Anomaly detection for wind turbine condition monitoring is an active area of research within the wind energy operations and maintenance (O & M) community. In this paper three models were compared for multi-megawatt operational wind turbine SCADA data. The models used for comparison were One-Class Support Vector Machine (OCSVM), Isolation Forest (IF), and Elliptical Envelope (EE). Each of these were compared for the same fault, and tested under various different data configurations. IF and EE have not previously been used for fault detection for wind turbines, and OCSVM has not been used for SCADA data. This paper presents a novel method of condition monitoring that only requires two months of data per turbine. These months were separated by a year, the first being healthy and the second unhealthy. The number of anomalies is compared, with a greater number in the unhealthy month being considered correct. It was found that for accuracy IF and OCSVM had similar performances in both training regimes presented. OCSVM performed better for generic training, and IF performed better for specific training. Overall, IF and OCSVM had an average accuracy of 82% for all configurations considered, compared to 77% for EE.

No abstract

A comparison has been made of the power electronics lifetime for 5MW horizontaland vertical-axis wind turbines, based on dynamic models supplied with generated wind speed time series. Both two-and three-bladed stall-regulated H-rotor vertical-axis turbines were modelled, with several different control parameters. Vertical-axis turbines are likely to lead to a shorter power electronics lifetime as the aerodynamic torque varies with rotor azimuth, leading to a cyclic generator torque, and increased thermal cycling in the power electronics.An electro-thermal model of a low-voltage converter was created, and used to calculate the switching device temperatures based on the generator torque and speed time series from the turbine model. An empirical lifetime model and rainflow-counting algorithm were used to calculate the lifetime, and this was repeated at different average wind speeds to determine the overall lifetime. The vertical-axis turbine was found to have a lower power electronics lifetime than the horizontal-axis, or require a larger number of parallel switching devices to achieve the same lifetime, although this was lessened by running the turbine with a more relaxed speed control, allowing the rotor inertia to partially absorb the aerodynamic torque ripple. The three-bladed turbine was also found to give a longer power electronic lifetime than the 2-bladed, due to the lower overall torque ripple.

An analytical model based on the double multiple streamtube method is proposed for calculating the rotor performance and aerodynamic blade forces for vertical axis wind turbines (VAWTs) with variable pitch straight blades. An interception method is utilized to determine induction factors which can be used to calculate local blade forces. The model makes allowance for flow expansion, flow curvature, tip loss and dynamic stall. Aerodynamic prediction output from this model is compared with experimental data available in the public domain for validation purposes.