Skip to main content

Research Repository

Advanced Search

Wind turbine SCADA alarm pattern recognition

Chen, Bindi; Qiu, Y.N.; Feng, Y.; Tavner, P.J.; Song, W.W.

Wind turbine SCADA alarm pattern recognition Thumbnail


Authors

Bindi Chen

Y.N. Qiu

Y. Feng

P.J. Tavner

W.W. Song



Abstract

Current wind turbine (WT) studies focus on improving their reliability and reducing the cost of energy, particularly when they are operated offshore. WT Supervisory Control and Data Acquisition (SCADA) systems contain alarm signals providing significant important information. Pattern recognition embodies a set of promising techniques for intelligently processing WT SCADA alarms. This paper presents the feasibility study of SCADA alarm processing and diagnosis method using an artificial neural network (ANN). The back-propagation network (BPN) algorithm was used to supervise a three layers network to identify a WT pitch system fault, known to be of high importance, from pitch system alarm. The trained ANN was then applied on another 4 WTs to find similar pitch system faults. Based on this study, we have found the general mapping capability of the ANN help to identify those most likely WT faults from SCADA alarm signals, but a wide range of representative alarm patterns are necessary for supervisory training.

Citation

Chen, B., Qiu, Y., Feng, Y., Tavner, P., & Song, W. (2011, September). Wind turbine SCADA alarm pattern recognition. Presented at Renewable Power Generation (RPG 2011), IET Conference, Edinburgh, UK

Presentation Conference Type Conference Paper (published)
Conference Name Renewable Power Generation (RPG 2011), IET Conference
Start Date Sep 6, 2011
End Date Sep 8, 2011
Publication Date Jan 1, 2011
Deposit Date Jul 10, 2013
Publicly Available Date Jul 12, 2013
Publisher IET
Pages 363-368
Series Title IET Conference Publications
Series Number 579
Book Title IET Conference on Renewable Power Generation 2011 (RPG 2011)
DOI https://doi.org/10.1049/cp.2011.0164
Keywords SCADA Alarms, Wind Turbine, Reliability, Artificial Neural Network, Back-propagation network.
Public URL https://durham-repository.worktribe.com/output/1155622
Publisher URL http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6136113

Files

Accepted Conference Proceeding (579 Kb)
PDF

Copyright Statement
This paper is a postprint of a paper submitted to and accepted for publication in IET Conference on Renewable Power Generation 2011 (RPG 2011) and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library.




You might also like



Downloadable Citations