Use of Artificial Neural Networks for Modelling the Drape Behaviour of Woollen Fabrics Treated with Dry Finishing Processes

The relationship between fabric drape, low stress mechanical properties and finishing processes is relatively complex. This paper demonstrates the possibility of using artificial neural networks to identify the fabric drape of woollen fabrics treated with different dry fin ishing processes (stenter, decatising, superfinish, formula, KADE strong/weak - autoclave decatizing). The mechanical and surface properties of woollen fabrics were measured by both the KES-FB and FAST systems, and then the results obtained were applied to artifi cial neural network (ANN) modelling. ANN models were compared by verifying the Mean Square Error (MSE) and Correlation coefficient (R-value). The results indicated that each model is capable of making quantitatively accurate drape behaviour predictions for wool fabrics (Rmin = 0.92, MSEmin = 0).

[1]  S. Lewandowski,et al.  Prediction of Properties of Unknotted Spliced Ends of Yarns Using Multiple Regression and Artificial Neural Networks. Part 2, Verification of Regression Models , 2008 .

[2]  A. G. De Boos,et al.  Appendix B – SiroFAST – fabric assurance by simple testing* , 2005 .

[3]  Jinlian Hu,et al.  Structure and Mechanics of Woven Fabrics , 2004 .

[4]  Harumi Morooka,et al.  Relation between Drape Coefficients and Mechanical Properties of Fabrics , 1976 .

[5]  M. Shanbeh,et al.  Analysis of Two Modeling Methodologies for Predicting the Tensile Properties of Cotton-covered Nylon Core Yarns , 2007 .

[6]  Faouzi Sakli,et al.  Prediction of fabric drape using the FAST system , 2007 .

[7]  Chokri Cherif,et al.  Use of Artificial Neural Networks for Determining the Leveling Action Point at the Auto-leveling Draw Frame , 2008 .

[8]  Suzaini Abdul Ghani.  Seam performance: Analysis and Modelling , 2011 .

[9]  Asimananda Khandual,et al.  Prediction of drape profile of cotton woven fabrics using artificial neural network and multiple regression method , 2011 .

[10]  Omer Berk Berkalp,et al.  Investigation of the Mechanics and Performance of Woven Fabrics Using Objective Evaluation Techniques. Part I: The Relationship Between FAST, KES-F and Cusick's Drape-Meter Parameters , 2010 .

[11]  Kazim Yildiz,et al.  Use of Artificial Neural Networks for Modelling of Seam Strength and Elongation at Break , 2013 .

[12]  Billie J. Collier,et al.  Drape Prediction by Means of Finite-element Analysis , 1991 .

[13]  I. Frydrych,et al.  Mechanical fabric properties influencing the drape and handle , 2000 .

[14]  Darko Golob,et al.  Determination of Pigment Combinations for Textile Printing Using Artificial Neural Networks , 2008 .

[15]  Abstr Act,et al.  Analysis and modelling , 2007 .

[16]  D. Bhattacharjee,et al.  A Neural Network System for Prediction of Thermal Resistance of Textile Fabrics , 2007 .

[17]  Xungai Wang,et al.  An Artificial Neural Network-based Hairiness Prediction Model for Worsted Wool Yarns , 2009 .

[18]  Herbert Barndt,et al.  THE USE OF KES AND FAST INSTRUMENTS: IN PREDICTING PROCESSABILITY OF FABRICS IN SEWING , 1990 .

[19]  Analysing the Effect of Decatising on the Frictional Properties of Wool Fabrics , 2014 .

[20]  Pin-Ning Wang,et al.  A Comparison of the Key Parameters Affecting the Dynamic and Static Drape Coefficients of Natural-Fibre Woven Fabrics by a Newly Devised Dynamic Drape Automatic Measuring System , 2007 .

[21]  P. Gendarz,et al.  Analysis and modelling , 2009 .

[22]  John W. S. Hearle,et al.  Analysis of Drape by Means of Dimensionless Groups , 1986 .

[23]  George Stylios.  Textile objective measurement and automation in garment manufacture , 1991 .

[24]  Nuray Ucar.  Prediction of Fuzz Fibers on Fabric Surface by Using Neural Network and Regression Analysis , 2007 .

[26]  Ezzatollah Haghighat,et al.  Study of the Hairiness of Polyester-Viscose Blended Yarns. Part III - Predicting Yarn Hairiness Using an Artificial Neural Network , 2012 .

[27]  SiroFAST Fabric Assurance by Simple Testing , 2001 .