Prediction of Bursting Strength and Pilling Rating of Three Thread Fleece Fabric Using Artificial Neural Network
Abstract
Rabiul Islam,
Md. Arman Islam, Jobaidur Rahman Jisan, Ahmed Muhiminul Haider, Al-Muntasir* Department of
Industrial & Production Engineering, Bangladesh University of Textiles. Corresponding
Author: muntasir9513@gmail.com.
In this work, the bursting strength and
pilling rating of polyester-cotton fiber-blended three-thread fleece fabric were
predicted using an artificial neural network (ANN) back propagation (BP) model.
Bursting strength and pilling were predicted from 50 three-thread fleece fabrics with different stitch lengths, grams per square meter
(GSM), yarn counts,
and twists per inch. All three-thread fleece fabrics have their own bursting strength and pilling rate, which were used for the prediction.
To validate the two models in the training steps, training precision, and
simulation precision, 40 fabrics were used for training and 10 fabrics were
used for testing, and the predicted pilling property was obtained. The results
show that the predicted values of bursting strength and pilling rating were closer to the
experimental values, which are determined by the ANN backpropagation (BP)
model. This study shows that an optimized model with BP can predict the
bursting strength and pilling rating of polyester–cotton three-thread fleece
fabrics with acceptable accuracy.
Georgia Reader Reply
Et rerum totam nisi. Molestiae vel quam dolorum vel voluptatem et et. Est ad aut sapiente quis molestiae est qui cum soluta. Vero aut rerum vel. Rerum quos laboriosam placeat ex qui. Sint qui facilis et.