Abstract:

In order to solve the problems of poor practicality and low accuracy of the existing paper tensile strengthprediction models,two prediction models respectively based on the partial least-squares ( PLS) and the supportvector machine ( SVM) are established for a corrugated paper mill by selecting parameters affecting paper tensilestrength through mechanism analysis.Then,the two models are simplified by deleting parameters of low correlationwith tensile strength,and the simplified models are compared in terms of prediction accuracy.The results show thatthe simplified SVM model,whose root mean square error and Pearson correlation coefficient are 321N/m and 0.909respectively,is a quick prediction model with a high accuracy,so it is more suitable for the on-line prediction oftensile strength.

Key words: paper, tensile strength, modeling, partial least squares, support vector machines