DocumentCode :
2566254
Title :
Identification of spatially interconnected systems using neural network
Author :
Ali, Mukhtar ; Abbas, Hossam ; Chughtai, Saulat S. ; Werner, Herbert
Author_Institution :
Inst. of Control Syst., Hamburg Univ. of Technol., Hamburg, Germany
fYear :
2010
fDate :
15-17 Dec. 2010
Firstpage :
6938
Lastpage :
6943
Abstract :
This paper presents an identification technique based on linear recurrent neural network to identify spatially interconnected systems both in open and closed-loop form. The latter has not been addressed in the literature for the systems under consideration. The paper considers identification of two-dimensional (time and space) systems; the method can be easily extended to have more than one dimension in space. In this paper we consider a semi-causal (causal in time and non-causal in space) two-dimensional (2-D) system, which may be separable or non-separable but the method can also be used for 2-D systems which are causal in both dimensions. Furthermore the algorithm can handle boundary conditions. The effectiveness of the method is shown with application to simulation examples.
Keywords :
boundary-value problems; distributed control; identification; interconnected systems; recurrent neural nets; 2D space system; 2D time system; boundary conditions; closed-loop form; identification technique; linear recurrent neural network; open-loop form; spatially interconnected systems; Artificial neural networks; Interconnected systems; Mathematical model; Noise; Recurrent neural networks; Training; Two dimensional displays;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control (CDC), 2010 49th IEEE Conference on
Conference_Location :
Atlanta, GA
ISSN :
0743-1546
Print_ISBN :
978-1-4244-7745-6
Type :
conf
DOI :
10.1109/CDC.2010.5717080
Filename :
5717080
Link To Document :
بازگشت