Home > Research > Publications & Outputs > Kullback-Leibler divergence based wind turbine ...

Associated organisational unit

Electronic data

  • p_204

    Accepted author manuscript, 1.27 MB, PDF document

    Available under license: CC BY-NC

Links

Text available via DOI:

View graph of relations

Kullback-Leibler divergence based wind turbine fault feature extraction

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Kullback-Leibler divergence based wind turbine fault feature extraction. / Wu, Yueqi; Ma, Xiandong.

24th International Conference on Automation & Computing. IEEE, 2019. p. 507-512.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Wu, Y & Ma, X 2019, Kullback-Leibler divergence based wind turbine fault feature extraction. in 24th International Conference on Automation & Computing. IEEE, pp. 507-512. https://doi.org/10.23919/IConAC.2018.8749103

APA

Wu, Y., & Ma, X. (2019). Kullback-Leibler divergence based wind turbine fault feature extraction. In 24th International Conference on Automation & Computing (pp. 507-512). IEEE. https://doi.org/10.23919/IConAC.2018.8749103

Vancouver

Wu Y, Ma X. Kullback-Leibler divergence based wind turbine fault feature extraction. In 24th International Conference on Automation & Computing. IEEE. 2019. p. 507-512 https://doi.org/10.23919/IConAC.2018.8749103

Author

Wu, Yueqi ; Ma, Xiandong. / Kullback-Leibler divergence based wind turbine fault feature extraction. 24th International Conference on Automation & Computing. IEEE, 2019. pp. 507-512

Bibtex

@inproceedings{a433f5cafa85417bb832f0b403a7c370,
title = "Kullback-Leibler divergence based wind turbine fault feature extraction",
abstract = "In this paper, a multivariate statistical technique combined with a machine learning algorithm is proposed to provide a fault classification and feature extraction approach for the wind turbines. As the probability density distributions (PDDs) of the monitoring variables can illustrate the inner correlations among variables, the dominant factors causing the failure are figured out, with the comparison of PDD of the variables under the healthy and unhealthy scenarios. Then the selected variables are used for fault feature extraction by using kernel support vector machine (KSVM). The presented algorithms are implemented and assessed based on the supervisory control and data acquisition (SCADA) data acquired from an operational wind farm. The results show the features relating specifically to the faults are extracted to be able to identify and analyse different faults for the wind turbines.",
keywords = "Wind turbine , Condition monitoring, Kernel support vector machine, Kullback-Leibler divergence, Supervisory Control and Data Acquisition",
author = "Yueqi Wu and Xiandong Ma",
year = "2019",
month = jul,
day = "1",
doi = "10.23919/IConAC.2018.8749103",
language = "English",
pages = "507--512",
booktitle = "24th International Conference on Automation & Computing",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Kullback-Leibler divergence based wind turbine fault feature extraction

AU - Wu, Yueqi

AU - Ma, Xiandong

PY - 2019/7/1

Y1 - 2019/7/1

N2 - In this paper, a multivariate statistical technique combined with a machine learning algorithm is proposed to provide a fault classification and feature extraction approach for the wind turbines. As the probability density distributions (PDDs) of the monitoring variables can illustrate the inner correlations among variables, the dominant factors causing the failure are figured out, with the comparison of PDD of the variables under the healthy and unhealthy scenarios. Then the selected variables are used for fault feature extraction by using kernel support vector machine (KSVM). The presented algorithms are implemented and assessed based on the supervisory control and data acquisition (SCADA) data acquired from an operational wind farm. The results show the features relating specifically to the faults are extracted to be able to identify and analyse different faults for the wind turbines.

AB - In this paper, a multivariate statistical technique combined with a machine learning algorithm is proposed to provide a fault classification and feature extraction approach for the wind turbines. As the probability density distributions (PDDs) of the monitoring variables can illustrate the inner correlations among variables, the dominant factors causing the failure are figured out, with the comparison of PDD of the variables under the healthy and unhealthy scenarios. Then the selected variables are used for fault feature extraction by using kernel support vector machine (KSVM). The presented algorithms are implemented and assessed based on the supervisory control and data acquisition (SCADA) data acquired from an operational wind farm. The results show the features relating specifically to the faults are extracted to be able to identify and analyse different faults for the wind turbines.

KW - Wind turbine

KW - Condition monitoring

KW - Kernel support vector machine

KW - Kullback-Leibler divergence

KW - Supervisory Control and Data Acquisition

U2 - 10.23919/IConAC.2018.8749103

DO - 10.23919/IConAC.2018.8749103

M3 - Conference contribution/Paper

SP - 507

EP - 512

BT - 24th International Conference on Automation & Computing

PB - IEEE

ER -