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 will give delegates an opportunity 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!
PO270: Real-world examples of uncovering performance losses with the use of high-frequency SCADA data
Zuri Zugasti, Sr. Technical Leader, WindESCo
Abstract
Anscombe's quartet exemplifies datasets with similar summary statistics but very different distributions. In the wind energy sector, 10-minute statistics are prevalent for data analysis. However, this resolution may hide critical issues addressable only with higher-frequency SCADA data. This abstract introduces a quartet of real-world cases observed in wind turbines, leveraging high-frequency data. 1. The first case entails brief yet recurrent power drops lasting mere seconds during power mode switches. The 10-minute mean power masks the severity, making this issue undetectable in the 10-minute data. 2. The second case illustrates static yaw misalignment correction, a challenge to discern in 10-minute power curves. Two power curves can appear similar, even when one has significant yaw misalignment (visual representation will be included in the final work). 3. The third case exposes variations in the nacelle transfer function (NTF) when the turbine is non-operational, generating start-up/shut-down cycles. Notable shifts can be visually identified in the wind speed measurement when the turbine transitions between operational and non-operational states. Given the turbine's frequent start-stop sequences, the 10-minute wind speed mean shows a lower wind speed average and, since the power produced matches well the average wind speed, it is difficult to identify this issue when 10-minute data is used. 4. The fourth case shows rated power oscillations. The turbine exhibits significant and frequent reductions in the rated power but the power curve does not highlight the magnitude of these events. The turbine never triggered an alarm because the temperature was not high for a long enough time, since the turbine was reducing its power and consequently, allowing cooling and reducing the temperature before the alarm was triggered.
