Ajou University repository

Two-dimensional polygon classification and pairwise clustering for pairing in ship parts nesting
Citations

SCOPUS

4

Citation Export

DC Field Value Language
dc.contributor.authorNa, Gun Yeol-
dc.contributor.authorYang, Jeongsam-
dc.date.issued2024-10-01-
dc.identifier.issn1572-8145-
dc.identifier.urihttps://aurora.ajou.ac.kr/handle/2018.oak/33620-
dc.identifier.urihttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85168967684&origin=inward-
dc.description.abstractIn the shipbuilding industry, nesting is arranging the cutting patterns of ship parts to increase the utilization rate of steel sheets and reduce the scrap rate. The nesting complexity is high because of the large number of ship parts with complex shapes and various sizes. Arrangement algorithms for minimizing steel-sheet wastage cannot be readily applied to nesting without pairing the two parts to reduce the nesting complexity because of the considerable computation time involved. This study proposes a pairing method to reduce nesting complexity. Ship parts were classified, and pairwise clustering was applied for pairing. A method in which a deep neural network architecture learns polygons without rasterization for classifying ship parts and a method for pairing ship parts of different shapes for pairwise clustering were proposed. Using 265 actual ship parts, the proposed method was compared with pairing methods involving shape-based matching algorithms currently employed by shipbuilding companies. Subsequently, 82 more parts were paired, and the average pairing time, arrangement time, and scrap rate decreased by 44.1%, 47.5%, and 11.0%, respectively. Pairing based on deep learning classifiers and pairwise clustering can rapidly and accurately pair ship parts, thereby improving nesting efficiency.-
dc.description.sponsorshipFunding was supported by Ministry of Trade, Industry and Energy, 20011164.-
dc.description.sponsorshipThis work was supported by the \u2018Autonomous Ship Technology Development Program (20011164, Development of Performance Monitoring and Failure Prediction and Diagnosis Technology for Engine System of Autonomous ships)\u2019 funded by the Ministry of Trade, Industry & Energy(MOTIE, Korea).-
dc.language.isoeng-
dc.publisherSpringer-
dc.subject.mesh2d polygon classification-
dc.subject.meshCutting plan-
dc.subject.meshDeep learning-
dc.subject.meshIrregular strip packing problem-
dc.subject.meshNesting problem-
dc.subject.meshPairing-
dc.subject.meshPairing method-
dc.subject.meshPairwise clustering-
dc.subject.meshScrap rate-
dc.subject.meshStrip packing problem-
dc.titleTwo-dimensional polygon classification and pairwise clustering for pairing in ship parts nesting-
dc.typeArticle-
dc.citation.endPage3184-
dc.citation.number7-
dc.citation.startPage3169-
dc.citation.titleJournal of Intelligent Manufacturing-
dc.citation.volume35-
dc.identifier.bibliographicCitationJournal of Intelligent Manufacturing, Vol.35 No.7, pp.3169-3184-
dc.identifier.doi10.1007/s10845-023-02196-z-
dc.identifier.scopusid2-s2.0-85168967684-
dc.identifier.urlhttps://www.springer.com/journal/10845-
dc.subject.keyword2D polygon classification-
dc.subject.keywordCutting plan-
dc.subject.keywordDeep learning-
dc.subject.keywordIrregular strip packing problem-
dc.subject.keywordNesting problem-
dc.subject.keywordPairing-
dc.type.otherArticle-
dc.identifier.pissn0956-5515-
dc.description.isoafalse-
dc.subject.subareaSoftware-
dc.subject.subareaIndustrial and Manufacturing Engineering-
dc.subject.subareaArtificial Intelligence-
Show simple item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Yang, Jeongsam Image
Yang, Jeongsam양정삼
Department of Industrial Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.