Predicting Faults in Wind Turbines Using SCADA Data

Anders Bech Borchersen, Jesper Abildgaard Larsen, Jakob Stoustrup

Research output: Contribution to book/anthology/report/conference proceedingConference abstract in proceedingResearchpeer-review

2 Citations (Scopus)

Abstract

The cost of operation and maintenance of wind turbines is a significant part of the overall cost of wind turbines. To reduce this cost a method for enabling early fault detection is proposed and tested in this paper. The method is taking advantage of the fact that wind turbines in wind farms are located near similar wind turbines. This is done by generating a model for each turbine, the model is then used to evaluate the performance of that turbine and the nearby turbines. The evaluations from the models are then combined and used as votes to identify the faulty turbines. The method is applied and tested on historical Supervisory Control And Data Acquisition (SCADA) data from nine operational turbines over a testing period of nine months. The performance of the fault detection is found to be acceptable based on the testing period. During the testing period several gear related services were performed, some of these were predicted by the proposed fault detection systems. The advantage of the purposed method is that it applicable for operational turbines without requiring any extra measurements, since the used SCADA data is available from most modern wind turbines.
Original languageEnglish
Title of host publication51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition
PublisherAmerican Institute of Aeronautics and Astronautics
Publication date7 Jan 2013
ISBN (Print)978-1-62410-181-6
DOIs
Publication statusPublished - 7 Jan 2013
Event31st ASME Wind Energy Symposium - Grapevine, TX, United States
Duration: 7 Jan 201310 Jan 2013

Conference

Conference31st ASME Wind Energy Symposium
CountryUnited States
CityGrapevine, TX
Period07/01/201310/01/2013

Fingerprint

Wind turbines
Data acquisition
Turbines
Fault detection
Testing
Costs
Farms
Gears

Cite this

Borchersen, A. B., Larsen, J. A., & Stoustrup, J. (2013). Predicting Faults in Wind Turbines Using SCADA Data. In 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition American Institute of Aeronautics and Astronautics. https://doi.org/10.2514/6.2013-313
Borchersen, Anders Bech ; Larsen, Jesper Abildgaard ; Stoustrup, Jakob. / Predicting Faults in Wind Turbines Using SCADA Data. 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition. American Institute of Aeronautics and Astronautics, 2013.
@inbook{6de3c6279b5a4078a1a43731535346b4,
title = "Predicting Faults in Wind Turbines Using SCADA Data",
abstract = "The cost of operation and maintenance of wind turbines is a significant part of the overall cost of wind turbines. To reduce this cost a method for enabling early fault detection is proposed and tested in this paper. The method is taking advantage of the fact that wind turbines in wind farms are located near similar wind turbines. This is done by generating a model for each turbine, the model is then used to evaluate the performance of that turbine and the nearby turbines. The evaluations from the models are then combined and used as votes to identify the faulty turbines. The method is applied and tested on historical Supervisory Control And Data Acquisition (SCADA) data from nine operational turbines over a testing period of nine months. The performance of the fault detection is found to be acceptable based on the testing period. During the testing period several gear related services were performed, some of these were predicted by the proposed fault detection systems. The advantage of the purposed method is that it applicable for operational turbines without requiring any extra measurements, since the used SCADA data is available from most modern wind turbines.",
author = "Borchersen, {Anders Bech} and Larsen, {Jesper Abildgaard} and Jakob Stoustrup",
year = "2013",
month = "1",
day = "7",
doi = "10.2514/6.2013-313",
language = "English",
isbn = "978-1-62410-181-6",
booktitle = "51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition",
publisher = "American Institute of Aeronautics and Astronautics",
address = "United States",

}

Borchersen, AB, Larsen, JA & Stoustrup, J 2013, Predicting Faults in Wind Turbines Using SCADA Data. in 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition. American Institute of Aeronautics and Astronautics, 31st ASME Wind Energy Symposium, Grapevine, TX, United States, 07/01/2013. https://doi.org/10.2514/6.2013-313

Predicting Faults in Wind Turbines Using SCADA Data. / Borchersen, Anders Bech; Larsen, Jesper Abildgaard; Stoustrup, Jakob.

51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition. American Institute of Aeronautics and Astronautics, 2013.

Research output: Contribution to book/anthology/report/conference proceedingConference abstract in proceedingResearchpeer-review

TY - ABST

T1 - Predicting Faults in Wind Turbines Using SCADA Data

AU - Borchersen, Anders Bech

AU - Larsen, Jesper Abildgaard

AU - Stoustrup, Jakob

PY - 2013/1/7

Y1 - 2013/1/7

N2 - The cost of operation and maintenance of wind turbines is a significant part of the overall cost of wind turbines. To reduce this cost a method for enabling early fault detection is proposed and tested in this paper. The method is taking advantage of the fact that wind turbines in wind farms are located near similar wind turbines. This is done by generating a model for each turbine, the model is then used to evaluate the performance of that turbine and the nearby turbines. The evaluations from the models are then combined and used as votes to identify the faulty turbines. The method is applied and tested on historical Supervisory Control And Data Acquisition (SCADA) data from nine operational turbines over a testing period of nine months. The performance of the fault detection is found to be acceptable based on the testing period. During the testing period several gear related services were performed, some of these were predicted by the proposed fault detection systems. The advantage of the purposed method is that it applicable for operational turbines without requiring any extra measurements, since the used SCADA data is available from most modern wind turbines.

AB - The cost of operation and maintenance of wind turbines is a significant part of the overall cost of wind turbines. To reduce this cost a method for enabling early fault detection is proposed and tested in this paper. The method is taking advantage of the fact that wind turbines in wind farms are located near similar wind turbines. This is done by generating a model for each turbine, the model is then used to evaluate the performance of that turbine and the nearby turbines. The evaluations from the models are then combined and used as votes to identify the faulty turbines. The method is applied and tested on historical Supervisory Control And Data Acquisition (SCADA) data from nine operational turbines over a testing period of nine months. The performance of the fault detection is found to be acceptable based on the testing period. During the testing period several gear related services were performed, some of these were predicted by the proposed fault detection systems. The advantage of the purposed method is that it applicable for operational turbines without requiring any extra measurements, since the used SCADA data is available from most modern wind turbines.

U2 - 10.2514/6.2013-313

DO - 10.2514/6.2013-313

M3 - Conference abstract in proceeding

SN - 978-1-62410-181-6

BT - 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition

PB - American Institute of Aeronautics and Astronautics

ER -

Borchersen AB, Larsen JA, Stoustrup J. Predicting Faults in Wind Turbines Using SCADA Data. In 51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition. American Institute of Aeronautics and Astronautics. 2013 https://doi.org/10.2514/6.2013-313