Estimation of Areal Weight, Grab Tensile Strength, and Elongation at Break of PP Spunbond Nonwovens using Digital Image Analysis and Artificial Neural Networks

Abstract

Polypropylene (PP) spunbond nonwoven fabrics are very important especially for health, furniture, and household industries. These industrial applications require fabrics with high tensile strength properties. In the textile industry, Digital Image Analysis (DIA) is used commonly on fabric property determination and online controlling. The estimation of fabric weight using digital image analysis is well established in the literature. But limited information can be found about the prediction of grab tensile strength and elongation at break using Digital Image Analysis (DIA). In this study, DIA and Artificial Neural Network (ANN) are used for the prediction of areal weight, tensile strength and elongation at break values of PP nonwoven fabrics at various weights (12g/m2, 20g/m2, 25g/m2, 30g/m2, 50g/m2). The experimentally tested fabric properties and the numerical defined statistical parameters obtained from DIA are related with each other using ANN. Results show that ANN is capable of prediction of fabric material properties by using data obtained by DIA without any experiments for the investigated type of PP nonwovens.