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

TL;DR

This paper develops a data-driven reduced order model to predict temperature distributions in plastic profile extrusion, aiming to improve process control and reduce defects.

Contribution

It introduces a novel ROM approach specifically tailored for temperature prediction in plastic extrusion, enhancing process control capabilities.

Findings

ROM accurately predicts temperature distributions

Improves process control for plastic extrusion

Reduces risk of warpage and damage

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.