Modeling and optimization of pulp and paper processes using neural networks

被引：8

作者：

Aguiar, HCIL ^{[1
]}

Maciel, R ^{[1
]}

机构：

[1] Univ Estadual Campinas, Fac Engn Quim, Dept Proc Quim, BR-13081970 Campinas, SP, Brazil

来源：

COMPUTERS & CHEMICAL ENGINEERING | 1998年 / 22卷

关键词：

neural networks; hybrid model; pulping; optimization;

D O I：

10.1016/S0098-1354(98)00195-1

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Two different methods are used to simulate the pulping process in a Kraft digestor - a deterministic model based on kinetic equations and mass transfer and a neural network model, based on a series of training patterns with usual process variables as inputs and pulp composition as output. The study indicates which process parameter have stronger influence on delignification rate, and shows that the neural network and the deterministic model present equivalent results. (C) 1998 Published by Elsevier Science Ltd. All rights reserved.

引用

页码：S981 / S984

页数：4