Application of machine learning methods for predicting the mechanical behavior of dispersion-strengthened composite material

Abstract

The work is devoted for creating a model for approximating the solution by the finite element method of the problem of plane deformation of a dispersion-strengthened composite material. An algorithm for constructing a parametric 2-D composite model is proposed. The processing of the parameters of the microstructure material stress-strain state occurs using a convolutional neural network. A surrogate model is used for calculations speed up and determine the overall approximations quality of such type mechanics problems.