Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Learning theory”

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 1,369 records · Page 76
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Grid Topology Discovery Algorithm Evaluation of Suitability for Utility Deployment (CRADA 606 Final Report)

This work presents the results of a field-informed demonstration aimed at evaluating the practical suitability of a topology discovery algorithm for utility environments. We demonstrated an algorithm that uses a graph-theory-informed state estimation approach for model selection. In collaboration with Survalent and Peninsula Light Co., the algorithm was applied to real feeder models and field measurements from supervisory control and data acquisition (SCADA) and advanced metering infrastructure (AMI) systems to identify the operational topology of a power distribution system. The demonstration assessed the algorithm’s performance under realistic data conditions, including sparse and noisy measurements, and examined its ability to identify the most likely network configurations. The results confirmed that the approach can effectively narrow down feasible topologies, providing operators with improved situational awareness of network status. Key lessons learned emphasize the need for systematic data validation and strategic sensor placement to enhance observability. These insights inform future deployment strategies and guide refinements for broader adoption in utility operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1988

AI and simulation: What can they learn from each other

Simulation and Artificial Intelligence share a fertile common ground both from a practical and from a conceptual point of view. Strengths and weaknesses of both Knowledge Based System and Modeling and Simulation are examined and three types of systems that combine the strengths of both technologies are discussed. These types of systems are a practical starting point, however, the real strengths of both technologies will be exploited only when they are combined in a common knowledge representation paradigm. From an even deeper conceptual point of view, one might even argue that the ability to reason from a set of facts (i.e., Expert System) is less representative of human reasoning than the ability to make a model of the world, change it as required, and derive conclusions about the expected behavior of world entities. This is a fundamental problem in AI, and Modeling Theory can contribute to its solution. The application of Knowledge Engineering technology to a Distributed Processing Network Simulator (DPNS) is discussed.

Colombano, Silvano P.↗
DOE OSTI2024

Cluster expansion by transfer learning for phase stability predictions

Recent progress towards universal machine-learned interatomic potentials holds considerable promise for materials discovery. Yet the accuracy of these potentials for predicting phase stability may still be limited. In contrast, cluster expansions provide accurate phase stability predictions but are computationally demanding to parameterize from first principles, especially for structures of low dimension or with a large number of components, such as interfaces or multimetal catalysts. We overcome this trade-off via transfer learning. Using Bayesian inference, we incorporate prior statistical knowledge from machine-learned and physics-based potentials, enabling us to sample the most informative configurations and to efficiently fit first-principles cluster expansions. Furthermore, this algorithm is tested on Pt:Ni, showing robust convergence of the mixing energies as a function of sample size with reduced statistical fluctuations.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Learning heterogeneous reaction kinetics from X-ray videos pixel by pixel

Reaction rates at spatially heterogeneous, unstable interfaces are notoriously difficult to quantify, yet are essential in engineering many chemical systems, such as batteries and electrocatalysts. Experimental characterizations of such materials by operando microscopy produce rich image datasets, but data-driven methods to learn physics from these images are still lacking because of the complex coupling of reaction kinetics, surface chemistry and phase separation. Here we show that heterogeneous reaction kinetics can be learned from in situ scanning transmission X-ray microscopy (STXM) images of carbon-coated lithium iron phosphate (LFP) nanoparticles. Combining a large dataset of STXM images with a thermodynamically consistent electrochemical phase-field model, partial differential equation (PDE)-constrained optimization and uncertainty quantification, we extract the free-energy landscape and reaction kinetics and verify their consistency with theoretical models. We also simultaneously learn the spatial heterogeneity of the reaction rate, which closely matches the carbon-coating thickness profiles obtained through Auger electron microscopy (AEM). Across 180,000 image pixels, the mean discrepancy with the learned model is remarkably small (<7%) and comparable with experimental noise. Our results open the possibility of learning nonequilibrium material properties beyond the reach of traditional experimental methods and offer a new non-destructive technique for characterizing and optimizing heterogeneous reactive surfaces.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Integrated design of aluminum-enriched high-entropy refractory B2 alloys with synergy of high strength and ductility

Refractory high-entropy alloys (RHEAs) are promising high-temperature structural materials. Their large compositional space poses great design challenges for phase control and high strength-ductility synergy. The present research pioneers using integrated high-throughput machine learning with Monte Carlo simulations supplemented by ab initio calculations to effectively navigate phase selection and mechanical property predictions, developing single-phase ordered B2 aluminum-enriched RHEAs (Al-RHEAs) demonstrating high strength and ductility. These Al-RHEAs achieve remarkable mechanical properties, including compressive yield strengths up to 1.7 gigapascals, fracture strains exceeding 50%, and notable high-temperature strength retention. They also demonstrate a tensile yield strength of 1.0 gigapascals with a ductility of 9%, albeit with B2 ordering. Furthermore, we identify valence electron count domains for alloy ductility and brittleness with the explanation from density functional theory and provide crucial insights into elemental influence on atomic ordering and mechanical performance. The work sets forth a strategic blueprint for high-throughput alloy design and reveals fundamental principles governing the mechanical properties of advanced structural alloys.

Science & Technology - Other Topics↗
DOE OSTI2021

Artificial intelligence “sees” split electrons

Chemical bonds between atoms are stabilized by the exchange-correlation (xc) energy, a quantum-mechanical effect in which “social distancing” by electrons lowers their electrostatic repulsion energy. Kohn-Sham density functional theory (DFT) states that the electron density determines this xc energy, but the density functional must be approximated. Furthermore, this is usually done by satisfying exact constraints of the exact functional (making the approximation predictive), by fitting to data (making it interpolative), or both. Two exact constraints—the ensemble-based piecewise linear variation of the total energy with respect to fractional electron number and fractional electron z-component of spin —require hard-to-control nonlocality. On page 1385 of this issue, Kirkpatrick et al. have taken a big step toward more accurate predictions for chemistry through the machine learning of molecular data plus the fractional charge and spin constraints, expressed as data that a machine can learn.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2025

Triangle Method for Dense ReLU Layers [SWR-25-72]

This software is an implementation of the methods for initializing and training neural networks to be more efficient per parameter, described more fully below and in the related publication: In theory, depth should make a ReLU network EXPONENTIALLY more efficient by enabling it to produce an exponential number of piecewise linear sections in its output. This reasoning is largely based on the work of mathematicians that have hand-constructed networks that make good use of depth. In practice however, even very deep ReLU networks that have been randomly initialized will behave identically to their shallow counterparts - missing an entire exponential dimension of efficiency. The triangle method is a first attempt at realizing the exponential potential of deep networks. Instead of randomly setting weights, we force pairs of neurons in each layer learn to build triangles (i.e. functions from [0,1] -> [0,1] that look like triangles). This is a very efficient pattern for generating lots of linear pieces because composing two triangular functions doubles the number of pieces with each composition. The triangle method is more than just a different initialization, it is a new paradigm of training. Instead of making direct updates to the matrix weights, we do an extra step of backpropagation to collect the derivatives of the loss function with respect to the shapes of the triangles, training them to tilt left or right. This process essentially holds the networks hand throughout the loss landscape and forces it to always use depth effectively by producing triangular shapes internally. This can produce several orders of magnitude of improvement on convex one-dimensional regression problems. Much more theoretical work is needed to realize its full potential beyond this context, but the implementation in this repository will still work in arbitrary numbers of dimensions. The file Triangle_Method.py is a generalized form of the method that will build each neuron its own custom 1-d convex activation function (with exponential efficiency). Example usage on one dimensional problems can be found in Example_Usage.ipynb and an example of using this in a real neural network can be found in Example_VGG16_CIFAR10.ipynb.

Milkert, Max [National Renewable Energy Laboratory↗
NASA NTRS2003

All in the Family: What Brown Dwarfs Teach Us About Extrasolar Giant Planets

As we await the first direct image of an extrasolar giant planet, we can turn to theory and the experience gained in the campaign to detect and understand brown dwarfs for guidance on what to expect. As with any new arrival to a family, there should be a strong family resemblance (one hopes) along with notable unique features and interesting peculiarities. The 300 or so known L and T dwarfs, combined with our own giant planets, already span much of the effective temperature range within which extrasolar planets will be found. Only objects with thick, easily detectable, water clouds have yet to be seen. Thus we already know much of the family. I will describe what we have learned from studying these objects, focusing on the important roles clouds and atmospheric chemistry play in affecting their atmospheres and emergent spectra. Relying on these findings and theoretical models, I'll sketch out what we can expect from extrasolar giant planets, focusing on easily detectable features. Some wild cards, of course, are to be expected. Photochemical hazes, in particular, may obscure the family traits on the faces of Jupiter's distant cousins and may make one wonder, at least momentarily, about the milkman.

Marley, M.↗
NASA NTRS2014

MDO and Cross-Disciplinary Practice in R&D: A Portrait of Principles and Current Practice

For several decades, Multidisciplinary Design Optimization (MDO) has served an important role in aerospace engineering by incorporating physics based disciplinary models into integrated system or sub-system models for use in research, development, (R&D) and design. This paper examines MDO's role in facilitating the integration of the researchers from different single disciplines during R&D and early design of large-scale complex engineered systems (LaCES) such as aerospace systems. The findings in this paper are summarized from a larger study on interdisciplinary practices and perspectives that included considerable empirical data from surveys, interviews, and ethnography. The synthesized findings were derived by integrating the data with theories from organization science and engineering. The over-arching finding is that issues related to cognition, organization, and social interrelations mostly dominate interactions across disciplines. Engineering issues, such as the integration of hardware or physics-based models, are not as significant. Correspondingly, the data showed that MDO is not the primary integrator of researchers working across disciplines during R&D and early design of LaCES. Cognitive focus such as analysis versus design, organizational challenges such as incentives, and social opportunities such as personal networks often drove the human interactive practices among researchers from different disciplines. Facilitation of the inherent confusion, argument, and learning in crossdisciplinary research was identified as one of several needed elements of enabling successful research across disciplines.

Rivas McGowan, Anna-Maria↗
NASA NTRS2017

Organics and Ices in the Outer Solar System: Connections to the Interstellar Medium

The solar nebula, that aggregate of gas and dust that formed the birthplace of the Sun, planets and plethora of small bodies comprising the Solar System, originated in a molecular cloud that is thought to have spawned numerous additional stars, some with their own planets and attendant small bodies. The question of the chemical and physical reprocessing of the original interstellar materials in the solar nebula has challenged both theory and observations. The acquisition and analysis of samples of comet and asteroid solids, and a growing suite of in-situ and close-up analyses of relatively unaltered small Solar System bodies now adds critical new dimensions to the study of the origin and evolution of the early solar nebula. Better understanding the original composition of the material from which our solar nebula formed, and the processing that material experienced, will aid in formulations of chemistry that might occur in other solar systems. While we seek to understand the compositional history of planetary bodies in our own Solar System, we will inevitably learn more about the materials that comprise exoplanets and their surrounding systems.

SOLAR NEBULA↗
NASA NTRS2014

ATLAS LTCS Vertically Challenged System Lessons Learned

Re-planning of LTCS TVAC testing and supporting RTA (Receiver Telescope Assembly) Test Plan and Procedure document preparation. The Laser Thermal Control System (LTCS) is designed to maintain the lasers onboard Advanced Topographic Laser Altimeter System (ATLAS) at their operational temperatures. In order to verify the functionality of the LTCS, a thermal balance test of the thermal hardware was performed. During the first cold start of the LTCS, the Loop Heat Pipe (LHP) was unable to control the laser mass simulators temperature. The control heaters were fully on and the loop temperature remained well below the desired setpoint. Thermal analysis of the loop did not show these results. This unpredicted behavior of the LTCS was brought up to a panel of LHP experts. Based on the testing and a review of all the data, there were multiple diagnostic performed in order to narrow down the cause. The prevailing theory is that gravity is causing oscillating flow within the loop, which artificially increased the control power needs. This resulted in a replan of the LTCS test flow and the addition of a GSE heater to allow vertical operation.

Loop Heat Pipe↗
DOE OSTI2023

Peri-Net-Pro: the neural processes with quantified uncertainty for crack patterns

Abstract This paper develops a deep learning tool based on neural processes (NPs) called the Peri-Net-Pro, to predict the crack patterns in a moving disk and classifies them according to the classification modes with quantified uncertainties. In particular, image classification and regression studies are conducted by means of convolutional neural networks (CNNs) and NPs. First, the amount and quality of the data are enhanced by using peridynamics to theoretically compensate for the problems of the finite element method (FEM) in generating crack pattern images. Second, case studies are conducted with the prototype microelastic brittle (PMB), linear peridynamic solid (LPS), and viscoelastic solid (VES) models obtained by using the peridynamic theory. The case studies are performed to classify the images by using CNNs and determine the suitability of the PMB, LBS, and VES models. Finally, a regression analysis is performed on the crack pattern images with NPs to predict the crack patterns. The regression analysis results confirm that the variance decreases when the number of epochs increases by using the NPs. The training results gradually improve, and the variance ranges decrease to less than 0.035. The main finding of this study is that the NPs enable accurate predictions, even with missing or insufficient training data. The results demonstrate that if the context points are set to the 10th, 100th, 300th, and 784th, the training information is deliberately omitted for the context points of the 10th, 100th, and 300th, and the predictions are different when the context points are significantly lower. However, the comparison of the results of the 100th and 784th context points shows that the predicted results are similar because of the Gaussian processes in the NPs. Therefore, if the NPs are employed for training, the missing information of the training data can be supplemented to predict the results.

Mathematics↗
DOE OSTI2024

Atomistic origin of the entropy of melting from inelastic neutron scattering and machine learned molecular dynamics

The latent heat, L, is central to melting, but its atomic origin remains elusive. It is proportional to the entropy of fusion, ΔS fus = L/T m (T m is the melting temperature), which depends on changes of atom configurations, atom vibrations, and thermal electron excitations. Here, we combine inelastic neutron scattering and machine-learned molecular dynamics to separate ΔS fus into these components for Ge, Si, Bi, Sn, Pb, and Li. When the vibrational entropy of melting, ΔS vib , is zero, ΔS fus ≃ 1.2 kB per atom. This result provides a baseline for ΔSconfig and nearly coincides with “Richard’s Rule” of melting. The ΔSfus deviates from this value for most elements, however, and we show that this deviation originates with extra ΔS vib and extra ΔS config . These two components are correlated for positive and negative deviations from Richard’s rule – the extra ΔS config is consistently ~ 80% of ΔS vib . Our results, interpreted with potential energy landscape theory, imply a correlation between the change in the number of basins and the change in the inverse of their curvature for the melting of pure elements.

36 MATERIALS SCIENCE↗
DOE OSTI2020

US Department of Energy, Office of Science High Performance Computing Facility Operational Assessment 2019 Oak Ridge Leadership Computing Facility

Oak Ridge National Laboratory's (ORNL's) Leadership Computing Facility (OLCF) continues to surpass its operational target goals: supporting users; delivering fast, reliable computational ecosystems; creating innovative solutions for high performance computing (HPC) needs; and managing risks, safety, and security associated with operating some of the most powerful computers in the world. The results can be seen in the cutting-edge science conducted by users and the praise from the research community. Calendar year (CY) 2019 was a big year as OLCF staff ran five world-class resources (the leadershipclass computers Titan and Summit, the large analysis cluster called Eos, and the massive parallel filesystems called Atlas and Alpine)) and also began power and cooling upgrades for a 2021 exascale system called Frontier. While continuing exceptional operation of Titan, Eos, and Rhea, the OLCF released the Summit supercomputer for production on January 1, 2019. Summit debuted as the most capable and efficient system in its class and has been recognized as the most powerful system in the world for its performance on both the high performance linpack (HPL) and conjugate gradient (HPCG) benchmark applications since June 2018 according to TOP500. Summit represents the culmination of a multiyear effort between the OLCF, IBM, NVIDIA, and Mellanox to deliver a system that is unmatched for modeling, simulation, data analysis, and learning. To hit the ground running with science-ready applications on day one, application teams worked closely with the OLCF through the Center for Accelerated Application Readiness (CAAR) program for years in advance of the Summit deployment. CY 2019 was filled with outstanding results and accomplishments: a very high rating from users on overall satisfaction for the sixth year in a row; a tremendous amount of core-hours delivered to researchers from two leadership-class systems; and success in delivering on the allocation split of roughly 60%, 30%, and 10% of core-hours offered for the Innovative and Novel Computational Impact on Theory and Experiment (INCITE), Advanced Scientific Computing Research Leadership Computing Challenge (ALCC), and Director's Discretionary (DD) programs, respectively (see Operational Performance section). These accomplishments, coupled with the high utilization rates (overall and capability usage), represent the fulfillment of the promise of both leadership-class machines: efficient facilitation of leadership-class computational applications. Table ES.1 presents a summary of the 2019 OLCF metric targets and the associated results. More information can be found in the Operational Performance section for each OLCF resource. The scientific accomplishments of OLCF users are a strong indication of long-term operational success, with publications this year in such notable journals and publications as Nature, Nature Physics, Nature Plants, Physical Review X, Journal of the American Physical Society, Cell, Nano Letters, and Trends in Biotechnology. Crucial domain-specific discoveries facilitated by resources at the OLCF are described in the High Performance Computing Facility Operational Assessment 2019 Oak Ridge Leadership Computing Facility (OAR) Strategic Results section. For example, researchers used Summit to pinpoint and understand the production of proteins from genetic information, including mutations and the functional expression of disease (Section 8.2).

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1988

The near-infrared polarization and color of Comet Halley: What can we learn about the grains

The near infrared polarization and JHK colors of light scattered by dust grains in comet Halley were measured over a wide range in phase angle and heliocentric distance. Colors were redder than solar with no statistically significant variation with phase angle, heliocentric distance, or pre- and post-perihelion. This suggests that the grain population did not change drastically over time and that the data may be combined and modeled. However, short term variations in visible polarization and dust albedo were seen in Halley. Also, near infrared colors became systematically bluer after the observations were completed. The near infrared colors of Halley fall in the range of those of other comets. The near infrared polarization is similar to the visible polarization of Halley and other comets in showing a negative branch at small phase angles and an approximately linear rise toward positive values at larger phase angles. Mie theory calculations and a size distribution based on spacecraft data were used to model the near infrared polarization and color of comet Halley. Numerous lines of evidence point to the presence of dark, absorbing, probably carbonaceous materials in comets.

Brooke, Timothy Y.↗
DOE OSTI2021

Microstructure and water absorption of ancient concrete from Pompeii: An integrated synchrotron microtomography and neutron radiography characterization

There is renewed interest in using advanced techniques to characterize ancient Roman concrete due to its exceptional durability and low-carbon footprint. In the present work, samples were drilled from the “Hospitium” in Pompeii and were analyzed by synchrotron microtomography (μCT) and neutron radiography to study how the microstructure, including the presence of induced cracks, affects their water adsorption. The water distribution and absorptivity were quantified by neutron radiography. The 3D crack propagation, pore size distribution and orientation, tortuosity, and connectivity were analyzed from μCT results using advanced imaging methods. Porosity was also measured by mercury intrusion porosimetry (MIP) as a reference. Ductile fracture patterns were observed once cracks were introduced. Compared to Portland cement mortar/concrete, the Pompeii samples had relatively high porosity, low connectivity, and a similar coefficient of capillary penetration. In addition, permeability was predicted from models based on percolation theory and pore structure data to evaluate the fluid transport properties. Understanding the microstructure of ancient Pompeii concrete is important because it could inspire the development of modern concrete with high durability.

36 MATERIALS SCIENCE↗
DOE OSTI2021

SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.

This report details the results of a three-fold investigation of sensitivity analysis (SA) for machine learning (ML) explainability (MLE): (1) the mathematical assessment of the fidelity of an explanation with respect to a learned ML model, (2) quantifying the trustworthiness of a prediction, and (3) the impact of MLE on the efficiency of end-users through multiple users studies. We focused on the cybersecurity domain as the data is inherently non-intuitive. As ML is being using in an increasing number of domains, including domains where being wrong can elicit high consequences, MLE has been proposed as a means of generating trust in a learned ML models by end users. However, little analysis has been performed to determine if the explanations accurately represent the target model and they themselves should be trusted beyond subjective inspection. Current state-of-the-art MLE techniques only provide a list of important features based on heuristic measures and/or make certain assumptions about the data and the model which are not representative of the real-world data and models. Further, most are designed without considering the usefulness by an end-user in a broader context. To address these issues, we present a notion of explanation fidelity based on Shapley values from cooperative game theory. We find that all of the investigated MLE explainability methods produce explanations that are incongruent with the ML model that is being explained. This is because they make critical assumptions about feature independence and linear feature interactions for computational reasons. We also find that in deployed, explanations are rarely used due to a variety of reason including that there are several other tools which are trusted more than the explanations and there is little incentive to use the explanations. In the cases when the explanations are used, we found that there is the danger that explanations persuade the end users to wrongly accept false positives and false negatives. However, ML model developers and maintainers find the explanations more useful to help ensure that the ML model does not have obvious biases. In light of these findings, we suggest a number of future directions including developing MLE methods that directly model non-linear model interactions and including design principles that take into account the usefulness of explanations to the end user. We also augment explanations with a set of trustworthiness measures that measure geometric aspects of the data to determine if the model output should be trusted.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2011

Fermi-LAT Gamma-ray Bursts and Insight from Swift

A new revolution in GRB observation and theory has begun over the last 3 years since the launch of the Fermi gamma-ray space telescope. The new window into high energy gamma-rays opened by the Fermi-LAT is providing insight into prompt emission mechanisms and possibly also afterglow physics. The LAT detected GRBs appear to be a new unique subset of extremely energetic and bright bursts. In this talk I will discuss the context and recent discoveries from these LAT GRBs and the large database of broadband observations collected by Swift over the last 7 years and how through comparisons between the Swift, GBM, and LAT GRB samples, we can learn about the unique characteristics and relationships between each population.

Racusin, Judith L.↗