This work deals with the creation of a surrogate model for approximating the finite element solution of the problem of dispersion-strengthened composite plane sample deformation. The authors propose an algorithm for constructing a parametric two-dimensional model of a composite and use the ANSYS Mechanical program to create the calculation model. The stress-strain state of the material microstructure is processed using a convolutional neural network based on the U-Net architecture of the encoder-decoder type. The model loss function is defined as the root mean square error, and optimisation of the loss function is performed using the ADAM optimisation method. The surrogate model is significantly ahead of the FEM and is used to speed up calculations and determine the overall quality of the approximation of problems of mechanics of this type.