Evolutionary search for optimal combinations of markers in clothing manufacturing

Optimizing combinations of placements of parts, known as markers, is an important preparatory step in order-based industrial production of clothes. Given a work order in the form of a matrix of pieces in size numbers and designs, the task is to find a list of combinations of size numbers to complete the work order. The outcome of this step influences the number of cut out pieces, the amount of material used in the production phase, and the speed of the work order processing. The optimization task is demanding since a number of factors affect production costs and several conflicting criteria can be involved in marker assessment. We consider minimum number of markers per work order as an optimization criterion and transform the problem into the knapsack problem which is then solved with several variants of an evolutionary algorithm. Numerical experiments are performed on real problem instances from industrial clothes production and the results compare favorably with those produced by the algorithm regularly used in practice.