Adaptive Neuro-fuzzy Inference System-based Modelling of Cotton Yarn Properties

In this paper, an adaptive neuro-fuzzy inference system (ANFIS) is developed for effective prediction of yarn tenacity and unevenness based on a set of six input cotton fibre properties, i.e. fibre strength, fibre elongation, upper half mean length, uniformity index, fineness and short fibre content. The ANFIS model integrates the advantageous features of both the systems of fuzzy control and neural network. A neural network is applied with learning and computational capability in fuzzy control. On the other hand, fuzzy control provides high level of knowledge and fuzzy rules for use in the neural network. Using a past experimental dataset, the developed ANFIS model is trained and subsequently tested to envisage yarn tenacity and unevenness values. Its prediction performance is validated with respect to five statistical metrics, i.e. correlation coefficient, mean absolute percentage error, root-mean-square error, coefficient of efficiency and variance performance index, and is also contrasted against other prediction tools, like multivariate regression analysis, artificial neural network, fuzzy logic and support vector machine. Based on their acceptable values, it can be concluded that the ANFIS models can be effectively employed for prediction of diverse yarn quality characteristics while treating fibre properties as the input variables.

[1]  Anindya Ghosh,et al.  Prediction of cotton yarn properties using support vector machine , 2010 .

[2]  Chongwen Yu,et al.  The Performance of Data Mining Techniques in Prediction of Yarn Quality , 2013 .

[3]  Abhijit Majumdar,et al.  Modeling of cotton yarn hairiness using adaptive neuro-fuzzy inference system , 2010 .

[4]  Rocco Furferi,et al.  Yarn Strength Prediction: A Practical Model Based on Artificial Neural Networks , 2010 .

[5]  Vali Derhami,et al.  Yarn tenacity modeling using artificial neural networks and development of a decision support system based on genetic algorithms , 2014 .

[6]  Reza Teimouri,et al.  Application of Taguchi, ANFIS and grey relational analysis for studying, modeling and optimization of wire EDM process while using gaseous media , 2014 .

[7]  R. Chattopadhyay,et al.  Artificial neural networks in yarn property modeling , 2011 .

[8]  Abhijit Majumdar,et al.  SELECTING COTTON BALES BY SPINNING CONSISTENCY INDEX AND MICRONAIRE USING ARTIFICIAL NEURAL NETWORKS , 2004 .

[9]  Shankar Chakraborty,et al.  A Grey Fuzzy Logic Approach for Cotton Fibre Selection , 2017 .

[10]  Chokri Cherif,et al.  Prediction of Blended Yarn Evenness and Tensile Properties by Using Artificial Neural Network and Multiple Linear Regression , 2016 .

[11]  Alireza Fallahpour,et al.  Yarn Strength Modelling Using Adaptive Neuro-Fuzzy Inference System (ANFIS) and Gene Expression Programming (GEP) , 2013 .

[12]  Sherien El-Kateb,et al.  Yarn Tensile Properties Modeling Using Artificial Intelligence , 2020 .

[13]  Xin Hou Wang,et al.  Using Intelligent Control Systems to Predict Textile Yarn Quality , 2012 .

[14]  Rızvan Erol,et al.  Comparison of the neural network model and linear regression model for predicting the intermingled yarn breaking strength and elongation , 2014 .

[15]  M. E. Üreyen,et al.  The Prediction of Cotton Ring Yarn Properties from AFIS Fibre Properties by Using Linear Regression Models , 2007 .

[16]  Anindya Ghosh,et al.  Yarn engineering using hybrid artificial neural network-genetic algorithm model , 2013, Fibers and Polymers.

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

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

[19]  Sami Ekici,et al.  An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM , 2009, Expert Syst. Appl..

[20]  Esmaeil Hadavandi,et al.  A Grey Wolf Optimizer-based neural network coupled with response surface method for modeling the strength of siro-spun yarn in spinning mills , 2018, Appl. Soft Comput..

[21]  Ahmet Çay,et al.  Artificial Neural Networks and Their Applications in the Engineering of Fabrics , 2010 .

[22]  Anindya Ghosh,et al.  Yarn Strength Modelling Using Genetic Fuzzy Expert System , 2012 .

[23]  Anindya Ghosh,et al.  Yarn Strength Modelling Using Fuzzy Expert System , 2008 .

[24]  C.-Y. Liu,et al.  Analysis and application of the adaptive neuro-fuzzy inference system in prediction of CMP machining parameters , 2003, Int. J. Comput. Appl. Technol..

[25]  Jianguo Yang,et al.  Application of Genetic Algorithm-Support Vector Machine for Prediction of Spinning Quality , 2011 .