Learning Metal Microstructural Heterogeneity through Spatial Mapping of Diffraction Latent Space Features

TL;DR

This paper introduces a novel spatial mapping method of diffraction latent space features using machine learning to effectively encode and analyze complex microstructural heterogeneity in metallic materials, especially additive manufacturing alloys.

Contribution

It presents a new approach combining variational autoencoders and physical mapping to better describe microstructures beyond traditional metrics, enabling improved property prediction.

Findings

Effectively encodes microstructural heterogeneity

Identifies heterogeneity not captured by physics-based models

Enhances machine learning applications in materials design

Abstract

To leverage advancements in machine learning for metallic materials design and property prediction, it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of current physics-based discrete microstructure descriptors. This need is particularly relevant for metallic materials processed through additive manufacturing, which exhibit complex hierarchical microstructures that cannot be adequately described using the conventional metrics typically applied to wrought materials. Furthermore, capturing the spatial heterogeneity of microstructures at the different scales is necessary within such framework to accurately predict their properties. To address these challenges, we propose the physical spatial mapping of metal diffraction latent space features. This approach integrates (i) point diffraction data encoding via variational autoencoders or contrastive learning and (ii) the physical mapping of the encoded values. Together these steps offer a method offers a novel means to comprehensively describe metal microstructures. We demonstrate this approach on a wrought and additively manufactured alloy, showing that it effectively encodes microstructural information and enables direct identification of microstructural heterogeneity not directly possible by physics-based models. This data-reduced microstructure representation opens the application of machine learning models in accelerating metallic material design and accurately predicting their properties.