SUPERCRITICAL FLUID DOSAGE CONTROL USING ARTIFICIAL NEURAL NETWORK (ANN) FOR MICROCELLULAR INJECTION MOLDING

摘要

Supercritical fluid (SCF) dosage is one of the most important parameters for microcellular injection molding. Highly accurate and repeatable SCF dosage is required to ensure high part quality and consistency. In this study, an artificial neural network (ANN) based SCF dosage control strategy was proposed to predict and compensate for the possible variations in the coming SCF dosing stage to achieve a more repeatable SCF dosage. The result shows that this control strategy can be successfully implemented, and that it leads to significant improvements in dosage consistency and part quality.