Application of an intuitive novelty metric for jet engine condition monitoring

Authors:
David A. Clifton;Peter R. Bannister;Lionel Tarassenko
Affiliations:
Department of Engineering Science, Oxford University, UK;Department of Engineering Science, Oxford University, UK;Department of Engineering Science, Oxford University, UK
Venue:
IEA/AIE'06 Proceedings of the 19th international conference on Advances in Applied Artificial Intelligence: industrial, Engineering and Other Applications of Applied Intelligent Systems
Year:
2006

Citing 5
Cited 1

NETLAB: algorithms for pattern recognition

NETLAB: algorithms for pattern recognition
Guide to Neural Computing Applications

Guide to Neural Computing Applications
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
A System for the Analysis of Jet Engine Vibration Data

Integrated Computer-Aided Engineering
A Nonlinear Mapping for Data Structure Analysis

IEEE Transactions on Computers

Novelty detection in large-vehicle turbocharger operation

IEA/AIE'07 Proceedings of the 20th international conference on Industrial, engineering, and other applications of applied intelligent systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Application of novelty detection to a new class of jet engine is considered within this paper, providing a worked example of the steps necessary for constructing a model of normality. Abnormal jet engine vibration signatures are automatically identified with respect to a training set of normal examples. Pre-processing steps suitable for this area of application are investigated. An intuitive metric for assigning novelty scores to patterns is introduced, with benefits for reducing model sensitivity to noise, and in pruning patterns from the model training set.