Search NASA⌕ Search

Engineering topics

Vaughan, Matthew W.

Publications and source records attributed to Vaughan, Matthew W..

Predicting Failure Using Deep Learning SAND Report

Accurate prediction of ductile failure is critical to Sandia’s NW mission, but the models are computationally heavy. The costs of including high-fidelity physics and mechanics that are germane to the failure mechanisms are often too burdensome for analysts either because of the person-hours it requires to input them or because of the additional computational time, or both. In an effort to deliver analysts a tool for representing these phenomena with minimal impact to their existing workflow, our project sought to develop modern data-driven methods that would add microstructural information to business-as-usual calculations and expedite failure predictions. The goal is a tool that receives as input a structural model with stress and strain fields, as well as a machine-learned model, and output predictions of structural response in time, including failure. As such, our project spent substantial time performing high-fidelity, three-dimensional experiments to elucidate materials mechanisms of void nucleation and evolution. We developed crystal-plasticity finite-element models from the experimental observations to enrich the findings with fields not readily measured. We developed engineering length-scale simulations of replicated test specimens to understand how the engineering fields evolve in the presence of fine-scale defects. Finally, we developed deep learning convolutional neural networks, and graph-based neural networks to encode the findings of the experiments and simulations and make forward predictions in time for structural performance. This project demonstrated the power of data-driven methods for model development, which have the potential to vastly increase both the accuracy and speed of failure predictions. These benefits and the methods necessary to develop them are highlighted in this report. However, many challenges remain to implementing these in real applications, and these are discussed along with potential methods for overcoming them.

97 MATHEMATICS AND COMPUTING↗

Effects of chemical segregation on ductility-anisotropy in high strength Fe-Mn-Al-C lightweight austenitic steels

Ductile Fe-Mn-Al-C lightweight steels offer great potential as high specific strength materials for weight critical applications. In the present work, very high yield (~1 GPa) and ultimate tensile strength levels (~1.5 GPa) were obtained along the rolling and transverse directions of Fe-30Mn-8.5Al-0.9Si-0.9C-0.5Mo (wt.%), with high tensile elongation to failure of ~35%. This excellent mechanical behavior was attributed to the nanoscale, ordered κ-carbide precipitates formed during aging after rolling. However, tensile ductility was not isotropic through all directions of the rolled plate. In particular, the ductility was consistently lower than 5% true strain along the normal direction. Upon detailed microstructural investigations, micro-scale lamellar chemical micro-segregation bands were detected, which caused the observed anisotropic embrittlement along certain plate directions. These bands resulted in low failure strains along the normal direction since it is oriented perpendicular to these chemical segregation bands, resulting in a failure type reminiscent of delamination-induced cleavage fracture. Chemical segregation causes an inhomogeneous κ-carbide precipitate distribution upon aging, producing more pronounced mechanical anisotropy after peak-aging as compared to the solution heat treated samples. Surprisingly, deformation twinning was observed after tensile deformation of solution-heat treated specimens via electron-backscatter diffraction experiments, which is anomalous for a high stacking faulty energy (SFE) material. Further, it was proposed that chemical micro-segregation promotes locally different SFE regions, leading to deformation twinning in this nominally high SFE material. Overall, this work demonstrates the effects of chemical segregation on mechanical properties and microstructural evolution in a high performance, lightweight Fe-Mn-Al-C steel.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗