DocumentCode
1541258
Title
Neural networks for system identification
Author
Chu, S. Reynold ; Shoureshi, Rahmat ; Tenorio, Manoel
Author_Institution
Purdue Univ., West Lafayette, IN, USA
Volume
10
Issue
3
fYear
1990
fDate
4/1/1990 12:00:00 AM
Firstpage
31
Lastpage
35
Abstract
Two approaches are presented for utilization of neural networks in identification of dynamical systems. In the first approach, a Hopfield network is used to implement a least-squares estimation for time-varying and time-invariant systems. The second approach, which is in the frequency domain, utilizes a set of orthogonal basis functions and Fourier analysis to construct a dynamic system in terms of its Fourier coefficients. Mathematical formulations are presented, along with simulation results.<>
Keywords
Fourier analysis; frequency-domain analysis; identification; least squares approximations; neural nets; Fourier analysis; Hopfield network; dynamical systems; frequency domain; least-squares estimation; neural networks; system identification; time varying systems; time-invariant systems; Artificial neural networks; Computer simulation; Control systems; Frequency domain analysis; Hopfield neural networks; Neural networks; Neurons; Shape; System identification; Time varying systems;
fLanguage
English
Journal_Title
Control Systems Magazine, IEEE
Publisher
ieee
ISSN
0272-1708
Type
jour
DOI
10.1109/37.55121
Filename
55121
Link To Document