Title :
Multivariate statistical monitoring of a continuous steel slab caster
Author :
Dudzic, Michael ; Miletic, Ivan
Author_Institution :
Dofasco Inc., Hamilton, Ont., Canada
Abstract :
Principal components analysis (PCA) is a multivariate statistical (MVS) technology that can be applied in process monitoring and fault diagnosis. Dofasco has developed on-line multivariate statistical process control (SPC) monitoring systems for both its #1 and #2 continuous casters (#1CC & #2CC) based on this technology. The paper introduces the reader to the basic process of steel casting and the motivation for MVS modeling. As well, the paper highlights various experiences involved in implementing on-line multivariate monitoring strategies and resulting outcome.
Keywords :
casting; principal component analysis; process monitoring; statistical process control; steel industry; Dofasco; continuous steel slab caster; fault diagnosis; multivariate statistical monitoring; principal components analysis; process monitoring; statistical process control; Casting; Delay; Fault detection; Fault diagnosis; Instruments; Monitoring; Principal component analysis; Process control; Slabs; Steel;
Conference_Titel :
American Control Conference, 2002. Proceedings of the 2002
Print_ISBN :
0-7803-7298-0
DOI :
10.1109/ACC.2002.1024872
