基于几何特征自识别的机加工智能分析标签数据采集系统  

Acquisition System of Intelligent Machining Analysis Label Data Based on Geometric Feature Self Recognition

作　　者：张平豪 鞠鹏飞 刘昊霖 ZHANG Pinghao;JU Pengfei;LIU Haolin(Naval Research Institute,Beijing 102442,China)

机构地区：[1]海军研究院,北京102442

出　　处：《信息与电脑》2022年第2期162-164,共3页Information & Computer

摘　　要：标签数据获取是深度学习在机加工分析领域应用的关键问题之一,笔者基于几何特征自动识别技术设计并开发了机加工标签数据采集系统。以各厂家通用格式step文件作为研究对象,在Visual studio开发环境下进行数据导入、初步分析以及工步工时输入,将step文件中的三维模型数据与几何模型、工步工时等数据绑定,为下一步深度学习模型训练提供大量数据集,解决了机加工分析领域中的深度学习应用的训练数据集的问题,对智能制造技术的发展具有工程实用价值。Since the acquisition of label data is one of the key issues in the application of deep learning in the field of machining analysis, the author designed and developed a machining label data acquisition system based on the automatic recognition technology of geometric features. Taking step files in the common format of various manufacturers as the research object, data import, preliminary analysis, and input of working hours are carried out in the Visual studio development environment. The next step is to provide a large number of data sets for deep learning model training, which solves the problem of training data sets for deep learning applications in the field of machining analysis, and has engineering practical value for the development of intelligent manufacturing technology.

关 键 词：标签数据 几何特征 STEP文件 

分 类 号：TP274.4[自动化与计算机技术—检测技术与自动化装置]