Novel CAD model feature recognition method based on graph and point cloud neural network

By combining graph and point cloud technology, a new CAD model feature recognition method is proposed, which solves the problem of heterogeneous processing feature recognition, and achieves high accuracy and good generalization capabilities in actual industrial scenarios.

CN119623271AActive Publication Date: 2025-03-14ZHENGZHOU UNIV
View PDF 5 Cites 6 Cited by

Patent Information

Application Number
CN202411693530.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-25
Publication Date
2025-03-14
Estimated Expiration
2044-11-25

AI Technical Summary

Technical Problem

The prior art is difficult to accurately identify heterogeneous processing features that appear in CAD models in actual industrial scenarios, and the graph neural network-based methods are prone to encounter difficulties in generalizing distributions when topological structure changes.

Method used

A new CAD model feature recognition method based on graph and point cloud neural network is adopted. By creating a data set containing training sets, verification sets and test sets, the graph encoder and point encoder extract embedded vectors from the face adjacency graph and surface point clouds, and semantic segmentation, instance segmentation and bottom surface segmentation are performed through multi-task headers to identify processing features.

Benefits of technology

The accurate identification of heterogeneous processing features in the CAD model is achieved, the external generalization trap is avoided, and significant effects are shown in actual industrial applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119623271A_ABST
    Figure CN119623271A_ABST
Patent Text Reader

Abstract

The invention discloses a novel CAD model feature recognition method based on a graph and a point cloud neural network, and the method comprises the steps: creating a data set containing heterogeneous machining features, converting a B-Rep model into a surface adjacent graph with surface-edge attributes, a surface UV grid, and a surface point cloud input neural network model; the neural network model integrates a graph encoder, a point encoder and a multi-task head, and the graph encoder and the point encoder learn classifiable embedded vectors from shape primitives of different scales of points, edges and surfaces respectively; and the multi-task head converts the embedded vector into corresponding semantic segmentation, instance segmentation and bottom surface segmentation results through three meta-learners. According to the method, insights can be extracted from different representation forms of a CAD model, semantic segmentation, instance segmentation and bottom surface segmentation tasks of heterogeneous processing features are processed in parallel, and experiments prove that Gamp is a Gamp; the PCNet has effectiveness and superiority in non-heterogeneous and heterogeneous processing feature recognition, and has application potential in real industrial scenes.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Dressing pedestrian re-identification and retrieval method based on multi-mode intelligent perception and fusion

    CN114998934A

  • Feature-preserving multi-source collaborative fusion geometric modeling method and system

    CN116363317A

  • Method and system for carrying out 3D shape recognition based on multi-modal neural network

    CN118918576A

  • Bird's eye view based velocity estimation

    US20210358296A1

  • Three-dimensional lidar point cloud semantic segmentation method and apparatus based on deep learning

    WO2024130776A1

Cited By

  • STEP-NC processing feature identification method based on deep learning

    CN121350556A

  • CAD model fillet feature recognition and removal method based on graph neural network

    CN121482415A

  • Machining feature recognition method of CAD model

    CN121524606A

  • Aircraft CAD model intelligent component identification and segmentation method based on three-mode fusion

    CN122067244A

  • Aircraft CAD model intelligent component recognition and segmentation method based on three-mode fusion

    CN122067244B