Early Detection and Diagnosis of Wind Turbine Abnormal Conditions Using an Interpretable Supervised Variational Autoencoder Model

The operation and maintenance of wind turbines benefit from reliable information on the wind turbine condition. Data-driven models use data from the supervisory data acquisition system. In particular, great performance is reported for artificial intelligence models. However, the lack of interpretabi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Energies (Basel) Ročník 16; číslo 12; s. 4544
Hlavní autoři: Oliveira-Filho, Adaiton, Zemouri, Ryad, Cambron, Philippe, Tahan, Antoine
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.06.2023
Témata:
Air-turbines
Analysis
Bearings
Case studies
condition monitoring
diagnosis
early detection
False alarms
Photovoltaic cells
Preventive maintenance
SCADA data
Turbines
variational autoencoder
Visualization
wind turbine
Canada
ISSN:1996-1073, 1996-1073
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The operation and maintenance of wind turbines benefit from reliable information on the wind turbine condition. Data-driven models use data from the supervisory data acquisition system. In particular, great performance is reported for artificial intelligence models. However, the lack of interpretability limits their effective industrial implementation. The present work introduces a new condition-monitoring approach for wind turbines featuring a built-in visualization tool that confers interpretability upon the model outcomes. The proposed approach is based on a supervised implementation of the variational autoencoder model, which allows the projection of the wind turbine system onto a low-dimensional representation space. Three outcomes follow from such representation: a health indicator for the early detection of abnormal conditions, a classifier providing the diagnosis status, and a visualization tool depicting the wind turbine condition as a trajectory in a 2D plot. The approach is implemented with a vast database. Two case studies demonstrate the potential of the proposed approach. The proposed health indicator detects the main bearing overtemperature 11 days before the control system alarm, one week earlier than a competing approach. Study cases illustrate that the built-in visualization tool enhances the interpretability and trust in the model outcomes, thus supporting wind turbine operation and maintenance.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1996-1073
1996-1073
DOI:10.3390/en16124544