Application of Modified ART1 Neural Network in Aero-engine Fault Diagnosis

DOI

10.2991/ipemec-15.2015.28How to use a DOI?

Keywords

Aero-Engine; Adaptive Resonance Theory (ART) Network; Fault Diagnosis; Quadratic-estimation Four-circumscription

Abstract

According to principles of aero-engine fault diagnosis and flight data,this paper introduces a fault diagnosis method based on reformative ART1 neural network.After data pretreatment,it uses four-circumscription and quadratic-estimation to build fault codes and eliminate inveracious fault,and also ameliorate input layer of ART1 network.So this network can diagnoses not only gusty fault,but also gradual fault.It is proved that this method has high precision,strong restrain against noises,and low rate of inveracious alarms.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hong-li Wang
AU  - Bing Xu
AU  - Yuan Zheng
AU  - Xue-dong Xue
AU  - Kan Cheng
PY  - 2015/05
DA  - 2015/05
TI  - Application of Modified ART1 Neural Network in Aero-engine Fault Diagnosis
BT  - Proceedings of the 2015 International Power, Electronics and Materials Engineering Conference
PB  - Atlantis Press
SP  - 140
EP  - 144
SN  - 2352-5401
UR  - https://doi.org/10.2991/ipemec-15.2015.28
DO  - 10.2991/ipemec-15.2015.28
ID  - Wang2015/05
ER  -