Inter-engine variation analysis for health monitoring of aerospace gas turbine engines

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jul 1, 2018
William Jacobs Huw Edwards Visakan Kadirkamanathan Andrew Mills

Abstract

This study investigates the development of a new inter-engine
variation analysis method for the purpose of Equipment health
monitoring, in which the similarity - in both system behaviour
and external disturbances - across multiple (sister) engines is
leveraged. The sister engine provides a baseline description
of the engine under observation, such that the challenge becomes
the differentiation between normal inter-engine variation
and the anomalous behaviour, bypassing the need to
describe highly complex engine dynamics. The inter-engine
residuals are modelled directly with input data from both engines,
using previous healthy data for training. The trained
model is used to compensate known differences between real
engines. Anomalous data is detected by comparison of the
simulated output with the true residuals. The method is demonstrated
on a real data set containing both nominal, healthy engine
data, and engine data containing anomalies.

How to Cite

Jacobs, W., Edwards, H., Kadirkamanathan, V., & Mills, A. (2018). Inter-engine variation analysis for health monitoring of aerospace gas turbine engines. PHM Society European Conference, 4(1). https://doi.org/10.36001/phme.2018.v4i1.444
Abstract 344 | PDF Downloads 368

##plugins.themes.bootstrap3.article.details##

Keywords

modeling, health monitoring, EHM

Section
Technical Papers