SEARCH · Search NASA

Results for “Machine Leaning”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3

All sources NASA NTRS DOE OSTI

DOE OSTI2019

Ignition, Flame Progation, and End-Gas Autoignition Studies of Natural Gas/ EGR Blends in a Rapid Compression Machine

The development of high efficiency, spark ignited natural gas engines is currently limited by engine knock at high power density (at high compression ratio and/or elevated boost pressures) and misfire (at lean conditions and/or high exhaust gas recirculation levels). The knock and misfire limits are further confounded by the wide variety in fuel reactivity observed in “pipeline quality” natural gas. In this study, a rapid compression machine (RCM) was used to characterize the effects of variation in natural gas fuel reactivity and exhaust gas recirculation (EGR) on homogeneous ignition delay, flame propagation rate and end-gas autoignition (EGAI) propensity for stoichiometric natural gas/oxidizer/EGR blends. Pipeline quality natural gas with variable reactivity (68 < Methane Number < 95) was simulated using mixtures of methane, ethane, and propane. EGR was simulated with mixtures of Ar, CO2, CO, and NO. EGR substitution rates were varied from 0 to 30 mass percent. Ignition delay period under homogeneous autoignition conditions was measured at compressed pressures of 24.0 to 33.1 bar and compressed temperatures of 667 to 980 K. Flame propagation rate and EGAI propensity was measured at spark-ignition pressures of 29.9 to 32.9 bar and temperatures of 721 to 782 K.

Mohr, Jeffrey↗

DOE OSTI2019

Ignition, Flame Propagation, and End-Gas Autoignition Studies of Natural Gas/EGR Blends in a Rapid Compression Machine

Ignition Delay, Flame Propagation Rate, Rapid Comp↗

DOE OSTI2020

Autoignition of CRC diesel surrogates at low temperature combustion conditions: Rapid compression machine experiments and modeling

As federal programs require increasingly stringent engine emissions and fuel economy standards, these ambitions can only be met if next-generation combustion technology is developed focusing on high-efficiency and low-emissions engines. Recent research has indicated the need to operate engines at higher compression ratios and with low temperature combustion (LTC) to achieve the needed gains in engine efficiency and reductions in emissions. Because there is a lack of understanding of the chemistry of diesel fuel components and their mixtures at these LTC conditions, this limits the ability to develop predictive chemical kinetic models that can be used to optimize engine combustion. The current study aims to fill in gaps in fundamental combustion data on surrogate fuel mixtures relevant to diesel fuels. Specifically, four multicomponent diesel surrogates formulated by the Coordinating Research Council (CRC) to emulate an ultra-low-sulfur research-grade #2 certification diesel fuel (CFA), namely V0a (4 components), V0b (5 components), V1 (8 components), and V2 (9 components), have been investigated in a rapid compression machine (RCM) through determination of total and first-stage ignition delay times. Autoignition characteristics of lean to rich fuel/O 2 /N 2 mixtures, for the four CRC surrogates and CFA, have been measured using an RCM at LTC relevant pressures and temperatures, in the ranges of 10–20 bar and 650–1000 K, respectively. The equivalence ratios have been varied by independently changing the oxygen mole fraction and the fuel mole fraction in the test mixtures, thereby illustrating the individual effects of oxygen concentration and fuel loading on diesel autoignition. Autoignition results of these four CRC surrogates are compared among them and with those of CFA. Some degree of agreement in autoignition response between each CRC surrogate and CFA is observed, while discrepancies are also identified and discussed. In addition, a detailed chemical kinetic model for diesel surrogates has been developed and validated against these newly-acquired RCM data. We find that this model shows reasonable agreement with the overall ignition delay time results of the current RCM experiments. Chemical kinetic analyses of the developed model were further conducted to help identify the reactions controlling the autoignition processes and the consumption of fuel components in CRC surrogates.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Factorization Machine Learning for Disaggregation of Transmission Load Profiles with High Penetration of Behind-the-Meter Solar

The ever-growing high penetration of ubiquitously distributed energy resources, especially behind-the-meter solar (BTM) generations, has significant impacts on nodal load (i.e., net injection) profiles and consequently caused imperative operational challenges to system operators such as regional transmission organizations (RTOs). Illustrated by real-world nodal data and examples at PJM Interconnection, this paper first discusses the application and necessity of effectively extracting daily nodal load profiles in a non-intrusive manner. More importantly, a novel bi-level architecture, including Factorization Machines (FM) learning procedure has been proposed to effectively disaggregate not only one node but every node in an RTO service territory. Specifically, FM leaning is adopted to capture the interconnections between related features to better utilize the correlation between buses in the same region and between a single bus and the zonal load. The proposed bi-level technique is numerically validated using real-world, minute-level, normalized, and anonymized nodal data at PJM service territory.

behind the meter solar, load disaggregation, load ↗

DOE OSTI2022

FutureTense

Protective vaccines and reliable diagnostics are essential tools for controlling viral diseases. However, the efficacy of these tools can be diminished by mutations in viral genomes. The delay between the emergence of new viral strains and the redesign of vaccines and diagnostics allows for continued viral transmission. Is it possible to address this challenge by computationally predicting viral genome sequence evolution? Can we “future-proof” vaccines and diagnostics by targeting both current and anticipated future sequence variants? While predicting viral evolution is still an unsolved, “grand challenge” problem in biology, the large, and rapidly growing, number of SARS-CoV-2 genome sequences provide an opportunity to quantify the ability of machine learning to predict viral genome sequence evolution. Towards this end, we have developed a simple computational model for predicting viral evolution at the level of individual nucleotides. The key metric for quantifying the per-base, prediction accuracy for viral evolution is the Mann-Whitney U statistic (or, equivalently, the area under the receiver operator curve). Since the Mann-Whitney U statistic is not a differentiable function, existing deep leaning packages (like Pytorch and Keras/TensorFlow) are not useful, as they require that the accuracy metric/objective function be analytically differentiable with respect to the model parameters. To overcome this challenge, we have implemented custom software, “FutureTense”, that can train a machine learning model by maximizing the non-differentiable Mann-Whitney U statistic. This software trains a machine learning model by exploring along the direction of the discrete gradient of the Mann-Whitney U statistic in the model parameter space. Parallel computing and genome sequence-specific optimizations are used to accelerate model training. The resulting machine learning model learns the observed high C->U mutation rates in the SARS-CoV-2 genome (which are potentially induced by host defenses) and provides prediction accuracies that are significantly better than one would expect from random chance. While predicting viral evolution is still quite far from a solved problem, the surprising performance of this simple model gives hope that the accuracy of predicting viral genome evolution can be further increased by more sophisticated approaches.

Gans, Jason↗

DOE OSTI2025

Computational Investigation of a CO 2 Conversion Strategy via Diels–Alder Reaction in a Carbon Capture Solvent

Molecular-level insights into reactive separations are crucial for the design of new conversion pathways of carbon dioxide (CO 2 ). This work explores a postulated pathway that directs CO 2 to undergo inverse-electron-demand Diels–Alder reactions to produce heterocycles using the CO 2 chemically fixed on water-lean solvent molecules. Density functional theory calculations are applied to evaluate the lowest unoccupied molecular orbital (LUMO) energies of three types of reactants (1,3-butadiene, 1,3-cyclohexadiene, and 1,2,4,5-tetrazine) with various functional substituents. These calculations also provide a data set (5.8k data) for developing a machine learning model to efficiently predict LUMO energies. A computational screening of LUMO energies for an additional 47k diene and tetrazine candidates is performed, and a list of candidates with lowered LUMO energies by electron-withdrawing substituents is provided. These candidates are further examined by their reaction energy barriers computed from the interatomic potential or density functional theory. Two major energy barriers are identified, one for the proton transfer within the water-lean solvent and the other for the CO 2 transfer from the solvent molecule to the reactant candidate (diene or tetrazine). The functional substituents have a more significant impact on the second barrier but a very slight one on the first barrier. This exploratory work demonstrates a new possibility for guiding experimental efforts toward the chemical conversion of fixated CO 2 to value-added compounds.

Chemical reactions↗

DOE OSTI2020

THE EFFECT OF FUEL REACTIVITY AND EXHAUST GAS RECIRCULATION ON KNOCK PROPENSITY OF NATURAL GAS

The development of high efficiency, spark ignited natural gas engines is currently limited by engine knock at high compression ratio/elevated boost pressures and misfire at lean conditions/high exhaust gas recirculation (EGR) levels. The knock and misfire limits are further confounded by the wide variety in fuel reactivity observed in “pipeline quality” natural gas. In this study, a rapid compression machine was used to characterize the effects of EGR and variation in natural gas fuel reactivity on the homogeneous ignition delay, flame propagation rate, and end- gas autoignition propensity for stoichiometric natural gas/oxidizer/EGR blends. A reduced chemical kinetic mechanism was also developed to accurately model the homogeneous ignition delays measured in the Colorado State University rapid compression machine (CSU RCM). Pipeline quality natural gas with a range of chemical reactivity (68 < Methane Number < 95) was simulated using mixtures of CH4, C2H6, and C3H8. Exhaust gas recirculation gases were simulated with mixtures of Ar, CO2, CO, and NO at substitution rates of 0 to 30 mass percent. Ignition delay period under homogeneous autoignition conditions was measured at compressed pressures of 30.2 to 34.0 bar and compressed temperatures of 667 to 980 K. End-gas autoignition fraction and flame propagation rate were measured by initiating a laser spark in the center of the combustion chamber, after compression, at pressures of 30.7 to 32.7 bar and temperatures of 751 to 795 K. The results indicate that both fuel reactivity and the presence of reactive species (NO and CO) in the exhaust gas recirculation have a strong impact on end-gas autoignition fraction. A chemical kinetic mechanism was developed to predict homogeneous ignition delays for pipeline quality natural gas in a pressure and temperature range of 1-100 bar and 500-1000 K respectively. This mechanism accurately predicted measured homogeneous ignition delay in the RCM with a total average relative error of 11.0%.

Mohr, Jeffrey↗

DOE OSTI2021

Improvements to the Powder Processing of near-Final Shape alnico Magnets

Alnico permanent magnets (PMs), a recent PM system of interest as an attractive rare earth-free PM alternative, have advantageous high operating temperature and magnetic saturation with the potential for utilization in electric machines, e.g. interior-PM motors found in electric vehicles, if current directional solidification methods can be replaced by a true mass production approach. Recently, two unique alnico compositions, termed Full-Co and Co-lean, with improved coercivity, were gas atomized, compression molded, and vacuum sintered (4h at 1240°C) to high densities of 97.8% and 99.3%, respectively. However, the Co-lean remained fine grained isotropic magnets and the Full-Co grains were not textured, lowering magnetic strength in spite of attempts to grow large textured grains by a stress-biased solid state grain alignment method to convert them to high energy anisotropic magnets. It was hypothesized that oxidation during de-binding in air left many prior particle boundary oxides within the sintered microstructure that hindered grain growth and texturing during the stress-biased texturing procedure and prevented the desired abnormal grain growth (AGG). Here we explored a vacuum de-binding step that was linked (in-place) to vacuum sintering and found that the Co-lean exhibited faster uniform grain growth that doubled the average grain size (40 μm to 80 μm). Linked vacuum de-binding and sintering of Full-Co produced some AGG after only 1 h of 1240°C sintering. A new direction for promoting AGG (and stress-biased texturing) in alnico is being explored that utilizes a fundamental analysis of systems with second phase particles that either inhibit or boost grain growth. This effort explores the influence of vacuum de-binding linked to a series of lower sintering temperatures at a fixed time (4h) to see if oxide particle size and volume fraction can be changed to promote AGG conditions in alnico. Surprising qualitative results indicate that AGG may be promoted for vacuum sintering at less than 1200°C.

Rinko, Emily↗

DOE OSTI2024

DLSIA: Deep Learning for Scientific Image Analysis

DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features easy-to-use architectures, such as autoencoders, tunable U-Nets and parameter-lean mixed-scale dense networks (MSDNets). Additionally, this article introduces sparse mixed-scale networks (SMSNets), generated using random graphs, sparse connections and dilated convolutions connecting different length scales. For verification, several DLSIA-instantiated networks and training scripts are employed in multiple applications, including inpainting for X-ray scattering data using U-Nets and MSDNets, segmenting 3D fibers in X-ray tomographic reconstructions of concrete using an ensemble of SMSNets, and leveraging autoencoder latent spaces for data compression and clustering. As experimental data continue to grow in scale and complexity, DLSIA provides accessible CNN construction and abstracts CNN complexities, allowing scientists to tailor their machine learning approaches, accelerate discoveries, foster interdisciplinary collaboration and advance research in scientific image analysis.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1963

Integrated Mission Simulation for Long Term Space Flight

The problems of evaluating pilot performance, pilot training, and the integration of the man-machine system for proper functioning become increasingly difficult as the length of projected space flights increases. Further, actual in-flight experience becomes harder to obtain and the major means for training and evaluation becomes simulation. The first major source of difficulty in any simulation stems from a basic requirement of leaning theory: that for increased proficiency of performance to occur within any biologically capable system, the stimuli which are the bases for the expected behavior must be presented in an amenable form to the learner. Further, the sequence of presentation of the pertinent stimuli must be such that the learner can form the appropriate concepts and interactions required for the ultimate use of the learned material. It can then be seen that two basic factors of learning complex skills are: 1) Fidelity of simulation of pertinent stimuli. 2) Appropriate sequencing of stimuli during learning for proper concept formation.

SPACE FLIGHT↗

DOE OSTI2020

Ignition delay time and speciation of dibutyl ether at high pressures

Dibutyl ether (DBE) is a promising biofuel due to its high cetane number (~ 100) and high volumetric energy density (31.6 MJ/L). It could either be used directly in compression ignition engines or blended with other conventional or renewable fuels. Oxidation and pyrolysis kinetics of DBE are not well known, particularly at high pressures. In this work, we have experimentally investigated the chemical kinetics of DBE in three domains: (a) ignition delay time measurements in a rapid compression machine over T = 550–650 K, P = 10, 20, 40 bar, φ = 0.5, 1; (b) ignition delay time measurements in a shock tube over T = 900–1300 K, P = 20, 40 bar, φ = 0.5, 1; (c) laser-based carbon monoxide speciation measurements in a shock tube during DBE pyrolysis and oxidation over T = 1100–1400 K, P = 20 bar. Pressure time-histories measured in RCM experiments exhibited unique 3-stage and 4-stage ignition behavior predominantly at fuel-lean conditions. Experimental data were compared with the predictions of two recent chemical kinetic models of DBE. Sensitivity analyses were carried out to identify key reactions which may have caused the discrepancy between experiments and simulations. We found that the rate of decomposition of DBE may need to be revisited to improve the oxidative and pyrolytic predictions of DBE kinetic model.

09 BIOMASS FUELS↗

NASA NTRS1982

NOx results from two combustors tested on medium BTU coal gas

The results of tests of two combustor configurations using coal gas from a 25 ton/day fluidized bed coal gasifier are reported. The trials were run with a ceramic-lined, staged rich/lean burner and an integral, all metal multiannular swirl burner (MASB) using a range of temperatures and pressures representative of industrial turbine inlet conditions. A lean mixture was examined at 104, 197, and 254 Btu/Scf, yielding NO(x) emissions of 5, 20, and 70 ppmv, respectively. The MASB was employed only with a gas rated at 220-270 Btu/Scf, producing 80 ppmv NO(x) at rated engine conditions. The results are concluded to be transferrable to current machines. Further tests on the effects of gas composition, the scaling of combustors to utility size, and the development of improved wall cooling techniques and variable geometry are indicated.

Sherlock, T. P.↗

DOE OSTI2019

Autoignition behavior of iso-olefins

Olefins, and particularly iso-olefins constitute a significant portion of petroleum-derived gasoline, while they also represent a production route for bio-derived transportation-relevant fuels. Although linear structures have been studied for some time, the combustion behavior of iso-olefins is not as well understood. To appropriately mimic gasoline in fundamental tests and in computational models, this lack of understanding must be addressed. Towards this end, rapid compression machine (RCM) experiments were performed for 2-methyl-2-butene (2M2B) and 2-methyl-2-pentene (2M2P) as two representative structures. A detailed chemical kinetic model for these iso-olefins is under development to gain further insight into their autoignition chemistry. In the kinetic model, reaction types and associated rate constants for olefins are less clear than those for n-alkanes. The structural similarity of the two studied iso-olefins allows the development of consistent reaction rate rules to accurately simulate their behavior. The RCM tests cover temperatures from 700 to 1000 K, pressures of 25 and 45 bar, with lean, stoichiometric and rich conditions, and indicate that 2M2P is more reactive than 2M2B due to its longer hydrocarbon backbone. The difference is more extreme at rich conditions. These trends are investigated by the kinetic model where the presence of allylic carbons in the molecule limits the contribution to the low temperature reactivity.

2-methyl-2-butene↗

DOE OSTI2020

Industry 4.0 and Intelligent Manufacturing Processes: A Review of Modern Sensing Technologies

Digital Manufacturing technologies have quickly become ubiquitous in the manufacturing industry. The transformation commonly referred to as the fourth industrial revolution, or Industry 4.0, has ushered in a wide range of communication technologies, connection mechanisms, and data analysis capabilities. These technologies provide powerful tools to create a more lean, profitable, and data-driven manufacturing processes. In this paper, we review modern communication technologies and connection architectures for Digital Manufacturing and Industry 4.0 applications. An introduction to Cyber-Physical Systems and a review of digital manufacturing trends is followed by an overview of data acquisition methods for manufacturing processes. Numerous communication protocols are presented and discussed for connecting disparate machines and processes. Flexible data architectures are discussed and examples of machine monitoring implementations are provided. Finally, select implementations of these communication protocols and architectures are surveyed with recommendations for future architecture implementations.

42 ENGINEERING↗

DOE OSTI2019

Hot-spot induced mild ignition: Numerical simulation and scaling analysis

Mild ignition is a 'non-ideal' autoignition process observed at some conditions in rapid compression machine, shock tube and flow reactor experiments where flames and/or reaction fronts initiate due to non-uniformities within the test mixture. These flames/fronts can consume the entire mixture, or compression-heat the unburned gas, causing bulk ignition at times earlier than in homogeneous environments. This study numerically investigates mild ignition features using computational fluid dynamics techniques under a scenario where a small hot-spot is employed to initiate the process in a spherically-symmetric geometry. Only subsonic regimes are considered. The intent is to develop greater fundamental understandings of competing phenomena, and formulate a robust framework to quantify the perturbative behavior. Syngas blends (CO/H 2 = 80/20) are employed as the fuel, mixed with air at lean fuel loadings of phi = 0.2 and 0.5, with the initial temperatures and pressures covering 900-1120K, and 1.5-15 bar, respectively. Hot-spots ranging from 50 to 2,000 mu m in diameter are utilized with temperatures elevated from the surroundings by 1 to 90%, i.e., T hot /T 0 =1.01-1.90. Scaling arguments are derived to analyze competing processes of: (a) quenching vs. ignition, (b) extinction vs. propagation, and (c) flame consumption/forced autoignition vs. homogeneous ignition. Here, this work provides new insight into non-uniform autoignition phenomena, and discusses opportunities and challenges associated with mitigating it. In particular, scaling arguments indicate that experimental parameters could have potential to either suppress hot-spot initiated flame formation (e.g., via bath gases with high thermal diffusivity), or avert flame compression of the end gas (e.g., via lean/diluted mixtures, or bath gases with high heat capacity).

42 ENGINEERING↗

DOE OSTI2022

Snowmass2021 theory frontier white paper: Astrophysical and cosmological probes of dark matter

While astrophysical and cosmological probes provide a remarkably precise and consistent picture of the quantity and general properties of dark matter, its fundamental nature remains one of the most significant open questions in physics. Obtaining a more comprehensive understanding of dark matter within the next decade will require overcoming a number of theoretical challenges: the groundwork for these strides is being laid now, yet much remains to be done. Chief among the upcoming challenges is establishing the theoretical foundation needed to harness the full potential of new observables in the astrophysical and cosmological domains, spanning the early Universe to the inner portions of galaxies and the stars therein. Identifying the nature of dark matter will also entail repurposing and implementing a wide range of theoretical techniques from outside the typical toolkit of astrophysics, ranging from effective field theory to the dramatically evolving world of machine learning and artificial-intelligence-based statistical inference. Through this work, the theory frontier will be at the heart of dark matter discoveries in the upcoming decade.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

Net Present Value Optimization of a Natural Gas Combined Cycle Plant with CO 2 Capture using a Water-Lean Solvent Considering Transient Electricity Price for Multiple Regions

Global CO 2 emissions are increasing at about a 1.5% rate per year. Fossil fuel-based plants are one of the main contributors to this rise. In the power generation industry, fossil fuel plants are dominant, and many plants are under development. In this study, a natural gas combined cycle (NGCC) power plant with postcombustion capture using a leading water-lean solvent is considered. For optimal design and operating schedule, large-scale dynamic optimization is undertaken for net present value (NPV) optimization. The first principle dynamic model of NGCC is developed, including a model of the highly efficient H-class gas turbines. For computational tractability of the dynamic optimization problem, a reduced-order model is developed by using the Hankel singular value decomposition. A waterlean solvent, N-(2-ethoxyethyl)-3-morpholinopropan-1-amine, is used for carbon capture. A model of the capture system is developed in Aspen Plus, which is used to develop a reduced-order model by using ALAMO, a machine learning software. In addition, a reduced model of the CO 2 compression system with a dehydration unit is also considered. The integrated system is used for NPV optimization by using the Python-based PYOMO platform. The PCC process is analyzed for three configurations-conventional packed bed, rotating packed bed (RPB), and a combination of RPB and direct contact cooler. The NPV optimization is performed for 14 regional markets by considering year-long clustered and continuous locational marginal price data with a 1 h interval. Optimization results show that the PCC can achieve 90% CO 2 capture with a positive NPV for six regions. Sensitivity studies conducted by using the PCC configurations indicate that the process is economically feasible for 9 regions out of 14 regional electricity markets with NPV values in the range of 33−540 $MM.

cabon capture↗

NASA NTRS1982

Low NO sub x heavy fuel combustor concept program. Phase 1A: Combustion technology generation coal gas fuels

Combustion tests of two scaled burners using actual coal gas from a 25 ton/day fluidized bed coal gasifier are described. The two combustor configurations studied were a ceramic lined, staged rich/lean burner and an integral, all metal multiannual swirl burner (MASB). The tests were conducted over a range of temperature and pressures representative of current industrial combustion turbine inlet conditions. Tests on the rich lean burner were conducted at three levels of product gas heating values: 104, 197 and 254 btu/scf. Corresponding levels of NOx emissions were 5, 20 and 70 ppmv. Nitrogen was added to the fuel in the form of ammonia, and conversion efficiencies of fuel nitrogen to NOx were on the order of 4 percent to 12 percent, which is somewhat lower than the 14 percent to 18 percent conversion efficiency when src-2 liquid fuel was used. The MASB was tested only on medium btu gas (220 to 270 btu/scf), and produced approximately 80 ppmv NOx at rated engine conditions. Both burners operated similarly on actual coal gas and erbs fuel, and all heating values tested can be successfully burned in current machines.

Sherlock, T. P.↗