Clustering Algorithms in Process Monitoring and Control Application to Continuous Digesters

In this study, the controlability of the Kappa number in two cooking applications is investigated. The Kappa number is one of the quality measures in the pulp cooking process and usually the only on-line measurement. It is a measure of the residual lignin content in the pulp. The cooking of the pulp mainly takes place in the digester, where the significant part of the lignin is removed from the chips. The control of the Kappa number is mainly carried out by temperature before the cooking zone, therefore it is important to get some indication of the quality (Kappa number) beforehand. The Kappa number is predicted before the cooking zone in two different cooking applications with the main variables affecting the Kappa number using a clustering and fault diagnosis system (SOM and fuzzy clustering). The clustering and fault diagnosis system is used also for a monitoring of the input variables. The data is collected from industrial conventional and Downflow Lo-Solids continuous cooking digesters. Good results were achieved using the clustering and fault diagnosis system.