Preprints
https://doi.org/10.5194/wes-2025-123
https://doi.org/10.5194/wes-2025-123
06 Aug 2025
 | 06 Aug 2025
Status: this preprint is currently under review for the journal WES.

Fault Detection in Wind Turbines Using Health Index Monitoring with Variational Autoencoders

Shun Wang, Yolanda Vidal, and Francesc Pozo

Abstract. As wind energy capacity expands globally, ensuring the operational reliability and economic viability of wind turbines has become a critical industrial challenge. Effective fault detection systems are essential for minimizing high maintenance costs and preventing catastrophic failures. To address this need, this paper presents a semi-supervised framework designed to identify anomalies in wind turbines using only healthy operational data. The methodology begins by extracting a comprehensive set of features from the time and frequency domains of raw vibration signals to capture a rich representation of the dynamics of wind turbines. A variational autoencoder, a deep generative model, is then trained exclusively on these features from healthy operational periods to learn a robust model of normal behavior and generate reconstruction errors as health indicators with exponentially weighted moving average smoothing to enhance robustness and reduce false alarms. The framework is evaluated using public data from the Aventa AV-7 ETH Zurich Research Wind Turbine, which includes multiple failure events. Experimental results demonstrate effective and early detection of pitch faults, as well as accurate detection of icing events and aerodynamic imbalances. The proposed approach therefore offers a robust and practical solution to improving operational safety and enabling proactive maintenance of wind turbines.

Competing interests: Yolanda Vidal is a member of the editorial board of Wind Energy Science.

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.
Share
Shun Wang, Yolanda Vidal, and Francesc Pozo

Status: open (until 03 Sep 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Shun Wang, Yolanda Vidal, and Francesc Pozo
Shun Wang, Yolanda Vidal, and Francesc Pozo

Viewed

Total article views: 23 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
20 2 1 23 0 0
  • HTML: 20
  • PDF: 2
  • XML: 1
  • Total: 23
  • BibTeX: 0
  • EndNote: 0
Views and downloads (calculated since 06 Aug 2025)
Cumulative views and downloads (calculated since 06 Aug 2025)

Viewed (geographical distribution)

Total article views: 23 (including HTML, PDF, and XML) Thereof 23 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 07 Aug 2025
Download
Short summary
This research aims to improve wind turbine maintenance by detecting faults early using only data from normal operation. The method analyzes vibration signals in both time and frequency domains and uses a variational autoencoder, a type of deep learning model, to learn normal behavior. It then detects anomalies by measuring how much new data deviates from this learned model. Tests on real turbine data show early and accurate detection of faults such as pitch issues and icing.
Share
Altmetrics