Prediction of Elastic Parameters of Particle Reinforced Composites Using Finite Element Simulations

The macroscopic properties of composite materials depend on the microscopic properties of the constituents and the geometric arrangement of their phases. Therefore, it is essential to predict heterogeneous materials' mechanical properties by simulating microstructural finite element models. The present article aims to analyze particle reinforced composites composed of spherical alumina inclusions surrounded by a glass matrix using a tridimensional representative volume element. Herein, microstructures are artificially created considering a regular or random arrangement of the inclusions. Two materials systems previously studied in the literature were analyzed. The discretization of the models was performed to have periodic mesh, thus enabling the use of periodic boundary conditions. A finite element model is created using Abaqus software. Numerical results show that the macroscopic properties can be estimated with high accuracy for the temperature where linear matrix behavior stands. The predictions were compared to experimental data from the literature. The models with a regular arrangement of inclusions show a difference inferior to 10%, while random arrangements show a difference inferior to 3.9%. The developed numerical algorithms can be modified to include new features, such as other dispersed phase arrangements or nonlinear material behavior.