A Data-driven Reduced Order Modeling Approach Applied In Context Of Numerical Analysis And Optimization Of Plastic Profile Extrusion

2022/09/07 by Daniel Hilger, Hilger, Daniel, Norbert Hosters +1
Engineering · #65N30 #65Z99 #FOS: Computer and information sciences #FOS: Mathematics #G.1.8 #Granular flow and fluidized beds #I.2.1 #I.6.3 #Machine Learning (cs.LG) #Metallurgy and Material Forming #Numerical Analysis (math.NA) #Powder Metallurgy Techniques and Materials

paper · pdf · doi:10.48550/arxiv.2209.03121

openalex publication_date 2022/09/07 · openalex created_date 2022/09/30 · openalex updated_date 2026/07/28

Abstract

In course of this work, we examine the process of plastic profile extrusion, where a polymer melt is shaped inside the so-called extrusion die and fixed in its shape by solidification in the downstream calibration unit. More precise, we focus on the development of a data-driven reduced order model (ROM) for the purpose of predicting temperature distributions within the extruded profiles inside the calibration unit. Therein, the ROM functions as a first step to our overall goal of prediction based process control in order to avoid undesired warpage and damages of the final product.

Related

• Standardized Non-Intrusive Reduced Order Modeling Using Different Regression Models With Application to Complex Flow Problems
• Modeling and simulation for varying die gap fluid extrusion
• Pressure drop non-linearities in material extrusion additive manufacturing: a novel approach for pressure monitoring and numerical modeling
• Quasi-1D Modeling of Polymer Melt Die Swell in Short Dies
• Cross-scale Modeling of Polymer Topology Impact on Extrudability through Molecular Dynamics and Computational Fluid Dynamics