A soft sensor for prediction of mechanical properties of extruded PLA sheet using an instrumented slit die and machine learning algorithms

Abstract A soft sensor has been designed to accurately predict the yield stress of extruded Polylactide (PLA) sheet inline, during extrusion processing using an instrumented slit die. A number of experiments over a wide range of processing conditions have been carried out to develop the soft sensor model. The instrumented slit die had a number of embedded sensors monitoring pressure and temperature. The data collected from the slit die sensors was then used to predict the yield stress of the extruded PLA sheet using machine learning algorithms. The yield stress of the extruded sheet, which was measured offline, is compared to the model predictions to check the performance of the model. The soft sensor has the potential to provide real time feedback into the process and become a Quality Assurance (QA) tool which indicates if a product is going out of specification. This model can lead to reduced scrap rates and lower manufacturing costs by reducing machine downtime and making the process more energy efficient. Soft sensors have the potential to be introduced as part of a smart manufacturing process in keeping with the developments of Industry 4.0.