Optimal Cut Order Planning Solutions using Heuristic and Meta-Heuristic Algorithms: A Systematic Literature Review

Abstract

Cut order planning is a significant task in the apparel industry which determines the fabric spreading layout that can affect different aspects of the apparel industry including the cost of garments, the efficiency of the sewing line, etc. Due to the nature of the cut order problem, it is very hard to determine an optimal solution for the cut order plan although there are ready-made software and also industry experts working on this. Hence, various attempts have been made to optimize it by using machine learning algorithms in the modern world. This review aims at identifying how heuristic and meta-heuristic algorithms are used to optimize the cut-order planning solutions to obtain a near-optimal solution. Furthermore, the lack of research limits it down to 13 papers to be reviewed, and this paper discusses the methodologies and algorithms used, research parameters, issues, and future areas that need to be investigated for the cut order problem. The review shows that the genetic algorithm is widely used to optimize the cut-order plans by adopting the hybridization approaches along with some other meta-heuristic algorithms such as simulated annealing, tabu search, etc. Experimental results indicate that researchers were able to minimize fabric waste by optimizing the cut order plans.