Canonical Genetic Algorithm To Optimize Cut Order Plan Solutions in Apparel Manufacturing

In practice, cutting large number of pieces with different shapes often requires a well plan of assigning number of shapes on the cut template. The working arrangement of the cut-template is treated as Cut order plan (COP). The aim is to optimize cutting templates of fabric cutting function in apparel manufacturing firms when the cut order requirement is known. This solving of cut order plan problem is usually a tedious procedure so a signi ficant amount of arithmetic operations are required if conventional heuristic algorithms being used. However, optimization of COP solutions is not guaranteed by the conventional heuristics. This study presents a canonical genetic algorithm (CGA) approach to the problems of cut order planning with the objective of finding the optimum size ratios for each cut template used to fulfill the cut order requirement. General CGA techniques were used to achieve better solutions under a self-tuning attached to the proposed algorithm. Several cut order cases were employed to justify the performance of the proposed approach. Experimental results indicated that the proposed method can yield better solutions compared to the available methodologies of generating cut-order plans available in apparel industry.