Predicting the Properties of Needlepunched Nonwovens Using Artificial Neural Network

摘要

Needlepunching is a well-known nonwoven process of converting fibrous webs into self-locking or coherent structures using barbed needles. In this study, Artificial Neural Network (ANN) modeling technique has been used to predict the bulk density and tensile properties of needlepunched nonwoven structures by relating them with the main process parameters, namely, web area density, punch density, and depth of needle penetration. The simultaneous effect of more than one parameter on bulk density and tensile properties of needlepunched nonwoven structures have been investigated based upon the results of trained ANN models. A comparison is also made between the experimental and predicted values of fabric bulk density and tensile strength in the machine and crossmachine directions in unseen or test data sets. It has been inferred that the ANN models have achieved good level of generalization that is further ascertained by the acceptable level of mean absolute error obtained between predicted and experimental results.