Prediction of Elastic Stresses in Porous Materials Using Fully Convolutional Networks

Abstract

Machine learning (ML) models enable exploration of vast structural space faster than the traditional methods, such as finite element method (FEM). This makes ML models suitable for stochastic fracture problems in brittle porous materials, where large number of tests are needed to understand the origins of the variations in fracture strength. In this work, fully convolutional networks (FCNs) were trained to predict stress and stress concentration factor distributions in two-dimensional isotropic elastic materials with uniform porosity. We show that even with downsampled data, the FCN models predict the stress distributions for a given porous structure. Stress concentration factors were predicted with a mean prediction performance greater than 0.94. FCN predicted stress concentration factors >104 times faster than the FEM simulations. Furthermore, the FCN model predicts the pore configurations with the lowest and highest stresses from a set of structures, enabling ML optimization of porous microstructures for increased reliability.

Keywords: fracture strength, porosity, materials informatics, artificial intelligence, AI optimization