Wind Energy Science
Wind Energy Science
WES
Articles | Volume 11, issue 10
Articles | Volume 11, issue 10
https://doi.org/10.5194/wes-11-3983-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-11-3983-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 11, issue 10
Research article
 | 
23 Oct 2026
Research article |  | 23 Oct 2026

A real-time IoT, LLM, AI-supported wind turbine failure prediction system

İlhan Gamze Saygı, Sara Mahyanbakhshayesh, Berdan Ak, Mehmet Hilal Özcanhan, and Mehmet Süleyman Ünlütürk

Viewed

Total article views: 1,553 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
994 400 159 1,553 183 148
  • HTML: 994
  • PDF: 400
  • XML: 159
  • Total: 1,553
  • BibTeX: 183
  • EndNote: 148
Views and downloads (calculated since 18 Jun 2026)
Cumulative views and downloads (calculated since 18 Jun 2026)

Viewed (geographical distribution)

Total article views: 1,553 (including HTML, PDF, and XML) Thereof 1,505 with geography defined and 48 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 11 Nov 2026
Download
Short summary
Wind turbines break down due to harsh weather, causing costly energy losses. We built a sensor model to track conditions like sound and temperature and trained artificial intelligence to detect warning signs of failure. Our system predicted breakdowns with high accuracy. We also added a smart assistant to provide operators with clear repair advice. This technology prevents unexpected failures, cuts costs, and makes renewable wind energy more reliable.
Read more
Share
Altmetrics
Final-revised paper
Preprint