Title
Prediction of status patterns of wind turbines: A data-mining approach
Document Type
Article
Peer Reviewed
1
Publication Date
1-1-2011
Journal/Book/Conference Title
Journal of Solar Energy Engineering, Transactions of the ASME
Volume
133
Abstract
This paper presents the application of data-mining techniques for identification and prediction of status patterns in wind turbines. Early prediction of status patterns benefits turbine maintenance by indicating the deterioration of components. An association rule mining algorithm is used to identify frequent status patterns of turbine components and systems that are in turn predicted using historical wind turbine data. The status patterns are predicted at six time periods spaced at 10 min intervals. The prediction models are generated by five data-mining algorithms. The random forest algorithm has produced the best prediction results. The prediction results are used to develop a component performance monitoring scheme. 2011 American Society of Mechanical Engineers.
Keywords
Sustainability, This paper presents the application of data-mining techniques for identification and prediction of status patterns in wind turbines. Early prediction of status patterns benefits turbine maintenance by indicating the deterioration of components. An association rule mining algorithm is used to identify frequent status patterns of turbine components and systems that are in turn predicted using historical wind turbine data. The status patterns are predicted at six time periods spaced at 10 min intervals. The prediction models are generated by five data-mining algorithms. The random forest algorithm has produced the best prediction results. The prediction results are used to develop a component performance monitoring scheme. 2011 American Society of Mechanical Engineers.
Published Article/Book Citation
Journal of Solar Energy Engineering, Transactions of the ASME, 133:1 (2011) pp.
URL
http://ir.uiowa.edu/cee_pubs/464