Logo Landing Page Logo HAW Hamburg

Health Monitoring for Aircraft Systems using Decision Trees and Genetic Evolution

Mike Gerdes

Abstract
Reducing unscheduled maintenance is important for aircraft operators. There are significant costs if flights must be delayed or cancelled, for example, if spares are not available and have to be shipped across the world. This thesis describes three methods of aircraft health condition monitoring and prediction; one for system monitoring, one for forecasting and one combining the two other methods for a complete monitoring and prediction process. Together, the three methods allow organizations to forecast possible failures. The first two use decision trees for decision-making and genetic optimization to improve the performance of the decision trees and to reduce the need for human interaction. Decision trees have several advantages: the generated code is quickly and easily processed, it can be altered by human experts without much work, it is readable by humans, and it requires few resources for learning and evaluation. The readability and the ability to modify the results are especially important; special knowledge can be gained and errors produced by the automated code generation can be removed. A large number of data sets is needed for meaningful predictions. This thesis uses two data sources: first, data from existing aircraft sensors, and second, sound and vibration data from additionally installed sensors. It draws on methods from the field of big data and machine learning to analyse and prepare the data sets for the prediction process.

Download full text: PDF/A TextGerdes.pdf    Size:  14M
Date:2019-12-20
Type of work: Dissertation
Advisor:Dieter Scholz, HAW Hamburg
Advisor:Diego Galar, Luleå Tekniska Universitet
Advisor:Uday Kumar, Luleå Tekniska Universitet
Examiner:David Baglee, University of Sunderland
Examiner:Del Carmen   Valero Ferrando, Universitat Politècnica de Catalunya
Examiner:Giulio D’Emilia, Universit degli Studi dell Aquila
Oponent:Piotr Bilski, Politechnika Warszawska
Public Defence:2019-12-20, F1031, Luleå, 10:00 (English)
Published by:Aircraft Design and Systems Group (AERO), Department of Automotive and Aeronautical Engineering, Hamburg University of Applied Sciences
This work is part of:transparent pin for text alignment Digital Library - Projects & Theses - Prof. Dr. Scholz --- http://library.ProfScholz.de pin
Project:http://PAHMIR.ProfScholz.de pin
 
PERSISTENT IDENTIFIER:
URN: https://nbn-resolving.org/urn:nbn:de:gbv:18302-aero2019-12-20.012 (to reach this page)
URN: https://nbn-resolving.org/urn:nbn:se:ltu:diva-76703
DOI:https://doi.org/10.15488/9213
ARK:https://n2t.net/ark:/13960/t7mq3cm3r
No associated research data 
URLs registered with URN: Show all links associated with this text!
 
CATALOG ENTRY:
DNB: Check inclusion of this title in German National Library!
WorldCat: Check inclusion of this title in WorldCat!
DataCite: Check inclusion of this title in DataCite!
Google Scholar: Check inclusion of this title in Google Scholar!
Semantic Scholar: Check inclusion of this title in Semantic Scholar!
OpenAIRE: Check inclusion of this title in OpenAIRE!
BASE: Check inclusion of this title in BASE!
CORE: Check inclusion of this title in CORE!
Google: Check inclusion of this title in Google!
 
Keywords, German (GND): Luftfahrt,   Luftfahrzeug,   Instandhaltung,   Maschinelles Lernen
Keywords, English (LCSH): Aeronautics,   Airplanes,   Decision Trees,   Genetic Algorithms,   Expert Systems,    Machine Learning,    Big Data,    Pattern Recognition Systems
Keywords, free: Flugzeugsysteme, Wartung, Condition Monitoring, Remaining Useful Life Prediction, Fuzzy Decision Tree Evaluation, System Monitoring, Aircraft Health Monitoring, Feature Extraction, Feature Selection, Data Driven, Health Prognostic, Knowledge Based System, Supervised Learning, Data-Driven Predictive Health Monitoring, Health Indicators
DDC: 629.13,    629.133340423,    629.13437,    620.0046,    006.31
RVK: ZO 7229

© This work is protected by copyright

The work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
CC BY-NC-SA
https://creativecommons.org/licenses/by-nc-sa/4.0

CC-BY-NC-SA

Any further request may be directed to:
Prof. Dr.-Ing. Dieter Scholz, MSME
E-Mail see: http://www.ProfScholz.de

VISIBILITY:  (more)

Share this text:
Twitter LinkedIn Facebook XING Mendeley InternetArchive E-Mail

Print Friendly and PDF

Quote this text:
ISO 690:
GERDES, Mike, 2019. Health Monitoring for Aircraft Systems using Decision Trees and Genetic Evolution. Dissertation. Hamburg University of Applied Sciences, Aircraft Design and Systems Group (AERO). Available from: https://nbn-resolving.org/urn:nbn:de:gbv:18302-aero2019-12-20.012 [viewed YYYY-MM-DD].

Major results / graphical abstract:
Major results / graphical abstract

Front page:
Cover Page


LAST UPDATE:  12 December 2021
AUTHOR:  Prof. Dr. Scholz
IMPRESSUM (PDF)

E-Mail-Address
home  Prof. Dr. Scholz
home  Aircraft Design and Systems Group (AERO)
home  Aeronautical Engineering
home  Department of Automotive and Aeronautical Engineering
home  Faculty of Engineering and Computer Science
home  Hamburg University of Applied Sciences