欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2026, Vol. 43 ›› Issue (1): 115-124.DOI: 10.7523/j.ucas.2024.041

• 电子信息与计算机科学 • 上一篇    下一篇

PT-MFR: 一种基于Point Transformer的CAD模型加工特征识别方法

何皓辰, 方正, 卢政达, 肖俊(), 王颖   

  1. 中国科学院大学人工智能学院,北京 100049
  • 收稿日期:2024-03-01 修回日期:2024-05-07 发布日期:2024-06-04
  • 通讯作者: 肖俊
  • 基金资助:
    国家自然科学基金(U21A20515);国家自然科学基金(62102393);国家自然科学基金(62206263);国家自然科学基金(62271467);北京市自然科学基金(4242053);中国博士后科学基金(2022T150639);中国博士后科学基金(2021M703162);机器人技术与系统国家重点实验室开放研究课题(SKLRS-2022-KF-11);中央高校基本科研业务费专项资助

PT-MFR: a CAD model machining feature recognition method based on Point Transformer

Haochen HE, Zheng FANG, Zhengda LU, Jun XIAO(), Ying WANG   

  1. School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 100049,China
  • Received:2024-03-01 Revised:2024-05-07 Published:2024-06-04
  • Contact: Jun XIAO

摘要:

加工特征识别在计算机辅助设计(CAD)和制造(CAM)中至关重要,是连接CAD和CAM系统的重要环节。研究者们提出了基于规则和基于学习的2类加工特征识别方法,其中基于学习的方法表现更出色且备受关注。然而,现有识别方法面临着几何信息利用不足、加工特征定位不精准、实例分割过程复杂等挑战。针对这些问题,提出PT-MFR,一种基于Point Transformer的CAD模型加工特征识别方法,它执行语义分割和实例分割2个任务,分别预测模型每个面的加工特征语义类别并计算面相似度以分割加工特征实例,综合2个任务得到加工特征识别结果。实验结果表明,提出的方法性能优于现有的其他方法。

关键词: 加工特征识别, 点云, 神经网络, Point Transformer

Abstract:

Machining feature recognition is crucial in computer-aided design (CAD) and manufacturing (CAM) as it serves as a vital link between CAD and CAM systems. Researchers have proposed two types of machining feature recognition methods: rule-based and learning-based, with the latter showing superior performance and garnering more attention. However, existing recognition methods face challenges such as insufficient utilization of geometric information, inaccurate machining feature localization, and complexity in the instance segmentation process. To address these issues, this paper proposes PT-MFR, a CAD model machining feature recognition method based on Point Transformer. It performs two tasks: semantic segmentation and instance segmentation, predicting the semantic category of machining features for each face and calculating face similarity to segment the machining feature instances. The results of both tasks are integrated to obtain the machining feature recognition results. Experimental results demonstrate that the proposed method outperforms other methods.

Key words: machining feature recognition, point cloud, neural network, Point Transformer

中图分类号: