An intelligent identification and retrieval method for three-dimensional processing characteristics

A technology for processing features and intelligent recognition, applied in neural learning methods, special data processing applications, image data processing, etc., can solve the problems of slow calculation speed and few network layers, and achieve the effect of reducing the amount of data calculation

Inactive Publication Date: 2019-05-21
XI AN JIAOTONG UNIV
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing 3D convolutional neural network architecture needs to learn many parameters, the number of network layers is small, the calcu...

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
  • An intelligent identification and retrieval method for three-dimensional processing characteristics
  • An intelligent identification and retrieval method for three-dimensional processing characteristics
  • An intelligent identification and retrieval method for three-dimensional processing characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The invention provides an intelligent identification and retrieval method for three-dimensional processing features, which includes two parts: processing feature learning and processing feature retrieval. The processing feature learning process includes: obtaining 3D processing features; voxelizing the 3D processing features; performing data enhancement processing on the voxelized model to obtain a 3D processing feature dataset; building a 3D convolutional neural network; training 3D processing features and recording Model parameters; processing feature retrieval process includes: input 3D processing features; voxelize the 3D model; calculate the similarity between the retrieved processing features and the processing features in the data set according to the recorded model parameters; obtain the processing features belonging to each category probability, and finally output the retrieval results in descending order. The invention extends the convolutional neural network ...

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 identification and retrieval method for three-dimensional processing characteristics. The method comprises the following steps: firstly, obtaining a processing characteristic three-dimensional model; Performing voxelization processing on the three-dimensional model; Performing data enhancement processing on the voxelization model to obtain a three-dimensionalmodel data set; Then constructing a three-dimensional convolutional neural network, training a three-dimensional model and recording model parameters; Then inputting a three-dimensional model, and performing voxelization processing on the three-dimensional model of the processing characteristics; And calculating the similarity between the retrieval model and the data set model according to the recorded model parameters to obtain the probability that the model belongs to each category, and finally arranging and outputting a retrieval result according to a descending order. The method is smallin calculated amount and high in recognition speed, and has higher three-dimensional processing feature recognition and retrieval accuracy.

Description

technical field [0001] The invention belongs to the technical field of deep learning and three-dimensional model intelligent identification and retrieval, and specifically relates to an intelligent identification and retrieval method for three-dimensional processing features. Background technique [0002] In recent years, with the development of the manufacturing industry, the development mode of enterprises has changed from mass production to multi-variety and small-scale production, and the types of processing features of parts and components have increased and their shapes are complex and changeable. In addition, with the increasing maturity of 3D modeling technology, the number of 3D models of parts has shown an explosive growth trend, and 3D process design technology has gradually been applied in enterprises. In the process design of traditional machining parts, technicians often rely on coding technology or empirical knowledge to identify the shape and size of parts pr...

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): G06F17/50G06N3/04G06N3/08G06T17/00
Inventor 周光辉杨雄军张超黎志
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap