# Toward quantitative fractography using convolutional neural networks

## TL;DR

This paper introduces a convolutional neural network-based method to quantitatively analyze fracture surface images, enabling automated identification of fracture mechanisms with high accuracy, which advances fractography from qualitative to quantitative analysis.

## Contribution

It presents a novel CNN-based approach for semantic segmentation of fracture surfaces, demonstrating high accuracy across different ceramic materials with minimal training data.

## Key findings

- High prediction accuracy on ceramic fracture images
- Effective transferability across different materials
- Potential for extension to various fracture morphologies

## Abstract

The science of fractography revolves around the correlation between topographic characteristics of the fracture surface and the mechanisms and external conditions leading to their creation. While being a topic of investigation for centuries, it has remained mostly qualitative to date. A quantitative analysis of fracture surfaces is of prime interest for both the scientific community and the industrial sector, bearing the potential for improved understanding on the mechanisms controlling the fracture process and at the same time assessing the reliability of computational models currently being used for material design. With new advances in the field of image analysis, and specifically with machine learning tools becoming more accessible and reliable, it is now feasible to automate the process of extracting meaningful information from fracture surface images. Here, we propose a method of identifying and quantifying the relative appearance of intergranular and transgranular fracture events from scanning electron microscope images. The newly proposed method is based on a convolutional neural network algorithm for semantic segmentation. The proposed method is extensively tested and evaluated against two ceramic material systems ($Al_2O_3$,$MgAl_2O_4$) and shows high prediction accuracy, despite being trained on only one material system ($MgAl_2O_4$). While here attention is focused on brittle fracture characteristics, the method can be easily extended to account for other fracture morphologies, such as dimples, fatigue striations, etc.