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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

