header

Prediction of Elastic Stresses in Porous Materials Using Fully Convolutional Networks

13 Pages Posted: 19 Oct 2020 Publication Status: Under Review

See all articles by Ozgur Keles

Ozgur Keles

San Jose State University

Yinchuan He

Electrical Engineering Department, San Jose State University

Birsen Sirkeci-Mergen

Electrical Engineering Department, San Jose State University

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

Suggested Citation

Keles, Ozgur and He, Yinchuan and Sirkeci-Mergen, Birsen, Prediction of Elastic Stresses in Porous Materials Using Fully Convolutional Networks. Available at SSRN: https://ssrn.com/abstract=3714501 or http://dx.doi.org/10.2139/ssrn.3714501

Ozgur Keles (Contact Author)

San Jose State University

San Jose, CA 95192-0066
United States

Yinchuan He

Electrical Engineering Department, San Jose State University ( email )

Birsen Sirkeci-Mergen

Electrical Engineering Department, San Jose State University ( email )

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
96
Downloads
8
PlumX Metrics