Learning Decision Rules by Particle Swarm Optimization (PSO) for Wind Turbine Fault Diagnosis

Xiang Ye, Yanjun Yan, and Lisa Osadciw
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_10_007.pdf994.96 KBOctober 1, 2010 - 7:01am

Wind turbine systems require an accurate health checking procedure to ensure their reliability. On a wind farm, sibling turbines should see similar wind speed, measured by anemometer, if they both work properly. A wrong reading can be caused by system breakdown, anemometer faults, etc. We design wind speed difference tests to detect both hard failures and soft failures, including anemometer faults. It is crucial to determine the decision boundary optimally to tell apart the abnormal state from the normal state. We propose a Particle Swarm Optimization (PSO) based approach to learn from historical data to decide the location and size of the boundary without the need to install extra sensors. This procedure is adaptable to each turbine using SCADA (Supervisory Control And Data Acquisition) data only. The adaptability and data-driven nature of our approach are advantageous to monitor a large wind farm. The test result has verified by the operational reports, which indicates the effectiveness of our approach. We have also observed the anemometer aging in data.

Publication Control Number: 
007
Submission Keywords: 
wind energy
Diagnosis and fault isolation methods
Asset health management
Data-driven detection methodologies
Submitted by: 
  
 
 
 

follow us

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