Diagnosing and predicting wind turbine faults from SCADA data using support vector machines

Thumbnail Image
4987.pdf(417.18 KB)
Published Version
Leahy, Kevin
Hu, R. Lily
Konstantakopoulos, Ioannis C.
Spanos, Costas J.
Agogino, Alice M.
O'Sullivan, Dominic T. J.
Journal Title
Journal ISSN
Volume Title
Prognostics and Health Management Society
Published Version
Research Projects
Organizational Units
Journal Issue
Unscheduled or reactive maintenance on wind turbines due to component failure 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. 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, fault and alarm data from a turbine on the Southern coast of Ireland is analysed to identify periods of nominal and faulty operation. Classification techniques are then applied to detect and diagnose faults 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 recall scores generally above 80\% for fault detection and diagnosis, and prediction up to 24 hours in advance of specific faults, representing significant improvement over previous techniques.
Wind turbine , SCADA data , Faults , Diagnosis , Vector machines
Leahy, K., Hu, R. L., Konstantakopoulos, I. C., Spanos, C. J., Agogino, A. M. and O’Sullivan, D. T. (2018) 'Diagnosing and predicting wind turbine faults from SCADA data using support vector machines', International Journal of Prognostics and Health Management, 9(1), 006 (11pp).