Comparative assessments of binned and support vector regression-based blade pitch curve of a wind turbine for the purpose of condition monitoring

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The unexpected failure of wind turbine components leads to significant downtime and loss of revenue. To prevent this, supervisory control and data acquisition (SCADA) based condition monitoring is considered as a cost-effective approach. In several studies, the wind turbine power curve has been used as a critical indicator for power performance assessment. In contrast, the application of the blade pitch angle curve has hardly been explored for wind turbine condition monitoring purposes. The blade pitch angle curve describes the nonlinear relationship between pitch angle and hub height wind speed and can be used for the detection of faults. A support vector machine (SVM) is an improved version of an artificial neural networks (ANN) and is widely used for classification- and regression-related problems. Support vector regression is a data-driven approach based on statistical learning theory and a structural risk minimization principle which provides useful nonlinear system modeling. In this paper, a support vector regression (a nonparametric machine learning approach)-based pitch curve is presented and its application to anomaly detection explored for wind turbine condition monitoring. A radial basis function (RBF) was used as the kernel function for effective SVR blade pitch curve modeling. This approach is then compared with a binned pitch curve in the identification of operational anomalies. The paper will outline the advantages and limitations of these techniques.
LanguageEnglish
Pages1-8
Number of pages8
JournalInternational Journal of Energy and Environmental Engineering
Early online date12 Oct 2018
DOIs
Publication statusE-pub ahead of print - 12 Oct 2018

Fingerprint

Condition monitoring
Wind turbines
Turbomachine blades
Turbine components
Support vector machines
Learning systems
Nonlinear systems
Data acquisition
Neural networks
Costs

Keywords

  • condition monitoring
  • support vector regression
  • performance monitoring
  • performance curves
  • wind turbine
  • SCADA analysis

Cite this

@article{24e5d5c264c2429db03b673fa011cc90,
title = "Comparative assessments of binned and support vector regression-based blade pitch curve of a wind turbine for the purpose of condition monitoring",
abstract = "The unexpected failure of wind turbine components leads to significant downtime and loss of revenue. To prevent this, supervisory control and data acquisition (SCADA) based condition monitoring is considered as a cost-effective approach. In several studies, the wind turbine power curve has been used as a critical indicator for power performance assessment. In contrast, the application of the blade pitch angle curve has hardly been explored for wind turbine condition monitoring purposes. The blade pitch angle curve describes the nonlinear relationship between pitch angle and hub height wind speed and can be used for the detection of faults. A support vector machine (SVM) is an improved version of an artificial neural networks (ANN) and is widely used for classification- and regression-related problems. Support vector regression is a data-driven approach based on statistical learning theory and a structural risk minimization principle which provides useful nonlinear system modeling. In this paper, a support vector regression (a nonparametric machine learning approach)-based pitch curve is presented and its application to anomaly detection explored for wind turbine condition monitoring. A radial basis function (RBF) was used as the kernel function for effective SVR blade pitch curve modeling. This approach is then compared with a binned pitch curve in the identification of operational anomalies. The paper will outline the advantages and limitations of these techniques.",
keywords = "condition monitoring, support vector regression, performance monitoring, performance curves, wind turbine, SCADA analysis",
author = "Pandit, {Ravi Kumar} and David Infield",
year = "2018",
month = "10",
day = "12",
doi = "10.1007/s40095-018-0287-3",
language = "English",
pages = "1--8",
journal = "International Journal of Energy and Environmental Engineering",
issn = "2251-6832",

}

TY - JOUR

T1 - Comparative assessments of binned and support vector regression-based blade pitch curve of a wind turbine for the purpose of condition monitoring

AU - Pandit, Ravi Kumar

AU - Infield, David

PY - 2018/10/12

Y1 - 2018/10/12

N2 - The unexpected failure of wind turbine components leads to significant downtime and loss of revenue. To prevent this, supervisory control and data acquisition (SCADA) based condition monitoring is considered as a cost-effective approach. In several studies, the wind turbine power curve has been used as a critical indicator for power performance assessment. In contrast, the application of the blade pitch angle curve has hardly been explored for wind turbine condition monitoring purposes. The blade pitch angle curve describes the nonlinear relationship between pitch angle and hub height wind speed and can be used for the detection of faults. A support vector machine (SVM) is an improved version of an artificial neural networks (ANN) and is widely used for classification- and regression-related problems. Support vector regression is a data-driven approach based on statistical learning theory and a structural risk minimization principle which provides useful nonlinear system modeling. In this paper, a support vector regression (a nonparametric machine learning approach)-based pitch curve is presented and its application to anomaly detection explored for wind turbine condition monitoring. A radial basis function (RBF) was used as the kernel function for effective SVR blade pitch curve modeling. This approach is then compared with a binned pitch curve in the identification of operational anomalies. The paper will outline the advantages and limitations of these techniques.

AB - The unexpected failure of wind turbine components leads to significant downtime and loss of revenue. To prevent this, supervisory control and data acquisition (SCADA) based condition monitoring is considered as a cost-effective approach. In several studies, the wind turbine power curve has been used as a critical indicator for power performance assessment. In contrast, the application of the blade pitch angle curve has hardly been explored for wind turbine condition monitoring purposes. The blade pitch angle curve describes the nonlinear relationship between pitch angle and hub height wind speed and can be used for the detection of faults. A support vector machine (SVM) is an improved version of an artificial neural networks (ANN) and is widely used for classification- and regression-related problems. Support vector regression is a data-driven approach based on statistical learning theory and a structural risk minimization principle which provides useful nonlinear system modeling. In this paper, a support vector regression (a nonparametric machine learning approach)-based pitch curve is presented and its application to anomaly detection explored for wind turbine condition monitoring. A radial basis function (RBF) was used as the kernel function for effective SVR blade pitch curve modeling. This approach is then compared with a binned pitch curve in the identification of operational anomalies. The paper will outline the advantages and limitations of these techniques.

KW - condition monitoring

KW - support vector regression

KW - performance monitoring

KW - performance curves

KW - wind turbine

KW - SCADA analysis

UR - https://link.springer.com/journal/40095

U2 - 10.1007/s40095-018-0287-3

DO - 10.1007/s40095-018-0287-3

M3 - Article

SP - 1

EP - 8

JO - International Journal of Energy and Environmental Engineering

T2 - International Journal of Energy and Environmental Engineering

JF - International Journal of Energy and Environmental Engineering

SN - 2251-6832

ER -