Multi-scale topological optimization design method based on Mobile-U-Net

Abstract

The invention belongs to the technical field related to multi-scale topological optimization, and discloses a multi-scale topological optimization design method based on Mobile-U-Net. The method comprises the following steps: S1, gridding a multi-scale topological structure to obtain a plurality of grids and the stress state of each grid, and calculating the corresponding initial displacement by using the stress state of each grid; S2, constructing a parallel Mobile-U-Net convolutional neural network prediction model, constructing a plurality of information input channels, and taking the optimized configuration as output; and S3, obtaining a macroscopic data sample set and a microscopic data sample set, training to obtain a macroscopic prediction model and a microscopic prediction model, and respectively predicting the configuration of the to-be-optimized multi-scale topological structure by using the macroscopic prediction model and the microscopic prediction model so as to obtain an optimized macroscopic configuration and an optimized microscopic configuration. The macro-micro topological configuration corresponding to the initial structure setting information can be output in real time without any finite element iteration step.

Description

technical field [0001] The invention belongs to the related technical field of multi-scale topology optimization, and more specifically relates to a design method for multi-scale topology optimization based on Mobile-U-Net. Background technique [0002] The porous structure is a structure composed of porous unit cells periodically arranged, with high porosity, it not only shows a specific macrostructure organization shape, but also its internal shape shows a dense periodic microstructure organization arrangement . The internal shape of the porous structure can absorb a large amount of energy when resisting impact loads, and is favored by engineering designers because of its high physical properties such as specific stiffness and specific strength, and has been widely used in modern biomedicine , Manned space vehicles and other fields. [0003] As an efficient optimization method, the structure topology optimization design method can complete the simultaneous optimization d...

AI Technical Summary

Problems solved by technology

However, in the traditional multi-scale structural topology optimization design method, the optimization process of the macro-micro topological configuration interacts, and in each iteration step of the multi-scale parallel design, the sensitivity information of the macro-structure guides the configuration of the micro-structure The direction of optimization, the elastic tensor of the microstructure will then affect the evolution of the macrostructure

Therefore, the multi-scale structural topology optimization design method is a computationally intensive and time-consuming design method, and it is urgent to find an efficient multi-scale structural topology optimization design method

Images