Plastic Extrusion Process Optimization by Digital Twins

Continuous plastics compounding processes are highly complex from a physicochemical point of view and correspondingly difficult to optimize. Model-based digital twins suitable for this purpose require simulation approaches, trained personnel input variables that determine. However, data-based twins, which in principle purpose, often fail because the enormous trial effort is required generate sufficiently large database. To overcome problem paper describes hybrid approach generating necessary database twin. By intelligent combination real experiments, adaptation physical-chemical process model these few experimental data subsequent cloud generation with adapted results sufficient base