Artificial neural network approach for predicting colour properties of laser-treated denim fabrics

In this study, artificial neural network (ANN) and linear regression (LR) approaches are proposed for predicting colour properties of laser-treated denim fabrics. Denim fabrics were treated under different combinations of laser processing parameters, including pixel time (μs), resolution (dot per inch) and grayscale (lightness percentage) as inputs. Colour properties, including colour yield (K/S sum value), CIE L*, a* and b* values and yellowness index were predicted as outputs in these approaches. Later, the prediction performances of two approaches were compared and the statistical findings revealed that ANN approach was able to provide more accurate prediction than LR approach, especially for L value. Moreover, among the three input variables, grayscale (lightness percentage) was found to be the most important factor affecting colour properties of laser-treated denim fabrics.

[1]  Bin Gang Xu,et al.  An Artificial Neural Network Model for the Prediction of Spirality of Fully Relaxed Single Jersey Fabrics , 2009 .

[2]  Murat Tarhan,et al.  A Comparison Among Performance Characteristics of Various Denim Fading Processes , 2009 .

[3]  Chi-wai Kan,et al.  Using artificial neural network to predict colour properties of laser-treated 100% cotton fabric , 2011 .

[4]  M. Senthilkumar,et al.  Achieving expected depth of shade in reactive dye application using artificial neural network technique , 2006 .

[5]  Traian Dascalu,et al.  Removal of the indigo color by laser beam–denim interaction , 2000 .

[6]  Halbert White,et al.  Artificial Neural Networks: Approximation and Learning Theory , 1992 .

[7]  R. Ogulata,et al.  Prediction of CIELab data and wash fastness of nylon 6,6 using artificial neural network and linear regression model , 2008 .

[8]  Magdalena Tokarska,et al.  Neural Model of the Permeability Features of Woven Fabrics , 2004 .

[9]  R. Tuğrul Oğulata,et al.  Prediction of the changes on the CIELab values of fabric after chemical finishing using artificial neural network and linear regression models , 2009 .

[10]  Sofia E. Acosta-Ortiz,et al.  A comparison between characteristics of various laser-based denim fading processes , 2003 .

[11]  Y. Guo,et al.  Structural characteristics of low torque and ring spun yarns , 2011 .

[12]  Nuray Ucar,et al.  Predicting Bursting Strength of Cotton Plain Knitted Fabrics Using Intelligent Techniques , 2000 .

[13]  Arif Taner Özgüney,et al.  The comparison of laser surface designing and pigment printing methods for the product quality , 2007 .

[14]  Yong Yu,et al.  Intelligent Fabric Hand Prediction System With Fuzzy Neural Network , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[15]  Paul Kiekens,et al.  Use of Neural Nets for Determining the Spinnability of Fibres , 1995 .

[16]  Bin Gang Xu,et al.  Structure and Properties of Low Twist Short-staple Singles Ring Spun Yarns , 2007 .

[17]  Yih-Fang Huang,et al.  Bounds on the number of hidden neurons in multilayer perceptrons , 1991, IEEE Trans. Neural Networks.

[18]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.