Using high-frequency SCADA data for wind turbine performance monitoring: a sensitivity study

Elena Gonzales, Bruce Stephen, David Infield, Julio J. Melero

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Intensive condition monitoring of wind generation plant through analysis of routinely collected SCADA data is seen as a viable means of forestalling costly plant failure and optimising maintenance through identification of failure at the earliest possible stage. The challenge to operators is in identifying the signatures of failure within data streams and disambiguating these from other operational factors. The well understood power curve representation of turbine performance offers an intuitive and quantitative means of identifying abnormal operation, but only if noise and artefacts of operating regime change can be excluded. In this paper, a methodology for wind turbine performance monitoring based on the use of high-frequency SCADA data is employed featuring state-of-the-art multivariate non-parametric methods for power curve modelling. The model selection considerations for these are examined together with their sensitivity to several factors, including site specific conditions, seasonality effects, input relevance and data sampling rate. The results, based on operational data from four wind farms, are discussed in a practical context with the use of high frequency data demonstrated to be beneficial for performance monitoring purposes whereas further attention is required in the area of expressing model uncertainty.

LanguageEnglish
Pages841-853
Number of pages13
JournalRenewable Energy
Volume131
Early online date19 Jul 2018
DOIs
Publication statusPublished - 28 Feb 2019

Fingerprint

Wind turbines
Monitoring
Condition monitoring
Farms
Turbines
Sampling
Uncertainty

Keywords

  • wind turbine
  • power curve
  • high-frequency data
  • performance monitoring
  • SCADA data

Cite this

@article{df634a0a0ef64e088a4ddf048239f0fd,
title = "Using high-frequency SCADA data for wind turbine performance monitoring: a sensitivity study",
abstract = "Intensive condition monitoring of wind generation plant through analysis of routinely collected SCADA data is seen as a viable means of forestalling costly plant failure and optimising maintenance through identification of failure at the earliest possible stage. The challenge to operators is in identifying the signatures of failure within data streams and disambiguating these from other operational factors. The well understood power curve representation of turbine performance offers an intuitive and quantitative means of identifying abnormal operation, but only if noise and artefacts of operating regime change can be excluded. In this paper, a methodology for wind turbine performance monitoring based on the use of high-frequency SCADA data is employed featuring state-of-the-art multivariate non-parametric methods for power curve modelling. The model selection considerations for these are examined together with their sensitivity to several factors, including site specific conditions, seasonality effects, input relevance and data sampling rate. The results, based on operational data from four wind farms, are discussed in a practical context with the use of high frequency data demonstrated to be beneficial for performance monitoring purposes whereas further attention is required in the area of expressing model uncertainty.",
keywords = "wind turbine, power curve, high-frequency data, performance monitoring, SCADA data",
author = "Elena Gonzales and Bruce Stephen and David Infield and Melero, {Julio J.}",
year = "2019",
month = "2",
day = "28",
doi = "10.1016/j.renene.2018.07.068",
language = "English",
volume = "131",
pages = "841--853",
journal = "Renewable Energy",
issn = "0960-1481",

}

Using high-frequency SCADA data for wind turbine performance monitoring : a sensitivity study. / Gonzales, Elena; Stephen, Bruce; Infield, David; Melero, Julio J.

In: Renewable Energy, Vol. 131, 28.02.2019, p. 841-853.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using high-frequency SCADA data for wind turbine performance monitoring

T2 - Renewable Energy

AU - Gonzales, Elena

AU - Stephen, Bruce

AU - Infield, David

AU - Melero, Julio J.

PY - 2019/2/28

Y1 - 2019/2/28

N2 - Intensive condition monitoring of wind generation plant through analysis of routinely collected SCADA data is seen as a viable means of forestalling costly plant failure and optimising maintenance through identification of failure at the earliest possible stage. The challenge to operators is in identifying the signatures of failure within data streams and disambiguating these from other operational factors. The well understood power curve representation of turbine performance offers an intuitive and quantitative means of identifying abnormal operation, but only if noise and artefacts of operating regime change can be excluded. In this paper, a methodology for wind turbine performance monitoring based on the use of high-frequency SCADA data is employed featuring state-of-the-art multivariate non-parametric methods for power curve modelling. The model selection considerations for these are examined together with their sensitivity to several factors, including site specific conditions, seasonality effects, input relevance and data sampling rate. The results, based on operational data from four wind farms, are discussed in a practical context with the use of high frequency data demonstrated to be beneficial for performance monitoring purposes whereas further attention is required in the area of expressing model uncertainty.

AB - Intensive condition monitoring of wind generation plant through analysis of routinely collected SCADA data is seen as a viable means of forestalling costly plant failure and optimising maintenance through identification of failure at the earliest possible stage. The challenge to operators is in identifying the signatures of failure within data streams and disambiguating these from other operational factors. The well understood power curve representation of turbine performance offers an intuitive and quantitative means of identifying abnormal operation, but only if noise and artefacts of operating regime change can be excluded. In this paper, a methodology for wind turbine performance monitoring based on the use of high-frequency SCADA data is employed featuring state-of-the-art multivariate non-parametric methods for power curve modelling. The model selection considerations for these are examined together with their sensitivity to several factors, including site specific conditions, seasonality effects, input relevance and data sampling rate. The results, based on operational data from four wind farms, are discussed in a practical context with the use of high frequency data demonstrated to be beneficial for performance monitoring purposes whereas further attention is required in the area of expressing model uncertainty.

KW - wind turbine

KW - power curve

KW - high-frequency data

KW - performance monitoring

KW - SCADA data

UR - https://journals.elsevier.com/renewable-energy

U2 - 10.1016/j.renene.2018.07.068

DO - 10.1016/j.renene.2018.07.068

M3 - Article

VL - 131

SP - 841

EP - 853

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

ER -