Deep learning approaches to semantic segmentation of fatigue cracking within cyclically loaded nickel superalloy

Abstract

Improvements to synchrotron-based micro-computed tomography scanning capabilities have gifted researchers the ability to characterize 4D material thermomechanical responses more thoroughly than ever before. These advancements, however, have brought about new challenges in analyzing the resulting deluge of data. We report on a nickel-based superalloy specimen imaged 26 times in-situ during cyclic loading at Argonne National Laboratory Advanced Photon Source beamline 1ID, in order to monitor crack growth within the microstructure. Several deep learning approaches which utilize convolutional neural networks are implemented to segment crack features from reconstructed tomography scans. U-Net architecture implementations are found to be especially effective, achieving IoU=0.995±0.004 and Matthews correlation coefficient scores of ϕ=0.826±0.085. These advancements broaden possibilities for scientists seeking to automate segmentation analyses of similar large datasets.