11/06/2023
By Danielle Fretwell

The Francis College of Engineering, Department of Electrical and Computer Engineering, invites you to attend a Master's Thesis defense by Sage Lyon on: Design and Deployment of Acoustic-based Sensors and Cloud Services for Wind Turbine Health Monitoring.

Candidate Name: Sage Lyon
Degree: Master’s
Defense Date: Friday, Nov. 17, 2023
Time: 12:30 - 2 p.m.
Location: Ball Hall 302


Committee

  • Advisor: Yan Luo, Professor, Electrical & Computer Engineering, University of Massachusetts Lowell
  • Orlando Arias, Assistant Professor, Electrical & Computer Engineering, UMass Lowell
  • Murat Inalpolat, Associate Professor, Mechanical and Industrial Engineering, UMass Lowell
  • Christopher Niezrecki, Professor, Mechanical and Industrial Engineering, UMass Lowell

Brief Abstract:
As the demand for sustainable energy grows, wind energy production has gained prevalence as a sustainable alternative to fossil fuels. Wind turbines are expensive to construct and to maintain. Wind turbine blades contribute significantly to the overall cost of the turbine and over time can become damaged as a result of environmental factors or aging. To improve the reliability and cost of operating these wind turbines, it is crucial to detect and address any structural damage to a turbine blade as early as possible. Acoustic based structural monitoring has drawn attention in recent years as an effective method in detecting and monitoring blade damage.

This thesis research focuses on the design and improvement of a system of acoustic embedded sensors and the control software and cloud-based services that enable acoustic sample data collection, storage, transfer, and analysis. Two types of sensor platforms are designed and compared, both of which can acquire acoustic samples, temperature, three-dimensional acceleration, and wireless signal strength from the installation spot (e.g. inside a wind turbine blade). A controller node running multiple software services is developed to facilitate data aggregation from the sensors and data transfer to a cloud-based time-series database. A web-based dashboard is designed to visualize the health metrics of the sensors. The research work also enhances the reliability of the health monitoring system through a watchdog mechanism. The sensor system has been deployed to a few wind farms in the U.S. The data obtained from these long-term deployments have provided insights on the performance of the sensors and can be utilized for further studies in structural health monitoring.