Research Papers

Fault Monitoring of Wind Turbine Generator Brushes: A Data-Mining Approach

[+] Author and Article Information
Anoop Verma, Andrew Kusiak

Department of Mechanical and Industrial Engineering, 3131 Seamans Center,  The University of Iowa, Iowa City, IA 52242–1527andrew-kusiak@uiowa.edu

J. Sol. Energy Eng 134(2), 021001 (Feb 27, 2012) (9 pages) doi:10.1115/1.4005624 History: Received January 06, 2011; Revised December 06, 2011; Published February 27, 2012; Online February 27, 2012

Components of wind turbines are subjected to asymmetric loads caused by variable wind conditions. Carbon brushes are critical components of the wind turbine generator. Adequately maintaining and detecting abnormalities in the carbon brushes early is essential for proper turbine performance. In this paper, data-mining algorithms are applied for early prediction of carbon brush faults. Predicting generator brush faults early enables timely maintenance or replacement of brushes. The results discussed in this paper are based on analyzing generator brush faults that occurred on 27 wind turbines. The datasets used to analyze faults were collected from the supervisory control and data acquisition (SCADA) systems installed at the wind turbines. Twenty-four data-mining models are constructed to predict faults up to 12 h before the actual fault occurs. To increase the prediction accuracy of the models discussed, a data balancing approach is used. Four data-mining algorithms were studied to evaluate the quality of the models for predicting generator brush faults. Among the selected data-mining algorithms, the boosting tree algorithm provided the best prediction results. Research limitations attributed to the available datasets are discussed.

Copyright © 2012 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Cause and effect diagram of the “generator brush worn” fault

Grahic Jump Location
Figure 2

Samples of worn out carbon brushes

Grahic Jump Location
Figure 3

Distribution of generator brush worn out faults across 27 wind turbines

Grahic Jump Location
Figure 4

Power curve of wind turbine during generator brush fault (Turbine 14): (a) During fault emergence; (b) one day after the fault; and (c) two days after the fault

Grahic Jump Location
Figure 5

Identifying Tomek links

Grahic Jump Location
Figure 6

Iterative sampling of dataset t + 21 using Tomek links

Grahic Jump Location
Figure 7

Process flow for random forest based data sampling approach

Grahic Jump Location
Figure 8

Distribution of fault and normal class: (a) original dataset; (b) dataset after Tomek links based sampling; and (c) dataset after Tomek links and random forest based sampling

Grahic Jump Location
Figure 9

Boosted tree plot of prediction error function for dataset t + 21

Grahic Jump Location
Figure 10

The relative contribution of f_measure corresponding to different data sampling techniques




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In