工艺元聚类驱动的高维机加工艺设计方法研究  

The higher-dimensional machining process planning method driven by process meta-clustering

作　　者：李春磊 LI Chun-lei(College of Mechanical Engineering, Baoji University of Arts and Sciences, Baoji 721016, Shaanxi, China;Key Laboratory of Advanced Manufacturing and Detection Technology for Industrial Robot and Its Major Component, Baoji 721016, Shaanxi, China)

机构地区：[1]宝鸡文理学院机械工程学院,陕西宝鸡721016 [2]陕西省机器人关键零部件先进制造与评估省市共建重点实验室,陕西宝鸡721016

出　　处：《宝鸡文理学院学报（自然科学版）》2022年第1期95-102,共8页Journal of Baoji University of Arts and Sciences(Natural Science Edition)

基　　金：陕西省教育厅自然科学类专项研究计划项目(21JK0490);浙江大学CAD&CG国家重点实验室开放课题(A2204)。

摘　　要：目的提出新的高维机加工艺设计方法,解决工艺元聚类驱动的工艺设计方法效率低和精度差等问题,使最终得到的工艺设计过程能够更加贴近高维机加工艺设计的本质,符合工艺设计者的加工意图。方法建立多维度工艺信息场中的高维工艺元描述模型,通过运用核函数原理对高维工艺元模型进行维数约简,得到带有高维机加工艺特性的低维工艺元模型;在此基础上,构建基于高维相似性度量算法的工艺元聚类分析方法,并结合加工意图实现基于工艺元组的机加工艺设计。结果实现了更贴近加工意图的工艺设计,保证了工艺设计的高维特性,具有客观、准确、高效等特性。结论实例证明,该方法能够应用于解决传统的基于聚类分析的工艺设计结果与实际需求匹配度低的问题。Purposes—To propose a novel high-dimensional machining process planning method driven by process meta-clustering by solving the problems of low efficiency and poor precision of process design driven by process meta-clustering,and making the final process design process closer to the nature of high-dimensional machining planning and meet the machining intention of technicists.Methods—Firstly,a high-dimensional process meta-model was established under the multi-dimensional process information field.Then the dimension of the high-dimensional process meta-model was reduced by using the kernel function principle,thus obtaining the low-dimensional process meta-model with high-dimensional machining characteristics.On that basis,a process meta-clustering method based on high-dimensional similarity measurement algorithm was constructed,and the machining process planning was realized in combination with machining intention.Results—The method realizes the process planning that can be closer to processing intention,which has the advantage of objectiveness,accuracy and efficiency.Conclusion—The result of case-study proves that the method can be used to solve the problem of low matching degree between the traditional process planning results based on cluster analysis and actual demand.

关 键 词：高维工艺元 工艺设计 维数约简 聚类分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]