Condition Monitoring of Wind Power System With Nonparametric Regression Analysis

Condition monitoring helps reduce the operations and maintenance costs by providing information about the physical condition of wind power systems. This study proposes to use a statistical method for effective condition monitoring. The turbine operation is significantly affected by external weather conditions. We model the wind turbine response as a function of weather variables, using a nonparametric regression method named least squares support vector regression. In practice, online condition monitoring of wind power systems often relies on datasets contaminated with outliers. This study proposes to use a weighted version of least squares support vector regression that provides a formal procedure for removing the outlier effects. We determine the decision boundaries to distinguish faulty conditions from normal conditions by examining the variations in the operational responses that are significantly affected by external weather. The results show that the proposed method effectively detects anomalies.

[1]  P Pinson,et al.  Conditional Prediction Intervals of Wind Power Generation , 2010, IEEE Transactions on Power Systems.

[2]  S. Osowski,et al.  Accurate fault location in the power transmission line using support vector machine approach , 2004, IEEE Transactions on Power Systems.

[3]  Gerry Leversha.  Statistical inference (2nd edn), by Paul H. Garthwaite, Ian T. Jolliffe and Byron Jones. Pp.328. £40 (hbk). 2002. ISBN 0 19 857226 3 (Oxford University Press). , 2003, The Mathematical Gazette.

[4]  Jochen Giebhardt,et al.  Rotor Condition Monitoring for Improved Operational Safety of Offshore Wind Energy Converters , 2005 .

[5]  Katya Scheinberg,et al.  Efficient SVM Training Using Low-Rank Kernel Representations , 2002, J. Mach. Learn. Res..

[6]  B Stephen,et al.  A Copula Model of Wind Turbine Performance , 2011, IEEE Transactions on Power Systems.

[7]  Sung-Hoon Ahn,et al.  Condition monitoring and fault detection of wind turbines and related algorithms: A review , 2009 .

[8]  D. Srinivasan,et al.  Composite Reliability Evaluation Using Monte Carlo Simulation and Least Squares Support Vector Classifier , 2011, IEEE Transactions on Power Systems.

[9]  H. A. David.  Early sample measures of variability , 1998 .

[10]  Rong Chen,et al.  Online weighted LS-SVM for hysteretic structural system identification , 2006 .

[11]  L. Bertling,et al.  Maintenance Management of Wind Power Systems Using Condition Monitoring Systems—Life Cycle Cost Analysis for Two Case Studies , 2007, IEEE Transactions on Energy Conversion.

[12]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[13]  Johan A. K. Suykens,et al.  Approximate Confidence and Prediction Intervals for Least Squares Support Vector Regression , 2011, IEEE Transactions on Neural Networks.

[14]  Yu Ding,et al.  Phase I Analysis for Monitoring Nonlinear Profiles in Manufacturing Processes , 2006 .

[15]  Andrew Kusiak,et al.  On-line monitoring of power curves , 2009 .

[16]  Wenxian Yang,et al.  Cost-Effective Condition Monitoring for Wind Turbines , 2010, IEEE Transactions on Industrial Electronics.

[17]  L Y Pao,et al.  Control of Wind Turbines , 2011, IEEE Control Systems.

[18]  A. D. Dominguez-Garcia,et al.  A Framework for Reliability and Performance Assessment of Wind Energy Conversion Systems , 2011, IEEE Transactions on Power Systems.

[19]  Senjian An,et al.  Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression , 2007, Pattern Recognit..

[20]  Zijun Zhang,et al.  Fault Analysis and Condition Monitoring of the Wind Turbine Gearbox , 2012, IEEE Transactions on Energy Conversion.

[21]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[22]  Kwok-Leung Tsui,et al.  Regression Control Charts , 2008 .

[23]  Wendy Foslien,et al.  Power Curve Analytic for Wind Turbine Performance Monitoring and Prognostics , 2011 .

[24]  Raja Ayyanar,et al.  Control strategy to mitigate the impact of reduced inertia due to doubly fed induction generators on large power systems , 2011, 2011 IEEE Power and Energy Society General Meeting.

[25]  V. Barnett,et al.  Applied Linear Statistical Models , 1975 .