Multi-Network Neural Model for nonlinear systems modeling

Author

Turki, Amina ; Chtourou, Mohamed

Author_Institution

Nat. Eng. Sch. of Sfax, Univ. of Sfax, Sfax, Tunisia

fYear

2014

fDate

1-4 June 2014

Firstpage

162

Lastpage

166

Abstract

This paper proposes a Multi-Network Neural Model (“MNNM”) to deal with complex systems modeling. Indeed, the training of this architecture was performed using a parallel algorithm consisting on training simultaneously all local neural networks. The obtained results show the effectiveness of the “MNNM” compared to the Single-Network Neural Model (“SNNM”). This work will be supported by two examples: a second order non linear system and a chemical reactor.

Keywords

chemical reactors; large-scale systems; learning systems; neurocontrollers; nonlinear systems; parallel algorithms; MNNM; SNNM; chemical reactor; complex systems modeling; local neural networks; multinetwork neural model; nonlinear systems modeling; parallel algorithm; second order nonlinear system; single-network neural model; Biological neural networks; Chemical reactors; Educational institutions; Mathematical model; Neurons; Nonlinear systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics (ISIE), 2014 IEEE 23rd International Symposium on

Conference_Location

Istanbul

Type

conf

DOI

10.1109/ISIE.2014.6864604

Filename

6864604

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1767366