A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys

Hydride precipitation within zirconium alloys affects ductility and fracture behavior. The complex distribution of hydrides and their interaction with defects, such as dislocations, have a significant role in crack nucleation and failure. Hence, there is substantial variability in the microstructural behavior of hydrided zirconium. A deterministic fracture model coupled to a dislocation-density based crystalline plasticity approach was used to predict failure. Deterministic simulations were used to develop a database of crack initiation for representative microstructural characteristics, such as texture, crystalline structure, hydride orientations and spacing, and hydride geometry. The machine learning (ML) analysis is based on Extreme Value Theory (EVT) and a Bayesian based Gaussian Process Regression (GPR). Fracture probability is significantly influenced by hydride orientation and dislocation-density interactions. Furthermore, surrogate reduced order models (ROM) models were used to predict the likelihood of failure. This approach provides a ML framework to predict failure at different physical scales.

Automated summary

Hydride precipitation in zirconium alloys affects their ductility and fracture behavior. The complex distribution of hydrides and their interaction with defects, such as dislocations, play a significant role in crack nucleation and failure. Deterministic fracture modeling coupled with dislocation-density based crystalline plasticity approach was used to predict failure. Machine learning analysis based on Extreme Value Theory (EVT) and a Bayesian based Gaussian Process Regression (GPR) was employed to predict fracture probability. Surrogate reduced order models (ROM) were also used for predicting failure likelihood, providing a multi-scale machine learning framework for failure prediction.