Articles | Volume 5, issue 4
Research article
27 Oct 2020
Research article |  | 27 Oct 2020

Change-point detection in wind turbine SCADA data for robust condition monitoring with normal behaviour models

Simon Letzgus

Related subject area

Design methods, reliability and uncertainty modelling
Effectively using multifidelity optimization for wind turbine design
John Jasa, Pietro Bortolotti, Daniel Zalkind, and Garrett Barter
Wind Energ. Sci., 7, 991–1006,,, 2022
Short summary
Efficient Bayesian calibration of aerodynamic wind turbine models using surrogate modeling
Benjamin Sanderse, Vinit V. Dighe, Koen Boorsma, and Gerard Schepers
Wind Energ. Sci., 7, 759–781,,, 2022
Short summary
Fast yaw optimization for wind plant wake steering using Boolean yaw angles
Andrew P. J. Stanley, Christopher Bay, Rafael Mudafort, and Paul Fleming
Wind Energ. Sci., 7, 741–757,,, 2022
Short summary
A simplified, efficient approach to hybrid wind and solar plant site optimization
Charles Tripp, Darice Guittet, Jennifer King, and Aaron Barker
Wind Energ. Sci., 7, 697–713,,, 2022
Short summary
Influence of wind turbine design parameters on linearized physics-based models in OpenFAST
Jason M. Jonkman, Emmanuel S. P. Branlard, and John P. Jasa
Wind Energ. Sci., 7, 559–571,,, 2022
Short summary

Cited articles

Aminikhanghahi, S. and Cook, D. J.: A survey of methods for time series change point detection, Knowl. Inf. Syst., 51, 339–367, 2017. a
Arlot, S., Celisse, A., and Harchaoui, Z.: Kernel change-point detection, arXiv [preprint], arXiv:1202.3878v1, 2012. a
Arlot, S., Celisse, A., and Harchaoui, Z.: A Kernel Multiple Change-point Algorithm via Model Selection, J. Mach. Learn. Res., 20, 1–56, 2019. a, b, c, d, e
Bach-Andersen, M., Rømer-Odgaard, B., and Winther, O.: Flexible non-linear predictive models for large-scale wind turbine diagnostics, Wind Energ., 20, 753–764, 2017. a, b
Bangalore, P., Letzgus, S., Karlsson, D., and Patriksson, M.: An artificial neural network-based condition monitoring method for wind turbines, with application to the monitoring of the gearbox, Wind Energ., 20, 1421–1438, 2017. a, b, c, d, e, f
Short summary
One of the major challenges when working with wind turbine sensor data in practice is the presence of systematic changes in signal behaviour induced by malfunctions or maintenance actions. We found that approximately every third signal is affected by such change points and introduce an algorithm which reliably detects them in a highly automated fashion. The algorithm enables the application of data-driven techniques to monitor wind turbine components using data from commonly installed sensors.
Final-revised paper