Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/133156
Title: ROBUST PROGNOSTICS FOR AEROSPACE APPLICATIONS
Authors: LIM PIN
Keywords: Prognostics, Aerospace, Machine Learning, Feature Extraction, Neural Network,Imbalanced Learning
Issue Date: 10-Aug-2016
Citation: LIM PIN (2016-08-10). ROBUST PROGNOSTICS FOR AEROSPACE APPLICATIONS. ScholarBank@NUS Repository.
Abstract: The bene ts of Prognostics and Health Management has been well documented and unanimously agreed between researchers, this has led to an increased focus in prognostic methods by both academia and industry. Nevertheless, despite the increased focus to develop prognostic methods, the real-world implementation of prognostic methods are still limited to a few de-facto methods. As the availability of monitoring data of systems increases, the potential to build robust prognostic methods in predicting the remaining useful life solely based on monitored data increases. This thesis therefore aims develop a holistic prognostic framework with an application focus for the aerospace industry. As such, the thesis reviews individual components within a typical prognostic framework to address gaps created by current literature. In this thesis, novel solutions addressing the gaps in class imbalance problems, feature extraction methods and multi-model degradation is proposed.
URI: http://scholarbank.nus.edu.sg/handle/10635/133156
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LimP.pdf8.52 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

51
checked on Nov 8, 2019

Download(s)

3
checked on Nov 8, 2019

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.