Application of Modified ART1 Neural Network in Aero-engine Fault Diagnosis
Hong-li Wang, Bing Xu, Yuan Zheng, Xue-dong Xue, Kan Cheng
Available Online May 2015.
- https://doi.org/10.2991/ipemec-15.2015.28How to use a DOI?
- Aero-Engine; Adaptive Resonance Theory (ART) Network; Fault Diagnosis; Quadratic-estimation Four-circumscription
- 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.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
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 - 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 - https://doi.org/10.2991/ipemec-15.2015.28 ID - Wang2015/05 ER -