Wind turbines in cold climate are defined as wind turbine operating in an environment where the temperature is 0℃ or lower, and/or operating with icing on wind turbine. Wind turbines in cold climate have been installed around 30% of worldwide installation of wind turbines. It is important for the wind turbines in cold climate to clarify the influence on the performance due to icing airfoil. When the temperature is -20℃ to 0℃, icing phenomenon occurs remarkably on the wind turbine blade, which causes the failure of the wind turbine by the fluctuation of the aerodynamic force on the blade. In this paper, the aerodynamic characteristics is clarified by the airfoil performance test of icing airfoil model in wind tunnel. With the use of these results, numerical analysis was carried out to clarify the influence of icing airfoil on the averaged output power and load on wind turbine. As result of the analysis, the output power is decreased by icing airfoil, the averaged moment of blade root is increased at high wind speed and the edgewise moment amplitude of blade root is increased.

View full abstract

This paper presents autoencoder (AE)/Gaussian mixture model (GMM) tandem connectionist anomaly detection for an efficient deployment of wind turbine anomaly detection systems. In this method, robust features are extracted using AE that is trained with a large variety of normal state data and taken as inputs to an anomaly identifier based on a GMM for a specific target machine. Since the AE is trained with data from various machines, the feature representations obtained using this AE can be robust against the difference in the machine types and operation conditions of wind turbines. Experimental comparisons conducted using vibration signals from wind turbines demonstrated that the proposed method achieved ideal anomaly detection, which detects anomalies without miss detections and with few false alarms. Even when the training data were small, the proposed system gave better performance than existing systems, showing its effectiveness in early operation.

View full abstract

It is required to establish cost-effective wind observation methods for installing offshore wind farms near the coastline. In a wind measurement campaign at three coastal sites in Akita prefecture, we installed three types of equipment on the coast: a meteorological mast, a vertical Doppler LiDAR, and a scanning Doppler LiDAR targetted at 2 km offshore. This method is cost-effective because no marine construction is involved, which also implies easy access for maintenance. In a preliminary verification study, the scanning Doppler LiDAR was found to satisfy accuracy thresholds for comparison against meteorological masts. We are proceeding with analysis toward the establishment of measurement methods and the elucidation of wind conditions in coastal areas.

View full abstract