Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Transformer model”

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.

At least 1,621 records · Page 90
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

OPTIMIZATION OF A NUCLEAR VESSEL OUTLET FOR INCIDENT MONITORING

Classical nuclear core fluidic design techniques require improvement to better align with modern technological innovations. The US Department of Energy’s Office of Nuclear Energy (DOE-NE) Transformational Challenge Reactor (TCR) program is deploying additive manufacturing and advanced modeling and simulation to reimagine these designs. With the aid of modern computing power, computerized design optimization can be implemented to remove unwanted pressure drop while simultaneously optimizing flow structures, resulting in new opportunities to enable advanced instrumentation and monitoring capabilities.Previous development of geometric specifications for the TCR pressure vessel’s outlet plenum used design optimization to (1) limit pressure losses below 3.5 kPa (~0.5 psi) and (2) create a fluidic plane in which the temperature variation would not exceed ±5°C. This significant limit of the allowable pressure drop stems from the overarching goal of the TCR program to apply cutting edge techniques and unconventional thinking to demonstrate potential opportunities in additive manufacturing (AM).This paper expands the previous work by optimizing thermowell locations for robust measurements by explicitly modeling them and the resulting flow impacts. Additionally, a single core coolant channel was chosen to represent an event that causes an increased bulk flow temperature increase of 100°C.High fidelity unsteady Reynolds-averaged Navier-Stokes (URANS) simulations of the conjugate heat transfer problem were run in Siemen’s Star-CCM+ for this study. Next, the bulk flow temperature of a single coolant channel was increased by 100°C and was allowed to converge again. Finally, statistical analysis using a sequential probability ratio test (SPRT) was used to determine the elapsed time the thermocouples took to discover the increased bulk flow temperature.

See, Nate↗
DOE OSTI2022

TRANSSFORM Workshop Empowering the US manufacturing industry proceedings report

The U.S. Department of Energy (DOE), Office of Energy Efficiency and Renewable Energy, and Advanced Manufacturing Office (AMO) hosted the TRANSSFORM (Transformative, Resilient, Adaptive, Nimble, Sustainable, Smart, Flexible, Optimal, Robust, and Model-based1 – A Bold Vision for the Future of U.S. Manufacturing) Workshop on September 8–10, 2021. The objective of the workshop was to hear from stakeholders about how manufacturing digitalization can improve manufacturing competitiveness and reduce energy consumption and emissions production from U.S. manufacturing, and what research, development, and demonstrations are needed to have the desired impact.

manufacturing digitalization, decarbonization, IoT↗
DOE OSTI2023

Sustainable Manufacturing and the Circular Economy

The manufacturing industry predominantly follows a linear model of production in which raw materials are mined or grown, transformed into manufactured goods, used for a period, and then discarded. However, this once-through flow of materials to manufactured products is not sustainable. Many high-grade ore bodies have been consumed, increasing the energy and material impacts per ton of mined material. At the other end of the cycle, there are challenges with the efficiency and effectiveness of our waste disposal system.

life cycle, ReX↗
NASA NTRS1994

An initiation-promotion model of tumour prevalence from high-charge and energy radiations

A repair/misrepair kinetic model for multiple radiation-induced lesions (mutation inactivation) is coupled to a two-mutation model of initiation-promotion in tissue to provide a parametric description of tumour prevalence in the mouse Harderian gland from high-energy and charge radiations. Track-structure effects are considered using an action-cross section model. Dose-response curves are described for gamma rays and relativistic ions, and good agreement with experiment is found. The effects of nuclear fragmentation are also considered for high-energy proton and alpha-particle exposures. The model described provides a parametric description of age-dependent cancer induction for a wide range of radiation fields. Radiosensitivity parameters found in the model for an initiation mutation (sigma 0 = 7.6 x 10(-10) cm2 and D0 = 148.0 Gy) are somewhat different than previously observed for neoplastic transformation of C3H10T1/2 cell cultures (sigma 0 = 0.7 x 10(-10) cm2 and D0 = 117.0 Gy). We consider the two hypotheses that radiation acts solely as an initiator or as both initiator and promoter and make model calculations for fractionation exposures from gamma rays and relativistic Fe ions. For fractionated Fe exposures, an inverse-dose-rate effect is provided by a promotion hypothesis with an increase of 30% or more, dependent on the dose level and fractionation schedule, using a mutation rate for promotion similar to that of single-gene mutations.

NASA Discipline Radiation Health↗
DOE OSTI2024

Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems

This study proposes using neural networks, specifically gated recurrent unit (GRU), long-short-term memory (LSTM), and transformer networks, to improve control strategies in a 450 MW coal-fired power plant. However, neural networks face issues of becoming overly dependent on just a few variables to make predictions, which negatively impacts control decisions that rely on the model to determine the value of all manipulated variables. The paper introduces regularization techniques, including noise injection and input gradient regularization, during the training phase. Here, the work presents novel contributions in adapting neural networks to control industrial systems and applying regularization techniques from computer vision to industrial process control. Results demonstrate the effectiveness of input gradient regularization in reducing model dependence on subsets of variables, emphasizing the balance between fidelity and controllability. Further exploration is recommended, including the development of recurrent transformers, closed-loop control testing, and a sensitivity analysis on computer models to provide further insight.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2025

A Data-Agnostic, Continuous Machine Learning Framework for Application in High Energy Physics and Beyond: Phase 1 Final Scientific/Technical Report

This Phase 1 effort has focused on the development of continual learning frameworks for use in machine learning, specifically in the applied context of High Energy Physics (HEP). Machine learning (ML) is a transformative technology by which computers, typically through the use of neural networks, are able to perform tasks with proficiency that rivals or surpasses that of human users. Model Degradation & Catastrophic Forgetting are two undesired phenomena which can occur in ML where the performance of a model degrades when either deployed on novel data streams, or trained on novel data which are sufficiently different than the data the models were initially trained on. A natural example where these sorts of effects can be observed is in the performance of detectors in harsh environments, where the detector signature may change over the lifetime of the detector as it ages and deteriorates — precisely what occurs in the experiments conducted in HEP. Real world HEP data is therefore an excellent test-ground and use-case for Continual Learning paradigms, which are techniques used in ML to counteract these problems. Ensemble learning is one such technique, where multiple smaller models are trained on subsets of the overall data and are ensembled together during inference. The intuition behind this technique is that, although there are shifts in the distributions which govern the incoming data streams, these shifts are not expected to be homogeneous or global. If a sufficient diversity in solutions within the various sub-models has been achieved, then at least one sub-model is expected to retain its performance within the overall ensemble. One further strength of this approach is that the architectures of the various models do not need to be identical, and in fact even different modalities of data can naturally be combined in this way. This work focused on applying ensemble learning techniques to derive results using two main datasets, anomaly detection in HEP data & time-series forecasting in semiconductor manufacturing data. Semiconductor manufacturing involves data with surprising similarity to that of HEP (e.g. wafer maps look very similar to digi-occupancy maps) and Cerium Lab’s prominence within the semiconductor industry makes semiconductor manufacturing a natural opportunity for commercialization of this work. Our efforts have led to two strong results. The first is that we evaluated the proposed ensembling techniques using previously proposed machine learning architectures for use in anomaly detection, namely AutoEncoder based models and their derivatives. We also developed new architectures which have not been evaluated in this context before. In fact, this work marks the first use of Vision Transformers for anomaly detection in HEP. Second, we demonstrated that ensemble learning significantly improves model performance in scenarios prone to degradation, validating its effectiveness across both HEP and semiconductor datasets. These results further support ensemble learning as a powerful strategy for mitigating catastrophic forgetting and maintaining robust performance in evolving data environments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1996

Constitutive Models for Shape Memory Alloy Polycrystals

Shape memory alloys (SMA) exhibiting the superelastic or one-way effects can produce large recoverable strains upon application of a stress. In single crystals this stress and resulting strain are very orientation dependent. We show experimental stress/strain curves for a Ni-Al single crystal for various loading orientations. Also shown are model predictions; the open and closed circles indicate recoverable strains obtained at various stages in the transformation process. Because of the strong orientation dependence of shape memory properties, crystallographic texture can be expected to play an important role in the mechanical behavior of polycrystalline SMA. It is desirable to formulate a constitutive model to better understand and exploit the unique properties of SMA.

Comstock, R. J., Jr.↗
NASA NTRS2006

Determining Kinetic Parameters for Isothermal Crystallization of Glasses

Non-isothermal crystallization techniques are frequently used to determine the kinetic parameters for crystallization in glasses. These techniques are experimentally simple and quick compared to the isothermal techniques. However, the analytical models used for non-isothermal data analysis, originally developed for describing isothermal transformation kinetics, are fundamentally flawed. The present paper describes a technique for determining the kinetic parameters for isothermal crystallization in glasses, which eliminates most of the common problems that generally make the studies of isothermal crystallization laborious and time consuming. In this technique, the volume fraction of glass that is crystallized as a function of time during an isothermal hold was determined using differential thermal analysis (DTA). The crystallization parameters for the lithium-disilicate (Li2O.2SiO2) model glass were first determined and compared to the same parameters determined by other techniques to establish the accuracy and usefulness of the present technique. This technique was then used to describe the crystallization kinetics of a complex Ca-Sr-Zn-silicate glass developed for sealing solid oxide fuel cells.

Ray, C. S.↗
DOE OSTI2024

The melt memory effects in polymer crystallization

This paper presents a systematic review of the literature on the melt memory effects observed in polymers, an area that has engendered considerable debate for over 50 years. Recent advances in experimental techniques have provided fresh insights into how a polymer's thermal history influences its recrystallization behavior. It has been observed that given other conditions unchanged, the crystallization temperature during recrystallization decreases with an increase in the melt temperature T s above the melting point T m until a critical melt temperature is attained. This phenomenon also extends to the half-time of crystallization and the secondary structures, such as lamellar thickness, of semi-crystalline polymers. Despite these findings, a comprehensive constitutive model that encapsulates polymer melt memory effects remains elusive. Cutting-edge instrumentation, including in situ small and wide-angle X-ray scattering, temperature-controlled Fourier transform infrared spectroscopy, and flash differential scanning calorimetry, have posed significant challenges to the traditional nucleation and growth models established in the 1970s. These models are foundational to our understanding of polymer crystallization, which is an integral part of polymer processing and production. In this review, the historical contours of this discourse are traced, with an examination of both the recent experimental breakthroughs and theoretical advancements pertinent to polymer melt memory effects. In conclusion, this paper delves into the prevailing theories of polymer nucleation and crystallization and engages with theoretical discussions and numerical simulations that attempt to elucidate and rationalize these melt memory phenomena.

36 MATERIALS SCIENCE↗
NASA NTRS1985

Statistical comparison of galaxy formation models - The bispectrum

To discriminate between galaxy-formation models that give similar two-point correlation functions, higher moments, specifically the three-point function in transform space or bispectrum, are looked to for an ensemble of numerical simulations. Different behaviors of this statistic are found that can be used to distinguish between classes of models. Up to the uncertainty in identifying the galaxy distribution with the mass distribution in the models, the results seem to prefer the isothermal or the cold-particle models. No model, however, agrees in all detail with the observational bispectrum of the Shane-Wirtanen galaxy catalog.

Fry, J. N.↗
NASA NTRS1992

Linear velocity fields in non-Gaussian models for large-scale structure

Linear velocity fields in two types of physically motivated non-Gaussian models are examined for large-scale structure: seed models, in which the density field is a convolution of a density profile with a distribution of points, and local non-Gaussian fields, derived from a local nonlinear transformation on a Gaussian field. The distribution of a single component of the velocity is derived for seed models with randomly distributed seeds, and these results are applied to the seeded hot dark matter model and the global texture model with cold dark matter. An expression for the distribution of a single component of the velocity in arbitrary local non-Gaussian models is given, and these results are applied to such fields with chi-squared and lognormal distributions. It is shown that all seed models with randomly distributed seeds and all local non-Guassian models have single-component velocity distributions with positive kurtosis.

Scherrer, Robert J.↗
DOE OSTI2022

PyOECP: A flexible open-source software library for estimating and modeling the complex permittivity based on the open-ended coaxial probe (OECP) technique

Here, we present PyOECP, a Python-based flexible open-source software for estimating and modeling the complex permittivity obtained from the open-ended coaxial probe (OECP) technique. The transformation of the measured reflection coefficient to complex permittivity is performed based on three different methods. The software library contains the dielectric spectra of common reference liquids, which can be used to transform the reflection coefficient into the dielectric spectra. Several Python routines that are commonly employed (e.g., SciPy and NumPy) in the field of science and engineering are required only so that the users can alter the software structure depending on their needs. The modeling algorithm exploits the Markov Chain Monte Carlo method for the data regression. The discrete relaxation models can be built by a proper combination of well-known relaxation models. In addition to these models, electrode polarization, a typical measurement artifact for interpreting dielectric spectra, can be incorporated into the modeling algorithm. A continuous relaxation model, which solves the Fredholm integral equation of the first kind (a mathematically ill-posed problem), is also included. This open-source software enables users to freely adjust the physical parameters to obtain physical insight into their materials under test and will be consistently updated for more accurate measurement and interpretation of dielectric spectra in an automated manner. This work describes the theoretical and mathematical background of the software, lays out the workflow, and validates the software functionality based on both synthetic and empirical data included in the software.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Scaling similarities and quasinormal modes of D0 black hole solutions

We study the gravity solution dual to the D0 brane quantum mechanics, or BFSS matrix model, in the ’t Hooft limit. The classical physics described by this gravity solution is invariant under a scaling transformation, which changes the action with a specific critical exponent, sometimes called the hyperscaling violating exponent. We present an argument for this critical exponent from the matrix model side, which leads to an explanation for the peculiar temperature dependence of the entropy in this theory, S ∝ T 9/5 . We also present a similar argument for all other Dp-brane geometries. We then compute the black hole quasinormal modes. This involves perturbing the finite temperature geometry. These perturbations can be easily obtained by a mathematical trick where we view the solution as the dimensional reduction of an Ad S2+9/5 × S 8 geometry.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1995

Advanced Modeling of Micromirror Devices

The flexure-beam micromirror device (FBMD) is a phase only piston style spatial light modulator demonstrating properties which can be used for phase adaptive corrective optics. This paper presents a complete study of a square FBMD, from advanced model development through final device testing and model verification. The model relates the electrical and mechanical properties of the device by equating the electrostatic force of a parallel-plate capacitor with the counter-acting spring force of the device's support flexures. The capacitor solution is derived via the Schwartz-Christoffel transformation such that the final solution accounts for non-ideal electric fields. The complete model describes the behavior of any piston-style device, given its design geometry and material properties. It includes operational parameters such as drive frequency and temperature, as well as fringing effects, mirror surface deformations, and cross-talk from neighboring devices. The steps taken to develop this model can be applied to other micromirrors, such as the cantilever and torsion-beam designs, to produce an advanced model for any given device. The micromirror devices studied in this paper were commercially fabricated in a surface micromachining process. A microscope-based laser interferometer is used to test the device in which a beam reflected from the device modulates a fixed reference beam. The mirror displacement is determined from the relative phase which generates a continuous set of data for each selected position on the mirror surface. Plots of this data describe the localized deflection as a function of drive voltage.

Michalicek, M. Adrian↗
NASA NTRS2021

On-Orbit Cryogenic Refueling: Potential Mission Benefits, Associated Orbital Mechanics, and Fuel Transfer Thermodynamic Modeling Efforts

The placement of cryogenic fuel/propellant depot stations in Earth orbit has the potential to transform the nature and operations for many types of spaceflight missions. Today, spaceflight missions are almost universally required to carry the entire amount of fuel required for the mission, for the entire duration of the mission, from the point of launch. This is the rough equivalent of making a drive from Ohio to California, requiring the traveler to bring along the total sum of gasoline required for the entire trip, without being able to ‘fill-up’ anywhere along the route. Obviously, this framework of travel greatly encumbers the breadth, scope, and efficiency of potential journeys. Cryogenic fuel/propellant depots have not been implemented because many technical, operational, and engineering challenges still exist. These must be overcome prior to the placement of usable on-orbit propellant depots. This thesis investigates three specific engineering challenges related to on-orbit propellant depots, and presents the current state, technological challenges, and ultimate benefits of on-orbit cryogenic refueling.

No vent fill↗
DOE OSTI2023

Modelling populations of kilonovae

Abstract The 2017 detection of a kilonova coincident with gravitational-wave emission has identified neutron star mergers as the major source of the heaviest elements and dramatically constrained alternative theories of gravity. Observing a population of such sources has the potential to transform cosmology, nuclear physics, and astrophysics. However, with only one confident multi-messenger detection currently available, modelling the diversity of signals expected from such a population requires improved theoretical understanding. In particular, models that are quick to evaluate and are calibrated with more detailed multi-physics simulations are needed to design observational strategies for kilonovae detection and to obtain rapid-response interpretations of new observations. We use grey-opacity models to construct populations of kilonovae, spanning ejecta parameters predicted by numerical simulations. Our modelling focuses on wavelengths relevant for upcoming optical surveys, such as the Rubin Observatory Legacy Survey of Space and Time (LSST). In these simulations, we implement heating rates that are based on nuclear reaction network calculations. We create a Gaussian-process emulator for kilonova grey opacities, calibrated with detailed radiative transfer simulations. Using recent fits to numerical relativity simulations, we predict how the ejecta parameters from binary neutron star (BNS) mergers shape the population of kilonovae, accounting for the viewing-angle dependence. Our simulated population of BNS mergers produce peak i-band absolute magnitudes of −20 ≤ Mi ≤ −11. A comparison with detailed radiative transfer calculations indicates that further improvements are needed to accurately reproduce spectral shapes over the full light curve evolution.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2011

Range 7 Scanner Integration with PaR Robot Scanning System

An interface bracket and coordinate transformation matrices were designed to allow the Range 7 scanner to be mounted on the PaR Robot detector arm for scanning the heat shield or other object placed in the test cell. A process was designed for using Rapid Form XOR to stitch data from multiple scans together to provide an accurate 3D model of the object scanned. An accurate model was required for the design and verification of an existing heat shield. The large physical size and complex shape of the heat shield does not allow for direct measurement of certain features in relation to other features. Any imaging devices capable of imaging the entire heat shield in its entirety suffers a reduced resolution and cannot image sections that are blocked from view. Prior methods involved tools such as commercial measurement arms, taking images with cameras, then performing manual measurements. These prior methods were tedious and could not provide a 3D model of the object being scanned, and were typically limited to a few tens of measurement points at prominent locations. Integration of the scanner with the robot allows for large complex objects to be scanned at high resolution, and for 3D Computer Aided Design (CAD) models to be generated for verification of items to the original design, and to generate models of previously undocumented items. The main components are the mounting bracket for the scanner to the robot and the coordinate transformation matrices used for stitching the scanner data into a 3D model. The steps involve mounting the interface bracket to the robot's detector arm, mounting the scanner to the bracket, and then scanning sections of the object and recording the location of the tool tip (in this case the center of the scanner's focal point). A novel feature is the ability to stitch images together by coordinates instead of requiring each scan data set to have overlapping identifiable features. This setup allows models of complex objects to be developed even if the object is large and featureless, or has sections that don't have visibility to other parts of the object for use as a reference. In addition, millions of points can be used for creation of an accurate model [i.e. within 0.03 in. (=0.8 mm) over a span of 250 in. (=635 mm)].

Schuler, Jason↗
DOE OSTI2020

High-Performance Integrated Window and Façade Solutions for California

The researchers developed a new generation of high-performance façade systems and supporting design and management tools to support industry in meeting California’s greenhouse gas reduction targets, reduce energy consumption, and enable an adaptable response to minimize real-time demands on the electricity grid. The project resulted in five outcomes: (1) The research team developed an R-5, 1-inch thick, triplepane, insulating glass unit with a novel low-conductance aluminum frame. This technology can help significantly reduce residential cooling and heating loads, particularly during the evening. (2) The team developed a prototype of a windowintegrated local ventilation and energy recovery device that provides clean, dry fresh air through the façade with minimal energy requirements. (3) A daylight-redirecting louver system was prototyped to redirect sunlight 15–40 feet from the window. Simulations estimated that lighting energy use could be reduced by 35–54 percent without glare. (4) A control system incorporating physics-based equations and a mathematical solver was prototyped and field tested to demonstrate feasibility. Simulations estimated that total electricity costs could be reduced by 9-28 percent on sunny summer days through adaptive control of operable shading and daylighting components and the thermostat compared to state-of-the-art automatic façade controls in commercial building perimeter zones. (5) Supporting models and tools needed by industry for technology R&D and market transformation activities were validated. Attaining California’s clean energy goals require making a fundamental shift from today’s ad-hoc assemblages of static components to turnkey, intelligent, responsive, integrated building façade systems. These systems offered significant reductions in energy use, peak demand, and operating cost in California.

24 POWER TRANSMISSION AND DISTRIBUTION↗