APPLICATION OF WAVELET-BASED NEURAL NETWORKS TO THE MODELING AND OPTIMIZATION OF AN EXPERIMENTAL DISTILLATION COLUMN

Authors
SAFAVI AA ROMAGNOLI JA
Citation
Aa. Safavi et Ja. Romagnoli, APPLICATION OF WAVELET-BASED NEURAL NETWORKS TO THE MODELING AND OPTIMIZATION OF AN EXPERIMENTAL DISTILLATION COLUMN, Engineering applications of artificial intelligence, 10(3), 1997, pp. 301-313
Citations number
25
Categorie Soggetti
Computer Application, Chemistry & Engineering","Computer Science Artificial Intelligence",Engineering,"Robotics & Automatic Control","Engineering, Eletrical & Electronic
Journal title
Engineering applications of artificial intelligence → ACNP
ISSN journal
09521976
Volume
10
Issue
3
Year of publication
1997
Pages
301 - 313
Database
ISI
SICI code
0952-1976(1997)10:3<301:AOWNNT>2.0.ZU;2-Y
Abstract
This paper presents an application of wavelet-based neural networks wi th localised and hierarchical multiresolution learning, namely wave-ne ts. The multiresolution framework of wave-nets is briefly explained an d a misconception in the original presentation of wave-nets is modifie d A simple numerical example is provided, to clarify the idea. Then, w ave-nets are employed to simplify the mechanistic model of a distillat ion column. The capability of the wave-net model is also verified with in a hybrid modelling framework for the optimisation study of the colu mn. (C) 1997 Elsevier Science Ltd. All rights reserved.