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

Letzgus, Simon

doi:https://doi.org/10.5194/wes-5-1375-2020

Articles | Volume 5, issue 4

https://doi.org/10.5194/wes-5-1375-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Wind Energy Science Conference 2019

https://doi.org/10.5194/wes-5-1375-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

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

Download

Final revised paper (published on 27 Oct 2020)
Preprint (discussion started on 27 Mar 2020)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Review of wes-2020-38', Anonymous Referee #1, 21 May 2020
- AC1: 'Author's reply to Anonymous Referee #1', Simon Letzgus, 10 Aug 2020
RC2: 'Comments to the manuscript WES-2020-38', Anonymous Referee #2, 22 Jul 2020
- AC2: 'Author's reply to Anonymous Referee #2', Simon Letzgus, 10 Aug 2020

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Simon Letzgus on behalf of the Authors (12 Aug 2020) Author's response Manuscript

ED: Publish as is (26 Aug 2020) by Michael Muskulus

ED: Publish as is (08 Sep 2020) by Jakob Mann (Chief editor)

AR by Simon Letzgus on behalf of the Authors (10 Sep 2020) Manuscript

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.