Cantilever beam structure design method based on self-attention mechanism neural network

Abstract

The invention discloses a cantilever beam structure design method based on a self-attention mechanism neural network. According to the design method, the problem that the calculation iteration time is long in the cantilever beam structure generation process of a traditional MMC algorithm can be solved, The method comprises the following steps: using an MMC method in advance to generate a training set and a test set; 2, performing data cleaning on the generated data; 3, constructing a word-like vector model by using a multi-perceptron model; 4, generating a final output by using an improved Transform model; 5, training by using the model; and 6, obtaining a final result by using the model. When a final model is used for structure optimization design, a boundary condition vector is input into the model to obtain model output, and then the model output is input into an MMC drawing function, so that rapid calculation of a final optimization structure is realized.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and structure design optimization, and in particular relates to a cantilever beam structure design method based on a self-attention mechanism neural network. Background technique [0002] In order to design the optimal cantilever beam structure under the given load conditions, constraints and performance indicators, researchers at home and abroad use topology optimization methods to optimize the design. The basic idea of ​​topology optimization is to transform the optimal topology problem of seeking structure into the distribution problem of seeking optimal material in a given design area. Currently, topology optimization methods mainly include SIMP algorithm, ESO algorithm, level set method and MMC algorithm, etc. , the amount of computation of the above methods depends on the size of the design domain. With the continuous increase of the design domain, the amount of computation increases e...

AI Technical Summary

Problems solved by technology

The basic idea of ​​topology optimization is to transform the optimal topology problem of seeking structure into the distribution problem of seeking optimal material in a given design area. Currently, topology optimization methods mainly include SIMP algorithm, ESO algorithm, level set method and MMC algorithm, etc. , the calculation amount of the above method depends on the size of the design domain. With the continuous increase of the design domain, the calculation amount increases exponentially, making it take a long time to obtain the optimal design result

Images