Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distance Learning”

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 235 records · Page 13

Reliable extrapolation of deep neural operators informed by physics or sparse observations

Deep neural operators can learn nonlinear mappings between infinite-dimensional function spaces via deep neural networks. As promising surrogate solvers of partial differential equations (PDEs) for real-time prediction, deep neural operators such as deep operator networks (DeepONets) provide a new simulation paradigm in science and engineering. Pure data-driven neural operators and deep learning models, in general, are usually limited to interpolation scenarios, where new predictions utilize inputs within the support of the training set. However, in the inference stage of real-world applications, the input may lie outside the support, i.e., extrapolation is required, which may result to large errors and unavoidable failure of deep learning models. Here, we address this challenge of extrapolation for deep neural operators. First, we systematically investigate the extrapolation behavior of DeepONets by quantifying the extrapolation complexity, via the 2-Wasserstein distance between two function spaces and propose a new strategy of bias–variance trade-off for extrapolation with respect to model capacity. Subsequently, we develop a complete workflow, including extrapolation determination, and we propose five reliable learning methods that guarantee a safe prediction under extrapolation by requiring additional information—the governing PDEs of the system or sparse new observations. The proposed methods are based on either fine-tuning a pre-trained DeepONet or multifidelity learning. We demonstrate the effectiveness of the proposed framework for various types of parametric PDEs. Furthermore, our systematic comparisons provide practical guidelines for selecting a proper extrapolation method depending on the available information, desired accuracy, and required inference speed.

42 ENGINEERING↗

Beyond the Solar System: A Challenge for Space Propulsion

Scientific exploration beyond the confines of our solar system has recently become a near-term goal for NASA. Early robotic probes beyond the Sun's heliopause [a few hundred Astronomical Units (AU) from the Sun] are planned for the first decade of the 21st century. A leading propulsion system for these early interstellar efforts is the solar sail unfurled as close to the Sun as possible. This report discusses the basic physics of the solar sail, the rationale for interstellar exploration, a recent materials breakthrough influencing solar-sail design concepts, and solar sail kinematics (for the case of sail unfurlment at perihelion from an initially parabolic solar orbit and sail orientation normal to the Sun). A number of possible mission scenarios to distances up to 1,000 AU are presented as is a short discussion of what we must learn to extend our exploratory reach to 10,000 AU.

Matloff, Gregory L.↗

OSIRIS-REx Orbit Determination Performance During the Navigation Campaign

The OSIRIS-REx mission Navigation Campaign consists of three sub-phases: Approach,Preliminary Survey, and Orbital A. Approach was designed for initial characterization ofBennu while matching Bennu's heliocentric velocity. Preliminary Survey provided the firstspacecraft-based estimate of Bennu's mass. This phase consisted of five target flybys witha close approach distance of about 7 km. Orbital A was a two-month phase devoted to theNavigation Team learning the close proximity operations dynamics and environment aroundBennu and transitioning from center-finding optical navigation to landmark feature-basednavigation. This paper provides a detailed summary of the orbit determination performancethroughout the Navigation Campaign.

Leonard, Jason M.↗

Update on Demolition Strategy and Progress at Hanford's Plutonium Finishing Plant - 17161

U.S. Department of Energy (DOE) contractor CH2M HILL Plateau Remediation Company (CH2M) is currently demolishing the Plutonium Finishing Plant (PFP). The facility is located on the Hanford Site and produced plutonium metal during the Cold War. Production was stopped in 1988, the facility was formally shut-down in 1996 and material processing completed in 2004. In November 2016, the project team, partnering with DOE-Richland Operations Office (DOE-RL) began demolition of the building. CH2M and DOE-RL will demolish PFP as a Hazardous Category II nuclear facility (HazCat II). The PFP is considered one of the most hazardous buildings on the Hanford site; employees have performed some of the most hazardous work anywhere across the DOE Environmental Management complex. Since 2008, employees have removed much of the plutonium-processing infrastructure. Four main buildings make up the majority of the PFP complex. As of November 2016, one building is undergoing demolition, another is ready for demolition and, concurrently, demolition preparations continue in the remaining two buildings. That hazard mitigation work includes removing contaminated ventilation duct work, process lines and performing asbestos abatement. To ensure safe and compliant demolition, CH2M employees researched, trained and deployed personal protective equipment never before used on the Hanford Site to complete some of the most hazardous demolition preparations. Project management commissioned the development of an air dispersion model that dictated ready-for-demolition criteria and established conservative demolition parameters. Management also sequenced project work to allow demolition to occur while demolition preparations continue a safe distance away in adjacent buildings. This paper will allow CH2M and DOE-RL to share lessons learned and progress to date with other complex and hazardous projects across the DOE complex. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Coincident learning for unsupervised anomaly detection of scientific instruments

Abstract Anomaly detection is an important task for complex scientific experiments and other complex systems (e.g. industrial facilities, manufacturing), where failures in a sub-system can lead to lost data, poor performance, or even damage to components. While scientific facilities generate a wealth of data, labeled anomalies may be rare (or even nonexistent), and expensive to acquire. Unsupervised approaches are therefore common and typically search for anomalies either by distance or density of examples in the input feature space (or some associated low-dimensional representation). This paper presents a novel approach called coincident learning for anomaly detection (CoAD), which is specifically designed for multi-modal tasks and identifies anomalies based on coincident behavior across two different slices of the feature space. We define an unsupervised metric, F ^ β , out of analogy to the supervised classification F β statistic. CoAD uses F ^ β to train an anomaly detection algorithm on unlabeled data , based on the expectation that anomalous behavior in one feature slice is coincident with anomalous behavior in the other. The method is illustrated using a synthetic outlier data set and a MNIST-based image data set, and is compared to prior state-of-the-art on two real-world tasks: a metal milling data set and our motivating task of identifying RF station anomalies in a particle accelerator.

43 PARTICLE ACCELERATORS↗

Data Mining for Anomaly Detection

The Vehicle Integrated Prognostics Reasoner (VIPR) program describes methods for enhanced diagnostics as well as a prognostic extension to current state of art Aircraft Diagnostic and Maintenance System (ADMS). VIPR introduced a new anomaly detection function for discovering previously undetected and undocumented situations, where there are clear deviations from nominal behavior. Once a baseline (nominal model of operations) is established, the detection and analysis is split between on-aircraft outlier generation and off-aircraft expert analysis to characterize and classify events that may not have been anticipated by individual system providers. Offline expert analysis is supported by data curation and data mining algorithms that can be applied in the contexts of supervised learning methods and unsupervised learning. In this report, we discuss efficient methods to implement the Kolmogorov complexity measure using compression algorithms, and run a systematic empirical analysis to determine the best compression measure. Our experiments established that the combination of the DZIP compression algorithm and CiDM distance measure provides the best results for capturing relevant properties of time series data encountered in aircraft operations. This combination was used as the basis for developing an unsupervised learning algorithm to define "nominal" flight segments using historical flight segments.

Biswas, Gautam↗

Metric Learning for Hyperspectral Image Segmentation

We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

Compact Reconnaissance Imaging Spectrometer (CRISM↗

Protein model quality assessment using rotation–equivariant transformations on point clouds

Machine learning research concerning protein structure has seen a surge in popularity over the last years with promising advances for basic science and drug discovery. Working with macromolecular structure in a machine learning context requires an adequate numerical representation, and researchers have extensively studied representations such as graphs, discretized 3D grids, and distance maps. As part of CASP14, we explored a new and conceptually simple representation in a blind experiment: atoms as points in 3D, each with associated features. These features—initially just the basic element type of each atom—are updated through a series of neural network layers featuring rotation-equivariant convolutions. Starting from all atoms, we further aggregate information at the level of alpha carbons before making a prediction at the level of the entire protein structure. We find that this approach yields competitive results in protein model quality assessment despite its simplicity and despite the fact that it incorporates minimal prior information and is trained on relatively little data. As a result, its performance and generality are particularly noteworthy in an era where highly complex, customized machine learning methods such as AlphaFold 2 have come to dominate protein structure prediction.

59 BASIC BIOLOGICAL SCIENCES↗

How accurate is a machine learning-based wind speed extrapolation under a round-robin approach?

As the size of commercial wind turbines keeps increasing, having accurate ways to vertically extrapolate wind speed is essential to obtain a precise characterization of the wind resource for wind energy production. Recently, machine learning has been proposed and applied to extrapolate wind speed to hub heights. However, previous studies trained and tested the machine learning methods at the same site, giving them an unfair advantage over the conventional extrapolation techniques, which are instead more universal. Here, we use data from four sites in Oklahoma to test a round-robin validation approach for machine learning, under which we train a random forest at a site, and test it at a different site, where the model has no prior knowledge of the wind resource. We quantify how the accuracy of this technique varies with distance from the training site, and we find that it outperforms conventional techniques for wind extrapolation at all the considered spatial separations. We then assess how the accuracy of the machine-learning based approach varies when it is used to predict wind speed in a wind farm far wake. Finally, we explore as case study the performance of the random forest in extrapolating winds during a low-level jet event.

17 WIND ENERGY↗

Learning Management System User Requirements for the National Nuclear Security Administration's International Nuclear Safeguards Engagement Program

The National Nuclear Security Administration's (NNSA) International Nuclear Safeguards Engagement Program (INSEP) is considering investing in new tools that would allow the program to support its partner states from a distance. At the same time, the program is considering approaches that would allow several organizations, including NNSA, IAEA, national laboratories and contractor staff, to collaborate in the development and maintenance of instructional content. Software systems known as Learning Management Systems (LMSs) might represent a mechanism through which INSEP could accomplish these goals (collaborative development and remote support). To assess the usefulness of an LMS, INSEP has specified its needs for delivering online training and compared those needs to the capability of a range of LMSs. This comparison will allow INSEP to determine whether an LMS would be a useful tool and may set the stage for a "make-buy" decision in the future. The study team concluded that INSEP's content development and delivery needs align well with the capabilities of the leading LMSs on the market today and that that INSEP performance requirements allow for a customized approach using existing training portals that are already available to NNSA. Additional work would be required to specify the desired processes for developing online training and outreach materials, structuring the databases, specifying the data that should be collected, and detailing the desired system reports and documentation.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Plasma membrane ordering agent pluronic F-68 (PF-68) reduces neurotransmitter uptake and release and produces learning and memory deficits in rats

A substantial body of evidence indicates that aged-related changes in the fluidity and lipid composition of the plasma membrane contribute to cellular dysfunction in humans and other mammalian species. In the CNS, reductions in neuronal plasma membrane order (PMO) (i.e., increased plasma membrane fluidity) have been attributed to age as well as the presence of the beta-amyloid peptide-25-35, known to play an important role in the neuropathology of Alzheimer's disease (AD). These PMO increases may influence neurotransmitter synthesis, receptor binding, and second messenger systems as well as signal transduction pathways. The effects of neuronal PMO on learning and memory processes have not been adequately investigated, however. Based on the hypothesis that an increase in PMO may alter a number of aspects of synaptic transmission, we investigated several neurochemical and behavioral effects of the membrane ordering agent, PF-68. In cell culture, PF-68 (nmoles/mg SDS extractable protein) reduced [3H]norepinephrine (NE) uptake into differentiated PC-12 cells as well as reduced nicotine stimulated [3H]NE release. The compound (800-2400 microg/kg, i.p., resulting in nmoles/mg SDS extractable protein in the brain) decreased step-through latencies and increased the frequencies of crossing into the unsafe side of the chamber in inhibitory avoidance training. In the Morris water maze, PF-68 increased the latencies and swim distances required to locate a hidden platform and reduced the time spent and distance swam in the previous target quadrant during transfer (probe) trials. PF-68 did not impair performance of a well-learned working memory task, the rat delayed stimulus discrimination task (DSDT), however. Studies with 14C-labeled PF-68 indicated that significant (pmoles/mg wet tissue) levels of the compound entered the brain from peripheral (i.p.) injection. No PF-68 related changes were observed in swim speeds or in visual acuity tests in water maze experiments, rotorod performance, or in tests of general locomotor activity. Furthermore, latencies to select a lever in the DSDT were not affected. These results suggest that PF-68 induced deficits in learning and memory without confounding peripheral motor, sensory, or motivational effects at the tested doses. Furthermore, none of the doses induced a conditioned taste aversion to a novel 0.1% saccharin solution indicating a lack of nausea or gastrointestinal malaise induced by the compound. The data indicate that increases in neuronal plasma membrane order may have significant effects on neurotransmitter function as well as learning and memory processes. Furthermore, compounds such as PF-68 may also offer novel tools for studying the role of neuronal PMO in mnemonic processes and changes in PMO resulting from age-related disorders such as AD.

Poloxamer/pharmacology↗

Marcus Theory of Ion-Pairing

We present a theory for ion pair dissociation and association, motivated by the concepts of the Marcus theory of electron transfer. Despite the extensive research on ion-pairing in many chemical and biological processes, much can be learned from the exploration of collective reaction coordinates. To this end, we explore two reaction coordinates, ion pair distance and coordination number. The study of the correlation between these reaction coordinates provides a new insight into the mechanism and kinetics of ion pair dissociation and association in water. The potential of mean force on these 2D-surfaces computed from molecular dynamics simulations of different monovalent ion pairs reveal a Marcus-like mechanism for ion-pairing: Water molecules rearrange forming an activated coordination state prior to ion pair dissociation or association, followed by relaxation of the coordination state due to further water rearrangement. Like Marcus theory, we find the existence of an inverted region where the transition rates are slower with increasing exergonicity. This study provides a new perspective for the future investigations of ion-pairing and transport. SR, CJM, and GKS were supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Division of Chemical Sciences, Geosciences, and Biosciences. MDB was supported by MS3 (Materials Synthesis and Simulation Across Scales) Initiative, a Laboratory Directed Research and Development Program at Pacific Northwest National Laboratory (PNNL). The research was performed using PNNL Institutional Computing. PNNL is a multi-program national laboratory operated by Battelle for the U.S. Department of Energy.

Roy, Santanu↗

DETECTION OF A GIANT EXTRASOLAR PLANET ORBITING THE ECLIPSING POLAR DP LEO

DP Leo is the first discovered eclipsing polar with a short period of 1.4967 hours. The period variation of the eclipsing binary was analyzed by using five new determined eclipse times together with those compiled from the literature. It is discovered that the O - C curve of DP Leo shows a cyclic variation with a period of 23.8 years and a semiamplitude of 31.5 s. The small-amplitude periodic change can be plausibly explained as the light-travel time effect due to the presence of a tertiary companion. The mass of the tertiary component is determined to be M {sub 3}sin i' = 0.00600({+-}0.00055) M {sub sun} = 6.28({+-}0.58) M {sub Jupiter} when a total mass of 0.69 M {sub sun} is adopted. If the tertiary companion is coplanar to the eclipsing binary (i.e., i' = 79.{sup 0}5), it should be a giant extrasolar planet with a mass of 6.39 M {sub Jupiter} at a distance of 8.6 astronomical units to the central binary. One of the most interesting things that we have learned about extrasolar planets over the last 17 years is that they can exist almost anywhere. The detection of a giant planet orbiting a polar would provide insight into the formation and evolution of circumbinary planets (planets orbiting both components of short-period binaries) as well as the late evolution of binary stars.

79 ASTRONOMY AND ASTROPHYSICS↗

Distance Metrics and Clustering Methods for Mixed-type Data

In spite of the abundance of clustering techniques and algorithms, clustering mixed interval (continuous) and categorical (nominal and/or ordinal) scale data remain a challenging problem. In order to identify the most effective approaches for clustering mixed–type data, we use both theoretical and empirical analyses to present a critical review of the strengths and weaknesses of the methods identified in the literature. Here, the guidelines on approaches to use under different scenarios are provided, along with potential directions for future research.

97 MATHEMATICS AND COMPUTING↗

November 2019 Initial Deployment of LiDAR in the H-Canyon Exhaust Tunnel

The H-Canyon Exhaust Tunnel (CAEX) structure is periodically inspected under the Structural Integrity Program using camera equipped crawlers or poles to remotely perform visual inspections. To explore the use of enhanced inspection methods a “Proof of Concept” using the Light Detection and Ranging (LiDAR) technology was performed over a 2-day period in November 2019. The purpose of the “Proof of Concept” deployment was to confirm whether a commercially available LiDAR unit could successfully operate and remotely transmit data from the tunnel CAEX environment and whether the data would provide quantitative information to establish baseline measurements. The LiDAR performance requirement was a measurement accuracy of ± 0.25-inches over a 30-foot distance. This report documents the work activities leading to the deployment, the deployment and processing of data, lessons learned from the deployment and the post data processing methods that will be applied to future deployments.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Exploring the Extreme Universe! (2nd Edition)

A large array of web sites devoted to the science that the NASA Goddard Space Flight Center Laboratory for High Energy Astrophysics (LHEA) studies have been frozen in time and included on this CD. Featured are five of our 'Understanding the Extreme Universe' sites, which offer explanations about cosmic ray, gamma ray, and X-ray science and satellites, as well as cosmic distances. They also include images and engaging activities that are great for helping both children and adults to learn more about science and basic physical principles. The 'Missions That Take Us There' section contains web sites on the satellite, balloon-borne, International Space Station, and rocket missions in our Laboratory that study X-rays, gamma rays, and cosmic rays. There are also two multi-mission sites and an experiment that measures Earth's UV light in preparation for a future cosmic ray mission. Most of the sites on this CD contain high-resolution images that are great for scientific presentations, study, or just your own enjoyment. This CD shows our web sites as they existed in April of 2001. We have made sure to include the WWW address for every site, so you will know where to go to access the most current versions of them.

White, Nicholas E.↗

Application of OpenFOAM to Plume Impingement in Space Environments

After 30 years of continuous human presence in low-earth orbit, NASA is returning to the moon and eventually will go to Mars. Travelling beyond low earth orbit requires NASA to learn how humans can live in Deep Space environments – beyond the protection of Earth’s magnetosphere and at distances from Earth that prevent a quick return in case of trouble. To this end, NASA is constructing the Lunar Gateway, an ISS-like space station to be put in orbit around the moon to act as a home base for Lunar exploration for NASA astronauts. The Gateway Lunar outpost will be built incrementally, via modules which will arrive at separate times and dock to the existing structure. The incremental addition of Gateway modules, and the docking of visiting vehicles, is achieved via a sequence of firings from the approaching body’s onboard reaction control system (RCS) thrusters to achieve the required approach trajectory. The typical hypergolic chemical RCS thrusters work by firing hot gases to produce adverse thrust and the needed change in velocity to safely finish the docking process. The exhaust gas from the RCS thrusters form plumes that expand into the vacuum of space and can impinge onto the outer surfaces of the Lunar Gateway, causing unwanted forces and moments, heat loads, sediment deposition, and in extreme cases, even surface erosion - all mechanisms that can damage the Lunar Gateway and must be minimized. Both permanent and visiting modules will have this RCS thruster exhaust impingement problem. This research aims to establish existing OpenFOAM solvers as a methodology for improving simulation techniques of rocket exhaust plume impingement in space environments. The flow structure of a plume in a space environment is complex; a plume that originates from a hypergolic chemical RCS thruster and expands into a vacuum will experience several regimes of rarefication. This range includes the continuum flow in the rocket nozzle through the fully rarefied free molecular flow further from the nozzle. The flow physics is different at these two extremes, and as such, the simulation approach for plumes is generally divided into a traditional computational fluid dynamics (CFD) simulation in and near the nozzle which is coupled to a subsequent direct simulation Monte Carlo (DSMC) simulation. At this time, the scope of this research is developing, verifying, and validating a method using existing solvers in the OpenFOAM framework for performing coupled CFD/DSMC calculations to determine the extent of plume impingement loading on generic space structures. This presentation will detail code-to-code comparisons between the hyStrath dsmcFoam+ solver, developed using OpenFOAM and available as open-source, and NASA’s in-house DSMC Analysis Code (DAC). Comparisons to several open-source publication findings using DAC [3,4] are presented, and advantages of using an OpenFOAM based solver are also discussed. The presentation concludes with a discussion of future work, and a plan for coupling the dsmcFoam+ solver with CFD simulations of chemical rocket engines for unified coupled plume simulation.

DSMC↗