In the manufacturing process of polyvinyl chloride (PVC) tubes, the required thickness and weight depend on the extruder flow rate. The extruder setup can be very time-consuming and inefficient since it requires adjusting the screw rotational speed by trial and error, as the relation between the flow rate and the rotational speed is not known a priori. Furthermore, it is also affected by the material properties, the melt temperature, and the pressure drop in the die. Direct measuring the flow rate or the tube thickness would require expensive gravimetric dosers or X-ray systems, respectively. Therefore, a soft sensor was developed to monitor tube thickness and its weight per unit length. Two alternative approaches are proposed to predict the extruder flow rate under wall slip conditions: one is based on a developed analytical model and one on data-driven algorithms. Results show that machine learning regression models can achieve high predictive performance (a relative error of 1.2% using a support vector regressor).

No abstract

In manufacturing polyvinyl chloride (PVC) tubes, the required thickness and weight depend on the extruder flow rate. The extruder setup can be very time-consuming and inefficient since it requires adjusting the screw rotational speed by trial & error, as the relation between the flow rate and the rotational speed is not known a priori. Furthermore, it is also affected by the material properties, the melt temperature, and the pressure drop in the die. Direct measuring the flow rate or the tube thickness would require expensive gravimetric dosers or X-ray systems, respectively. Therefore, a soft-sensor was developed to monitor tube thickness and its weight per unit length. Two alternative approaches are proposed to predict the extruder flow rate under wall slip conditions: one is based on a developed analytical model and one on data-driven algorithms. Results show that machine learning regression models can achieve high predictive performance (a relative error of 1.2% using a Support Vector Regressor).

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