面向数字化检测的阵列特征自动标注方法  

Automatic labeling method of array feature for digital detection

作　　者：郭建烨 万景洋 GUO Jianye, WAN Jingyang(School of Mechanical and Electrical Engineering, Shenyang Aerospace University, Shenyang 110136, Liaoning Chin)

机构地区：[1]沈阳航空航天大学机电工程学院

出　　处：《锻压装备与制造技术》2018年第2期96-100,共5页China Metalforming Equipment & Manufacturing Technology

基　　金：航空科学基金资助项目(2015ZE12013)

摘　　要：随着机械设计领域的飞速发展,计算机辅助设计技术和模型产品定义技术（Model Based Definition,MBD）实现了巨大飞跃,MBD全三维模型标注技术越来越受各企业的重视。针对现阶段基于MBD三维模型中阵列特征的产品制造信息（Product Manufacturing Information PMI）的标注缺失问题,采用主成分分析法和最近点迭代法对阵列特征成员上分布的点云进行配准运算,确定出阵列特征成员之间对应关系,对未标注产品制造信息的阵列特征成员进行快速自动标注。结果证明：该方法不仅保证了MBD模型检测信息的准确性和完整性,而且有效地解决了MBD模型从设计环节到检测环节信息的自动化传递问题,为数字化检测工艺实现自动化提供了基础保障。With the rapid development in the field of mechanical design, the computer-aided design technology and Model Based Definition（MBD） have achieved a tremendous leap. MBD-full 3 D model labeling technology has been increasingly valued by companies. Aiming at the lack of labeling of Product Manufacturing Information（PMI） based on array features in MBD 3 D model at this stage, Principal Component Analysis method（PCA） and nearest-point iterative method have been used to perform registration operations on point clouds distributed on the array feature members. The corresponding relationship between array feature members has been determined, and the array feature members without labeling product manufacturing information have been quickly and automatically labeled. The results prove that this method not only guarantees the accuracy and completeness of the MBD model detection information, but also effectively solves the problem of the automatic transmission of information from the design link to the detection link of the MBD model. It provides the basic guarantee for the automation of the digital detection process.

关 键 词：MBD 阵列特征 主成分分析 最近点迭代 快速自动标注 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]