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

Intelligent processing feature identification method based on point cloud semantic segmentation

A technology for processing features and semantic segmentation, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve problems such as poor generality of methods, difficulty in identifying special-shaped processing features and free-form surface features, etc. The expansion of the training set size and the effect of accelerating the training speed

Pending Publication Date: 2020-11-10
XI AN JIAOTONG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Over the past three decades, researchers have proposed different types of feature recognition techniques to identify processing features, including graph-based methods, neural network-based methods, volumetric decomposition-based methods, cell-based methods, hint-based method, rule-based method and mixed-based method, these methods generally need to establish a large number of complex rules, and at the same time, the method has poor versatility in the face of different types of processing features. For the identification of compound processing features, special-shaped processing features and free-form surface features Difficulties exist; recently, a method that takes three-dimensional voxels as input and uses 3D-CNN to identify processing features, but only achieves certain results in the identification of single features and simple part models

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
  • Intelligent processing feature identification method based on point cloud semantic segmentation
  • Intelligent processing feature identification method based on point cloud semantic segmentation
  • Intelligent processing feature identification method based on point cloud semantic segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041]The invention provides a processing feature intelligent recognition method based on point cloud semantic segmentation, which converts the processing feature intelligent recognition problem of a part CAD model into the semantic segmentation problem of a three-dimensional point cloud model. Establish a 3D part CAD model library for small batch-customized products and preprocess to obtain a training data set, and further input the data set into the improved PointNet semantic segmentation network. This network is based on the PointNet semantic segmentation network. By introducing the ResNet network The residual block structure improves the segmentation accuracy. Finally, various processing features are input into the detection module, and the types of processing features are verified and the number of processing features is determined through abnormal point detection and DBSCAN clustering algorithm. The processing feature intelligent recognition method proposed by the presen...

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 an intelligent processing feature recognition method based on point cloud semantic segmentation, and the method comprises the steps: converting a machining feature intelligentrecognition problem of a part CAD model into a semantic segmentation problem of a three-dimensional point cloud model, building a three-dimensional part CAD model library, and carrying out the preprocessing of the three-dimensional part CAD model library, and obtaining a training data set; furthermore, inputting the data set into an improved PointNet semantic segmentation network, enabling the network to take the PointNet semantic segmentation network as a basic framework, and improving the segmentation precision by introducing a residual block structure of a ResNet network; and finally, inputting the various machining features into a detection module, verifying the machining feature types through abnormal point detection and a DBSCAN clustering algorithm, and determining the number of themachining features. According to the intelligent process feature identification method, cross-part type and cross-feature type machining feature extraction is achieved, the problem that special-shaped machining features, free-form surfaces and composite machining features are difficult to recognize is solved, and system integration of full-life-cycle information of enterprise reuse machining features and manufacturing industry computer-aided software is facilitated.

Description

technical field [0001] The invention belongs to the field of intelligent information technology of advanced manufacturing technology, and in particular relates to an intelligent recognition method of processing features based on point cloud semantic segmentation. Background technique [0002] CAD, CAPP and CAM systems play an important role in the fields of product design, process planning and processing simulation. However, data between systems is difficult to convert, transfer and share. Therefore, it is very important to realize the integration of CAD, CAPP and CAM systems. This will reduce the design and manufacturing time of small batch-customized parts products, and enable enterprises to have stronger agile manufacturing capabilities in a highly competitive market. Machining features refer to specific shapes on mechanical parts, including holes, free-form surfaces, steps and keyways, etc. The automatic recognition technology of machining features has become a bridge fo...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06F30/17G06K9/34G06K9/62
CPCG06F30/27G06F30/17G06V10/267G06F18/23G06F18/214
Inventor 周光辉胡君生张超
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products