Search NASA⌕ Search

Engineering topics

Pant, Aniket

Publications and source records attributed to Pant, Aniket.

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↗

Angle-resolved polarimetry of hybrid perovskite emission for photonic technologies

Coupling between light and matter strongly depends on the polarization of the electromagnetic field and the nature of excitations in a material. As hybrid perovskites emerge as a promising class of materials for light-based technologies such as LEDs, LASERs, and photodetectors, it is critical to understand how their microstructure changes the intrinsic properties of the photon emission process. While the majority of optical studies have focused on the spectral content, quantum efficiency and lifetimes of emission in various hybrid perovskite thin films and nanostructures, few studies have investigated other properties of the emitted photons such as polarization and emission angle. Here, we use angle-resolved cathodoluminescence microscopy to access the full polarization state of photons emitted from large-grain hybrid perovskite films with spatial resolution well below the optical diffraction limit. In this work, mapping these Stokes parameters as a function of the angle at which the photons are emitted from the thin film surface, we reveal the effect of a grain boundary on the degree of polarization and angle at which the photons are emitted. Such studies of angle- and polarization-resolved emission at the single grain level are necessary for future development of perovskite-based flat optics, where effects of grain boundaries and interfaces need to be mitigated.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Automatic Detection of Defects in High-Reliability Components

Disastrous consequences can result from defects in manufactured parts—particularly the high consequence parts developed at Sandia. Identifying flaws in as-built parts can be done with nondestructive means, such as X-ray Computed Tomography (CT). However, due to artifacts and complex imagery, the task of analyzing the CT images falls to humans. Human analysis is inherently unreproducible, unscalable, and can easily miss subtle flaws. We hypothesized that deep learning methods could improve defect identification, increase the number of parts that can effectively be analyzed, and do it in a reproducible manner. We pursued two methods: 1) generating a defect-free version of a scan and looking for differences (PandaNet), and 2) using pre-trained models to develop a statistical model of normality (Feature-based Anomaly Detection System: FADS). Both PandaNet and FADS provide good results, are scalable, and can identify anomalies in imagery. In particular, FADS enables zero-shot (training-free) identification of defects for minimal computational cost and expert time. It significantly outperforms prior approaches in computational cost while achieving comparable results. FADS’ core concept has also shown utility beyond anomaly detection by providing feature extraction for downstream tasks.

47 OTHER INSTRUMENTATION↗