Articles | Volume 11, issue 3
https://doi.org/10.5194/wes-11-1057-2026
https://doi.org/10.5194/wes-11-1057-2026
Research article
 | 
01 Apr 2026
Research article |  | 01 Apr 2026

Failure classification of wind turbine operational conditions using hybrid machine learning

Marcela Rodrigues Machado, Amanda Aryda Silva Rodrigues de Sousa, Jefferson da Silva Coelho, and Rafael de Oliveira Teloli

Data sets

Aventa AV-7 ETH Zurich Research Wind Turbine SCADA and High-Frequency Structural Health Monitoring (SHM) Data Eleni Chatzi et al. https://doi.org/10.5281/zenodo.8229750

Model code and software

iMOSS-Lab/rp-wedowind-challenge-ASCE-EMI: v1 Marcela Machado https://doi.org/10.5281/zenodo.18940555

Download
Short summary
We have developed a method using artificial intelligence to detect and classify faults in wind turbines before major damage occurs. By analyzing data from multiple sensors, we can identify issues even under changing weather conditions, such as temperature and wind. This improves reliability, reduces downtime, and lowers maintenance costs, supporting cleaner and more affordable energy through stable production.
Share
Altmetrics
Final-revised paper
Preprint