Decision Support System for Cotton Bales Blending Using Genetic Algorithm

Abstract

Traditionally the commercial value of cotton is accessed on the basis of subjective grading. The grade of cotton is decided on the basis of color, trash and ginning preparation, staple length and strength. Characteristics like length variation, fineness and maturity are also taken into account.[14] It is necessary for the cotton spinning mills to produce good quality yarn and that too at a competitive price. The cost and quality of yarn is greatly dependent on the cost and quality of cotton. So, wise selection of cotton and control on the cost at different stages of spinning, weaving, processing and marketing is very essential. It is a common practice in textile mills to mix cottons of different varieties. Hence, it is imperative to select the right cottons for the same, since it is one of the major factors affecting the total yarn cost as well as the final yarn quality. The objective of this research is to design a decision support system which will optimize the cotton bales blending/mixing so as to reduce the cost of overall cotton cost subject to quality constraint. This paper presents a method of optimization based on genetic algorithms. The Genetic Algorithms are a versatile tool, which can be applied as a global optimization method to problems of mixing, because they are easy to implement to non-differentiable functions and discrete search spaces.[13] The test runs were performed with minimal attention to tuning of the genetic algorithm parameters. In most cases, better performance is possible simply by running the algorithm longer or by varying the selection method, population size or mutation rate.