expensive measurement campaigns, as they are replaced with physical modelling. Additionally, it requires no wind measurements acquired by the nacelle anemometer, which is known for its unreliability. To conclude, the solution proposed can unlock the potential of SCADA data to inform wind turbine life assessment. The promising results obtained offer comfort for the reliable use of wind turbine digital twins for commercial applications.
Follow the event on: