Diagnosing wind turbine faults using machine learning techniques applied to operational data

Unscheduled or reactive maintenance on wind turbines due to component failures incurs significant downtime and, in turn, loss of revenue. To this end, it is important to be able to perform maintenance before it's needed. By continuously monitoring turbine health, it is possible to detect incipient faults and schedule maintenance as needed, negating the need for unnecessary periodic checks. To date, a strong effort has been applied to developing Condition monitoring systems (CMSs) which rely on retrofitting expensive vibration or oil analysis sensors to the turbine. Instead, by performing complex analysis of existing data from the turbine's Supervisory Control and Data Acquisition (SCADA) system, valuable insights into turbine performance can be obtained at a much lower cost. In this paper, data is obtained from the SCADA system of a turbine in the South-East of Ireland. Fault and alarm data is filtered and analysed in conjunction with the power curve to identify periods of nominal and fault operation. Classification techniques are then applied to recognise fault and fault-free operation by taking into account other SCADA data such as temperature, pitch and rotor data. This is then extended to allow prediction and diagnosis in advance of specific faults. Results are provided which show success in predicting some types of faults.