On the use of high-frequency SCADA data for improved wind turbine performance monitoring

E Gonzales, B Stephen, D Infield, J Melero

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

SCADA-based condition monitoring of wind turbines facilitates the move from costly corrective repairs towards more proactive maintenance strategies. In this work, we advocate the use of high-frequency SCADA data and quantile regression to build a cost eective performance monitoring tool. The benets of the approach are demonstrated through the comparison between state-of-the-art deterministic power curve modelling techniques and the suggested probabilistic model. Detection capabilities are compared for low and high-frequency SCADA data, providing evidence for monitoring at higher resolutions. Operational data from healthy and faulty turbines are used to provide a practical example of usage with the proposed tool, eectively achieving the detection of an incipient gearbox malfunction at a time horizon of more than one month prior to the actual occurrence of the failure.

Fingerprint

wind turbines
Wind turbines
quantiles
transmissions (machine elements)
malfunctions
Monitoring
Condition monitoring
turbines
maintenance
horizon
regression analysis
Turbines
Repair
occurrences
low frequencies
costs
high resolution
curves
Costs
Statistical Models

Keywords

  • Operation & Maintenance
  • Wind Turbine
  • Power Curve
  • Performance Monitoring
  • SCADA
  • High-frequency data
  • Fault Detection

Cite this

@article{0a25da7b590b4878921820167239d244,
title = "On the use of high-frequency SCADA data for improved wind turbine performance monitoring",
abstract = "SCADA-based condition monitoring of wind turbines facilitates the move from costly corrective repairs towards more proactive maintenance strategies. In this work, we advocate the use of high-frequency SCADA data and quantile regression to build a cost eective performance monitoring tool. The benets of the approach are demonstrated through the comparison between state-of-the-art deterministic power curve modelling techniques and the suggested probabilistic model. Detection capabilities are compared for low and high-frequency SCADA data, providing evidence for monitoring at higher resolutions. Operational data from healthy and faulty turbines are used to provide a practical example of usage with the proposed tool, eectively achieving the detection of an incipient gearbox malfunction at a time horizon of more than one month prior to the actual occurrence of the failure.",
keywords = "Operation & Maintenance, Wind Turbine, Power Curve, Performance Monitoring, SCADA, High-frequency data, Fault Detection",
author = "E Gonzales and B Stephen and D Infield and J Melero",
year = "2017",
month = "11",
day = "23",
doi = "10.1088/1742-6596/926/1/012009",
language = "English",
volume = "926",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",

}

On the use of high-frequency SCADA data for improved wind turbine performance monitoring. / Gonzales, E; Stephen, B; Infield, D; Melero, J.

In: Journal of Physics: Conference Series, Vol. 926, 012009, 23.11.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On the use of high-frequency SCADA data for improved wind turbine performance monitoring

AU - Gonzales, E

AU - Stephen, B

AU - Infield, D

AU - Melero, J

PY - 2017/11/23

Y1 - 2017/11/23

N2 - SCADA-based condition monitoring of wind turbines facilitates the move from costly corrective repairs towards more proactive maintenance strategies. In this work, we advocate the use of high-frequency SCADA data and quantile regression to build a cost eective performance monitoring tool. The benets of the approach are demonstrated through the comparison between state-of-the-art deterministic power curve modelling techniques and the suggested probabilistic model. Detection capabilities are compared for low and high-frequency SCADA data, providing evidence for monitoring at higher resolutions. Operational data from healthy and faulty turbines are used to provide a practical example of usage with the proposed tool, eectively achieving the detection of an incipient gearbox malfunction at a time horizon of more than one month prior to the actual occurrence of the failure.

AB - SCADA-based condition monitoring of wind turbines facilitates the move from costly corrective repairs towards more proactive maintenance strategies. In this work, we advocate the use of high-frequency SCADA data and quantile regression to build a cost eective performance monitoring tool. The benets of the approach are demonstrated through the comparison between state-of-the-art deterministic power curve modelling techniques and the suggested probabilistic model. Detection capabilities are compared for low and high-frequency SCADA data, providing evidence for monitoring at higher resolutions. Operational data from healthy and faulty turbines are used to provide a practical example of usage with the proposed tool, eectively achieving the detection of an incipient gearbox malfunction at a time horizon of more than one month prior to the actual occurrence of the failure.

KW - Operation & Maintenance

KW - Wind Turbine

KW - Power Curve

KW - Performance Monitoring

KW - SCADA

KW - High-frequency data

KW - Fault Detection

UR - http://iopscience.iop.org/journal/1742-6596

U2 - 10.1088/1742-6596/926/1/012009

DO - 10.1088/1742-6596/926/1/012009

M3 - Article

VL - 926

JO - Journal of Physics: Conference Series

T2 - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

M1 - 012009

ER -