A Data-Driven Approach for Monitoring Blade Pitch Faults in Wind Turbines

被引：137

作者：

Kusiak, Andrew ^{[1
]}

Verma, Anoop ^{[1
]}

机构：

[1] Univ Iowa, Intelligent Syst Lab, Iowa City, IA 52242 USA

来源：

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY | 2011年 / 2卷 / 01期

关键词：

Blade angle asymmetry; blade angle implausibility; cost-sensitive classification; data mining; genetic programming (GP); SPEED;

D O I：

10.1109/TSTE.2010.2066585

中图分类号：

X [环境科学、安全科学];

学科分类号：

083001 [环境科学];

摘要：

A data-mining-based prediction model is built to monitor the performance of a blade pitch. Two blade pitch faults, blade angle asymmetry, and blade angle implausibility were analyzed to determine the associations between them and the components/subassemblies of the wind turbine. Five data-mining algorithms have been studied to evaluate the quality of the models for prediction of blade faults. The prediction model derived by the genetic programming algorithm resulted in the best accuracy and was selected to perform prediction at different time stamps.

引用

页码：87 / 96

页数：10

共 37 条

[1]

Agrawal R., 1993, SIGMOD Record, V22, P207, DOI 10.1145/170036.170072

[2]

AHA DW, 1991, MACH LEARN, V6, P37, DOI 10.1007/BF00153759

[3]

[Anonymous], 2006, Introduction to Data Mining

[4]

[Anonymous], 1994, P 20 INT C VER LARG

[5]

[Anonymous], 2003, Genetic programming IV: routine human-competitive machine intelligence

[6]

Bae H, 2003, IEEE IND ELEC, P2537

[7]

Long-term wind speed and power forecasting using local recurrent neural network models [J].

Barbounis, TG ;

Theocharis, JB ;

Alexiadis, MC ;

Dokopoulos, PS .

IEEE TRANSACTIONS ON ENERGY CONVERSION, 2006, 21 (01) :273-284

[8]

An empirical comparison of voting classification algorithms: Bagging, boosting, and variants [J].

Bauer, E ;

Kohavi, R .

MACHINE LEARNING, 1999, 36 (1-2) :105-139

[9]

Besemann C, 2004, P 4 WORKSH DAT MIN B, P72

[10]

Breiman L, 1996, MACH LEARN, V24, P123, DOI 10.1023/A:1018054314350

← 1 2 3 4 →