Machine Learning Algorithm for Online Identification of Web End Stability, 21TAPPICon Virtual

The wet end in paper and board making is a complex multivariable system strongly related to chemistry. Chemistry status in wet end can fluctuate due to the changes in raw materials (pulp, water), chemicals, production and process conditions. Unstable wet end chemistry can potentially be causing depositions, higher chemical consumption, quality issues in the product and runnability problems.   

As a solution this paper presents how machine learning algorithms with new chemistry specific online measurements and process data have been utilized for stabilizing wet end chemistry in paper and board production. Machine learning models are used for predicting quality related performance. The model predictions are utilized for identification of process disturbances and optimization of process parameters related to wet end stability. The results have been obtained in two iterations. The first phase was off-line data validation and model training. In this phase also initial process characteristics were identified. The second phase was an on-line iteration of the model, which currently is in daily use. The results demonstrate the use of ML algorithms for online diagnostics. The benefits are deeper understanding of the wet end and related processes, more stable production and enabling cost savings. In general, the solution is potentially applicable throughout pulp and paper making.  

TAPPI conference proceedings and presentations, technical papers, and publication articles provide technical and management data and solutions on topics covering the Pulp, Paper, Tissue, Corrugated Packaging, Flexible Packaging, Nanotechnology and Converting Industries.

Simply select the quantity, add to your cart and your conference paper, presentation or article will be available for immediate download.