Predicting the tensile strength of polyester/viscose blended open-end rotor spun yarns using artificial neural network and statistical models


Erdem K., Yürek O.

Industria Textila, vol.62, no.2, pp.81-87, 2011 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 62 Issue: 2
  • Publication Date: 2011
  • Journal Name: Industria Textila
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.81-87
  • Keywords: Artificial neural network, Blend, OE-rotor spinning, Polyester, Simplex lattice design, Tensile strength, Viscose
  • Erciyes University Affiliated: Yes

Abstract

In this study, an Artificia Neural Network (ANN) and a statistical model were developed to predict the tensile strength of polyester/viscose blended open-end rotor spun yarns. Seven different blend ratios of polyester/viscose slivers were produced and these slivers are manufactured with four different rotor speed and four different yarn counts in the rotor spinning machine. A Back Propagation Multi Layer Perception (MLP) network and a mixture process crossed regression model with two mixture components (polyester and viscose blend ratios) and two process variables (yarn count and rotor speed) were developed to predict the tensile properties of polyester/viscose blended open-end rotor spun yarns. In conclusion, both ANN, and the statistical model have given satisfactory predictions; however, the predictions of ANN gave relatively more reliable results than those of the statistical models. Since the prediction capacity of statistical models is also obtained as satisfactory, it can also be used for the strength prediction of yarns, because of its simplicity and non-complex structure.