Preprints
https://doi.org/10.5194/wes-2024-100
https://doi.org/10.5194/wes-2024-100
02 Sep 2024
 | 02 Sep 2024
Status: a revised version of this preprint is currently under review for the journal WES.

A machine learning-based approach for active monitoring of blades pitch misalignment in wind turbines

Sabrina Milani, Jessica Leoni, Stefano Cacciola, Alessandro Croce, and Mara Tanelli

Abstract. In recent years, timely anomaly detection in wind turbine operations, especially offshore, has become critical. Yet, promptly identifying faults and damages remains a significant challenge, leading to costly maintenance and consuming resources. Rotor blade pitch misalignment is a critical issue, causing downtime and reduced energy production. Traditional inspection methods are resource-intensive, time-consuming, and also struggle to identify the specific misaligned blades. In addition, their accuracy degrades in case of small misalignments and strongly depends on the wind regimes, as they are less reliable in turbulence. The absence of an effective automatic solution persists, requiring costly on-site verification.

To tackle this challenge, this paper introduces a novel machine-learning-based approach for automatic pitch misalignment detection and localization. This approach not only localizes the affected blades but also detects small misalignments as low as 0.1 degrees. The methodology relies on features extracted from a limited set of sensors already integrated into modern wind turbine systems. Specifically, the extracted indicators are designed to effectively integrate frequency and time-domain information on turbine operating conditions, enabling high detection performance even in turbulent wind regimes.

The approach is validated across an extended operational envelope using data gathered from a state-of-the-art simulation model commonly used for designing and certifying commercial wind turbine systems.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Sabrina Milani, Jessica Leoni, Stefano Cacciola, Alessandro Croce, and Mara Tanelli

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wes-2024-100', Anonymous Referee #1, 07 Oct 2024
    • AC1: 'Reply on RC1', Sabrina Milani, 25 Oct 2024
  • RC2: 'Comment on wes-2024-100', Anonymous Referee #2, 15 Oct 2024
    • AC2: 'Reply on RC2', Sabrina Milani, 25 Oct 2024
  • RC3: 'Comment on wes-2024-100', Anonymous Referee #3, 18 Oct 2024
    • AC3: 'Reply on RC3', Sabrina Milani, 25 Oct 2024
Sabrina Milani, Jessica Leoni, Stefano Cacciola, Alessandro Croce, and Mara Tanelli
Sabrina Milani, Jessica Leoni, Stefano Cacciola, Alessandro Croce, and Mara Tanelli

Viewed

Total article views: 385 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
273 85 27 385 8 7
  • HTML: 273
  • PDF: 85
  • XML: 27
  • Total: 385
  • BibTeX: 8
  • EndNote: 7
Views and downloads (calculated since 02 Sep 2024)
Cumulative views and downloads (calculated since 02 Sep 2024)

Viewed (geographical distribution)

Total article views: 384 (including HTML, PDF, and XML) Thereof 384 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 23 Nov 2024
Download
Short summary
In this paper, we propose a novel machine-learning framework pitch misalignment detection in wind turbines. By using a minimal set of standard sensors, our method detects misalignments as small as 0.1deg and localizes the affected blades. It combines signal processing with a hierarchical classification structure and linear regression for precise severity quantification. Evaluation results validate the approach, showing notable accuracy in misalignment classification, regression, and localization
Altmetrics