Signal Monitoring Using Adaptive Threshold Classifier in Pulp & Paper Processes
| Authors: | Hiltunen Jukka, University of Oulu, Finland
Tervaskanto Manne, University of Oulu, Finland
Kivikunnnas Sauli, Technical Research Centre of Finland, Finland
Pohjanheimo Lauri, Technical Research Centre of Finland, Finland
Haltamo Janne, UPM-Kymmene, Finland |
|---|
| Topic: | 6.1 Chemical Process Control |
|---|
| Session: | Advances in Automation in Paper Making Industry |
|---|
| Keywords: | Adaptive systems, Classification, Monitoring, Pulp industry, Paper industry |
|---|
Abstract
Typically in pulp and paper processes raw material quality variation due to seasonal deviations as well as measurement drifts cause difficulties in setting the tight alarm thresholds for quality and control measurements. By using adaptive thresholds, more sensitive measurement range and thus reduced quality variation can be achieved. In this paper, new adaptive classification algorithm is proposed and validated by using simulated and real mill data.
