Wind turbine generator slip ring damage detection through temperature data analysis

The use of condition monitoring techniques in wind energy has been recently growing and the average unavailability time of an operating wind turbine in an industrial wind farm is estimated to be less than the 3%. The most powerful approach for gearbox condition monitoring is vibration analysis, but it should be noticed as well that the collected data are complex to analyse and interpret and that the measurement equipment is costly. For these reasons, several wind turbine subcomponents are monitored through temperature sensors. It is therefore valuable developing analysis techniques for this kind of data, with the aim of detecting incoming faults as early as possible. On these grounds, the present work is devoted to a test case study of wind turbine generator slip ring damage detection. A principal component regression is adopted, targeting the temperature collected at the slip ring. Using also the data collected at the nearby wind turbines in the farm, it is possible to identify the incoming fault approximately one day before it occurs.