Predictive modeling of dynamic fracture growth in brittle materials with machine learning

We use simulation data from a high fidelity Finite-Discrete Element Model to build an efficient Machine Learning (ML) approach to predict fracture growth and coalescence. Our goal is for the ML approach to be used as an emulator in place of the computationally intensive high fidelity models in an uncertainty quantification framework where thousands of forward runs are required. The failure of materials with various fracture configurations (size, orientation and the number of initial cracks) are explored and used as data to train our ML model. This novel approach has shown promise in predicting spatial (path to failure) and temporal (time to failure) aspects of brittle material failure. Predictions of where dominant fracture paths formed within a material were similar to 85% accurate and the time of material failure deviated from the actual failure time by an average of similar to 16%. Additionally, the ML model achieves a reduction in computational cost by multiple orders of magnitude. Published by Elsevier B.V.