Generating Input Data for Microstructure Modelling: A Deep Learning Approach Using Generative Adversarial Networks

Abstract

For the generation of representative volume elements a statistical description of the relevant parameters is necessary. These parameters usually describe the geometric structure of a single grain. Commonly, parameters like area, aspect ratio and slope of the grain relative to the rolling direction are applied. However, usually simple distribution functions like log normal or gamma distribution are used. Yet, these do not take the interdependencies between the microstructural parameters into account. To fully describe any metallic microstructure though, these interdependencies between the singular parameters need to be accounted for. To accomplish this representation, a machine learning approach was applied in this study. By implementing a Wasserstein generative adversarial network, the distribution, as well as the interdependencies could accurately be described. A validation scheme was applied to verify the excellent match between microstructure input data and synthetically generated output data.

Generating polycrystalline microstructures with prescribed tensorial texture coefficients

“…As an additional benefit, for generating orientations, the TOP method requires only nine (or 22 variables, depending on the highest texture coefficient rank considered) to be stored, contrasting with methods that rely on the entire experimental database. Because of this low num-ber of parameters, it is possible to fuel data driven methods [96,97]. Additionally, as experimental data is always afflicted with some degree of measurement uncertainty, investigating the influence of the texture on the overall macroscopic response might be an interesting topic, i.e., via uncertainty quantification [98,99].…”