Combining Simulations and Machine Learning for Efficient Prediction of Process Parameters Evolution in Injection Moulding

In recent years, the emerging technologies in the context of Industry 4.0 have led to novel approaches in process monitoring and control, such as the introduction of Reinforcement Learning and Digital Twins. Consequently, large amounts of data, precise modelling and exhaustive simulations are required. The aim of this work is to propose a methodology based on the technique of backward selection to reduce the number of reference points in the simulation stage of manufacturing processes, enhancing the efficiency of data generation and the simplicity of the simulations. The methodology is proved in the particular case of plastic injection moulding simulations.

Optimisation of Shrinkage and Strength on Thick Plate Part Using Recycled LDPE Materials

Achieving good quality of products from plastic injection moulding processes is very challenging, since the process comprises many affecting parameters. Common defects such as warpage are hard to avoid, and the defective parts will eventually go to waste, leading to unnecessary costs to the manufacturer. The use of recycled material from postindustrial waste has been studied by a few researchers. However, the application of an optimisation method by which to optimise processing parameters to mould parts using recycled materials remains lacking. In this study, Response Surface Methodology (RSM) and Particle Swarm Optimisation (PSO) methods were conducted on thick plate parts moulded using virgin and recycled low-density polyethylene (LDPE) materials (100:0, 70:30, 60:40 and 50:50; virgin to recycle material ratios) to find the optimal input parameters for each of the material ratios. Shrinkage in the x and y directions increased in correlation with the recycled ratio, compared to virgin material. Meanwhile, the tensile strength of the thick plate part continued to decrease when the recycled ratio increased. R30 (70:30) had the optimum shrinkage in the x direction with respect to R0 (100:0) material where the shrinkage increased by 24.49% (RSM) and 33.20% (PSO). On the other hand, the shrinkage in the y direction for R30 material increased by 4.48% (RSM) and decreased by 2.67% (PSO), while the tensile strength of R30 (70:30) material decreased by 0.51% (RSM) and 2.68% (PSO) as compared to R0 (100:0) material. Validation tests indicated that the optimal setting of processing parameter suggested by PSO and RSM for R0 (100:0), R30 (70:30), R40 (60:40) and R50 (50:50) was less than 10%.

Rückführung von Messergebnissen in den Konstruktionsprozess/Partially automated mould correction for plastic injection moulding – Feedback of measurement results into the design process

Die Geometrie von Kunststoffspritzgußwerkstücken wird durch Abkühlung der Schmelze bei der Fertigung beeinflusst. Die hieraus resultierende Geometrieabweichung wird mittels Simulation abgeschätzt und bei der Konstruktion berücksichtigt. Trotz der eingesetzten Verfahren sind Abweichungen zwischen Soll- und Ist-Geometrie häufig zu groß. Durch Rückführung von Messergebnissen in den Konstruktionsprozess werden systematische Abweichungen reduziert. Aufwendige manuelle Verfahren können so entfallen.   The geometry of plastic injection molded workpieces is influenced by cooling of the melt during production. The resulting geometry deviation is estimated by means of simulation and taken into account in the design. Despite the methods used, deviations between nominal and actual geometry are often too high. Systematic deviations are reduced by feeding measurement results back into the design process. Time-consuming manual procedures can thus be eliminated.

Practical Approach to Optimal Cooling System Design for a Production Line Consisting of Plastic Injection Moulding Machines in Polish Specific Climat Conditions

The paper presents and describes cooling systems mainly used in industrial plants specialized in production based on injection moulding machines. Each solution is rated taking into account investment costs, technical complexity, exploitation costs and system flexibility in general. With regard to dynamically changing law regulations linked to refrigeration installations, mainly F-Gases Act, during optimal system selection new restrictions were respected. This approach ensures long-term exploitation without additional complications. The paper contains characteristics of cooled facility, i.e. production plastic plant using injection moulding machines, presents specifics for this type of application where two extremely different cooling processes are placed in parallel. One task is heat collection from injection moulds to ensure short production time and produced details recurrence, the second is keeping hydraulic oil temperature between temperature limits – this process ensures proper oil viscosity and prevents its premature wear.