Predicting Microstructure-Sensitive Fatigue-Crack Path in 3D Using a Machine Learning Framework

The overarching aim of this paper is to explore the use of machine learning (ML) to predict the microstructure-sensitive evolution of a three-dimensional (3D) crack surface in a polycrystalline alloy. A convolutional neural network (CNN)-based methodology is developed to establish spatial relationships between micromechanical/microstructural features in a cyclically loaded, uncracked microstructure and the 3D crack path, the latter quantified by the vertical deviation (i.e., z-offset) of the crack along a specified axis. The proposed methodology consists of (i) a feature selection and reduction scheme to identify a lower-dimensional representation of the experimentally measured microstructure and computed micromechanical fields, which allows for computational feasibility in predicting the z-offsets; (ii) a CNN model to compute the z-offset as a function of the local, lower-dimensional feature data; and (iii) a radial basis function smoothing spline to ensure spatial continuity between the independently predicted z-offsets. The proposed CNN-based methodology is shown to improve on the accuracies obtained using existing ML models such as XGBoost and to provide a definitive way of quantifying model uncertainty associated with CNN predictions. To further investigate the applicability of ML models, multiple prediction strategies with which to deploy ML algorithms are proposed and the relative performance of ML algorithms corresponding to each prediction strategy are analyzed. The presented work thus provides a framework to find an encoded representation of 3D microstructure and micromechanical data and develop methods to predict microstructure-sensitive crack evolution based on this encoded representation, while quantifying associated prediction uncertainties.