Modeling of cotton yarn hairiness using adaptive neuro-fuzzy inference system

This paper reports the modeling of cotton yarn hairiness using adaptive neuro-fuzzy inference system, combining the advantages of both artificial neural network and fuzzy logic. Three cotton fibre properties, namely mean length, short fibre content and maturity, measured by the advanced fibre information system and the yarn linear density (English count, Ne) have been used as the inputs to the model. Two levels of membership function have been considered for each of the four inputs and sixteen fuzzy rules are trained. The developed model predicts the cotton yarn hairiness with average error of around 2% even in the unseen test samples. Trained fuzzy rules give good understanding about the role of various input parameters on the cotton yarn hairiness. Yarn count and cotton fibre mean length are having major role in determining the yarn hairiness. Higher cotton fibre maturity reduces the yarn hairiness.

[1]  Abhijit Majumdar,et al.  Application of linear regression, artificial neural network and neuro-fuzzy algorithms to predict the breaking elongation of rotor-spun yarns , 2005 .

[2]  Luo Cheng,et al.  Yarn Strength Prediction Using Neural Networks , 1995 .

[3]  Chang-Chiun Huang,et al.  Fuzzy Neural Network Approach to Classifying Dyeing Defects , 2001 .

[4]  M. D. Ethridge,et al.  The Prediction of Cotton Yarn Irregularity Based on the ‘AFIS’ Measurement , 1996 .

[5]  M. C. Ramesh,et al.  The Prediction of Yarn Tensile Properties by Using Artificial Neural Networks , 1995 .

[6]  Paul Kiekens,et al.  The use of neural nets to simulate the spinning process. , 1997 .

[7]  Chang-Chiun Huang,et al.  Neural-Fuzzy Classification for Fabric Defects , 2001 .

[8]  K.P.R. Pillay,et al.  A Study of the Hairiness of Cotton Yarns Part I: Effect of Fiber and Yarn Factors , 1964 .

[9]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[10]  Jujang Lee,et al.  Adaptive network-based fuzzy inference system with pruning , 2003, SICE 2003 Annual Conference (IEEE Cat. No.03TH8734).

[11]  Sundaresan Jayaraman,et al.  Analysis of the Modeling Methodologies for Predicting the Strength of Air-Jet Spun Yarns , 1997 .

[12]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[13]  J. Fan,et al.  Predicting Garment Drape with a Fuzzy-Neural Network , 2001 .

[14]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[15]  Mirela Blaga,et al.  Modelling of ring yarn unevenness by soft computing approach , 2008 .

[16]  M. Dean Ethridge,et al.  Predicting Hairiness for Ring and Rotor Spun Yarns and Analyzing the Impact of Fiber Properties , 1997 .

[17]  R. Chattopadhyay,et al.  Predicting Yarn Tenacity: A Comparison of Mechanistic, Statistical, and Neural Network Models , 2001 .

[18]  P. Majumdar,et al.  Predicting the Breaking Elongation of Ring Spun Cotton Yarns Using Mathematical, Statistical, and Artificial Neural Network Models , 2004 .

[19]  Nuray Ucar,et al.  Predicting Circular Knitting Machine Parameters for Cotton Plain Fabrics Using Conventional and Neuro-Fuzzy Methods , 2002 .

[20]  Abhijit Majumdar,et al.  Application of an adaptive neuro-fuzzy system for the prediction of cotton yarn strength from HVI fibre properties , 2005 .

[21]  Sundaresan Jayaraman,et al.  Structure and Properties of Air-Jet Spun Yarns , 1990 .