Digital twins for the rapid startup of manufacturing processes: a case study in PVC tube extrusion

Abstract In this work, a soft sensor–based digital twin (DT) was developed to reduce the startup time in manufacturing plastic tubes and enable real-time product quality monitoring, i.e., weight per unit length inner outer diameters of tube. An experimental campaign conducted on real tube extrusion line using three polyvinyl chloride (PVC) compounds different process conditions, machine learning regression algorithms were trained tested create models extruder die DT is based on. The characterization considered material, whose properties given as input models, carried out according procedure only data collected by production line. for single-layer allowed achieve specified customer requirements (thickness weight) few minutes. proposed solution thus proved be valuable tool reducing setup time, increasing efficiency process.