Novelty detection is the identification of deviations from a training set. It is suitable for monitoring the health of mechanical systems where it usually is impossible to know every potential fault. In this paper, two novelty detectors are presented. The first detector which integrates One-Class Support Vector Machine (OCSVM) with an incremental clustering algorithm is designed for health monitoring of the turbopump, while the second one which is trained on sensor fault samples is designed to recognize faults from sensors and faults actually from the turbopump. Analysis results showed that these two detectors are both sensitive and efficient for the health monitoring of the turbopump.
|Number of pages||11|
|Journal||Journal of Physics: Conference Series|
|Publication status||Published - 28 May 2012|
|Event||25th International Congress on Condition Monitoring and Diagnostic Engineering: Sustained Prosperity through Proactive Monitoring, Diagnosis and Management - University of Huddersfield, Huddersfield, United Kingdom|
Duration: 18 Jun 2012 → 20 Jun 2012
Conference number: 25
http://compeng.hud.ac.uk/comadem2012/ (Link to Conference Website )