An insight into wind turbine planet bearing fault prediction using SCADA data

Research output: Contribution to journalConference Contribution

Abstract

Condition based maintenance is being adopted into the decision making process of wind farms, in order to reduce operation costs. SCADA systems are integrated in wind turbines, providing low frequency operational data and are increasingly being used in condition monitoring. The aim of this paper is to explore how can wind turbine gearbox components be monitored using SCADA data. The proposed methodology utilises 10-minute averaged data. Data preprocessing is applied using a clustering filter in order to improve prediction confidence. Normal behaviour models are used to predict potential faults. The efficacy of the proposed methodology is demonstrated with a case study using SCADA data from three operating wind turbines that have a double planetary stage gearbox. Historic data is collected for more than a year before the occurrence of a bearing failure on a planet of the first planetary stage. The case study results indicate the potential importance of generator speed estimation for planet bearing faults. A successful prediction of the bearing health state can be performed through this model and some insight is given into into the optimal SCADA sensors utilization for this type of failure mode.
LanguageEnglish
JournalProceedings of the European Conference of the PHM Society
Volume4
Issue number1
Publication statusPublished - 30 Jun 2018
EventFourth European Conference of the PHM Society - Utrecht, Netherlands
Duration: 3 Jul 20186 Jul 2018

Fingerprint

Bearings (structural)
Planets
Wind turbines
Turbine components
SCADA systems
Condition monitoring
Farms
Failure modes
Decision making
Health
Sensors
Costs

Keywords

  • wind turbines
  • SCADA data
  • fault prediction
  • gearbox

Cite this

@article{e9ae347dac3646a59f2ea5e3903cfe4f,
title = "An insight into wind turbine planet bearing fault prediction using SCADA data",
abstract = "Condition based maintenance is being adopted into the decision making process of wind farms, in order to reduce operation costs. SCADA systems are integrated in wind turbines, providing low frequency operational data and are increasingly being used in condition monitoring. The aim of this paper is to explore how can wind turbine gearbox components be monitored using SCADA data. The proposed methodology utilises 10-minute averaged data. Data preprocessing is applied using a clustering filter in order to improve prediction confidence. Normal behaviour models are used to predict potential faults. The efficacy of the proposed methodology is demonstrated with a case study using SCADA data from three operating wind turbines that have a double planetary stage gearbox. Historic data is collected for more than a year before the occurrence of a bearing failure on a planet of the first planetary stage. The case study results indicate the potential importance of generator speed estimation for planet bearing faults. A successful prediction of the bearing health state can be performed through this model and some insight is given into into the optimal SCADA sensors utilization for this type of failure mode.",
keywords = "wind turbines, SCADA data, fault prediction, gearbox",
author = "Sofia Koukoura and James Carroll and Alasdair McDonald",
year = "2018",
month = "6",
day = "30",
language = "English",
volume = "4",
number = "1",

}

An insight into wind turbine planet bearing fault prediction using SCADA data. / Koukoura, Sofia; Carroll, James; McDonald, Alasdair.

Vol. 4, No. 1, 30.06.2018.

Research output: Contribution to journalConference Contribution

TY - JOUR

T1 - An insight into wind turbine planet bearing fault prediction using SCADA data

AU - Koukoura, Sofia

AU - Carroll, James

AU - McDonald, Alasdair

PY - 2018/6/30

Y1 - 2018/6/30

N2 - Condition based maintenance is being adopted into the decision making process of wind farms, in order to reduce operation costs. SCADA systems are integrated in wind turbines, providing low frequency operational data and are increasingly being used in condition monitoring. The aim of this paper is to explore how can wind turbine gearbox components be monitored using SCADA data. The proposed methodology utilises 10-minute averaged data. Data preprocessing is applied using a clustering filter in order to improve prediction confidence. Normal behaviour models are used to predict potential faults. The efficacy of the proposed methodology is demonstrated with a case study using SCADA data from three operating wind turbines that have a double planetary stage gearbox. Historic data is collected for more than a year before the occurrence of a bearing failure on a planet of the first planetary stage. The case study results indicate the potential importance of generator speed estimation for planet bearing faults. A successful prediction of the bearing health state can be performed through this model and some insight is given into into the optimal SCADA sensors utilization for this type of failure mode.

AB - Condition based maintenance is being adopted into the decision making process of wind farms, in order to reduce operation costs. SCADA systems are integrated in wind turbines, providing low frequency operational data and are increasingly being used in condition monitoring. The aim of this paper is to explore how can wind turbine gearbox components be monitored using SCADA data. The proposed methodology utilises 10-minute averaged data. Data preprocessing is applied using a clustering filter in order to improve prediction confidence. Normal behaviour models are used to predict potential faults. The efficacy of the proposed methodology is demonstrated with a case study using SCADA data from three operating wind turbines that have a double planetary stage gearbox. Historic data is collected for more than a year before the occurrence of a bearing failure on a planet of the first planetary stage. The case study results indicate the potential importance of generator speed estimation for planet bearing faults. A successful prediction of the bearing health state can be performed through this model and some insight is given into into the optimal SCADA sensors utilization for this type of failure mode.

KW - wind turbines

KW - SCADA data

KW - fault prediction

KW - gearbox

UR - https://www.phmsociety.org/events/conference/phm/europe/18

M3 - Conference Contribution

VL - 4

IS - 1

ER -