SEARCH · Engineering Papers
Results for “Automatic”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
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.
REFINING AUTOMATICALLY GENERATED MICROKINETIC MECHANISMS IN A WORKFLOW.
Abstract not provided.
Automatic MCNP File Generation for Cherenkov Imaging Simulations [Slides]
Overview: Creating physics models to accurately simulate a variety of spent fuel assemblies. These characterized simulations will then be used to create a well documented repository that encompasses a wide variety of different fuel assemblies, burn-up and spent fuel pool conditions, and defects. The final project will use our simulations to train an AI, and for it to be effective it has to have a lot of reliable data; Automating an arbitrary amount of created spent fuel pins with materials, that will be passed into AI models for it to "learn" what a good spent nuclear fuel cell looks like and what a non-spent nuclear fuel cell looks like.
Automatic detection of defects in high reliability as-built parts using X-ray CT.
Abstract not provided.
An Automatic Tool for Data QC in Seismic Arrays using Signal Singular Values.
Abstract not provided.
Using Containers and Automatic Provenance Collection for Sustainable Scientific Software.
Abstract not provided.
Dualization for Automatic Mesh Generation in the Pixel to Mesh Workflow - Quad Chart.
Abstract not provided.
Dualization for Automatic Mesh Generation in the Pixel to Mesh Workflow.
Abstract not provided.
Toward Automatic Test Synthesis for Performance Portable Programs.
Abstract not provided.
PyTrilinos2: automatic (re)generation of a Python interface for Trilinos.
Abstract not provided.
Automatic Validation of Simulation and Reconstruction Software
Explore the source record for details and available documents.
GEOMWRITER - A Workflow for Automatically Generating MCNP Geometry for Neutron Guide Simulations
This report describes the functionality of the geomwriter.py script, which is a python script for producing complex MCNP CSG geometries from the IGES CAD format. It is specifically written to handle neutron supermirror guides, but can handle more complex objects through utilizing a convex hull algorithm. This work flow reduces the amount of time spent on generating the surface definitions for a complex neutron guide system with hundreds of segments such that changes to the neutron guide system design in McStas can be rapidly incorporated into an MCNP model and integrated with the shielding geometry present in that model.
A Software Tool for Automatic Estimation of X-Ray CT Scan Geometry [Slides]
Abstract not provided.
Wide Area Measurement System (WAMS) Automatic Depth Feature Analysis [Slides]
Abstract not provided.