Nonlinear system identification using integrated linear-NN models: series vs. parallel structures

H., Zabiri and M., Ramasamy and Lemma D, Tufa and Maulud, Abdulhalim (2011) Nonlinear system identification using integrated linear-NN models: series vs. parallel structures. In: 2011 International Conference on Modeling, Simulation and Control (IPCSIT), 2-4 September 2013, Singapore.

[thumbnail of 7-ICMSC2011S021.pdf]
Preview
PDF
7-ICMSC2011S021.pdf

Download (592kB) | Preview
Official URL: http://www.ipcsit.com/vol10/7-ICMSC2011S021.pdf

Abstract

In this paper, the performance of integrated linear-NN models is investigated for nonlinear
system identification using two different structures: series vs. parallel. In particular, Laguerre filters are
selected as the linear models, and multi-layer perceptron (MLP) or feed-forward neural networks (NN) are
selected for the nonlinear models. Results show promising capability of the (novel) parallel Laguerre-NN
structure especially in terms of its generalization capability when subjected to data different from those used
during the identification stage in comparison to the series Laguerre-NN.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: nonlinear system identification, parallel integration, OBF, MLP, extrapolation
Subjects: T Technology > TP Chemical technology
Departments / MOR / COE: Departments > Chemical Engineering
Depositing User: Haslinda Zabiri
Date Deposited: 16 Dec 2013 23:48
Last Modified: 16 Dec 2013 23:48
URI: http://scholars.utp.edu.my/id/eprint/10747

Actions (login required)

View Item
View Item