Online Prediction of Molded Part Quality in the Injection Molding Process Using High-Resolution Time Series

Abstract

Process-data-supported process monitoring in injection molding plays an important role in compensating for disturbances in the process. Until now, scalar process data from machine controls have been used to predict part quality. In this paper, we investigated the feasibility of incorporating time series of sensor measurements directly as features for machine learning models, as a suitable method of improving the online prediction of part quality. We present a comparison of several state-of-the-art algorithms, using extensive and realistic data sets. Our comparison demonstrates that time series data allow significantly better predictions of part quality than scalar data alone. In future studies, and in production-use cases, such time series should be taken into account in online quality prediction for injection molding.

A Simple Node Red Implementation for Digital Twins in the Area of Manufacturing

“…Because it enables the production of complex plastic objects with high precision and productivity, PIM is a manufacturing process that is widely used in industry. Around 110,000 new injection molding machines are put into operation worldwide every year [9]. PIM is a sequential process where the plastic is melted, pressed into the mold, cooled to solidify, and removed from the mold as a threedimensional shape [10].…”

Analysis of the Machine-Specific Behavior of Injection Molding Machines

“…Process parameter curves, such as injection pressure, can be applied to explain process variations, i.e., in part weight [ 22 ]. In addition to offline models, online models have been developed that enable the prediction of part quality during ongoing processes [ 23 , 24 , 25 ]. This included the creation of a digital twin, which can be used to recommend a new operating point in order to achieve the specified quality [ 24 , 25 ].…”