【作者】 王俊；

【导师】 方喜峰；

【作者基本信息】 江苏科技大学 ， 机械工程（专业学位）， 2018， 硕士

【摘要】 迈入21世纪后,产品数字化设计技术与先进机械制造技术得到快速发展,机械行业的整体设计制造水平大幅提高,这对机械产品的设计效率提出了更高的要求。零部件标准化为企业产品设计提供了技术支持,在提高企业产品设计效率、保证产品质量、降低生产成本等方面发挥了重要作用。目前企业在零部件标准化定制过程中还存在诸多问题:企业的设计资源未充分利用,零部件数据之间隐含的联系尚未挖掘,零部件检索方法较为落后及数据可视化程度较低。上述问题导致了企业资源利用率低,零部件检索不全面,企业数据信息处理能力不足,最终影响企业的可持续发展。为解决上述问题,本文以数据挖掘技术、零部件检索方法及数据可视化技术为关键技术展开深入研究,搭建基于数据挖掘和商业智能的零部件标准化平台,推动企业产品设计模式向先进制造方向发展。论文具体研究内容如下:(1)针对企业设计资源未能充分利用的情况,提出了基于马尔科夫(Markov)模型的零部件标准规格推荐方法。深度挖掘零部件规格库,提炼出信息关联度高的参数组合,结合Markov模型估算其条件概率,拟合出新的零部件设计方案,拓展设计人员的选择策略,提高设计效率。(2)基于零部件检索技术,提出了一种基于功能聚类的检索方法。根据零部件名称和功能,自动提取关键字,同步动态匹配与关键字同族的数据信息,扩大了零部件检索范围,方便企业设计人员根据实际需求筛选出符合产品设计要求的零件。(3)探究了数据可视化技术,提出将零部件推荐规格以产品商业图表库(Echarts)的形式进行可视化展示。结合可视化技术,以图像化形式直观地呈现零部件参数,提高企业设计人员对数据信息的处理能力,帮助设计人员理解和评估挖掘结果。基于上述理论分析,本文结合C#编程语言、NX及Visual Studio开发平台,搭建了基于数据挖掘与数据可视化的零部件标准化平台,并以自动扶梯验证本文所提方法的有效性。更多还原

【Abstract】 After entering the 21 st century,the digital design technology and advanced machinery manufacturing technology of the products have been rapidly developed,and the overall design and manufacturing level of the machinery industry has been greatly improved,which puts higher requirements on the design efficiency of mechanical products.Parts standardization provides technical support for enterprise product design,which plays an important role in improving product design efficiency,ensuring product quality and reducing production cost.At present,there are still many problems in the process of parts standardization and customization: the design resources of enterprises are not fully utilized,the implicit connections between parts data have not been explored,the parts retrieval method is relatively backward and the degree of data visualization is low.The above problems have led to low resource utilization of enterprises,incomplete search of parts and components,and insufficient ability to process data information of enterprises,which ultimately affects the sustainable development of enterprises.To solve the above problems,based on the data mining technology,component retrieval method and data visualization technology as the key technology research,set up based on data mining and business intelligence platform for the standardization of parts,promoting the development of enterprise product design model direction of advanced manufacturing.The specific research content of this paper is as follows:(1)In view of the insufficiency of enterprise design resources,a recommendation method of parts standard specification based on Markov model is proposed.Deeply excavate parts and parts specification database,extract the parameter combination with high information correlation,estimate its conditional probability with Markov model,fit out new parts and parts design scheme,expand the selection strategy of designers,and improve the design efficiency.(2)Based on parts retrieval technology,a retrieval method based on function clustering is proposed.According to the name and function of parts,key words are extracted automatically,and the data information of the same family of keywords is matched synchronously and dynamically,which expands the retrieval scope of parts and makes it convenient for enterprise designers to select the parts that meet the requirements of product design.(3)Investigated the data visualization technology,and proposed to display the component specifications in the form of product business chart library(Echarts),combined with visualization technology,the component parameters are visually presented in an image form,which improves the ability of enterprise designers to process data information and helps designers understand and evaluate the mining results.Based on the above theoretical analysis,combined with C# programming language,NX and Visual Studio development platform,this paper constructed a parts standardization platform based on data mining and data visualization,and verified the effectiveness of the method proposed in this paper with an escalator.更多还原