Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for identifying CAD model assembly interface based on improved graph attention network

A technology of model assembly and attention, applied in biological neural network models, geometric CAD, neural learning methods, etc., can solve problems such as rare and rare 3D CAD models, achieve high accuracy, improve classification accuracy, and improve The effect of the efficiency effect

Pending Publication Date: 2021-04-23
HANGZHOU DIANZI UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even so, deep neural networks are mainly used to identify or understand the two-dimensional image data content at present, and there are few related works on the research of three-dimensional CAD models with irregular structures, and the related research that can directly realize the goal of the present invention is even rare

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for identifying CAD model assembly interface based on improved graph attention network
  • Method for identifying CAD model assembly interface based on improved graph attention network
  • Method for identifying CAD model assembly interface based on improved graph attention network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with drawings and embodiments.

[0051] The present invention makes targeted improvements based on the graph attention network proposed by Petar in 2018.

[0052] Step 1: Quantitatively describe the CAD model for the graph-oriented attention network, obtain the quantitative description form of each CAD model, and form a data set;

[0053]Considering that the input of the graph attention network is a graph, the present invention first converts the CAD model into a graph structure—the attribute adjacency graph. Attribute adjacency graphs are used to represent topological and geometric information in the boundary representation of CAD models. Each face in the CAD model corresponds to a node in the attribute adjacency graph; the adjacent relationship (common edge) between faces corresponds to the connecting edge between nodes in the attribute adjacency graph. At the same time, each node in the attribute ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for identifying a CAD model assembly interface. The method comprises the following steps: step 1, quantitatively describing CAD models for a graph attention network to obtain a quantitative description form of each CAD model to form a data set; 2, screening the data set obtained in the step 1, and balancing the proportion of each assembly interface; and 3, modifying the graph attention neural network based on a direct-push type and a clustering strategy, and training the data set obtained in the step 2. Aiming at the problem that CAD model assembly semantic reconstruction is difficult in intelligent design, assembly planning and motion simulation of products at present, a graph attention network method is adopted for recognition, so that a user can be helped to recognize a geometric region, used for reflecting mechanism semantic information, in a CAD model; and therefore, the intelligence of product model assembly semantics, assembly constraints and motion mechanism recovery is improved, and the efficiency effect of CAD model reuse and the efficiency and effect of product assembly planning design are improved.

Description

[0001] technology neighborhood [0002] The invention relates to a CAD model assembly interface recognition method in product intelligent design, assembly planning, mechanism semantic reconstruction and motion simulation, in particular to a CAD model assembly interface recognition method based on a graph attention network. Background technique [0003] The assembly interface in the CAD model is located on the surface of the CAD model and is used to contact with other CAD models and generate a certain relative movement. It is the basic element of the mechanical function of the product (especially the complex mechanical product). The identification of the assembly interface on the CAD model is a key technology for intelligent design, assembly planning, mechanism semantic reconstruction, and motion simulation of products. However, as the basic geometric unit that embodies high-level motion semantic information, the geometric shape of the assembly interface on the part is very fle...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06F30/10G06F16/901G06F16/906G06N3/04G06N3/08
CPCG06F30/10G06F16/9024G06F16/906G06N3/04G06N3/08G06F18/214Y02P90/30
Inventor 王毅刚李虹潘万彬
Owner HANGZHOU DIANZI UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com