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

Abstract

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.

Hydrogen Embrittlement as a Conspicuous Material Challenge─Comprehensive Review and Future Directions

“…ML holds promise for bridging this gap by enabling the transfer of information across scales. Hasan et al , presented a novel approach to predict the failure probability of hydrided zirconium materials, using a combination of deterministic physics-based continuum simulations and ML techniques. At the microstructure level, their approach was able to predict the onset of cracks by focusing on features that reflect the buildup of stationary and moving dislocations (microstructural defects).…”