Optimization paper production through digitalization by developing an assistance system for machine operators including quality forecast: a concept
This addresses resource-intensive paper production for the paper industry, but it is incremental as it applies existing ML techniques to a specific domain.
The paper tackles the problem of high energy consumption in paper production from waste paper by developing an operator assistance system using machine learning to provide situation-specific knowledge, aiming to reduce the environmental footprint through better parameter adjustments.
Nowadays cross-industry ranging challenges include the reduction of greenhouse gas emission and enabling a circular economy. However, the production of paper from waste paper is still a highly resource intensive task, especially in terms of energy consumption. While paper machines produce a lot of data, we have identified a lack of utilization of it and implement a concept using an operator assistance system and state-of-the-art machine learning techniques, e.g., classification, forecasting and alarm flood handling algorithms, to support daily operator tasks. Our main objective is to provide situation-specific knowledge to machine operators utilizing available data. We expect this will result in better adjusted parameters and therefore a lower footprint of the paper machines.