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!
PO015: Developing Real Time Detection of Ice Formation in Wind Turbine Blades Using Acoustic Data.
Obdulia Ley, Subject Matter Expert - AE, Mistras Group
Abstract
This work focuses on the analysis and characterization of Acoustic Emission (AE) signatures collected from wind turbine blades during icing events and describes the initial stages of development of an ice detection filter/alarm to be implemented onboard SENSORIATM blade monitor[1-3]. Ice formation and melting are known to be linked to production of an acoustically detectable signal[4, 6], and the variation in the blade background noise during operation produced by a change in the aerodynamic properties of the blade due to the presence of a layer of ice on the blade surface[7-10]. This work presents acoustic data collected from turbines in the Mid-West of the United States that experienced severe ice formation during the winter storms experienced - February 2022 (Site #1) and compares with data collected from 25 turbines on a wind farm located in North America (Site #2) during periods of time with icy weather forecast. The turbines instrumented corresponded to GE 1.6. The turbines in Site #1 were stopped during the severe weather conditions experienced during the winter of 2022. Allowing identification of the acoustic characteristics of ice formation on the blade, with limited effect of aerodynamic noise produced by an operating rotor. The turbines in Site #2, presented continuous rotor operation during periods of time with ice forecast. The data collected from Site #2 was used to identify the dynamic changes in the acoustic signature during cold fronts in the farm with the turbines in operation. The data set collected from Site #2 (November 2022 to January 2023) was used to feed different Machine Learning (ML) models to identify the most sensitive acoustic features that can predict/identify ice formation in real time.
