Diagnosing and Predicting Wind Turbine Faults from SCADA Data Using Support Vector Machines

Kevin Leahy, R. Lily Hu, Ioannis C. Konstantakopoulos, Costas J. Spanos, Alice M. Agogino, and Dominic T.J. O'Sullivan
Publication Target: 
Publication Issue: 
Submission Type: 
Full Paper
ijphm_18_006.pdf418.7 KBFebruary 8, 2018 - 10:22am

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.

Publication Year: 
Publication Volume: 
Publication Control Number: 
Page Count: 
Submission Keywords: 
Wind Turbines
support vector machines
fault diagnosis
fault prediction
Submission Topic Areas: 
CBM and informed logistics
Component-level PHM
Data-driven methods for fault detection, diagnosis, and prognosis
Submitted by: 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed