Comparison of anomaly detection techniques for wind turbine gearbox SCADA data

C. Mckinnon, J. Carroll, A. McDonald, S. Koukoura, C. Soraghan

Research output: Contribution to conference › Abstract

Abstract

This analysis looks at the use of anomaly detection to assess the condition of wind turbine gearboxes based on data from a number of operational turbines. A comparison is made between various methods of anomaly detection, these being one class support vector machine (OCSVM), random forests, and nonlinear autoregressive neural networks with exogenous inputs (NARX).
LanguageEnglish
Number of pages1
Publication statusPublished - 17 Jun 2019
EventWind Energy Science Conference 2019 - University College Cork, Cork, Ireland
Duration: 17 Jun 2019 → 20 Jun 2019
Conference number: 2019
https://www.wesc2019.org/

Conference

ConferenceWind Energy Science Conference 2019
Abbreviated titleWESC
CountryIreland
CityCork
Period17/06/19 → 20/06/19
Internet address

Fingerprint

Wind turbines
Support vector machines
Turbines
Neural networks

Keywords

  • anomaly detection
  • operations and maintenance (O&M)
  • wind turbines
  • one class support vector machine
  • neural networks with exogenous inputs
  • wind energy

Cite this

Mckinnon, C., Carroll, J., McDonald, A., Koukoura, S., & Soraghan, C. (2019). Comparison of anomaly detection techniques for wind turbine gearbox SCADA data. Abstract from Wind Energy Science Conference 2019, Cork, Ireland.
Mckinnon, C. ; Carroll, J. ; McDonald, A. ; Koukoura, S. ; Soraghan, C. / Comparison of anomaly detection techniques for wind turbine gearbox SCADA data. Abstract from Wind Energy Science Conference 2019, Cork, Ireland.1 p.
@conference{ebd609ec1cd04a8c8343cc78f911f823,
title = "Comparison of anomaly detection techniques for wind turbine gearbox SCADA data",
abstract = "This analysis looks at the use of anomaly detection to assess the condition of wind turbine gearboxes based on data from a number of operational turbines. A comparison is made between various methods of anomaly detection, these being one class support vector machine (OCSVM), random forests, and nonlinear autoregressive neural networks with exogenous inputs (NARX).",
keywords = "anomaly detection, operations and maintenance (O&M), wind turbines, one class support vector machine, neural networks with exogenous inputs, wind energy",
author = "C. Mckinnon and J. Carroll and A. McDonald and S. Koukoura and C. Soraghan",
year = "2019",
month = "6",
day = "17",
language = "English",
note = "Wind Energy Science Conference 2019, WESC ; Conference date: 17-06-2019 Through 20-06-2019",
url = "https://www.wesc2019.org/",

}

Mckinnon, C, Carroll, J, McDonald, A, Koukoura, S & Soraghan, C 2019, 'Comparison of anomaly detection techniques for wind turbine gearbox SCADA data' Wind Energy Science Conference 2019, Cork, Ireland, 17/06/19 - 20/06/19, .

Comparison of anomaly detection techniques for wind turbine gearbox SCADA data. / Mckinnon, C.; Carroll, J.; McDonald, A.; Koukoura, S.; Soraghan, C.

2019. Abstract from Wind Energy Science Conference 2019, Cork, Ireland.

Research output: Contribution to conference › Abstract

TY - CONF

T1 - Comparison of anomaly detection techniques for wind turbine gearbox SCADA data

AU - Mckinnon, C.

AU - Carroll, J.

AU - McDonald, A.

AU - Koukoura, S.

AU - Soraghan, C.

PY - 2019/6/17

Y1 - 2019/6/17

N2 - This analysis looks at the use of anomaly detection to assess the condition of wind turbine gearboxes based on data from a number of operational turbines. A comparison is made between various methods of anomaly detection, these being one class support vector machine (OCSVM), random forests, and nonlinear autoregressive neural networks with exogenous inputs (NARX).

AB - This analysis looks at the use of anomaly detection to assess the condition of wind turbine gearboxes based on data from a number of operational turbines. A comparison is made between various methods of anomaly detection, these being one class support vector machine (OCSVM), random forests, and nonlinear autoregressive neural networks with exogenous inputs (NARX).

KW - anomaly detection

KW - operations and maintenance (O&M)

KW - wind turbines

KW - one class support vector machine

KW - neural networks with exogenous inputs

KW - wind energy

M3 - Abstract

ER -

Mckinnon C, Carroll J, McDonald A, Koukoura S, Soraghan C. Comparison of anomaly detection techniques for wind turbine gearbox SCADA data. 2019. Abstract from Wind Energy Science Conference 2019, Cork, Ireland.

Access to Document