Prevention of sheetbreaks using multi-variate statistical analysis in an expert system environment - A look at the effectiveness of such methods as PCA and PLS

Sheetbreaks in a pulp or paper production process can be very costly to the mill and hazardous to the operating personnel. Since the occurrence of sheetbreaks can be due to many factors and operating variables, this paper presents the use of principal component analysis and projection to latent structures techniques in an expert system environment to deal with this problem. Industrial data concerning sheetbreaks from pulp and paper machines were used to demonstrate the effectiveness of this approach.