MicroLib: A library of 3D microstructures generated from 2D micrographs using SliceGAN

TL;DR

This paper introduces MicroLib, a library of 3D microstructures generated from 2D micrographs using the SliceGAN machine learning method, enabling efficient creation of 3D datasets for material modeling.

Contribution

The paper demonstrates the application of SliceGAN to generate accurate 3D microstructures from 2D images across diverse materials, expanding available datasets for simulation.

Findings

Good agreement between real and generated microstructural properties

Successful application to 87 different microstructures

Broad applicability of SliceGAN demonstrated

Abstract

3D microstructural datasets are commonly used to define the geometrical domains used in finite element modelling. This has proven a useful tool for understanding how complex material systems behave under applied stresses, temperatures and chemical conditions. However, 3D imaging of materials is challenging for a number of reasons, including limited field of view, low resolution and difficult sample preparation. Recently, a machine learning method, SliceGAN, was developed to statistically generate 3D microstructural datasets of arbitrary size using a single 2D input slice as training data. In this paper, we present the results from applying SliceGAN to 87 different microstructures, ranging from biological materials to high-strength steels. To demonstrate the accuracy of the synthetic volumes created by SliceGAN, we compare three microstructural properties between the 2D training data and 3D generations, which show good agreement. This new microstructure library both provides valuable 3D microstructures that can be used in models, and also demonstrates the broad applicability of the SliceGAN algorithm.