Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep direct use”

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 109 records · Page 6

Automatic detection of cataclysmic variables from SDSS images

Abstract Investigating rare and new objects have always been an important direction in astronomy. Cataclysmic variables (CVs) are ideal and natural celestial bodies for studying the accretion process of semi-detached binaries with accretion processes. However, the sample size of CVs must increase because a lager gap exists between the observational and the theoretical expanding CVs. Astronomy has entered the big data era and can provide massive images containing CV candidates. CVs as a type of faint celestial objects, are highly challenging to be identified directly from images using automatic manners. Deep learning has rapidly developed in intelligent image processing and has been widely applied in some astronomical fields with excellent detection results. YOLOX, as the latest YOLO framework, is advantageous in detecting small and dark targets. This work proposes an improved YOLOX-based framework according to the characteristics of CVs and Sloan Digital Sky Survey (SDSS) photometric images to train and verify the model to realise CV detection. We use the Convolutional Block Attention Module to increase the number of output features with the feature extraction network and adjust the feature fusion network to obtain fused features. Accordingly, the loss function is modified. Experimental results demonstrate that the improved model produces satisfactory results, with average accuracy (mean average Precision at 0.5) of 92.0%, Precision of 92.9%, Recall of 94.3%, and $F1-score$ of 93.6% on the test set. The proposed method can efficiently achieve the identification of CVs in test samples and search for CV candidates in unlabeled images. The image data vastly outnumber the spectra in the SDSS-released data. With supplementary follow-up observations or spectra, the proposed model can help astronomers in seeking and detecting CVs in a new manner to ensure that a more extensive CV catalog can be built. The proposed model may also be applied to the detection of other kinds of celestial objects.

Astronomy & Astrophysics↗

Evidence for Impact of Galaxy Mergers on Stellar Kinematics of Early-type Galaxies

We provide observational evidence that galaxy mergers significantly affect stellar kinematics of early-type galaxies (ETGs) such as specific stellar angular momentum within the half-light radius (${\lambda }_{{R}_{e}}$) and kinematic misalignment (ψ mis ), using MaNGA integral field unit spectroscopic data that are in the Stripe 82 region of the Sloan Digital Sky Survey. In this study, tidal features around ETGs, which are detected in deep coadded images, are used as direct evidence for mergers that occurred recently. In the case of ETGs that do not have dust lanes, ${\lambda }_{{R}_{e}}$ is lower in ETGs with tidal features than in those without tidal features (median ${\lambda }_{{R}_{e}}$: 0.21 versus 0.39) in all stellar mass and Sérsic index ranges except the most massive bin, so that the fraction of ETGs with tidal features in slow rotators is more than twice as large as that in fast rotators (42% versus 18%). Moreover, ETGs with tidal features have larger ψ mis than those without tidal features (mean ψ mis : 28° versus 15°). By contrast, ETGs with dust lanes are fast rotators, and ETGs with both dust lanes and tidal features have the highest ${\lambda }_{{R}_{e}}$ (median ${\lambda }_{{R}_{e}}$: 0.59) among all ETG categories. In addition, ETGs with dust lanes have small ψ mis regardless of the existence of tidal features (Ψ mis <7$^{°}_{.}$5). Our results can be explained if mergers with different gas fractions generate merger remnants that have different kinematic properties.

79 ASTRONOMY AND ASTROPHYSICS↗

Multilevel semantic analysis and problem-solving in the flight-domain

The use of knowledge-base architecture and planning control; mechanisms to perform an intelligent monitoring task in the flight domain is addressed. The route level, the trajectory level, and parts of the aerodynamics level are demonstrated. Hierarchical planning and monitoring conceptual levels, functional-directed mechanism rationalization, and using deep-level mechanism models for diagnoses of dependent failures are discussed.

Chien, R. T.↗

Monitoring and prediction of porosity in laser powder bed fusion using physics-informed meltpool signatures and machine learning

In this work we accomplished the monitoring and prediction of porosity in laser powder bed fusion (LPBF) additive manufacturing process. This objective was realized by extracting physics-informed meltpool signatures from an in-situ dual-wavelength imaging pyrometer, and subsequently, analyzing these signatures via computationally tractable machine learning approaches. Porosity in LPBF occurs despite extensive optimization of processing conditions due to stochastic causes. Hence, it is essential to continually monitor the process with in-situ sensors for detecting and mitigating incipient pore formation. In this work a tall cuboid-shaped part (10 mm × 10 mm × 137 mm, material ATI 718Plus) was built with controlled porosity by varying laser power and scanning speed. This test caused various types of porosity, such as lack-of-fusion and keyhole formation, with varying degrees of severity in the part. The meltpool was continuously monitored using a dual-wavelength imaging pyrometer installed in the machine. Physically intuitive process signatures, such as meltpool length, temperature distribution, and ejecta (spatter) characteristics, were extracted from the meltpool images. Subsequently, relatively simple machine learning models, e.g., K-Nearest Neighbors, were trained to predict both the severity and type of porosity as a function of these physics-informed meltpool signatures. These models resulted in a prediction accuracy exceeding 95% (statistical F1-score). The same analysis was carried out with a complex, black-box deep learning convolutional neural network which directly used the meltpool images instead of physics-informed features. The convolutional neural network produced a comparable F1-score in the range of 89–97%. Finally, these results demonstrate that using pragmatic, physics-informed meltpool signatures within a simple machine learning model is as effective for flaw prediction in LPBF as using a complex and computationally demanding black-box deep learning model.

36 MATERIALS SCIENCE↗

Coordinated design of coding and modulation systems

The joint optimization of the coding and modulation systems employed in telemetry systems was investigated. Emphasis was placed on formulating inner and outer coding standards used by the Goddard Spaceflight Center. Convolutional codes were found that are nearly optimum for use with Viterbi decoding in the inner coding of concatenated coding systems. A convolutional code, the unit-memory code, was discovered and is ideal for inner system usage because of its byte-oriented structure. Simulations of sequential decoding on the deep-space channel were carried out to compare directly various convolutional codes that are proposed for use in deep-space systems.

Massey, J. L.↗

Toward an event-level analysis of hadron structure using differential programming

Reconstructing the internal properties of hadrons in terms of fundamental quark and gluon de- grees of freedom is a central goal in nuclear and particle physics. This effort lies at the core of major experimental programs, such as the Jefferson Lab 12 GeV program and the upcoming Electron-Ion Collider. A primary challenge is the inherent inverse problem: converting large-scale observational data from collision events into the fundamental QCD-defined densities that characterize the micro- scopic structure of hadronic systems. Recent advances in AI and machine learning have opened new avenues for addressing this challenge using deep learning techniques. A particularly promising direction is the integration of complex theoretical calculations and experimental simulations into a unified framework capable of reconstructing these densities directly from event-level information. In this document, we introduce a key algorithm called LOITS, which enables differentiable program- ming within such a framework, facilitating the use of AI/ML techniques to solve the inverse problem of QCF reconstruction at the event level.

Braga, Kevin [College of William and Mary, William↗

Low-energy Electron-track Imaging for a Liquid Argon Time-projection-chamber Telescope Concept Using Probabilistic Deep Learning

The GammaTPC is an MeV-scale single-phase liquid argon time-projection-chamber gamma-ray telescope concept with a novel dual-scale pixel-based charge-readout system. It promises to enable a significant improvement in sensitivity to MeV-scale gamma rays over previous telescopes. The novel pixel-based charge readout allows for imaging of the tracks of electrons scattered by Compton interactions of incident gamma rays. The two primary contributors to the accuracy of a Compton telescope in reconstructing an incident gamma-ray’s original direction are its energy and position resolution. In this work, we focus on using deep learning to optimize the reconstruction of the initial position and direction of electrons scattered in Compton interactions, including using probabilistic models to estimate predictive uncertainty. We show that the deep-learning models are able to predict locations of Compton scatters of MeV-scale gamma rays from simulated 500 μm pixel-based data to better than 1 mm rms error and are sensitive to the initial direction of the scattered electron. We compare and contrast different deep-learning uncertainty estimation algorithms for reconstruction applications. Additionally, we show that event-by-event estimates of the uncertainty of the locations of the Compton scatters can be used to select those events that were reconstructed most accurately, leading to improvement in locating the origin of gamma-ray sources on the sky.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Appalachian Basin Play Fairway Analysis: Revised 2016 Combined Risk Factor Analysis

This submission contains information used to compute the combined risk factors for deep geothermal energy opportunities in the Appalachian Basin, in the context of a the Play Fairway Analysis project. The risk factors are sedimentary rock reservoir quality, thermal resource quality, potential for induced seismicity, and utilization for direct-use heating of neighborhoods. The methods used to combine the risk factors included taking the average, the geometric mean, and the minimum of the four risk factors. Combined risk maps are provided for three different sedimentary rock reservoir metrics. Combined risk maps are also provided for the three geologic risk factors alone (thermal, reservoir, and seismic), and for the three risk factors that exclude reservoir quality (utilization, seismicity, and thermal qualities). The 2015 data submission should be visited to obtain associated shapefiles, which include: 1) definition of the High and Medium priority play fairways (Inner_Fairway, and Outer_Fairway), 2) definition of the US Census Places (usCensusPlaces), 3) places (cities) of interest in the region (Places_of_Interest) identified as geothermal play fairways, 4) the point centers of the raster cells (Raster_Center_Locations), and 5) locations of industries and special-use communities (e.g., colleges and military bases) identified as low temperature heat users (Industries). The 2015 submission also includes: 1) a methodology memo that explains how the risk factors were combined (GPFA-AB_combining_risk_factors.pdf), 2) the earthquake-based seismic risk map, and 3) supporting information with details of the calculations or processing used in generating these data files. More details on each file are given in the spreadsheet "list_of_contents.xlsx" in the folder "Supporting_Information". Code used to calculate values is available at https://github.com/calvinwhealton/geothermal_pfa under the folder "combining_metrics". Note that the 2016 code is currently under the branch named "combining_metrics_2016" in the folder called "combining_metrics". This branch may be merged with the master branch in the future. Many files contained within this submission update and replace the indicated files contained in: Cornell University. (2015). Risk Factor Analysis in Low-Temperature Geothermal Play Fairway Analysis for the Appalachian Basin (GPFA-AB) [data set]. Retrieved from https://gdr.openei.org/submissions/622. doi:10.15121/1261942

15 GEOTHERMAL ENERGY↗

Chapter 14: Machine Learning of Combustion LES Models from Reacting Direct Numerical Simulation

In this chapter we demonstrate how supervised deep learning techniques can be used to construct models for the filtered progress variable source term necessary for large eddy simulation (LES). The source data for the model is a direct numerical simulation (DNS) of a reacting flow in a low swirl burner configuration. Filtered quantities taken from the DNS data are used to train a deep neural network (DNN)-based model. An efficient data sampling strategy was devised to ensure that a uniform representation of all the states observed in the filtered DNS data are equally present in the training dataset. A-priori testing of the DNN-based model highlights the representative power of DNN to accurately reproduce the filtered reaction progress variable source term over a range of scales and various flame regimes as seen in an industrial burner.

combustion LES models↗

Endovascular Treatment of Phlegmasia Cerulea Dolens with Impending Venous Gangrene: Manual Aspiration Thrombectomy as the First-Line Thrombus Removal Method

Purpose: Our purpose was to report the outcome of endovascular treatment with manual aspiration thrombectomy as the first-line thromboablative method for phlegmasia cerulea dolens. Methods: Between October 2006 and May 2010, seven consecutive patients (5 women, 2 men; age range, 31-80 years) with the diagnosis of phlegmasia cerulea dolens secondary to acute iliofemoral deep venous thrombosis had endovascular treatment with manual aspiration thrombectomy. Catheter-directed thrombolysis and stent placement were used as adjunctive procedures. Phlegmasia was left-sided in five and right-sided in two patients. Results: All patients had associated great saphenous vein thrombosis in addition to iliofemoral deep vein thrombosis (DVT). Aspiration thrombectomy completely removed the thrombus from the popliteal vein to the inferior vena cava (IVC) in all cases. Three patients with May-Thurner syndrome had stent placement in the left common iliac vein. Two patients had early recurrences. Repeated aspiration thrombectomy was unsuccessful in one patient. There were no complications related to the procedure. One patient who had been successfully treated died of sepsis and another patient who had unsuccessful repeated interventions had below-the-knee amputation. Overall, the clinical success and survival rates of patients in this study were 86%. On follow-up, three patients with successful treatment were asymptomatic with no deep venous insufficiency. One of these patients died during the 4-month follow-up period. Two patients had mild ankle swelling with deep venous insufficiency. Conclusions: Manual aspiration thrombectomy with adjunctive use of catheter-directed thrombolysis and stent placement is an effective endovascular treatment method with high clinical success and survival rates for phlegmasia cerulean dolens.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Spent Nuclear Fuel Disposition

One interdisciplinary field devoted to achieving the end-state of used nuclear fuel (UNF) through reuse and/or permanent disposal. The reuse option aims to make use of the remaining energy content in UNF and reduce the amount of long-lived radioactive materials that require permanent disposal. The planned approach in the U.S., as well as in many other countries worldwide, is direct permanent disposal in a deep geologic repository. Used nuclear fuel is fuel that has been irradiated in a nuclear reactor to the point where it is no longer capable of sustaining operational objectives. The vast majority (by mass) of UNF is from electricity generation in commercial nuclear power reactors. Furthermore, the other main source of UNF in the U.S. is the Department of Energy’s (DOE) and other federal agencies’ operation of reactors in support of federal government missions, such as materials production, nuclear propulsion, research, testing, and training. Upon discharge from a reactor, UNF emits considerable heat from radioactive decay. Some period of active on-site cooling (e.g., 2 or more years) is typically required to facilitate efficient packaging and transportation to a disposition facility. Hence, the field of UNF disposition broadly includes storage, transportation and ultimate disposition. See also: Nuclear Fission (content/nuclear-fission/458400), Nuclear Fuels (/content/nuclear-fuels/458600), Nuclear Fuel Cycle (/content/nuclear-fuel-cycle/458500), Nuclear Fuels Reprocessing (/content/nuclear-fuels-reprocessing/458700), Nuclear Power (/content/nuclear-power/459600), Nuclear Reactor (/content/nuclear-reactor/460100), Radiation (/content/radiation/566300), and Radioactive Waste Management (/content/radioactive-waste-management/568900).

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Tribology and Tool Wear of Hot Dip Galvanized Zinc Magnesium Alloys on Cold Rolled Steel Sheets

Recently zinc based coatings on cold rolled steel with improved functionality in terms of forming and/or corrosion behaviour have been intensively investigated in the steel industry. One of the most promising products are zinc magnesium alloys produced in hot dip galvanizing process. These coatings were already introduced in construction industry a few years ago. With some modifications the improved properties of the coating are also interesting for automotive industry. In the present work the tribological potential of hot dip galvanized zinc magnesium coatings (HDG/ZM) produced at an industrial line under regular production, was studied in terms of sliding properties, adhesive and abrasive tool wear.First a short introduction into surface morphology of HDG/ZM will be given. For the tribological characterization of the material, which is the main topic of the contribution, different tests were performed on hot dip galvanised zinc magnesium material and results were compared with classic hot dip galvanized zinc coating (HDG/Z). The investigations are mainly based on the strip draw test which allows the determination of the friction coefficient directly by using a constant contact pressure. Deep drawing property was tested by forming model cups. The abrasive tool wear was tested using a standard test for material used in automotive industry. The adhesive tool wear was investigated by characterizing the coating material transferred to the tool in the strip draw test.All performed tests show an improved drawability of HDG/ZM compared to classical HDG/Z reference material. However the most promising difference between HDG/ZM and HDG/Z is that galling was found to be less for HDG/ZM than for HDG/Z. Therefore HDG/ZM is an interesting system not only with respect to corrosion protection but also in terms of tribology and provides clear advantages in formability.

36 MATERIALS SCIENCE↗

Bridging the gap between experiments and simulations using machine learning

The physics of inertial confinement fusion is rich and complex. Simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this work we use deep learning to build a fast emulator of experiments. To facilitate the development of the deep-learning model, an autoencoder is used to reduce the dimensionality of the input space. Two deep learning models are developed. One model is trained on a vast array of simulation data and is subsequently calibrated to expensive and limited experimental data using a technique known as “transfer learning.” The other model is trained on a statistical model and is subsequently calibrated using experimental data. A comparative study of the two predictive models is carried out. The models potentially reproduce key experimental observables with high accuracy and unprecedented inference times relative to those achieved with simulation codes. These models facilitate rapid exploration of a high dimensional input parameter space.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Thermal Evolution near Heat-Generating Nuclear Waste Canisters Disposed in Horizontal Drillholes

We consider the disposal of spent nuclear fuel and high-level radioactive waste in horizontal holes drilled into deep, low-permeable geologic formations using directional drilling technology. Residual decay heat emanating from these waste forms leads to temperature increases within the drillhole and the surrounding host rock. The spacing of waste canisters and the configuration of the various barrier components within the horizontal drillhole can be designed such that the maximum temperatures remain below limits that are set for each element of the engineered and natural repository system. We present design calculations that examine the thermal evolution around heat-generating waste for a wide range of material properties and disposal configurations. Moreover, we evaluate alternative layouts of a monitoring system to be part of an in situ heater test that helps determine the thermal properties of the as-built repository system. A data-worth analysis is performed to ensure that sufficient information will be collected during the heater test so that subsequent model predictions of the thermal evolution around horizontal deposition holes will reliably estimate the maximum temperatures in the drillhole. The simulations demonstrate that the proposed drillhole disposal strategy can be flexibly designed to ensure dissipation of the heat generated by decaying nuclear waste. Moreover, an in situ heater test can provide the relevant data needed to develop a reliable prediction model of repository performance under as-built conditions.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DeepONet-Assisted Optimization of Surface Topography for Transition Delay in A Mach 4.5 Boundary Layer

We use deep learning, an ensemble variationaltechnique (EnVar), and direct numerical simulations(DNS) to design an optimal topography for a two-dimensional roughness element that delays the on-set of laminar-turbulent transition in a Mach 4.5 flat-plate boundary layer. Deep operator networks (Deep-ONets), which have the known ability to learn com-plex nonlinear operators within dynamical systems,are used for machine learning. For the baseline config-uration of a smooth flat plate, the second-mode wavesat the DNS inflow cause a quick nonlinear breakdownof the high-speed boundary layer within the computa-tional domain. Results reported in the present studyvalidate the ability of DeepONets to model the tran-sition delay via a given topography of the roughnesselement. The computing cost to optimize the rough-ness element for minimal skin-friction drag is substan-tially lowered by the DeepONets-based reduced-ordermodel. In comparison to the baseline method of EnVaroptimization based on DNS alone, the DeepONets-based EnVar optimizer is able to delay transition pastthe outflow boundary of the computational domainwhile utilizing almost 5–6 times fewer DNS.

Machine Learning↗

Active Optical Control with Machine Learning: A Proof of Concept for the Vera C. Rubin Observatory

Abstract The Active Optics System of the Vera C. Rubin Observatory (Rubin) uses information provided by four wave front sensors to determine deviations between the reconstructed wave front and the ideal wave front. The observed deviations are used to adjust the control parameters of the optical system to maintain image quality across the 3.°5 field of view. The baseline approach from the project is to obtain amplitudes of the Zernike polynomials describing the distorted wave front from out-of-focus images collected by the wave front sensors. These Zernike amplitudes are related via an “influence matrix” to the control parameters necessary to correct the wave front. In this paper, we use deep-learning methods to extract the control parameters directly from the images captured by the wave front sensors. Our neural net model uses anti-aliasing pooling to boost performance, and a domain-specific loss function to aid learning and generalization. The accuracy of the control parameters derived from our model exceeds Rubin requirements even in the presence of full-moon background levels and mis-centering of reference stars. Although the training process is time consuming, model evaluation requires only a few milliseconds. This low latency should allow for the correction of the optical configuration during the readout and slew interval between successive exposures.

Astronomy & Astrophysics↗

Deep learning ferroelectric polarization distributions from STEM data via with and without atom finding

Over the last decade, scanning transmission electron microscopy (STEM) has emerged as a powerful tool for probing atomic structures of complex materials with picometer precision, opening the pathway toward exploring ferroelectric, ferroelastic, and chemical phenomena on the atomic scale. Analyses to date extracting a polarization signal from lattice coupled distortions in STEM imaging rely on discovery of atomic positions from intensity maxima/minima and subsequent calculation of polarization and other order parameter fields from the atomic displacements. Here, we explore the feasibility of polarization mapping directly from the analysis of STEM images using deep convolutional neural networks (DCNNs). In this approach, the DCNN is trained on the labeled part of the image (i.e., for human labelling), and the trained network is subsequently applied to other images. We explore the effects of the choice of the descriptors (centered on atomic columns and grid-based), the effects of observational bias, and whether the network trained on one composition can be applied to a different one. This analysis demonstrates the tremendous potential of the DCNN for the analysis of high-resolution STEM imaging and spectral data and highlights the associated limitations.

36 MATERIALS SCIENCE↗

Deep Borehole Disposal Research: Geological Data Evaluation Alternative Waste Forms and Borehole Seals

This report documents deep borehole disposal research during FY2014, as directed by U.S. Department of Energy (DOE) Used Fuel Disposition (UFD) Campaign. These research efforts are principally directed at advancing the deep borehole disposal project to the implementation of a full-scale Research, Development, and Demonstration (RD&D) project. Activities of particular relevance to this goal include evaluation of guidelines for selection of a deep borehole field test site, analyses of deep borehole disposal of alternative waste forms, and technical planning for borehole seals research.

Arnold, Bill W.↗