Prediction of Fiber Diameter of Melt Blown Nonwovens Produced by Dual Slot Annular Die from Process Parameters by Intelligent Techniques and Empirical Models

摘要

The objective of this work is to develop artificial neural network models for the prediction of fiber diameter of melt blowing nonwovens and to compare the performance of ANN models with empirical models based on regression analysis. The processing parameters (polymer flow rate,polymer melt temperature,initial air velocity,die-to-collector distance and initial air temperature) werernalso selected as input variables. Following the developed ANN models, sensitivity analysis results and coefficient of multiple determination values of ANN and empirical models were compared. Analyses are showed that ANN models improve the prediction performance with regards to empirical models. The results also reveal that the artificial neural network produces more accurate and stable predictions than the empirical model.This study demonstrates that neural network is a useful tool for development of prediction models. The results also show great perspective of this research in the field of computerrnassisted design of melt blowing technology.