Predicting the Pilling Propensity of Fabrics through Artificial Neural Network Modeling

Abstract

Fabric pilling is affected by many interacting factors. This study uses artificial neural networks to model the multi-linear relationships between fiber, yarn and fabric properties and their effect on the pilling propensity of pure wool knitted fabrics. This tool shall enable the user to gauge the expected pilling performance of a fabric from a number of given inputs. It will also provide a means of improving current products by offering alternative material specification and/or selection. In addition to having the capability to predict pilling performance, the model will allow for clarification of major fiber, yarn and fabric attributes affecting fabric pilling.Pilling may be defined as a surface fabric fault comprising of circular accumulations of entangled fibers that cling to the fabric surface thereby affecting the appearance and handle of the fabric. The pilling of fabrics is a serious problem for the apparel industry and in particular wool knitwear fabrics [13]. It is realized that the problem of pilling is one of the biggest quality issues for the wool industry, however the problem remains.The formation of pills occurs as a consequence of mechanical action during washing or wear. Under the influence of mechanical action, loose fibers that protrude from the fabric surface entangle. Subjected to further mechanical action the entanglements develop into roughly spherical accumulation of fibers (pills) that are distinct from the fabric surface. Wear-off of pills occurs under continued abrasion from laundering, drying, etc., and during wear. For a given fabric, the degree to which pills form and wear-off is determined by the physical properties of the fiber, yarn and fabric constituents [20]. Many researchers have investigated the influence of these properties and have identified numerous factors that contribute to the pilling of wool fabrics. At the fiber level, fiber tenacity [12], diameter [6,21], length [10,19], and curvature [9,11] have been proven to impact on the rate of fuzz formation, extent of entanglement and the degree of wear off. Of the yarn parameters to affect pilling, yarn type [2] along with the degree of singles twist and/or fold twist [16] are most influential parameters. Yarn hairiness [3, 10] and yarn linear density [5] have also been shown to contribute significantly in fabric pilling. Fabric construction also plays a role in the pilling process, the tightness of the knitted construction (cover factor) impacts on the development of fuzz and pills along with the tendency for pill wear-off [11,16].Although the problem of pilling has attracted extensive research over the decades, due to the nature of pilling, the accurate modeling or prediction of the process is still elusive. Much research has gone into understanding the key factors and mechanisms responsible for pilling but failed to move beyond assessing the problem at a single particular stage of the manufacturing process. Without considering the complex interactions of the various factors at the different processing stages, the weight o...

Artificial Neural Network Prosperities in Textile Applications

“…The pilling of fabrics is a serious problem for the apparel industry and in particular wool knitwear fabrics. The formations of pills occur as a consequence of mechanical action during washing or wear (Beltran et al, 2005). The development of pills on a fabric surface, spoils the original appearance and hand, initiates garment attrition and reduces serviceability.…”

“…The correlation coefficient for training and testing samples were reported up to 0.94 and 1 respectively (Chen & Huang, 2004). Beltran et al, 2005 also used artificial neural networks to model the multi-linear relationship between fiber, yarn and fabric properties and their effect on the pilling propensity of pure wool knitted fabrics. They used key fiber (diameter, CV, diameter > 30 μm and curvature), top (Hauteur, CV, short fiber <30mm, bundle strength and strain), yarn (count, hairiness, thin and thick places, twist factor, folding twist ratio) and fabric properties (cover factor) as quantitative inputs (normalized data) along with their corresponding pilling intensities in an ANN to predict the pilling performance of knitted wool fabrics.…”

“…105 sets of randomized data were assigned to training, 20 sets were assigned for cross validation and 10 data sets were selected for testing the network. The network consisted of a single hidden layer multi layer perception trained with the error back propagation algorithm possessing hyperbolic tanh activation function in both the hidden and output layers (Beltran et al, 2005). Zhang et al, 2010 investigated an approach for fabric defect classification using radial basis function (RBF) network improved by Gaussian mixture model (GMM).…”

Artificial Neural Networks and Their Applications in the Engineering of Fabrics

“…Further on, the impact permeability has been studied (Tokarska & Gniotek, 2009) and the quality of the neural models has been assessed (Tokarska, 2006). The pilling propensity of the fabrics has been predicted (Beltran et al, 2005) and the pilling of the fabrics has been evaluated (Chen & Huang, 2004;, while the presence of fuzz fibres has been modelled (Ucar & Ertugrul, 2007). The evaluation of the wrinkle of the fabrics has been realized on an objective basis with a system based on ANNs (Su & Xu, 1999;Kim, 1999;Mori & Komiyama, 2002).…”

Prediction of Fabric Stiffness

“…Researchers have already tried to use neural networks to predict various comfort-related properties such as human sensory perceptions and overall comfort index [6][7][8].…”