Multi Objective Optimization of Yarn Quality and Fibre Quality Using Evolutionary Algorithm

The quality and cost of resulting yarn play a significant role to determine its end application. The challenging task of any spinner lies in producing a good quality yarn with added cost benefit. The present work does a multi-objective optimization on two objectives, viz. maximization of cotton yarn strength and minimization of raw material quality. The first objective function has been formulated based on the artificial neural network input–output relation between cotton fibre properties and yarn strength. The second objective function is formulated with the well known regression equation of spinning consistency index. It is obvious that these two objectives are conflicting in nature i.e. not a single combination of cotton fibre parameters does exist which produce maximum yarn strength and minimum cotton fibre quality simultaneously. Therefore, it has several optimal solutions from which a trade-off is needed depending upon the requirement of user. In this work, the optimal solutions are obtained with an elitist multi-objective evolutionary algorithm based on Non-dominated Sorting Genetic Algorithm II (NSGA-II). These optimum solutions may lead to the efficient exploitation of raw materials to produce better quality yarns at low costs.

[1]  Arindam Basu,et al.  Relationship between USDA calibration cotton properties and yarn strength/unevenness , 2004 .

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

[3]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[4]  DebK.,et al.  A fast and elitist multiobjective genetic algorithm , 2002 .

[5]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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

[7]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[8]  Stefan Sette,et al.  The Use of Neural Nets to Predict Yarn Tensile Properties , 1996 .

[9]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[10]  Kalyanmoy Deb,et al.  MULTI-OBJECTIVE FUNCTION OPTIMIZATION USING NON-DOMINATED SORTING GENETIC ALGORITHMS , 1994 .

[11]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[12]  Ivo F. Sbalzariniy,et al.  Multiobjective optimization using evolutionary algorithms , 2000 .

[13]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[14]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[15]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[16]  Anindya Ghosh,et al.  Modelling, optimization and decision making techniques in designing of functional clothing , 2011 .

[17]  Lieva Van Langenhove,et al.  Optimising the Fibre-to-Yarn Production Process: Finding a Blend of Fibre Qualities to Create an Optimal Price/Quality Yarn. , 2002 .

[18]  Abhijit Majumdar,et al.  Prediction of single yarn tenacity of ring-and rotor-spun yarns from HVI results using artificial neural networks , 2004 .