Automated workflow identifies cracks and measures damage in fusion materials
An Automated and Reproducible Workflow for Crack Identification and Damage Assessment of Fusion Materials
Machine Learning
Summary
Checking materials used in fusion reactors for cracks is really important but can take a lot of time when done by hand. The authors created a computer workflow that automatically looks at microscope images to find cracks and measure damage in tungsten materials without needing to adjust settings for each image. Their system works across different types of tungsten and imaging details, saving time and making results easier to trust and share. They also provide tools to predict material damage and guide future experiments using this data.
What this means in practice
- •For materials engineering teams: Automatically detect and quantify cracks in tungsten fusion materials to speed up damage evaluation without manual image adjustments.
- •For industrial quality control teams: Standardize crack density measurements to support predictive modeling and improve inspection accuracy in metal component manufacturing.
Authors
Rinkle Juneja, Viktor Reshniak, Richard K. Archibald, John W. Duggan, Gregory R. Watson, Cory D. Hauck, Gary M. Staebler
Abstract
Post-exposure microscopy is central to qualification of fusion materials. However, manual analysis does not scale to the volume, heterogeneity, and multiresolution character of modern fusion-materials campaigns. To address this challenge, we present a reproducible workflow, implemented in the Galaxy scientific workflow environment, for automated crack identification and quantitative damage assessment from scanning electron microscopy images. The workflow processes SEM images and experimental metadata to identify cracks, quantify damage, and retain the intermediate products and processing history needed for reproducibility. Outputs include crack masks, skeletonized crack networks, quality-control visualizations, and scalar damage descriptors. The method is designed to operate without image-specific parameter tuning across tungsten grades, microstructures, magnifications, and damage states. We demonstrate the workflow on a sparse electron-beam thermal-shock dataset containing 418 images from 114 experiments spanning five tungsten grades and three microstructural states. We define a crack-density descriptor, which provides standardized inputs for downstream machine-learning prediction and physics-based crack simulation. These predictive components are exposed in the same Galaxy environment and are intentionally treated here as extensible workflow modules. The principal contribution is therefore an end-to-end, shareable, and computationally portable workflow that links experimental characterization, automated image analysis, preliminary damage prediction, and simulation-guided data acquisition for fusion-materials research.