Farm-wide dynamic event classification as load input for wind turbine drivetrain lifetime prognosis

One of the advantages of the current industrial digitalization trend, the so-called Industry 4.0, is that machines are becoming increasingly sensorized and connected to the internet. This is similar in the wind industry. Detailed measurements from hundreds of sensors embedded in the wind turbine are being sent continuously to cloud computing data-centers. Condition monitoring techniques can leverage these huge volumes of available data to increase detection potential and insights in system behavior by long-term trending. In addition to condition monitoring, these embedded sensors offer information for failure prognosis and lifetime insights. In this paper, a framework to automatically obtain the load history of different turbines within a farm is presented using high frequency SCADA. Special attention is paid to the effects of wake. The fact that data of similar machines of a fleet is collected in a central cloud environment allows for exploiting system similarity in a monitoring and root cause analysis context.