EBSD Grain Knowledge Graph Representation Learning for Material Structure-Property Prediction

TL;DR

This paper introduces a novel graph-based approach using EBSD data and graph neural networks to quantitatively predict material properties from microstructure, improving upon traditional methods.

Contribution

It proposes a new EBSD-based knowledge graph and graph neural network framework for material structure-property prediction, advancing materials informatics.

Findings

Outperforms traditional machine learning methods

Accurately predicts material mechanical properties

Effectively models microstructure-structure relationships

Abstract

The microstructure is an essential part of materials, storing the genes of materials and having a decisive influence on materials' physical and chemical properties. The material genetic engineering program aims to establish the relationship between material composition/process, organization, and performance to realize the reverse design of materials, thereby accelerating the research and development of new materials. However, tissue analysis methods of materials science, such as metallographic analysis, XRD analysis, and EBSD analysis, cannot directly establish a complete quantitative relationship between tissue structure and performance. Therefore, this paper proposes a novel data-knowledge-driven organization representation and performance prediction method to obtain a quantitative structure-performance relationship. First, a knowledge graph based on EBSD is constructed to describe the material's mesoscopic microstructure. Then a graph representation learning network based on graph attention is constructed, and the EBSD organizational knowledge graph is input into the network to obtain graph-level feature embedding. Finally, the graph-level feature embedding is input to a graph feature mapping network to obtain the material's mechanical properties. The experimental results show that our method is superior to traditional machine learning and machine vision methods.