Modelling and analysis of real-world wind turbine power curves: Assessing deviations from nominal curve by neural networks

The power curve of a wind turbine describes the generated power versus instantaneous wind speed. wind turbine performance under laboratory ideal conditions will always tend to be optimistic rarely reflects how the turbine actually behaves in a real situation. Occasionally, some aerogenerators significantly different from nominal power curve, causing economic losses to the promoters of investment. Our research aims to model actual wind turbine power curve and its variation from power curve. The study was carried out in three different phases starting from wind speed and power production data of a Senvion MM92 aero-generator with a rated power of 2.05 MW. The phase was focused on statistical analyses, using the most common and reliable probability density The second phase was focused on the analysis and modelling of real power curves obtained on during one year of operation by fitting processes on real production data. The third was focused on development of a model based on the use of an Artificial Neural Networks that can predict the of delivered power. The actual power curve modelled with a multi-layered neural network was with nominal characteristics and the performances assessed by the turbine SCADA. For the device, deviations are below 1% for the producibility and below 0.5% for the actual power curves with both methods. The model can be used for any wind turbine to verify real performances to check fault conditions helping operators in understanding normal and abnormal behaviour. (C) 2019 Elsevier Ltd. All rights reserved.