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 micro...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | npj Materials Degradation |
| Online Access: | https://doi.org/10.1038/s41529-023-00344-7 |
| _version_ | 1797853676893634560 |
|---|---|
| author | Tamir Hasan Laurent Capolungo Mohammed Zikry |
| author_facet | Tamir Hasan Laurent Capolungo Mohammed Zikry |
| author_sort | Tamir Hasan |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-09T19:54:33Z |
| format | Article |
| id | doaj.art-cd52a9c802d3462b969d75a56725692a |
| institution | Directory Open Access Journal |
| issn | 2397-2106 |
| language | English |
| last_indexed | 2024-04-09T19:54:33Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Materials Degradation |
| spelling | doaj.art-cd52a9c802d3462b969d75a56725692a2023-04-03T05:35:10ZengNature Portfolionpj Materials Degradation2397-21062023-03-017111110.1038/s41529-023-00344-7A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloysTamir Hasan0Laurent Capolungo1Mohammed Zikry2North Carolina State UniversityLos Alamos National LaboratoryNorth Carolina State UniversityAbstract 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.https://doi.org/10.1038/s41529-023-00344-7 |
| spellingShingle | Tamir Hasan Laurent Capolungo Mohammed Zikry A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys npj Materials Degradation |
| title | A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys |
| title_full | A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys |
| title_fullStr | A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys |
| title_full_unstemmed | A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys |
| title_short | A machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys |
| title_sort | machine learning microstructurally predictive framework for the failure of hydrided zirconium alloys |
| url | https://doi.org/10.1038/s41529-023-00344-7 |
| work_keys_str_mv | AT tamirhasan amachinelearningmicrostructurallypredictiveframeworkforthefailureofhydridedzirconiumalloys AT laurentcapolungo amachinelearningmicrostructurallypredictiveframeworkforthefailureofhydridedzirconiumalloys AT mohammedzikry amachinelearningmicrostructurallypredictiveframeworkforthefailureofhydridedzirconiumalloys AT tamirhasan machinelearningmicrostructurallypredictiveframeworkforthefailureofhydridedzirconiumalloys AT laurentcapolungo machinelearningmicrostructurallypredictiveframeworkforthefailureofhydridedzirconiumalloys AT mohammedzikry machinelearningmicrostructurallypredictiveframeworkforthefailureofhydridedzirconiumalloys |