Validation of Infinite Impulse Response Multilayer Perceptron for Modelling Nuclear Dynamics

Science and Technology of Nuclear Installations. 2008;2008 DOI 10.1155/2008/681890

 

Journal Homepage

Journal Title: Science and Technology of Nuclear Installations

ISSN: 1687-6075 (Print); 1687-6083 (Online)

Publisher: Hindawi Publishing Corporation

LCC Subject Category: Technology: Electrical engineering. Electronics. Nuclear engineering

Country of publisher: Egypt

Language of fulltext: English

Full-text formats available: PDF, HTML, ePUB, XML

 

AUTHORS

F. Cadini (Department of Nuclear Engineering, Polytechnic of Milan, Via Ponzio 34/3, Milan 20133, Italy)
E. Zio (Department of Nuclear Engineering, Polytechnic of Milan, Via Ponzio 34/3, Milan 20133, Italy)
N. Pedroni (Department of Nuclear Engineering, Polytechnic of Milan, Via Ponzio 34/3, Milan 20133, Italy)

EDITORIAL INFORMATION

Blind peer review

Editorial Board

Instructions for authors

Time From Submission to Publication: 22 weeks

 

Abstract | Full Text

Artificial neural networks are powerful algorithms for constructing nonlinear empirical models from operational data. Their use is becoming increasingly popular in the complex modeling tasks required by diagnostic, safety, and control applications in complex technologies such as those employed in the nuclear industry. In this paper, the nonlinear modeling capabilities of an infinite impulse response multilayer perceptron (IIR-MLP) for nuclear dynamics are considered in comparison to static modeling by a finite impulse response multilayer perceptron (FIR-MLP) and a conventional static MLP. The comparison is made with respect to the nonlinear dynamics of a nuclear reactor as investigated by IIR-MLP in a previous paper. The superior performance of the locally recurrent scheme is demonstrated.