Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region
A novel concept of wind farm fault detection by monitoring the wind speed in the wake region is proposed in this study. A wind energy dissipation model was coupled with a computational fluid dynamics solver to simulate the fluid field of a wind turbine array, and the wind velocity and direction in t...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/24/6559 |
id |
doaj-4e9523a401e14b88b04d3c98a51f9a74 |
---|---|
record_format |
Article |
spelling |
doaj-4e9523a401e14b88b04d3c98a51f9a742020-12-12T00:06:25ZengMDPI AGEnergies1996-10732020-12-01136559655910.3390/en13246559Wind Farm Fault Detection by Monitoring Wind Speed in the Wake RegionMinh-Quang Tran0Yi-Chen Li1Chen-Yang Lan2Meng-Kun Liu3Department of Mechanical Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanGreen Energy and Environment Research Laboratories, Industrial Technology Research Institute, Hsinchu 310, TaiwanDepartment of Mechanical Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Mechanical Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanA novel concept of wind farm fault detection by monitoring the wind speed in the wake region is proposed in this study. A wind energy dissipation model was coupled with a computational fluid dynamics solver to simulate the fluid field of a wind turbine array, and the wind velocity and direction in the simulation were exported for identifying wind turbine faults. The 3D steady Navier–Stokes equations were solved by using the cell center finite volume method with a second order upwind scheme and a<i> </i><em>k−ε</em><i> </i>turbulence model. In addition, the wind energy dissipation model, derived from energy balance and Betz’s law, was added to the Navier–Stokes equations’ source term. The simulation results indicate that the wind speed distribution in the wake region contains significant information regarding multiple wind turbine faults. A feature selection algorithm specifically designed for the analysis of wind flow was proposed to reduce the number of features. This algorithm proved to have better performance than fuzzy entropy measures and recursive feature elimination methods under a limited number of features. As a result, faults in the wind turbine array could be detected and identified by machine learning algorithms.https://www.mdpi.com/1996-1073/13/24/6559wind turbine fault detectionfeature selectionwind energy dissipation modeland machine learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Minh-Quang Tran Yi-Chen Li Chen-Yang Lan Meng-Kun Liu |
spellingShingle |
Minh-Quang Tran Yi-Chen Li Chen-Yang Lan Meng-Kun Liu Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region Energies wind turbine fault detection feature selection wind energy dissipation model and machine learning |
author_facet |
Minh-Quang Tran Yi-Chen Li Chen-Yang Lan Meng-Kun Liu |
author_sort |
Minh-Quang Tran |
title |
Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region |
title_short |
Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region |
title_full |
Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region |
title_fullStr |
Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region |
title_full_unstemmed |
Wind Farm Fault Detection by Monitoring Wind Speed in the Wake Region |
title_sort |
wind farm fault detection by monitoring wind speed in the wake region |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2020-12-01 |
description |
A novel concept of wind farm fault detection by monitoring the wind speed in the wake region is proposed in this study. A wind energy dissipation model was coupled with a computational fluid dynamics solver to simulate the fluid field of a wind turbine array, and the wind velocity and direction in the simulation were exported for identifying wind turbine faults. The 3D steady Navier–Stokes equations were solved by using the cell center finite volume method with a second order upwind scheme and a<i> </i><em>k−ε</em><i> </i>turbulence model. In addition, the wind energy dissipation model, derived from energy balance and Betz’s law, was added to the Navier–Stokes equations’ source term. The simulation results indicate that the wind speed distribution in the wake region contains significant information regarding multiple wind turbine faults. A feature selection algorithm specifically designed for the analysis of wind flow was proposed to reduce the number of features. This algorithm proved to have better performance than fuzzy entropy measures and recursive feature elimination methods under a limited number of features. As a result, faults in the wind turbine array could be detected and identified by machine learning algorithms. |
topic |
wind turbine fault detection feature selection wind energy dissipation model and machine learning |
url |
https://www.mdpi.com/1996-1073/13/24/6559 |
work_keys_str_mv |
AT minhquangtran windfarmfaultdetectionbymonitoringwindspeedinthewakeregion AT yichenli windfarmfaultdetectionbymonitoringwindspeedinthewakeregion AT chenyanglan windfarmfaultdetectionbymonitoringwindspeedinthewakeregion AT mengkunliu windfarmfaultdetectionbymonitoringwindspeedinthewakeregion |
_version_ |
1724385885096509440 |