pps proceeding - Abstract Preview
pps proceeding
Symposium: S10 - Injection Molding
Oral Presentation
 
 

Artificial neural networks to model formulation-property-connections in the process of inline-compounding on an injection moulding machine

Moritzer Elmar (1), Martin Yannick (1)*, Müller Ellen (1), Kleeschulte Rainer (2)

(1) Polymer Engineering Paderborn - Paderborn - Germany, (2) K-Lab - Paderborn - Germany

Today the global market poses great challenges for the industrial product development. Complexity, diversity of variants, flexibility and individuality are only some of the features the products have to fulfil today. Additionally, the product series have shorter life times. Because of their high capacity for adaption, polymers are increasingly able to substitute traditional materials such as wood, glass and metals out of various fields of application. But the polymers are only able to substitute other materials, if they are optimally suited for the specific applications. So a product specific material development is more and more important. The integration of the compounding step into the injection moulding process leads to a more efficient and faster development process of a new polymer formulation which results in the opportunity to create new product specific materials. This process is called inline-compounding on an injection moulding machine. The entire process sequence is supported by software from Bayer Technology called Product Design Workbench, which provides assistance for all the individual steps from data management, via analysis and model compilation, right through to the optimization of the formulation and the design of experiments. The software is based on artificial neural networks and can model the formulation-property-connections to realize for example optimizations of different formulations. In the presented study the workflow and the modelling by means of the software are presented.