Wind turbine power curve modeling and monitoring with Gaussian Process and SPRT

Peng Guo, David Infield

Research output: Contribution to journalArticle

2 Citations (Scopus)
10 Downloads (Pure)

Abstract

The wind turbine power curve is an important indicator of the performance of a wind turbine. Modeling and monitoring the power curve can detect wind turbine operating abnormalities and degradation in a timely manner. This paper firstly points out the drawbacks of the standard binned power curve modeling method of IEC-61400-12-1. Multiple factors that influence the wind energy capture and power output of a wind turbine are analyzed in detail and used as the power curve model inputs. A multivariable power curve model is constructed with a modified Cholesky decomposition Gaussian Process (GP) and validated using wind turbine SCADA data. A Sequential Probability Ratio Test (SPRT) with two groups of hypotheses is introduced to analyze and detect abnormal changes in GP power curve prediction residuals and thus detect abnormal operation. In order to locate failed components when an alarm is identified, longitudinal and transverse data comparisons are proposed to check the operation of specific components. The modeling and monitoring methods proposed in this paper successfully identify faults and locate the faulty component for two wind turbines with anemometer failure and pitch system failure respectively.
Original languageEnglish
Number of pages9
JournalIEEE Transactions on Sustainable Energy
Early online date3 Dec 2018
DOIs
Publication statusE-pub ahead of print - 3 Dec 2018

Keywords

  • wind turbine power curve
  • condition monitoring
  • gaussian process
  • SPRT
  • data comparison

Fingerprint Dive into the research topics of 'Wind turbine power curve modeling and monitoring with Gaussian Process and SPRT'. Together they form a unique fingerprint.

  • Research Output

    • 2 Citations
    • 2 Article
    Open Access
    File
  • 7 Citations (Scopus)
    5 Downloads (Pure)

    Comparison of advanced non-parametric models for wind turbine power curves

    Pandit, R. K., Infield, D. & Kolios, A., 8 Jul 2019, In : IET Renewable Power Generation. 13, 9, p. 1503-1510 8 p.

    Research output: Contribution to journalArticle

    Open Access
    File
  • 9 Citations (Scopus)
    36 Downloads (Pure)

    Cite this