@article{ref1,
title="Static and dynamic novelty detection methods for jet engine health monitoring",
journal="Philosophical transactions. Series A, Mathematical, physical, and engineering sciences",
year="2007",
author="Hayton, Paul and Utete, Simukai and King, D. and King, Sara and Anuzis, Paul and Tarassenko, Lionel",
volume="365",
number="1851",
pages="493-514",
abstract="Novelty detection requires models of normality to be learnt from training data known to be normal. The first model considered in this paper is a static model trained to detect novel events associated with changes in the vibration spectra recorded from a jet engine. We describe how the distribution of energy across the harmonics of a rotating shaft can be learnt by a support vector machine model of normality. The second model is a dynamic model partially learnt from data using an expectation-maximization-based method. This model uses a Kalman filter to fuse performance data in order to characterize normal engine behaviour. Deviations from normal operation are detected using the normalized innovations squared from the Kalman filter.<p /><p>Language: en</p>",
language="en",
issn="1364-503X",
doi="10.1098/rsta.2006.1954",
url="http://dx.doi.org/10.1098/rsta.2006.1954"
}