Automatic step response execution algorithm in profile control in paper machines that uses lateral inhibition neural networks and wavelet

被引：0

作者：

Sasaki, T ^{[1
]}

Yamamoto, S

Hashimoto, I

机构：

[1] Yokogawa Elect Corp, Ind Measurement & Control Business Div, Paper & Web Syst Ctr, Tokyo 1800006, Japan

[2] Kogakuin Univ, Dept Mech Syst Engn, Tokyo 16391, Japan

[3] Kyoto Univ, Dept Chem Engn, Kyoto 60601, Japan

来源：

KAGAKU KOGAKU RONBUNSHU | 1998年 / 24卷 / 03期

关键词：

wavelet; neural networks; lateral inhibition; paper machine; profile control; process identification;

D O I：

10.1252/kakoronbunshu.24.451

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

We have developed an algorithm that automatically executes step response tests for defining position correspondence, which is the most important tuning factor in basis weight profile control for paper machines. The algorithm is composed of two parts. One is the part that defines the slice bolts that are manipulated and their manipulation direction by using neural networks that have lateral inhibition. The other is the part that optimizes the amount of manipulation by using wavelet analysis. We show an example where step response test was executed automatically by actually using this algorithm and show the effects of this algorithm.

引用

页码：451 / 457

页数：7