Author：Yue Wang, David G. Infield, Bruce Stephen and Stuart J. Galloway
Abstract
Power curve measurements provide a conventional and effective means of assessing the performance of a wind turbine,both commercially and technically. Increasingly high wind penetration in power systems and offshore accessibility issuesmake it even more important to monitor the condition and performance of wind turbines based on timely and accurate windspeed and power measurements. Power curve data from Supervisory Control and Data Acquisition (SCADA) systemrecords, however, often contain significant measurement deviations, which are commonly produced as a consequence ofwind turbine operational transitions rather than stemming from physical degradation of the plant. Using such raw datafor wind turbine condition monitoring purposes is thus likely to lead to high false alarm rates, which would make the actualfault detection unreliable and would potentially add unnecessarily to the costs of maintenance. To this end, this paperproposes a probabilistic method for excluding outliers, developed around a copula-based joint probability model. Thisapproach has the capability of capturing the complex non-linear multivariate relationship between parameters, based on theirunivariate marginal distributions; through the use of a copula, data points that deviate significantly from the consolidatedpower curve can then be removed depending on this derived joint probability distribution. After filtering the data in thismanner, it is shown how the resulting power curves are better defined and less subject to uncertainty, whilst broadly retainingthe dominant statistical characteristics. These improved power curves make subsequent condition monitoring more effectivein the reliable detection of faults.
Keywords：wind turbine; power curve; outlier rejection; SCADA; copula model
