InSeLDiP
Intensification of separation processes in the food industry through digital twins and intelligent process control
Project description
Based on the example of two separation processes in the food industry, generalizable digitization concepts are developed, which use the chances of a plant control based on process understanding also in this area. For this purpose, data-driven and model-based methods are to be combined in order to optimize existing production processes. The combination of the methods allows the creation of hybrid digital twins, which can predict the production process and its influencing and output variables based on collected process data and existing expert knowledge as well as formalized physical/empirical models. This allows online optimization at production time and thus enables e.g. more sustainable process control by exploiting the historical data sets that have often not been used so far. The project differentiates between existing production processes (Brownfield) and newly projected plants (Greenfield). However, the developed solutions should be applicable to both applications at the same time, as far as possible. The focus is, therefore, on the generalization of the developed concepts.
