Parameter identification of a nonlinear two mass system using prior knowledge

C. Endisch, M. Brache, R. Kennel

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

Abstract

This article presents a new method for system identification based on dynamic neural networks using prior knowledge. A discrete chart is derived from a given signal flow chart. This discrete chart is implemented in a dynamic neural network model. The weights of the model correspond to physical parameters of the real system. Nonlinear parts of the signal flow chart are represented by nonlinear subparts of the neural network. An optimization algorithm trains the weights of the dynamic neural network model. The proposed identification approach is tested with a nonlinear two mass system.

OriginalspracheEnglisch
TitelMachine Learning and Systems Engineering
Seiten197-211
Seitenumfang15
DOIs
PublikationsstatusVeröffentlicht - 2010
VeranstaltungInternational Conference on Advances in Machine Learning and Systems Engineering - Berkeley, CA, USA/Vereinigte Staaten
Dauer: 20 Okt. 200922 Okt. 2009

Publikationsreihe

NameLecture Notes in Electrical Engineering
Band68 LNEE
ISSN (Print)1876-1100
ISSN (elektronisch)1876-1119

Konferenz

KonferenzInternational Conference on Advances in Machine Learning and Systems Engineering
Land/GebietUSA/Vereinigte Staaten
OrtBerkeley, CA
Zeitraum20/10/0922/10/09

Fingerprint

Untersuchen Sie die Forschungsthemen von „Parameter identification of a nonlinear two mass system using prior knowledge“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren