面向平缝工艺信息融合的知识图谱构建方法  

Knowledge graph construction technology for provision of sewing process information

作　　者：郑小虎 刘正好 刘冰 张洁[1,2,3] 徐修亮[6] 刘希 ZHENG Xiaohu;LIU Zhenghao;LIU Bing;ZHANG Jie;XU Xiuliang;LIU Xi(Institute of Artificial Intelligence,Donghua University,Shanghai 201620,China;Engineering Research Center of Artificial Intelligence Technology in the Textile Industry,Ministry of Education,Shanghai 201620,China;Shanghai Industrial Big Data and Intelligent Systems Engineering Technology Center,Shanghai 201620,China;College of Mechanical Engineering,Donghua University,Shanghai 201620,China;Hangzhou Zhongfu Technology&Innovation Research Institute Co.,Ltd.,Hangzhou,Zhejiang311199,China;HIKARI(Shanghai)Precise Machinery Scientific&Technology Co.,Ltd.,Shanghai 201599,China;College of Information Science and Technology,Donghua University,Shanghai 201620,China)

机构地区：[1]东华大学人工智能研究院,上海201620 [2]纺织工业人工智能技术教育部工程研究中心,上海201620 [3]上海工业大数据与智能系统工程技术研究中心,上海201620 [4]东华大学机械工程学院,上海201620 [5]杭州中服科创研究院有限公司,浙江杭州311199 [6]上海富山精密机械科技有限公司,上海201599 [7]东华大学信息科学与技术学院,上海201620

出　　处：《纺织学报》2024年第4期195-203,共9页Journal of Textile Research

基　　金：中央高校基本科研业务费专项资金资助项目(2232021D-15);国家工信部项目(2021-0173-2-1);上海市科技计划项目(20DZ2251400)。

摘　　要：针对缝纫工艺流程链路长,生产要素多样,工艺知识分散化的特点,首先,提出缝纫工艺信息组织建模方法,面向多源异构平缝工艺信息构建本体模型;其次,研究基于面料力学性能的平缝工艺推荐方法,构建面料基础性能、缝制性能知识体系,结合面料层次分类方法和实验参数分析,形成力学性能参数与缝制参数之间的数学模型;在此基础上,以专家经验文本、实验测量数据为原始数据,构建面向平缝工艺信息融合的知识图谱,开发WEB系统展开应用验证。结果表明:所构建的工艺推荐方法实现了对面料平整度和最大缝缩率的预测,知识融合系统实现了缝纫工艺知识的智能搜索和缝制参数的智能推荐,为工艺数据集成、装备故障运维、工艺路线设计、产品质量控制提供决策参考。Objective The sewing process is characterized by long processing chains,diverse production elements and scattered processing information.Using knowledge graph technology for the management of design,operation and maintenance data generated during the sewing process,this research proposed a knowledge graph construction method for sewing process information management to achieve standardized knowledge representation.Method Modelling methods for the organisation of sewing process information were investigated.The process information generated during the fabric sewing process was classified,and a sewing process knowledge ontology model was established based on the classification results to realise the construction of a knowledge graph.The process recommendation method was established based on the graph.Experiments were carried out on fabric structure,fabric mechanical parameters and fabric sewing process to establish a knowledge system and to analyse the mechanical properties of fabrics before and after sewing.Based on the analysis,a regression model of fabric mechanical properties and sewing flatness and a theoretical model of fabric sewing shrinkage were established.An ontology model of the sewing parameter knowledge system was created for sewing parameter recommendation based on knowledge graph.Results According to the requirements of sewing process corpus and knowledge graph,a process recommendation method based on knowledge graph was established by combining the characteristics of industry knowledge structure and knowledge management requirements.The developed ontology and knowledge graph contains a total of 2865 entities and 52 relations,with wide knowledge coverage and strong generalization,facilitating the standardized representation of unstructured knowledge.The relationship between mechanical parameters and sewing parameters were modelled for common fabrics in the flat sewing process,the flatness of the sewn fabric and the maximum sewing shrinkage were predicted and recommendations for sewing parameters,bon

关 键 词：服装 缝纫 知识图谱 工艺知识管理 平缝工艺 知识推荐 缝制参数 

分 类 号：TS941[轻工技术与工程—服装设计与工程]