Modelling of downflow lo-solids cooking in a continuous digester

摘要

Downflow Lo-Solids cooking technology was adopted at Arauco Mill in an attempt to reduce the variability in kappa number. In order to increase understanding of the cooking parameters on the final kappa number, a model was developed based on data extracted from the continuous digester at Arauco mill's line 2. Several modelling techniques were tested including multivariate linear regression and multi-layer perceptron neural networks. The best model obtained was shown to be an artificial neural network with Bayesian regularisation and one hidden layer which showed a correlation coefficient of 0.817.