Search In this Thesis
   Search In this Thesis  
العنوان
Intelligent information system to forecast the remaining life of aircraft turbofan engines /
المؤلف
El - Attar, Hatem Mohamed Mohamed Ibrahim.
هيئة الاعداد
باحث / حاتم محمد محمد ابراهيم العطار
مشرف / علاء الدين محمد رياض
مشرف / حمدى كمال المنير
مناقش / حمدى كمال المنير
الموضوع
Health management.
تاريخ النشر
2011.
عدد الصفحات
95 p. :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
علوم الحاسب الآلي
تاريخ الإجازة
01/01/2011
مكان الإجازة
جامعة المنصورة - كلية الحاسبات والمعلومات - Department of Information Systems
الفهرس
Only 14 pages are availabe for public view

from 116

from 116

Abstract

Integrated Systems Health Management includes as key elements fault detection, fault diagnostics, and failure prognostics. Prognostics as a discipline has only recently been recognized as a technology that can push the boundary of systems health management. Prognostics algorithms are one of two types model-based and data driven. In complex engineering systems it is too difficult to have a physical model of a system. Data driven approaches is automatically fit a model of system behavior to historical data, rather than hand-coding a model for a system itself. This research intended to establish an intelligent information system to solve the problem of forecasting remaining useful life of aircraft turbofan engines based on data driven prognostics techniques. The developed system performance is dramatically affected by the robustness of the utilized algorithms which are the core of this research. Data driven prognostics employs many types of algorithms, some are static and others are dynamic. Dynamic complex engineering systems such as automobiles, aircraft, and spacecraft require dynamic data modeling which is very efficient to represent time series data. Dynamic models are complex and increase computational demands. Instead of using dynamic models, algorithm implements creation of linear regression models based on least square method is used to solve remaining useful life forecast task and overcomes the complexity of using dynamic models. Although linear models can give satisfactory results, it has some drawbacks and limitations. For this reason MultiLayer Perceptron Neural Network (MLP NN) as a static network is utilized to overcome the drawbacks and limitations of the regression models and does not involve the complexity of dynamic models. The data used here is the same data of data challenge problem defined by the 2008 Prognostics and Health Management conference (PHM08) Data Challenge Competition, in which, run-to-failure data of turbofan engines are provided and the Remaining Useful Life (RUL) of a set of test units (engines) will be forecasted. Results show that the ability of regression models to give a satisfactory score while MLP NN gives a superior score that can be placed in the fifteenth position of the top 20 scores as published on the official site of the conference.