Unlock instant, AI-driven research and patent intelligence for your innovation.

Structure optimization design method for accelerating by using graph convolutional neural network structure

A network structure and convolution neural technology, applied in the field of artificial intelligence, can solve the problems that convolution operations cannot be directly applied, and achieve the effects of reducing computational complexity, improving time efficiency, and reducing the consumption of computing resources

Inactive Publication Date: 2020-11-06
XI AN JIAOTONG UNIV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although deep learning algorithms based on Convolutional Neural Networks (CNN) have achieved great success in regular Euclidean data, for non-Euclidean data with broader data representation capabilities The traditional convolution operation cannot be directly applied to the graph structure data, so the graph neural network came into being

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
  • Structure optimization design method for accelerating by using graph convolutional neural network structure
  • Structure optimization design method for accelerating by using graph convolutional neural network structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] The steps of the topology optimization design method accelerated using the graph neural network model are as follows:

[0033] First, the input sample dataset is normalized

[0034] For each training set sample, validation set sample, and each node in the test set sample retain its absolute position coordinate information (x, y, z), if the z column is set to 0 for the two-dimensional Ground Structure algorithm, and finally get The position coordinate information is a two-dimensional matrix of (x, y, 0), and the feature information of each node in each sample is saved at the same time. The feature information includes fixed points, and a two-dimensional matrix is ​​also obtained for the force point, and its The two matrices are spliced, and finally each input sample is represented by a (n, 5) two-dimensional matrix, n represents the number of nodes, and the 5-column distribution represents coordinate information and feature information.

[0035] Second, prepare the data...

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 structure optimization design method for accelerating by using a graph convolutional neural network structure. The method can solve the problems that a traditional Ground Stream algorithm is high in calculation complexity and large in time expenditure in structure optimization, the method comprises a model obtaining part and a model using part, and the model obtaining main process comprises the steps that 1, input sample data set standardization processing is carried out; 2, generating (10000 groups) optimized topological structure diagrams and standardized input diagram random distribution as a training set, a verification set and a test set by using a Ground Stream algorithm; 3, constructing a graph neural network model; and 4, training a graph neural network model, and storing the model and parameters. And finally, the network model is used for calculation, testing and evaluation, so that quick calculation of a final optimized structure is realized, the calculation cost is reduced, and the time overhead is improved.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and specifically relates to a structural optimization design method utilizing graph convolutional neural network structure acceleration, which minimizes computational complexity and improves time efficiency under the premise of ensuring that the generated sample results are as close as possible to the correct sample. Background technique [0002] The basic idea of ​​topology optimization is to find the best material distribution scheme in the specified design area with material distribution as the optimization object according to the given load conditions, constraints and performance indicators. According to different research objects, topology optimization can be divided into two different methods: topology optimization method of discrete structure and topology optimization method of continuum structure. For the discrete structure topology optimization problem, the base structure method 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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 郑帅范浩杰栗阳阳田智强李宝童
Owner XI AN JIAOTONG UNIV