A Parameter Selection Method for Wind Turbine Health Management through SCADA Data
Wind turbine anomaly or failure detection using machine learning techniques through supervisory control and data acquisition (SCADA) system is drawing wide attention from academic and industry While parameter selection is important for modelling a wind turbine’s condition, only a few papers have bee...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-02-01
|
Series: | Energies |
Subjects: | |
Online Access: | http://www.mdpi.com/1996-1073/10/2/253 |
id |
doaj-42b0f43fb824473a8905394e57b1421a |
---|---|
record_format |
Article |
spelling |
doaj-42b0f43fb824473a8905394e57b1421a2020-11-24T22:29:41ZengMDPI AGEnergies1996-10732017-02-0110225310.3390/en10020253en10020253A Parameter Selection Method for Wind Turbine Health Management through SCADA DataMian Du0Jun Yi1Peyman Mazidi2Lin Cheng3Jianbo Guo4Department of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaChina Electric Power Research Institute, Beijing 100192, ChinaDepartment of Electric Power and Energy Systems (EPE), KTH Royal Institute of Technology, Stockholm 10044, SwedenDepartment of Electrical Engineering, Tsinghua University, Beijing 100084, ChinaChina Electric Power Research Institute, Beijing 100192, ChinaWind turbine anomaly or failure detection using machine learning techniques through supervisory control and data acquisition (SCADA) system is drawing wide attention from academic and industry While parameter selection is important for modelling a wind turbine’s condition, only a few papers have been published focusing on this issue and in those papers interconnections among sub-components in a wind turbine are used to address this problem. However, merely the interconnections for decision making sometimes is too general to provide a parameter list considering the differences of each SCADA dataset. In this paper, a method is proposed to provide more detailed suggestions on parameter selection based on mutual information. First, the copula is proven to be capable of simplifying the estimation of mutual information. Then an empirical copulabased mutual information estimation method (ECMI) is introduced for application. After that, a real SCADA dataset is adopted to test the method, and the results show the effectiveness of the ECMI in providing parameter selection suggestions when physical knowledge is not accurate enough.http://www.mdpi.com/1996-1073/10/2/253wind turbinefailure detectionSCADA datafeature extractionmutual informationcopula |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mian Du Jun Yi Peyman Mazidi Lin Cheng Jianbo Guo |
spellingShingle |
Mian Du Jun Yi Peyman Mazidi Lin Cheng Jianbo Guo A Parameter Selection Method for Wind Turbine Health Management through SCADA Data Energies wind turbine failure detection SCADA data feature extraction mutual information copula |
author_facet |
Mian Du Jun Yi Peyman Mazidi Lin Cheng Jianbo Guo |
author_sort |
Mian Du |
title |
A Parameter Selection Method for Wind Turbine Health Management through SCADA Data |
title_short |
A Parameter Selection Method for Wind Turbine Health Management through SCADA Data |
title_full |
A Parameter Selection Method for Wind Turbine Health Management through SCADA Data |
title_fullStr |
A Parameter Selection Method for Wind Turbine Health Management through SCADA Data |
title_full_unstemmed |
A Parameter Selection Method for Wind Turbine Health Management through SCADA Data |
title_sort |
parameter selection method for wind turbine health management through scada data |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2017-02-01 |
description |
Wind turbine anomaly or failure detection using machine learning techniques through supervisory control and data acquisition (SCADA) system is drawing wide attention from academic and industry While parameter selection is important for modelling a wind turbine’s condition, only a few papers have been published focusing on this issue and in those papers interconnections among sub-components in a wind turbine are used to address this problem. However, merely the interconnections for decision making sometimes is too general to provide a parameter list considering the differences of each SCADA dataset. In this paper, a method is proposed to provide more detailed suggestions on parameter selection based on mutual information. First, the copula is proven to be capable of simplifying the estimation of mutual information. Then an empirical copulabased mutual information estimation method (ECMI) is introduced for application. After that, a real SCADA dataset is adopted to test the method, and the results show the effectiveness of the ECMI in providing parameter selection suggestions when physical knowledge is not accurate enough. |
topic |
wind turbine failure detection SCADA data feature extraction mutual information copula |
url |
http://www.mdpi.com/1996-1073/10/2/253 |
work_keys_str_mv |
AT miandu aparameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT junyi aparameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT peymanmazidi aparameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT lincheng aparameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT jianboguo aparameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT miandu parameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT junyi parameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT peymanmazidi parameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT lincheng parameterselectionmethodforwindturbinehealthmanagementthroughscadadata AT jianboguo parameterselectionmethodforwindturbinehealthmanagementthroughscadadata |
_version_ |
1725743545618268160 |