Machine learning-guided accelerated discovery of structure-property correlations in lean magnesium alloys for biomedical applications
Not provided.
Metallurgy & Metallurgical Engineering↗
SEARCH · Engineering Papers
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.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Predictive Modeling of NOx Emissions from Lean Direct Injection of Hydrogen and Hydrogen/Natural Gas Blends Using Flame Imaging and Machine Learning
This research paper explores the use of machine learning to relate images of flame structure and luminosity to measured NOx emissions. Images of reactions produced by 16 aero-engine derived injectors for a ground-based turbine operated on a range of fuel compositions, air pressure drops, preheat temperatures and adiabatic flame temperatures were captured and postprocessed. The experimental investigations were conducted under atmospheric conditions, capturing CO, NO and NOx emissions data and OH* chemiluminescence images from 27 test conditions. The injector geometry and test conditions were based on a statistically designed test plan. These results were first analyzed using the traditional analysis approach of analysis of variance (ANOVA). The statistically based test plan yielded 432 data points, leading to a correlation for NOx emissions as a function of injector geometry, test conditions and imaging responses, with 70.2% accuracy. As an alternative approach to predicting emissions using imaging diagnostics as well as injector geometry and test conditions, a random forest machine learning algorithm was also applied to the data and was able to achieve an accuracy of 82.6%. This study offers insights into the factors influencing emissions in ground-based turbines while emphasizing the potential of machine learning algorithms in constructing predictive models for complex systems.
08 HYDROGEN↗
Unit cell manufacture by blown powder directed energy deposition
Lattice structures manufactured by additive manufacturing show unique promise to alter existing components to improve the thermo-mechanical properties of the base structure. Here, in the present study, the manufacture of a self-supporting lattice structure by blown powder directed energy deposition was explored. Converging struts were manufactured using multiple lean angles to facilitate the self-supporting structure and to avoid machine-part collisions. The struts showed near uniform straightness relative to a fitted line with a maximum deviation of 1mm at a lean angle of 10°. Micro–hardness and porosity evaluation results showed no significant variation along the struts.
Additive manufacturing↗
EdgeAI: Machine learning via direct attached accelerator for streaming data processing at high shot rate x-ray free-electron lasers
We present a case for low batch-size inference with the potential for adaptive training of a lean encoder model. We do so in the context of a paradigmatic example of machine learning as applied in data acquisition at high data velocity scientific user facilities such as the Linac Coherent Light Source-II x-ray Free-Electron Laser. We discuss how a low-latency inference model operating at the data acquisition edge can capitalize on the naturally stochastic nature of such sources. We simulate the method of attosecond angular streaking to produce representative results whereby simulated input data reproduce high-resolution ground truth probability distributions. By minimizing the mean-squared error between the decoded output of the latent representation and the ground truth distributions, we ensure that the encoding layers and resulting latent representation maintains full fidelity for any downstream task, be it classification or regression. We present throughput results for data-parallel inference of various batch sizes, some with throughput exceeding 100 k images per second. We also show in situ training below 10 s per epoch for the full encoder–decoder model as would be relevant for streaming and adaptive real-time data production at our nation’s scientific light sources.
97 MATHEMATICS AND COMPUTING↗
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 ↗
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↗
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↗
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↗
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↗
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.↗
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↗
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↗
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.↗
Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data
Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine
03 NATURAL GAS↗
Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data (Final Report)
Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components: (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine.
20 FOSSIL-FUELED POWER PLANTS↗
Sentiment analysis of the United States public support of nuclear power on social media using large language models
This study utilized large language models (LLMs) to analyze public sentiment in the United States (US) regarding nuclear power on social media, focusing on X/Twitter, considering climate change challenges and advancements in nuclear power technology. Approximately, 1.26 million nuclear tweets from 2008–2023 were examined to fine-tune LLMs for sentiment classification. We found the crucial role of accurate data labeling for model performance, with potential implications for a 15% improvement, achieved through high-confidence labels. LLMs demonstrated better performance compared to traditional machine learning classifiers, with reduced susceptibility to overfitting and up to 96% classification accuracy. LLMs are used to segment the US public tweets into policy and energy-related categories, revealing that 68% are politically themed. Policy tweets tended to convey negative sentiment, often reflecting opposing political perspectives and focusing on nuclear deals and international relations. Energy-related tweets covered diverse topics with predominantly neutral to positive sentiment, indicating broad support for nuclear power in 48 out of 50 US states. The US public positive sentiments toward nuclear power stemmed from its high power density, reliability regardless of weather conditions, environmental benefits, application versatility, and recent innovations and advancements in both fission and fusion technologies. Negative sentiments primarily focused on waste management, high capital costs, and safety concerns. The neutral campaign highlighted global nuclear facts and advancements, with varying tones leaning towards positivity or negativity. An interesting neutral theme was the advocacy for the combined use of renewable and nuclear energy to attain net-zero goals.
Energy & Fuels↗
Amorphous Metal Ribbon (AMR) and Metal Amorphous Nanocomposite (MANC) Materials Enabled High Power Density Vehicle Motor Applications (Final Technical Report)
A collaborative team from Carnegie Mellon Univ. (CMU), North Carolina State Univ. (NCSU) and Metglas, South Carolina have studied new high speed motors (HSMs) with high-power density for traction motor applications. These are enabled by hybrid designs, including Flux Switching with Permanent Magnets (FSWPM) motors, exploiting permanent magnets without heavy rare earths (RE-lean) and high induction/high resistivity soft magnetic materials that allow for high switching frequencies needed to increase power densities. Team members include Michael E. McHenry, Prof. Materials Science & Eng., CMU, with > 30 years experience in magnetic materials development; Subashish Bhattacharya, Prof. Electrical Eng. and Freedom Center Director at NCSU with > 30 years experience in development of power electronic components and systems and Eric Theisen, Director of Research at Metglas, the only US located supplier of AMR and MANC materials. The team offers novel axial motor architectures exploiting soft magnetic materials (SMMs) that switch with low loss at high frequencies and heavy rare earth free permanent magnets that address materials criticality issues, supply chain risks, and high costs for traction motors. Axial-flux permanent magnet motors (APFM), offer efficiency improvements reducing rotor losses and also significantly higher power density. Axial-flux construction requires less core material, high torque-to-weight ratio. Since AFPM machines have thin magnets, they are smaller than radial flux motors making them attractive in space-limited applications. Noise and vibration are less and planar air gaps are easily adjusted. Flexibility in air-gap direction allows many topologies.
36 MATERIALS SCIENCE↗
Universal Electronic‐Structure Relationship Governing Intrinsic Magnetic Properties in Permanent Magnets
An electronic-structure-centered perspective is presented on permanent-magnet (PM) design, highlighting two key levers, that is, saturation magnetization (M s ), governed by 3d-band filling and exchange physics, and magnetocrystalline anisotropy energy (MAE), arising from spin-orbit coupling (SOC) on anisotropic orbital populations. Reviewing current practices, including DFT-based MAE/J ij extraction, atomistic-spin and micromagnetic modeling, and high-throughput machine learning (ML) pipelines, three bottlenecks limiting predictive discovery is identified that is i) electronic-structure accuracy for small MAE (sensitive to functional choice, Hubbard U, and many-body effects), ii) finite-temperature and kinetic realism (phonon/magnon renormalization, ordering kinetics), and iii) descriptor and multiscale decoupling (lack of SOC-weighted and orbital-resolved fingerprints). Deep dives into the electronic-structure of Nd─Fe─B and Fe─N show how these fingerprints govern magnetic performance, motivating DFT- and quantum-mechanics-based descriptors for discovery. Unbiased, structure-driven exploration, coupled with high-throughput simulations, ML, generative AI, and reasoning models, accelerates candidate identification and propagates insights across scales. Addressing supply-chain risks, on future needs of designing “critical-element-free” magnets with tailored microstructure and high energy products is emphasized. By integrating electronic fingerprints, AI reasoning, and multiscale modeling, a practical roadmap is provided for rare-earth-lean or rare-earth free, high-performance, sustainable PMs.
Singh, Prashant [Ames Laboratory, and Iowa State U↗