University of Twente Student Theses
Irregular Polygon Strip Packing for the Production Process Transition of the Fashion Industry
Andringa, André (2023) Irregular Polygon Strip Packing for the Production Process Transition of the Fashion Industry.
|
PDF
916kB |
| Abstract: | The fast fashion industry is widely recognised as one of the most polluting industries globally. In order to address this issue, a shift from mass production to made-to-order or made-to-measure models has emerged as a potential solution. These alternative models address overproduction by manufacturing clothing items upon order and tailoring garments to each client’s specific measurements, reducing returns. However, implementing these models in the fashion industry brings forth new challenges in the production process, particularly in generating marker files for pattern placement on fabric. Existing algorithms used for pattern placement optimisation can take days to converge, which poses a significant problem for unique garment production. In this paper, I propose two improvements to the sliding no-fit polygon generation algorithm, significantly enhancing its speed. Additionally, I introduce a novel ordering heuristic that improves efficiency and serves as a partial seed for the genetic algorithm and Q-learning. Furthermore, I propose a hybrid placement heuristic that prioritises border placement and then switches to the bottom-left strategy, resulting in improved packing efficiency. In conclusion, my advancements offer promising results for addressing the challenges of made-to-order and made-to-measure in the fashion industry and can contribute to reducing waste and improving sustainability. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Awards: | Best Paper Award |
| Link to this item: | https://purl.utwente.nl/essays/96123 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page