Application of wavelet-based neural networks to the modelling and optimisation of an experimental distillation column

被引：31

作者：

Safavi, AA

Romagnoli, JA

机构：

[1] UNIV SYDNEY,DEPT CHEM ENGN,ICI LAB PROC SYST ENGN,SYDNEY,NSW 2006,AUSTRALIA

[2] SHIRAZ UNIV,SHIRAZ,IRAN

来源：

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 1997年 / 10卷 / 03期

关键词：

wavelets; neural networks; multiresolution analysis; modelling;

D O I：

10.1016/S0952-1976(97)00009-2

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents an application of wavelet-based neural networks with localised and hierarchical multiresolution learning, namely wave-nets. The multiresolution framework of wave-nets is briefly explained and a misconception in the original presentation of wave-nets is modified A simple numerical example is provided, to clarify the idea. Then, wave-nets are employed to simplify the mechanistic model of a distillation column. The capability of the wave-net model is also verified within a hybrid modelling framework for the optimisation study of the column. (C) 1997 Elsevier Science Ltd. All rights reserved.

引用

页码：301 / 313

页数：13

共 25 条

[1]

[Anonymous], 1993, Ten Lectures of Wavelets

[2] Image coding using wavelet transform [J].