Comparative analysis of binning and support vector regression for wind turbine rotor speed based power curve use in condition monitoring
作者： Ravi Pandit , David Infield
DOI: 10.1109/UPEC.2018.8542057
关键词: Turbine 、 Reliability engineering 、 Condition monitoring 、 Support vector machine 、 Predictive maintenance 、 SCADA 、 Statistical learning theory 、 Computer science 、 Wind speed 、 Wind power
摘要: Unscheduled maintenance consumes a lot of time and effort hence reduces the overall cost-effectiveness wind turbines. Supervisory control data acquisition (SCADA) based condition monitoring is cost-effective approach to carry out diagnosis prognosis faults provide performance assessment turbine. The rotor speed power curve, which describes nonlinear relationship between turbine output, useful for appraisal though limited work on this area has been undertaken date. Support Vector Machine (SVM) data-driven, nonparametric used both classification regression problems developed initially from statistical learning theory (SLT) by Vapnik. SVM in forecasting prediction applications.This paper deals with application support vector estimate curve its usefulness identifying potential faults. It compared conventional binned identify operational anomalies. comparative studies summarise advantages disadvantages these techniques. SCADA obtained healthy train validate methods.
strath.ac.uk
sci-hub.se 参考文章(19)
V. N. Vapnik, The Nature of Statistical Learning Theory. ,(1995)
Nattavut Yampikulsakul, Eunshin Byon, Shuai Huang, Shuangwen Sheng, Mingdi You, Condition Monitoring of Wind Power System With Nonparametric Regression Analysis IEEE Transactions on Energy Conversion. ,vol. 29, pp. 288- 299 ,(2014) , 10.1109/TEC.2013.2295301
Andrew Kusiak, Haiyang Zheng, Zhe Song, On-line monitoring of power curves Renewable Energy. ,vol. 34, pp. 1487- 1493 ,(2009) , 10.1016/J.RENENE.2008.10.022
L.B. JACK, A.K. NANDI, FAULT DETECTION USING SUPPORT VECTOR MACHINES AND ARTIFICIAL NEURAL NETWORKS, AUGMENTED BY GENETIC ALGORITHMS Mechanical Systems and Signal Processing. ,vol. 16, pp. 373- 390 ,(2002) , 10.1006/MSSP.2001.1454
Y. Amirat, M.E.H. Benbouzid, E. Al-Ahmar, B. Bensaker, S. Turri, A Brief Status on Condition Monitoring and Fault Diagnosis in Wind Energy Conversion Systems Renewable & Sustainable Energy Reviews. ,vol. 13, pp. 2629- 2636 ,(2009) , 10.1016/J.RSER.2009.06.031
M. Lydia, S. Suresh Kumar, A. Immanuel Selvakumar, G. Edwin Prem Kumar, A comprehensive review on wind turbine power curve modeling techniques Renewable & Sustainable Energy Reviews. ,vol. 30, pp. 452- 460 ,(2014) , 10.1016/J.RSER.2013.10.030
Meik Schlechtingen, Ilmar Ferreira Santos, Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection Mechanical Systems and Signal Processing. ,vol. 25, pp. 1849- 1875 ,(2011) , 10.1016/J.YMSSP.2010.12.007
Yujie Lin, Uwe Kruger, Junping Zhang, Qi Wang, Lisa Lamont, Lana El Chaar, Seasonal Analysis and Prediction of Wind Energy Using Random Forests and ARX Model Structures IEEE Transactions on Control Systems and Technology. ,vol. 23, pp. 1994- 2002 ,(2015) , 10.1109/TCST.2015.2389031
Andrew Kusiak, Anoop Verma, Monitoring Wind Farms With Performance Curves IEEE Transactions on Sustainable Energy. ,vol. 4, pp. 192- 199 ,(2013) , 10.1109/TSTE.2012.2212470
Vladimir Cherkassky, Yunqian Ma, Practical selection of SVM parameters and noise estimation for SVM regression Neural Networks. ,vol. 17, pp. 113- 126 ,(2004) , 10.1016/S0893-6080(03)00169-2