Wind turbine intelligent gear fault identification

Research output: Contribution to conferencePaper

Abstract

This paper aims to present the development of a framework for monitoring of wind turbine gearboxes and prognosis of gear fracture faults, using vibration data and machine learning techniques. The proposed methodology analyses gear vibration signals in the order domain, using a shaft tachometer pulse. Indicators that represent the health state of the gear are algorithmically extracted. Those indicators are used as features to train diagnostic models that predict the health status of the gear. The efficacy of the proposed methodology is demonstrated with a case study using real wind turbine vibration data. Data is collected for a wind turbine at various time steps prior to failure and according to the maintenance reports there is enough data to form a healthy baseline. The data is classified according to the time before failure that the signal was collected.The learning algorithms used are discussed and their results are compared. The case study results indicate that this data driven model can lay the groundwork for a robust framework for the early detection of emerging gear tooth fracture faults. This can lead to minimisation of wind turbine downtime and revenue increase.

Conference

ConferenceAnnual Conference of the PHM Society
CountryUnited States
CitySt. Petersburg
Period2/10/175/10/17
Internet address

Fingerprint

Wind turbines
Gears
Tachometers
Health
Gear teeth
Learning algorithms
Learning systems
Monitoring

Keywords

  • wind turbine
  • gearbox
  • gear fracture faults
  • diagnostic

Cite this

Koukoura, S., Carroll, J., & McDonald, A. (2017). Wind turbine intelligent gear fault identification. Paper presented at Annual Conference of the PHM Society, St. Petersburg, United States.
Koukoura, Sofia ; Carroll, James ; McDonald, Alasdair. / Wind turbine intelligent gear fault identification. Paper presented at Annual Conference of the PHM Society, St. Petersburg, United States.7 p.
@conference{e570769fea4f4b3285b8292227a93f3d,
title = "Wind turbine intelligent gear fault identification",
abstract = "This paper aims to present the development of a framework for monitoring of wind turbine gearboxes and prognosis of gear fracture faults, using vibration data and machine learning techniques. The proposed methodology analyses gear vibration signals in the order domain, using a shaft tachometer pulse. Indicators that represent the health state of the gear are algorithmically extracted. Those indicators are used as features to train diagnostic models that predict the health status of the gear. The efficacy of the proposed methodology is demonstrated with a case study using real wind turbine vibration data. Data is collected for a wind turbine at various time steps prior to failure and according to the maintenance reports there is enough data to form a healthy baseline. The data is classified according to the time before failure that the signal was collected.The learning algorithms used are discussed and their results are compared. The case study results indicate that this data driven model can lay the groundwork for a robust framework for the early detection of emerging gear tooth fracture faults. This can lead to minimisation of wind turbine downtime and revenue increase.",
keywords = "wind turbine, gearbox, gear fracture faults, diagnostic",
author = "Sofia Koukoura and James Carroll and Alasdair McDonald",
year = "2017",
month = "10",
day = "2",
language = "English",
note = "Annual Conference of the PHM Society ; Conference date: 02-10-2017 Through 05-10-2017",
url = "https://www.phmsociety.org/events/conference/phm/17",

}

Koukoura, S, Carroll, J & McDonald, A 2017, 'Wind turbine intelligent gear fault identification' Paper presented at Annual Conference of the PHM Society, St. Petersburg, United States, 2/10/17 - 5/10/17, .

Wind turbine intelligent gear fault identification. / Koukoura, Sofia; Carroll, James; McDonald, Alasdair.

2017. Paper presented at Annual Conference of the PHM Society, St. Petersburg, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Wind turbine intelligent gear fault identification

AU - Koukoura, Sofia

AU - Carroll, James

AU - McDonald, Alasdair

PY - 2017/10/2

Y1 - 2017/10/2

N2 - This paper aims to present the development of a framework for monitoring of wind turbine gearboxes and prognosis of gear fracture faults, using vibration data and machine learning techniques. The proposed methodology analyses gear vibration signals in the order domain, using a shaft tachometer pulse. Indicators that represent the health state of the gear are algorithmically extracted. Those indicators are used as features to train diagnostic models that predict the health status of the gear. The efficacy of the proposed methodology is demonstrated with a case study using real wind turbine vibration data. Data is collected for a wind turbine at various time steps prior to failure and according to the maintenance reports there is enough data to form a healthy baseline. The data is classified according to the time before failure that the signal was collected.The learning algorithms used are discussed and their results are compared. The case study results indicate that this data driven model can lay the groundwork for a robust framework for the early detection of emerging gear tooth fracture faults. This can lead to minimisation of wind turbine downtime and revenue increase.

AB - This paper aims to present the development of a framework for monitoring of wind turbine gearboxes and prognosis of gear fracture faults, using vibration data and machine learning techniques. The proposed methodology analyses gear vibration signals in the order domain, using a shaft tachometer pulse. Indicators that represent the health state of the gear are algorithmically extracted. Those indicators are used as features to train diagnostic models that predict the health status of the gear. The efficacy of the proposed methodology is demonstrated with a case study using real wind turbine vibration data. Data is collected for a wind turbine at various time steps prior to failure and according to the maintenance reports there is enough data to form a healthy baseline. The data is classified according to the time before failure that the signal was collected.The learning algorithms used are discussed and their results are compared. The case study results indicate that this data driven model can lay the groundwork for a robust framework for the early detection of emerging gear tooth fracture faults. This can lead to minimisation of wind turbine downtime and revenue increase.

KW - wind turbine

KW - gearbox

KW - gear fracture faults

KW - diagnostic

M3 - Paper

ER -

Koukoura S, Carroll J, McDonald A. Wind turbine intelligent gear fault identification. 2017. Paper presented at Annual Conference of the PHM Society, St. Petersburg, United States.