Prediction of Polyester/Cotton Ring Spun Yarn Unevenness Using Adaptive Neuro Fuzzy Inference System

Authors

  • Samson Rwawiire Busitema University
  • Allan Kasedde Busitema University
  • Ildephonse Nibikora Busitema University
  • George Wandera Busitema University

Abstract

Yarn produced from a series of experiments carried out at Southern Range Nyanza Limited (SRNL) in Jinja – Uganda was used in developing an Adaptive Neuro-Fuzzy Inference System (ANFIS) model to probe the yarn unevenness of a polyester/cotton (65:35) blend. Blending was carried out at the draw frame. Parameters which are functions of yarn unevenness such as yarn count, spindle speeds and yarn twist were used as inputs for the ANFIS model. Coefficient of Variation (CV%) was used as a measure of yarn unevenness, the output of the model. The model had an R-square (R2) of 0.86, Root mean square error (RMSE) of 0.65 and SSE of 10.86, therefore rending the ANFIS model a success and superior to linear regression methods in predicting polyester/cotton yarn unevenness.

Author Biographies

  • Samson Rwawiire, Busitema University
    Textile and Ginning Engineering
  • Allan Kasedde, Busitema University
    Textile and Ginning Engineering
  • Ildephonse Nibikora, Busitema University
    Textile and Ginning Engineering
  • George Wandera, Busitema University
    Textile and Ginning Engineering

Downloads

Published

2014-05-23

Issue

Vol. 8 No. 4 (2014)

Section

Peer Reviewed Article

License

By submitting a manuscript, the authors agree that the copyright of all materials published in Journal of Textile and Apparel Technology and Management (JTATM) is transferred to the publisher if and when their manuscript is accepted for publication. Please note the following details as an understanding for submitting a manuscript to JTATM for publication.
Authors grant rights to JTATM to disseminate the paper and its contents as a file on the Internet when the paper is accepted. JTATM owns an exclusive right for the paper until it is either rejected or published. The authors cannot submit the same paper in part or in its entirety to another journal during the review.
Authors retain rights to be identified as the authors when the paper is published, and the patent right or rights relating to products or processes described in the paper. The authors retain rights to the educational and research uses of the paper, such as teaching and exchange of the published or pre-publication version of the paper with colleagues, for non-commercial purposes. The authors may obtain permission from the journal for a non-exclusive use of the contents in the paper, such as tables, figures and texts, with a proper acknowledgement to the journal.
Authors must warrant the originality of the paper in that the contents of the paper in part or in full have not been published or submitted elsewhere while the paper is under review.
Effective date for the above policies is December 1, 2010. The authors of the papers published before this date will be contacted via email for copyright transfer agreements.