Ari Isokangas

Intelligent Modelling of Continuous Pulp Cooking

Cooking is the major process in the pulp mill and its proper control is very important to the pulp production. The cooking should be done to the best quality at the minimum cost. Usually, the best quality means the minimisation of variation in the quality variables. Quality variations must simultaneously compensate for the effects of several types of disturbances. The main objective is to guarantee the similar cooking history for all chip particles as they pass through the digester. This leads to decreased variation in pulp quality compared with the conventional control.

Model selection in large-scale databases

Abstract A procedure for surveying process data sets is presented. For this, linear models constructed in varying length, sliding data windows to determine the usefulness of data segments for process identification are utilised. The discussed approach has been applied to an industrial wood debarking plant and a biomass boiler analysis, enabling the preliminary study of process variables and conditions affecting the non-optimal process conditions. In addition, main process interactions and delays were easily discovered from the structures of the interpretable linear model candidates. It is concluded that the analysis can provide valuable information also for modelling and control of continuous processes.