High throughput quantitative metallography for complex microstructures using deep learning: A case study in ultrahigh carbon steel

TL;DR

This paper demonstrates how deep learning can automate the segmentation of complex microstructures in ultrahigh carbon steel, enabling detailed microstructural analysis that was previously manual and subjective.

Contribution

It introduces a deep convolutional neural network approach for microstructure segmentation and combines models to extract quantitative microstructural features from complex images.

Findings

Automated segmentation of cementite particles achieved.

Microstructure features like grain boundary zones successfully extracted.

Deep learning models enable detailed microstructural analysis.

Abstract

We apply a deep convolutional neural network segmentation model to enable novel automated microstructure segmentation applications for complex microstructures typically evaluated manually and subjectively. We explore two microstructure segmentation tasks in an openly-available ultrahigh carbon steel microstructure dataset: segmenting cementite particles in the spheroidized matrix, and segmenting larger fields of view featuring grain boundary carbide, spheroidized particle matrix, particle-free grain boundary denuded zone, and Widmanst\"atten cementite. We also demonstrate how to combine these data-driven microstructure segmentation models to obtain empirical cementite particle size and denuded zone width distributions from more complex micrographs containing multiple microconstituents. The full annotated dataset is available on materialsdata.nist.gov (https://materialsdata.nist.gov/handle/11256/964).