Premium
Iterative modeling of wind turbine power curve based on least‐square B‐spline approximation
Author(s) -
Bao Yug,
Yang Qinmin,
Sun Youxian
Publication year - 2019
Publication title -
asian journal of control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.769
H-Index - 53
eISSN - 1934-6093
pISSN - 1561-8625
DOI - 10.1002/asjc.2150
Subject(s) - wind power , bin , turbine , scada , outlier , anomaly detection , computer science , normalization (sociology) , control theory (sociology) , algorithm , engineering , data mining , artificial intelligence , control (management) , mechanical engineering , electrical engineering , sociology , anthropology
Power curve plays a vital role in design, operation, control, and condition monitoring of wind turbines. Especially, it provides necessary information for wind farm maintenance decisions, allowing for not only comparison among the same type of wind turbines installed in different places, but also the same one at different time stamps. A standardized power curve iterative modeling procedure of wind turbines is proposed based on actual supervisory control and data acquisition (SCADA) data for performance evaluation in an online manner with guaranteed smoothness. The data are firstly preprocessed for anomaly detection by following normalization correction and then sliced into different wind speed bins. The least‐square B‐spline approximation method is iteratively implemented for power curve construction based on dominant points selected from the bin centroids, and turbulence intensity correction and outlier detection are conducted iteratively for refining identification results. Finally, the test results based on actual operating SCADA data demonstrate better performance in comparison with two counterparts.