본문 바로가기

Shape recognition performance analysis and improvement in Sendzimir rolling mills

문서 유형
연구출판물 · 학술지 논문
등재
KCISCIEScopus
저널 순위
JCR Q3Scopus Q2
저널
JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY28(4) · pp.1455 · 2014
피인용
Web of Science 6KCI 1
JCR IF
JCR 2013 0.703
ISSN
1738-494X

저자

  1. 정철수부산대학교
  2. 박정현부산대학교
  3. 한성익부산대학교
  4. 김종식교신저자부산대학교

초록

Twenty-high Sendzimir rolling mills (ZRMs) typically use small diameter work rolls to provide massive pass reduction. Because of the small diameter of the work rolls, a rolled steel strip has a complex shape mixed with quarter, edge, and center waves. When the strip shape is controlled automatically, actuator saturation occurs in the shape actuator such as AS-U rack. These problems affect productivity and the quality of products made from the rolled material. We analyzed problems on the shape control system of a ZRM. The shape recognition performance was analyzed by comparing the measured and recognized shapes by multi-layer perceptron (MLP) method. In addition, neural network using the radial basis function (RBF) method was proposed to improve the shape recognition performance of the shape control system in a ZRM. P-gain which compensates the scale of the strip shape is added to prevent actuator saturation. Finally, we verify the variation of actuator position using ZRM's shape control simulator. Through simulation results, we found that shape recognition performance can be improved by the proposed method based on RBF neural network and actuator saturation problem can be improved by increasing shape recognition performance.

키워드

Automatic shape controlMulti-layer perceptronRadial basis functionSendzimir rolling millShape recognitionZRM's shape control simulatorCROWN

식별자

WoS UID
000335638700033
KCI
ART001860014