Improved power curve monitoring of wind turbines. Issue 4 (August 2017)

• Record Type: Journal Article
• Authors: Morshedizadeh, Majid; Kordestani, Mojtaba; Carriveau, Rupp; Ting, David S-K; Saif, Mehrdad
• Is Part Of: Wind engineering. Volume 41:Issue 4(2017)
• Page Start: 260
• Page End: 271
• Publication Date: 2017-08
• Subjects: Performance monitoring -- wind turbines -- artificial neural networks -- Supervisory Control And Data Acquisition -- power curve; Wind-pressure -- Periodicals; Winds -- Periodicals; Wind power -- Periodicals; Engineering meteorology -- Periodicals; Pression du vent; Vents; Énergie éolienne; Météorologie appliquée; Engineering meteorology; Wind power; Wind-pressure; Winds; Periodicals; 621.4505
• DOI: 10.1177/0309524X17709730
• Languages: English
• ISSNs: 0309-524X

Abstract

Wind turbine power output monitoring can detect anomalies in turbine performance which have the potential to result in unexpected failure. This study examines common Supervisory Control And Data Acquisition data over a period of 20 months. It is common to have more than 150 signals acquired by Supervisory Control And Data Acquisition systems, and applying all is neither practical nor useful. Thus, to address the issue, correlation coefficients analysis has been applied in this work to reveal the most influential parameters on wind turbine active power. Then, radial basis function and multilayer perception artificial neural networks are set up, and their performance is compared in two static and dynamic states. The proposed combination of the feature selection method and the dynamic multilayer perception neural network structure has performed well with favorable prediction error levels compared to other methods. Thus, the combination may be a valuable tool for turbine power curve monitoring.