Employment of Kernel Methods on Wind Turbine Power Performance Assessment

Abstract

A power performance assessment technique is developed for the detection of power production discrepancies in wind turbines. The method employs a widely used nonparametric pattern recognition technique, the kernel methods. The evaluation is based on the trending of an extracted feature from the kernel matrix, called similarity index, which is introduced by the authors for the first time. The operation of the turbine and consequently the computation of the similarity indexes is classified into five power bins offering better resolution and thus more consistent root cause analysis. The accurate and proper detection of power production changes is demonstrated in cases of icing, power derating, operation under noise reduction mode, and incorrect controller input signal. Finally, overviews are illustrated for parks subjected to icing and operating under limited rotational speed. The comparison between multiple adjacent turbines contributes further to the correct evaluation of the park overall performance.

Using high-frequency SCADA data for wind turbine performance monitoring: A sensitivity study

“…To investigate the potential of such high-frequency data, a sensitivity study is undertaken to investigate the PC modelling accuracy of the selected methods for different data time resolutions. Furthermore, as stressed in [27] having a better understanding of the seasonality and location effects may contribute to more effective WT performance monitoring. To this end, the effect of seasonality and wind farm terrain complexity are also included as factors affecting PC modelling and WT monitoring capabilities.…”

“…Kernel methods were also explored in [27,28,29]. In general, non-parametric models seem to provide higher PC modelling accuracy due to their flexibility and capability to capture features inherent in the data.…”

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

“…Meanwhile, kernel methods were shown to have matched the accuracy of deep ANNs for speech recognition [54]. In the real world, kernel methods have been applied successfully to wind turbine performance assessment [55], machinery prognostics [56], and objective flow regime identification [57], to name a few.…”

Residual signal feature extraction for gearbox planetary stage fault detection

“…Data from supervisory control and data acquisition (SCADA) systems, like temperature and oil pressure, are also utilized in order to investigate any abnormal behaviour. Performance analysis based on power and wind speed data from the SCADA system offers a valuable insight regarding a variety of faults mainly related to controller malfunction, blade and pitch defects or external factors, such as icing, but has poor applicability in gearbox monitoring . Other techniques with limited field applications in wind turbines are ultrasonic testing, fibre‐optic strain measurements, electric signals and shock impulse method .…”