engleski

Automatic marker making method for apparel industry

Marker making is an optimization problem, where a set of cutting parts need to be placed on a marker so that the cutting parts do not overlap, and do not exceed the boundaries of a marker. Objective: The aim of the research was to develop an algorithm that would be able to perform with any type of marker and cutting parts shape. Method: In this research novel, raster inspired heuristics: Grid, Grid-BLP and Grid-Shaking have been introduced and hybridized with genetic algorithm. An All Equal First (AEF) placement order has been introduced that places equal groups of cutting parts together in a lay plan. Results: The implementation and experiments were conducted in MATLAB using GEATbx toolbox on five datasets from textile industry: ALBANO, DAGLI, MAO, MARQUES and MAN SHIRT. The best marker utilization of 79.07%, 75.06%, 74.71%, 79.21% and 84.37% has been obtained for the datasets respectively. Conclusions: The Grid-BLP and Grid-Shaking heuristics outperform the Grid heuristics, with Grid-Shaking obtaining the best results. AEF order has positive impact on marker utilization

lay planning, marker making, genetic algorithm, production optimization

nije evidentirano