Deakin University
Browse

File(s) under permanent embargo

Predicting the pilling tendency of wool knits

Version 2 2024-06-13, 07:42
Version 1 2014-10-27, 16:33
journal contribution
posted on 2024-06-13, 07:42 authored by R Beltran, L Wang, X Wang
This work investigates the application of artificial neural network modeling (ANN) to model the relationships between fiber, yarn, and fabric properties and the pilling propensity of single jersey and rib pure wool knitted fabrics based on the ICI Pilling Box method. Validation of the model on an independent validation data set suggests that the accurate prediction of pilling propensity is possible with the best performing model achieving a correlation with the subjectively rated pilling grades of approximately 85%. Importantly, it is also illustrated that a larger training set can lead to a marked improvement in the accuracy of predictions.

History

Journal

Journal of the Textile Institute

Volume

97

Pagination

129-136

Location

Manchester, England

ISSN

0040-5000

eISSN

1754-2340

Language

eng

Publication classification

C1 Refereed article in a scholarly journal

Copyright notice

2006, Taylor & Francis

Issue

2

Publisher

Taylor & Francis