Online Prediction of Longitudinal Facial Cracks in Thin Slab Casting Using Principal Component Analysis

被引：0

作者：

Lieftucht, Dirk ^{[1
]}

Arzberger, Matthias ^{[1
]}

Reifferscheid, Markus ^{[1
]}

Schlueter, Jochen ^{[1
]}

机构：

[1] SMS Demag AG, D-40237 Dusseldorf, Germany

来源：

JOURNAL OF IRON AND STEEL RESEARCH INTERNATIONAL | 2008年 / 15卷

关键词：

continuous casting; thin slab casting; mould monitoring system; longitudinal facial crack detection; multivariate statistical process control (MSPC); principal component analysis (PCA); expert systems; fault diagnosis; statistical analysis;

D O I：

暂无

中图分类号：

TF [冶金工业];

学科分类号：

0806 ;

摘要：

An online algorithm to detect longitudinal facial cracks (LFC) has been developed and integrated into the mould monitoring system (MMS) of a thin slab caster. The algorithm is based on the thermocouple readings in the mould and applies a hybrid model approach using principal component analysis (PCA) in terms of defect detection and an expert system including fuzzy rules regarding defect identification and isolation. The model-based technology is tolerant of distorted thermocouple readings and is consequently leading to a low false alarm rate. Results from thin slab casters in different Compact Strip Production (CSP) lines prove the practical benefits of the described concept for evaluating process stability regarding longitudinal facial crack occurrence as a function of different caster settings and process conditions.

引用

页码：255 / 259

页数：5