elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Kontakt | English
Schriftgröße: [-] Text [+]

Analysis of Nonlinear Learning Methods in the Adaptive Control Context of an Unmanned Helicopter

Kilic, Mehmet Can und Dauer, Johann (2012) Analysis of Nonlinear Learning Methods in the Adaptive Control Context of an Unmanned Helicopter. Masterarbeit. DLR-Interner Bericht. DLR-IB 111-2012/37, 73 S.

Dieses Archiv kann nicht den gesamten Text zur Verfügung stellen.

Kurzfassung

One research focus in DLR’s (German Aerospace Centre) Institute of Flight Systems is generation of artificial neural network benchmark for system identification uses. This thesis presents intermediate results which were obtained within forementioned research focus. The research will continue after the submission of this thesis. In this work, available literature were reviewed and reference criteria were produced, to be used for selection of suitable machine learning algorithms. With help of the reference criteria, multilayer feed forward neural networks (FFNN) and echo state networks (ESN) were selected for system identification use. wo different configurations of FFNN were applied to modelling of an unmanned helicopter dynamics. Lastly, approaches for capturing model uncertainties with FFNN were explained and it was shown that an existing flight dynamics model could be improved with a neural network correcting it. Finding optimal neural network structures for these different identification tasks, and providing performance comparison between FFNN and ESN were left as future work.

Dokumentart:Berichtsreihe (DLR-Interner Bericht, Masterarbeit)
Titel:Analysis of Nonlinear Learning Methods in the Adaptive Control Context of an Unmanned Helicopter
Autoren:
AutorenInstitution oder E-Mail-Adresse der Autoren
Kilic, Mehmet CanFT-UL
Dauer, JohannJohann.Dauer@dlr.de
Datum:Juni 2012
Seitenanzahl:73
Status:veröffentlicht
Stichwörter:Neural networks, system identification, unmanned helicopter dynamics, model uncertainties
Institution:Cranfield University
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Luftfahrt
HGF - Programmthema:Drehflügler
DLR - Schwerpunkt:Luftfahrt
DLR - Forschungsgebiet:L RR - Drehflüglerforschung
DLR - Teilgebiet (Projekt, Vorhaben):L - Der intelligente Drehflügler
Standort: Braunschweig
Institute & Einrichtungen:Institut für Flugsystemtechnik > Unbemannte Luftfahrzeuge
Hinterlegt von: Johann Dauer
Hinterlegt am:12 Jul 2012 14:25
Letzte Änderung:12 Jul 2012 14:25

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Copyright © 2008-2013 Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.