Microstructural Studies Using Generative Adversarial Network (GAN): a Case Study

TL;DR

This paper demonstrates that a GAN trained on phase-field generated microstructures can produce realistic synthetic images rapidly, enabling efficient and accurate FEM-based property predictions in materials science.

Contribution

The study introduces a GAN trained on phase-field microstructures, providing a fast and cost-effective method for generating realistic microstructures for FEM analysis.

Findings

GAN-generated microstructures yield FEM property predictions matching real data.

The GAN produces thousands of microstructure images within seconds.

Synthetic microstructures improve the efficiency of materials property simulations.

Abstract

The generative adversarial network (GAN) is one of the most widely used deep generative models for synthesizing high-quality images with the same statistics as the training set. Finite element method (FEM) based property prediction often relies on synthetically generated microstructures. The phase-field model is a computational method of generating realistic microstructures considering the underlying thermodynamics and kinetics of the material. Due to the expensive nature of the simulations, it is not always feasible to use phase-field for synthetic microstructure generation. In this work, we train a GAN with microstructures generated from the phase-field simulations. Mechanical properties calculated using the finite element method on synthetic and actual phase field microstructures show excellent agreement. Since the GAN model generates thousands of images within seconds, it has the potential to improve the quality of synthetic microstructures needed for FEM calculations or any other applications requiring a large number of realistic synthetic images at minimal computational cost.