Materials fatigue prediction using graph neural networks on microstructure representations.

The local prediction of fatigue damage within polycrystals in a high-cycle fatigue setting is a long-lasting and challenging task. It requires identifying grains tending to accumulate plastic deformation under cyclic loading. We address this task by transcribing ferritic steel microtexture and damage maps from experiments into a microstructure graph. Here, grains constitute graph nodes connected by edges whenever grains share a common boundary. Fatigue loading causes some grains to develop slip markings, which can evolve into microcracks and lead to failure. This data set enables applying graph neural network variants on the task of binary grain-wise damage classification. The objective is to identify suitable data representations and models with an appropriate inductive bias to learn the underlying damage formation causes. Here, graph convolutional networks yielded the best performance with a balanced accuracy of 0.72 and a F1-score of 0.34, outperforming phenomenological crystal plasticity (+ 68%) and conventional machine learning (+ 17%) models by large margins. Further, we present an interpretability analysis that highlights the grains along with features that are considered important by the graph model for the prediction of fatigue damage initiation, thus demonstrating the potential of such techniques to reveal underlying mechanisms and microstructural driving forces in critical grain ensembles.

A deep learning approach for complex microstructure inference.

Automated, reliable, and objective microstructure inference from micrographs is essential for a comprehensive understanding of process-microstructure-property relations and tailored materials development. However, such inference, with the increasing complexity of microstructures, requires advanced segmentation methodologies. While deep learning offers new opportunities, an intuition about the required data quality/quantity and a methodological guideline for microstructure quantification is still missing. This, along with deep learning's seemingly intransparent decision-making process, hampers its breakthrough in this field. We apply a multidisciplinary deep learning approach, devoting equal attention to specimen preparation and imaging, and train distinct U-Net architectures with 30-50 micrographs of different imaging modalities and electron backscatter diffraction-informed annotations. On the challenging task of lath-bainite segmentation in complex-phase steel, we achieve accuracies of 90% rivaling expert segmentations. Further, we discuss the impact of image context, pre-training with domain-extrinsic data, and data augmentation. Network visualization techniques demonstrate plausible model decisions based on grain boundary morphology.

Automated Quantitative Analyses of Fatigue-Induced Surface Damage by Deep Learning.

The digitization of materials is the prerequisite for accelerating product development. However, technologically, this is only beneficial when reliability is maintained. This requires comprehension of the microstructure-driven fatigue damage mechanisms across scales. A substantial fraction of the lifetime for high performance materials is attributed to surface damage accumulation at the microstructural scale (e.g., extrusions and micro crack formation). Although, its modeling is impeded by a lack of comprehensive understanding of the related mechanisms. This makes statistical validation at the same scale by micromechanical experimentation a fundamental requirement. Hence, a large quantity of processed experimental data, which can only be acquired by automated experiments and data analyses, is crucial. Surface damage evolution is often accessed by imaging and subsequent image post-processing. In this work, we evaluated deep learning (DL) methodologies for semantic segmentation and different image processing approaches for quantitative slip trace characterization. Due to limited annotated data, a U-Net architecture was utilized. Three data sets of damage locations observed in scanning electron microscope (SEM) images of ferritic steel, martensitic steel and copper specimens were prepared. In order to allow the developed models to cope with material-specific damage morphology and imaging-induced variance, a customized augmentation pipeline for the input images was developed. Material domain generalizability of ferritic steel and conjunct material trained models were tested successfully. Multiple image processing routines to detect slip trace orientation (STO) from the DL segmented extrusion areas were implemented and assessed. In conclusion, generalization to multiple materials has been achieved for the DL methodology, suggesting that extending it well beyond fatigue damage is feasible.