Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0812113-192702 Statistics This thesis had been viewed 1041 times. Download 0 times. Author Tung-ying Chen Author's Email Address No Public. Department Institute of Engineering Management Year 2012 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 75 Title USING BACK-PROPAGATION NETWORK TO PREDICT AIRCRAFT COMPONENT LIFE SPAN - A CASE STUDY ON HPV OF PNEUMATIC SYSTEM FOR A330-300 Keyword F/C TSO Aircraft Component BPN TSN TSC TSC TSN BPN Aircraft Component TSO F/C Abstract Global aviation property is currently flourishing, the aircraft maintenance is increasing in demand.The defects of aircraft components lead to flights delayed easily.If there is a prediction system, the aircraft components may perform inspection or repair before it get failure.It may lower flights delay issues caused by the components that encountered the unexpected failured, the prediction system can be a reference action for airline for further component maintenance management.
This study uses HPV installed on GE-CF6-80E1 engine of A330-300 as an example. Firstly, selecting the Delphi Method to collect experts’ key factors of HPV’s life span. Secondly, using Likert 5-Piont Scale to request experts to evaluate importance and give a score on the key factors. According to experts’ agreed indicators, four key factors have chosed, TSC、TSO、TSN & F/C.According to the historical maintenance reports from 2010 to 2012, put the data of the four key factors into the BPN (Back-Propagation Network) to train the relationship between input and output to build the prediction mode via Neuro Intelligence software.For best prediction mode, it resulted to 1 hidden layer with 2 neurons, learning rate at 0.1 and iteration at 30,000.
The research result indicates that correlation and R-squared model could reach 0.969 and 0.932 respectively after BPN training. Certainly, BPN serves as an effective method of predicting the aircraft component life span.
This study uses the BPN prediction capability, thereby enabling the aircraft component to develop a failure reaction strategy. Hopefully, maintenance knowledge management experiences builded could be passed to next generation and such model could be applied to different industries, so as to ensure maximum output and minimum input, and to strengthen the sustainable competitiveness of businesses.
Advisor Committee Ming-yung Wang, Yung-jen Lin - advisor
Rong-chi Wang - co-chair
Tian-syung Lan - co-chair
Yung-jen Lin - co-chair
Files Date of Defense 2013-07-16 Date of Submission 2013-08-13