Using Neural Network Theory to Predict the Properties of Melt Spun Fibers

Abstract

Melt spinning is the most economically useful method for producing artificial fibers in the industry. Though the extruder screw speed, the gear pump gear speed, and the winder winding speed of the melt spinning system are the main factors affecting the tensile strength of as-spun fibers and the yarn count (denier), no mathematical model has been proposed to describe the cause and effect of these relations. In this paper, using neural network theory, we consider the extruder screw speed, gear pump gear speed, and winder winding speed of a melt spinning system as the inputs and the tensile strength and yam count of as-spun fibers as the outputs. The data from the experiments are used as learning information for the neural network to establish a reliable prediction model that can be applied to new projects, and the model's performance is verified.