Automatic in-line process quality control plays a crucial role to enhance production efficiency in the injection molding industry. Industry 4.0 is leading the productivity and efficiency of companies to minimize scrap rates and strive for zero-defect production, especially in the injection molding industry. In this study, a fully automated closed-loop injection molding (IM) setup with a communication platform via OPC UA was built in compliance with Industry 4.0. The setup included fully automated inline measurements, in-line data analysis, and an AI control system to set the new machine parameters via the OPC UA communication protocol. The surface quality of the injection molded parts was rated using the ResNet-18 convolutional neural network, which was trained on data gathered by a heuristic approach. Further, eight different machine learning models for predicting the part quality (weight, surface quality, and dimensional properties) and for predicting sensor data were trained using data from a variety of production information sources, including in-mold sensors, injection molding machine (IMM) sensors, ambient sensors, and inline product quality measurements. These models are the backbone of the AI control system, which is a heuristic model predictive control (MPC) method. This method was applied to find new sets of machine parameters during production to control the specified part quality feature. The control system and predictive models were successfully tested for two groups of quality features: Geometry control and surface quality control. Control parameters were limited to injection speed and holding pressure. Moreover, the geometry control was repeated with mold temperature as an additional control parameter.

The gloss transition defect of injection-molded surfaces should be mitigated because it creates a poor impression of product quality. Conventional approaches for the suppression of the gloss transition defect employ a trial-and-error approach and additional equipment. The causes of the generation of a low-gloss polymer surface and the surface change during the molding process have not been systematically analyzed. This article proposes the causes of the generation of a low-gloss polymer surface and the occurrence of gloss transition according to the molding condition. The changes in the polymer surface and gloss were analyzed using gloss and topography measurements. The shrinkage of the polymer surface generates a rough topography and low glossiness. Replication to the smooth mold surface compensates for the effect of surface shrinkage and increases the surface gloss. The surface stiffness and melt pressure influence the degree of mold surface replication. The flow front speed and mold temperature are the main factors influencing the surface gloss because they affect the development rate of the melt pressure and the recovery rate of the surface stiffness. Therefore, the mold design and process condition should be optimized to enhance the uniformity of the flow front speed and mold temperature.

This study is concerned with the flow behaviour of a rubber compound in capillary and injection moulding dies in the temperature range of 80–120°C. The injection moulding die designs had a tapered angle ranging from 40° up to 150°. The rheological characterisation of the rubber compound in the capillary dies showed that rubber slips at the wall, and this was modelled with an appropriate slip law. The pressure drops in the system were measured for all tapered dies. Numerical simulations were then carried out with a purely viscous (Carreau) model and a multimode viscoelastic (K-BKZ) model. The results showed a good agreement with the experiments for both the capillary and the injection moulding dies, provided that slip is included in the simulations as determined experimentally.