Predicting torque of worsted singles yarn using an efficient radial basis function network-based method

Abstract

The torque in single-spun yarns is an inherent property of the twisting and bending of staple fibres during the formation of yarn combined with the effect of applied tension on the yarn.The consequences of yarn torque are well known and are widely observed as yarn instability, e.g., yarn rotation under tension; local snarling and entanglement at low loads, and as distortion in fabric, i.e., edge-curl and skewing in knitted fabric. In this paper, a method for predicting the yarn torque based on the radial basis function networks is presented and evaluated. This method uses a "universal approximator" based on neural network methodology to minimize noise during training of the network and to approximate the yarn torque as a function of the geometrical and physical parameters of yarns (twist, linear density) and the applied load. The current method is an integral radial basis function network-based approach suitable for textile engineering and gives very good prediction of yarn torque across a range of yarn structural parameters and test conditions.

Application of topological conservation to model key features of zero-torque multi-ply yarns

“…The torque in spun single wool yarns depends significantly on the yarn structural parameters and the environmental conditions (Tran and Phillips, 2006b;Mitchell et al, 2006). In particular for wool yarns that are investigated in normal conditions (65% r.h., 20°C) the viscoelastic nature of wool causes several time-dependent effects.…”

Artificial Neural Networks and Their Applications in the Engineering of Fabrics

“…The prediction of the tensile properties of yarns is of main interests of the international research community. Many publications appeared dealing with the prediction of the tensile properties of the yarns under general (Ramesh et al, 1995;Guha et al, 2001;Nurwaha & Wang, 2008;Mwasiagi et al, 2008;Nurwaha & Wang, 2010) or under specific conditions, such as is the case of core spun yarns (Gharehaghaji et al, 2007), air-jet spun yarns (Zeng et al, 2004) or for the estimation of the torque of worsted yarns (Tran & Phillips, 2007). The ANN prediction method is compared with the Support Vector Machine (SVM) approach and conditions under which each method is better suited are investigated (Ghosh & Chatterjee, 2010).…”

Stationary solution of the ring-spinning balloon in zero air drag using a RBFN based mesh-free method

“…As well as the advantages mentioned in Fraser (1993), the dimensionless presentation also advantages the training process of the RBF based networks by reducing the round-off error as shown in Tran and Phillips, 2006). Here, the variables z, r and T are scaled by h, r o and 2 2 o r ρω , respectively and the dimensionless variables are given by (Batra et al, 1989a;Padfield, 1958 andFraser, 1993) …”

“…In textile engineering, neural networks have been employed to predict the properties of textile products: (Pynckels et al, 1997;Fan and Hunter, 1998;Ramesh et al, 1995;Cheng and Adams, 1995;Sette and Bouliart, 1996;Behera andMuttigi, 2004 andPhillips, 2006). Among the NN methods, the radial basis function network (RBFN) based technique has proved to be promising because it is not only able to interpolate a function but also to approximate the solution of differential equations.…”

“…Among the NN methods, the radial basis function network (RBFN) based technique has proved to be promising because it is not only able to interpolate a function but also to approximate the solution of differential equations. In this work, we will extend the application of the Integral RBFN based mesh-less method for predicting the mechanical properties of yarns (Tran and Phillips, 2006) to identify behaviour of the ring-spinning balloon. In contrast to the finite element type approximation (Lisini et al, 1994), the present method does not require any fixed connectivity to satisfy a predetermined topology (i.e.…”