Combination of thermal modelling and machine learning approaches for fault detection in wind turbine gearboxes

Becky Corley, Sofia Koukoura, James Carroll, Alasdair McDonald

Research output: Contribution to journalArticlepeer-review

26 Downloads (Pure)

Abstract

This research aims to bring together thermal modelling and machine learning approaches to improve the understanding of the operation and fault detection of a wind turbine gearbox. Recent fault detection research has been focused on machine learning, black box approaches. Although it can be successful, it provides no indication of the physical behaviour. In this paper, thermal network modelling is applied to two datasets using SCADA temperature data, with the aim of detecting a fault one month before failure. A machine learning approach is used on the same data to compare results to the thermal modelling. The results found that thermal network modelling could successfully detect a fault in many of the turbines examined and was validated by the machine learning approach for one of the datasets. For that same dataset, it was found that combining the thermal model losses and the machine learning approach by using the modelled losses as a feature in the classifier resulted in the engineered feature becoming the most important feature in the classifier. It was also found that the results from the thermal modelling had a significantly greater effect on successfully classifying the health of a turbine compared to temperature data. The other dataset gave less conclusive results, suggesting that the location of the fault and the temperature sensors could impact the fault detection ability.
Original languageEnglish
Article number1375
Number of pages14
JournalEnergies
Volume14
Issue number5
DOIs
Publication statusPublished - 3 Mar 2021

Keywords

  • thermal modelling
  • machine learning
  • condition monitoring
  • wind turbine gearbox
  • fault detection
  • wind energy

Fingerprint Dive into the research topics of 'Combination of thermal modelling and machine learning approaches for fault detection in wind turbine gearboxes'. Together they form a unique fingerprint.

Cite this