Advertisement

Dimensionality Reduction for the Analysis of Time Series Data from Wind Turbines

  • Jochen Garcke
  • Rodrigo Iza-Teran
  • Marvin Marks
  • Mandar Pathare
  • Dirk Schollbach
  • Martin Stettner
Chapter

Abstract

We are addressing two related applications for the analysis of data from wind turbines. First, we consider time series data arising from virtual sensors in numerical simulations as employed during product development, and, second, we investigate sensor data from condition monitoring systems of installed wind turbines. For each application we propose a data analysis procedure based on dimensionality reduction. In the case of virtual product development we develop tools to assist the engineer in the process of analyzing the time series data from large bundles of numerical simulations in regard to similarities or anomalies. For condition monitoring we develop a procedure which detects damages early in the sensor data stream.

Notes

Acknowledgements

The authors would like to thank the German Federal Ministry of Education and Research (BMBF) for the opportunity to do research in the VAVID project under grant 01IS14005. We cordially thank Henning Lang and Tobias Tesch for their assistance with the numerical experiments.

References

  1. 1.
    I. Antoniadou, Accounting for Nonstationarity in the Condition Monitoring of Wind Turbine Gearboxes, PhD thesis, University of Sheffield, 2013Google Scholar
  2. 2.
    R. Coifman, F. Lafon, Diffusion maps. Appl. Comput. Harmon. Anal. 21, 5–30 (2006)CrossRefMathSciNetzbMATHGoogle Scholar
  3. 3.
    European Wind Energy Association (EWEA), Wind in power - 2015 European statistics, tech. report, European Wind Energy Association, February 2016Google Scholar
  4. 4.
    R. Gasch, J. Twele (eds.), Wind Power Plants (Springer, Berlin, 2012)Google Scholar
  5. 5.
    B. Hahn, M. Durstewitz, K. Rohrig, Reliability of wind turbines, in Wind Energy, ed. by J. Peinke, P. Schaumann, S. Barth (Springer, Berlin, 2007), pp. 329–332CrossRefGoogle Scholar
  6. 6.
    T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning, 2nd edn. (Springer, Berlin, 2009)CrossRefzbMATHGoogle Scholar
  7. 7.
    N.E. Huang, Z. Shen, S. Long, et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 454, 903–995 (1998)CrossRefMathSciNetzbMATHGoogle Scholar
  8. 8.
    F. Itakura, Minimum prediction residual principle applied to speech recognition. IEEE Trans. Acoust. Speech Signal Process. 23, 67–72 (1975)CrossRefGoogle Scholar
  9. 9.
    J.M. Jonkman, The new modularization framework for the FAST wind turbine CAE tool, in Proceedings of the 51st AIAA Aerospace Sciences Meeting, 2013. also Tech. RepNREL/CP-5000-57228, National Renewable Energy Laboratory, Golden, CO.Google Scholar
  10. 10.
    A. Kusiak, Z. Zhang, A. Verma, Prediction, operations, and condition monitoring in wind energy. Energy 60, 1–12 (2013)CrossRefGoogle Scholar
  11. 11.
    J.A. Lee, M. Verleysen, Nonlinear Dimensionality Reduction (Springer, Berlin, 2007)CrossRefzbMATHGoogle Scholar
  12. 12.
    W. Lu, F. Chu, Condition monitoring and fault diagnostics of wind turbines, in Prognostics and Health Management Conference, 2010. PHM ’10., Jan. 2010, pp. 1–11Google Scholar
  13. 13.
    L. Mujica, J. Rodellar, A. Fernández, A. Güemes, Q-statistic and T 2-statistic PCA-based measures for damage assessment in structures. Struct. Health Monit. 10, 539–553 (2011)CrossRefGoogle Scholar
  14. 14.
    R.B. Randall, Vibration-based Condition Monitoring: Industrial, Automotive and Aerospace Applications (Wiley, Hoboken, 2011)CrossRefGoogle Scholar
  15. 15.
    S. Salvador, P. Chan, FastDTW: Toward accurate dynamic time warping in linear time and space. Intell. Data Anal. 11, 561–580 (2007)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Jochen Garcke
    • 1
    • 2
  • Rodrigo Iza-Teran
    • 1
  • Marvin Marks
    • 1
  • Mandar Pathare
    • 1
  • Dirk Schollbach
    • 3
  • Martin Stettner
    • 4
  1. 1.Fraunhofer Institute for Algorithms and Scientific Computing SCAISankt AugustinGermany
  2. 2.Institute for Numerical SimulationRheinische Friedrich-Wilhelms-Universität BonnBonnGermany
  3. 3.Weidmüller Monitoring Systems GmbHDresdenGermany
  4. 4.GE Global ResearchGarching bei MünchenGermany

Personalised recommendations