Automated Segmentation of Large Image Datasets using Artificial Intelligence for Microstructure Characterisation and Damage Analysis

Many properties of commonly used materials are driven by their microstructure, which can be influencedby the composition and manufacturing processes. To optimise future materials, understanding themicrostructure is critically important. Here, we present two novel approaches based on artificial intelligencethat allow the segmentation of the phases of a microstructure for which simple numerical approaches, suchas thresholding, are not applicable: One is based on the nnU-Net neural network, and the other on generativeadversarial networks (GAN).Using scanning electron microscopy images collected from large areas (~1 mm²) of dual-phase steels as acase study, we demonstrate how both methods effectively segment intricate microstructural details,including martensite, ferrite, and damage sites, for subsequent analysis.Either method shows substantial generalizability across a range of image sizes and conditions, includingheat-treated microstructures with different phase configurations. The nnU-Net excels in mapping largeimage areas. Conversely, the GAN-based method performs reliably on smaller images, providing greaterstep-by-step control and flexibility over the segmentation process.This study highlights the benefits of segmented microstructural data for various purposes, such ascalculating phase fractions, modelling material behaviour through finite element simulation, andconducting geometrical analyses of damage sites and the local properties of their surroundingmicrostructure. https://doi.org/10.1016/j.matdes.2024.113031