Search NASA⌕ Search

SEARCH · Search NASA

Results for “NN”

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 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Understanding oxidation of Fe-Cr-Al alloys through explainable artificial intelligence

Abstract The oxidation resistance of FeCrAl based on alloying composition and oxidizing conditions is predicted using a combinatorial experimental and artificial intelligence approach. A neural network (NN) classification model was trained on the experimental FeCrAl dataset produced at GE Research. Furthermore, using the SHapley Additive exPlanations (SHAP) explainable artificial intelligence (XAI) tool, we explore how the NN can showcase further material insights that are unavailable directly from a black-box model. We report that high Al and Cr content forms protective oxide layer, while Mo in FeCrAl creates thick unprotective oxide scale that is vulnerable to spallation due to thermal expansion. Graphical abstract

Materials Science↗
DOE OSTI2020

Two-Nucleon Short-Range Correlations in Light Nuclei

Understanding the nucleon-nucleon interaction is a fundamental task in nuclear physics, as NN interaction models are a crucial input to modern nuclear structure calculations. While great progress has been made toward understanding this interaction, the available state-of-the-art models predict significantly different behaviors at short distances and high momenta (scale-and-scheme dependence), where two-nucleon Short-Range Correlations (SRCs) dominate the nuclear wave function. Thus, SRCs are a unique tool to constrain the NN interaction and vice versa. SRCs are naturallyoccurring high-local-density NN pairs that, as a result of their short-distance (approx. 0.1 fm) repulsive interaction, fly apart with high momenta, hence populating momentum states above the Fermi level. The study of SRCs also has significant implications for other fields, such as the astrophysics of neutron stars and the behavior of cold atomic gasses. This thesis describes experimental and phenomenological studies of the short-distance / high-momentum structure of the NN interaction through the study of SRCs and vice versa. Experimentally, I report the first measurement of the 3He and 3H(e,e'p) reactions in Hall A of the Thomas Jefferson National Accelerator Facility in kinematics in which the measured cross sections should be sensitive to the underlying nucleon momentum distributions in the range 40 to 500 MeV/c. The resulting cross-section ratios and absolute cross sections were compared to momentum-distribution ratios and precise cross-section calculations respectively. Phenomenologically, I report the generalization of the Contact Formalism (GCF) to nuclear systems, which exploits scale separation and universality to describe nucleons at short distances and high momenta.

Cruz Torres, Reynier↗
DOE OSTI2020

Isospin dependence of Nucleon-Nucleon Short-range Correlations in Inclusive Scattering with Tritium and Helium-3

The nucleon-nucleon (NN) potential has a strong repulsive core. When a two-nucleon (sub)system falls into this range, they will interact strongly at short distance, and move away from each other with momenta above the Fermi level. This is called the NN Short range Correlations (SRCs). Previous experiments reported a neutron-proton pair (isos inglet) dominance in high-momentum nucleons. In inclusive electron scattering, this np dominance will cause a scaling behavior of cross sections at 1.4 < xbj = Q2/2m? < 2 where the high-momentum nucleons dominate. At Je?erson Lab Hall A we checked this hypothesis with electron Quasi-elastic (QE) scattering on A=3 nuclei systems. Our unique gas cell design made electron-tritium scattering possible for the ?rst time in a decade. The 2H, 3H, and 3He inclusive cross sections at 1 < xbj < 3 were measured in two experiments (E12-11-112 and E12-14-011) with a wide Q2 range (0.4 < Q2 < 3 GeV2). This thesis dis cusses the physics goals, experiment setup, and data analysis of the E12-11-112 experiment. Ratios of 3H/2H, 3He/2H and 3H/3He as well as absolute cross sections are presented at 0.4 < Q2 < 1.8 GeV2. NN SRC plateaus are observed in the cross section ratios at high Q2. The 3H/3He ratio of 0.84±0.01 at NN SRC dominant kinematics indicates a np to pp SRC pair ratio of 2.2±0.2 in A=3 nuclei. That implies a preference in T = 0 isospin singlet con?guration. No plateaus are observed at xbj > 2.

Li, Shujie↗
DOE OSTI2025

Multiphysics Meshfree Degradation Modeling of Energy Storage Materials with Kernel Enrichment

Energy storage materials exhibit strong electro-chemo-mechanical coupling and highly anisotropic material properties, contributing to the formation and propagation of micro-cracking during charge/discharge cycling and ultimately diminishing performance and service life. With microstructural images supplied by the National Renewable Energy Laboratory (NREL), pixel-based meshfree model construction by the reproducing kernel particle method (RKPM) is used to represent the complex material microstructures that dictate the coupled physics of these systems. Traditional electro-chemo-mechanical models rely on mesh-based finite element methods, which can lead to difficulties in meshing such complex geometries and capturing crack propagation due to mesh dependency. The first kernel enrichment discussed will be the interface modified reproducing kernel (IM-RK) [1, 2], constructed by scaling a smooth kernel function with an interface-distance function to achieve strategic discontinuity types (i.e. weak discontinuities for strain discontinuities and strong discontinuities for cracks) and alleviate Gibbs oscillations near these transition zones. The IM-RK is especially useful for areas in which a known discontinuity-type is expected a priori. The second kernel enrichment to be discussed is a neural network-enhanced reproducing kernel (NN-RK) [3, 4], which is introduced to effectively model non-obvious damage and crack propagation in the material microstructures; the location, orientation, and solution transition near a localization are automatically captured by superimposed block-level NN optimizations. This NN enrichment approach allows for effective modeling of localizations via a fixed background discretization, relieving tedious efforts for adaptive refinement in traditional mesh-based methods. Applications to the heterogeneous microstructures of Li-ion battery cathodes will be presented to demonstrate the effectiveness of the proposed methods. NN-RK is additionally used to inform how crack opening and closure in turn affect the electro-chemo-mechanical responses in the material microstructure. Reference: [1] Wang, Y., Baek, J., Tang, Y. et al. "Support vector machine guided reproducing kernel particle method for image-based modeling of microstructures," Comput Mech 73, 907-942 (2024). https://doi.org/10.1007/s00466-023-02394-9. [2] Susuki, K., Allen, J. & Chen, J. S.. "Image-based modeling of coupled electro-chemo-mechanical behavior of Li-ion battery cathode using an interface-modified reproducing kernel particle method," Engineering with Computers (2024). https://doi.org/10.1007/s00366-024-02016-9. [3] Baek, J., Chen, J. S., Susuki, K., "Neural Network enhanced Reproducing Kernel Particle Method for Modeling Localizations," International Journal for Numerical Methods in Engineering, Vol. 123, 4422-4454 (2022). https://doi.org/10.1002/nme.7040.

25 ENERGY STORAGE↗
DOE OSTI2026

Describing Point Defect Topology in 2D Energy Materials Through Computer Vision

Point defects such as vacancies and impurity atoms strongly impact the performance of 2D materials. Traditional efforts often rely on manual detection, a process that is time-intensive, prone to human error, and challenging to scale. Here we leverage machine learning (ML) methods to identify and quantify vacancies within 2D transition metal carbides (Ti3C2, MXenes), aiming to expedite detection while improving accuracy. MXenes exhibit valuable defect-defined electrochemical properties, but we currently lack statistical understanding of defect topology needed to fully harness these materials. Here we employ a convolutional neural network for semantic segmentation of experimental MXene images, opening an opportunity to conduct a rigorous statistical study on defect hierarchy while investigating local relaxation in the lattice. We show how the integration of ML can yield fundamental insight into point defects, providing a powerful tool that will play an increasingly crucial role in the future of materials science. ML is often not just a matter of straightforward application, and pretrained models proved ineffective in this case. Instead, we trained our own neural network (NN) and applied data augmentation techniques and fine-tuning to the training dataset. Since labeled microscopy data is often scarce, we developed training data from a previously published wide-frame MXene image, using customized Gaussian fitting to locate atomic positions. Our trained model was then applied to a large dataset of experimental images, enabling a statistical study of defect configurations across three samples prepared with different HF etchant concentrations (5%, 9.1%, and 12.5%), as shown in Fig. 1. This also allowed us to investigate local strain around vacancies, though we find that we are limited by the precision of measurements using high-angle annular dark field (HAADF) images, as shown in Fig. 2. This study demonstrates how ML enables large-scale, quantitative analysis of atomic defects - an otherwise infeasible task with traditional methods. While our NN was specialized for Ti3C2 MXenes, the pipeline we developed provides a foundation for future ML models tailored to other materials. Ultimately, we envision embedding the NN onto the microscope to give real-time feedback to the user. To make this a reality, continued work is necessary to fully understand the NN's capabilities and limitations. This study gets one step closer to our goals of automated experimentation moving away from traditional methods of manual labeling. As ML capabilities advance, we hope to continue adapting and applying these techniques in microscopy.

2D materials↗
DOE OSTI2026

Kernel Enriched Meshfree Multiphysics Degradation Modeling of Energy Storage Materials

Energy storage materials exhibit strong electro-chemo-mechanical coupling and highly anisotropic material properties, contributing to the formation and propagation of micro-cracking during charge/discharge cycling and ultimately diminishing performance and service life. With microstructural images supplied by the National Laboratory of the Rockies (NLR), pixel-based meshfree model construction by the reproducing kernel particle method (RKPM) is used to represent the complex material microstructures that dictate the coupled physics of these systems. Traditional electro-chemo-mechanical models rely on mesh-based finite element methods, which can lead to difficulties in meshing such complex geometries and capturing crack propagation due to mesh dependency. The first kernel enrichment discussed will be the interface modified reproducing kernel (IM-RK) [1, 2], constructed by scaling a smooth kernel function with an interface-distance function to achieve strategic discontinuity types (i.e. weak discontinuities for strain discontinuities and strong discontinuities for cracks) and alleviate Gibbs oscillations near these transition zones. The IM-RK is especially useful for areas in which a known discontinuity-type is expected a priori. The second kernel enrichment to be discussed is a neural network-enhanced reproducing kernel (NN-RK) [3, 4], which is introduced to effectively model non-obvious damage and crack propagation in the material microstructures; the location, orientation, and solution transition near a localization are automatically captured by superimposed block-level NN optimizations. This NN enrichment approach allows for effective modeling of localizations via a fixed background discretization, relieving tedious efforts for adaptive refinement in traditional mesh-based methods. Applications to the heterogeneous microstructures of Li-ion battery cathodes will be presented to demonstrate the effectiveness of the proposed methods. NN-RK is additionally used to inform how crack opening and closure in turn affect the electro-chemo-mechanical responses in the material microstructure. References: [1] Wang, Y., Baek, J., Tang, Y. et al. "Support vector machine guided reproducing kernel particle method for image-based modeling of microstructures," Comput Mech 73, 907-942 (2024). https://doi.org/10.1007/s00466-023-02394-9. [2] Susuki, K., Allen, J. & Chen, J. S.. "Image-based modeling of coupled electro-chemo-mechanical behavior of Li-ion battery cathode using an interface-modified reproducing kernel particle method," Engineering with Computers (2024). https://doi.org/10.1007/s00366-024-02016-9. [3] Baek, J., Chen, J. S., Susuki, K., "Neural Network enhanced Reproducing Kernel Particle Method for Modeling Localizations," International Journal for Numerical Methods in Engineering, Vol. 123, 4422-4454 (2022). https://doi.org/10.1002/nme.7040.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

The Unitarity-Limit Expansion for Two Nucleons with Perturbative Pions: Digest and Ideas

Theorists love nontrivial fixed points. In the Unitarity Limit, the NN 𝑆-wave binding energies are zero, the scattering lengths infinite, Physics is universal, i.e. insensitive to details of the interactions, and observables display richer symmetries, namely invariance under both scaling and Wigner’s combined SU(4) transformation of spin and isospin. In “Pionless” EFT, both are explicitly but weakly broken and hence perturbative in the Unitarity Window (phase shifts 45° ≲ δ(k) ≲ 135°, i.e. momenta k≈mπ). This Unitarity Expansion provides strong hints that Nuclear Physics resides indeed in a sweet spot: bound weakly enough to be insensitive to the details of the nuclear interaction; and therefore interacting strongly enough that the NN scattering lengths are perturbatively close to the Unitarity Limit. In this paradigm change, NN details are less important than NNN interactions to explain the complexity and patterns of the nuclear chart. This presentation is a digest of the first quantitative exploration of corrections to this picture when pions are included [1] (see there for a more comprehensive list of references). Since the pion mass and decay constant introduce dimensionful scales in the NN system, they explicitly break the symmetries of the Unitarity fixed point. In χEFT, these symmetries must therefore be hidden and instead be classified as emergent.

Griesshammer, Harald W. [The George Washington Uni↗
DOE OSTI2020

Nucleon-Nucleon Scattering Up to N5LO in Chiral Effective Field Theory

During the past few decades a large effort has been made toward describing the NN interaction in the framework of chiral Effective Field Theory (EFT). The main idea is to exploit the symmetries of QCD to obtain an effective theory for low energy nuclear systems. In 2003, the first accurate charge-dependent NN potential in this scheme was developed and it has been applied to many ab-initio calculations, opening the possibility to study nuclear systems in a systematic and accurate way. It was shown that the fourth order (N3LO) was necessary and sufficient to describe the NN scattering data with a χ 2 /d.o.f on the order of so-called high precision potentials. However the systematics of chiral EFT also allow to relate two- and many-body interactions in a well-defined way. Since many-body forces make their first appearance at higher order, they are substantially smaller than their two-body counterparts, but may never-the-less be crucial for some processes. Thus, there are observables where they can have a big impact and, for example, there are indications that they solve the long standing Ay puzzle of N-d scattering. The last few years, have also seen substantial progress toward higher orders of chiral EFT which was motivated by the fact that only three-body forces of rather high order may solve some outstanding issues in microscopic nuclear structure and reactions. In this chapter we will review the latest contributions of the authors to development of chiral EFT based potentials up to N4LO as well as first calculations conducted for NN scattering at N5LO.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Deep Learning-Based Hardness Prediction of Novel Refractory High-Entropy Alloys with Experimental Validation

Hardness is an essential property in the design of refractory high entropy alloys (RHEAs). This study shows how a neural network (NN) model can be used to predict the hardness of a RHEA, for the first time. We predicted the hardness of several alloys, including the novel C0.1Cr3Mo11.9Nb20Re15Ta30W20 using the NN model. The hardness predicted from the NN model was consistent with the available experimental results. The NN model prediction of C0.1Cr3Mo11.9Nb20Re15Ta30W20 was verified by experimentally synthesizing and investigating its microstructure properties and hardness. This model provides an alternative route to determine the Vickers hardness of RHEAs.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Neural Networks for Prediction of Complex Chemistry in Water Treatment Process Optimization

Water chemistry plays a critical role in the design and operation of water treatment processes. Detailed chemistry modeling tools use a combination of advanced thermodynamic models and extensive databases to predict phase equilibria and reaction phenomena. The complexity and formulation of these models preclude their direct integration in equation-oriented modeling platforms, making it difficult to use their capabilities for rigorous water treatment process optimization. Neural networks (NN) can provide a pathway for integrating the predictive capability of chemistry software into equation-oriented models and enable optimization of complex water treatment processes across a broad range of conditions and process designs. Herein, we assess how NN architecture and training data impact their accuracy and use in equation-oriented water treatment models. We generate training data using PhreeqC software and determine how data generation and sample size impact the accuracy of trained NNs. The effect of NN architecture on optimization is evaluated by optimizing hypothetical black-box desalination processes using a range of feed compositions from USGS brackish water data set, tracking the number of successful optimizations, and testing the impact of initial guess on the final solution. Our results clearly demonstrate that data generation and architecture impact NN accuracy and viability for use in equation-oriented optimization problems.

Dudchenko, Alexander V↗
NASA NTRS1972

Nearest Neighbor Algorithms for Pattern Classification

A solution of the discrimination problem is considered by means of the minimum distance classifier, commonly referred to as the nearest neighbor (NN) rule. The NN rule is nonparametric, or distribution free, in the sense that it does not depend on any assumptions about the underlying statistics for its application. The k-NN rule is a procedure that assigns an observation vector z to a category F if most of the k nearby observations x sub i are elements of F. The condensed nearest neighbor (CNN) rule may be used to reduce the size of the training set required categorize The Bayes risk serves merely as a reference-the limit of excellence beyond which it is not possible to go. The NN rule is bounded below by the Bayes risk and above by twice the Bayes risk.

Barrios, J. O.↗
NASA NTRS1988

Pseudo-scalar pi N coupling and relativistic proton-nucleus scattering

Relativistic p-Ca-40 elastic scattering observables are calculated using relativistic NN amplitudes obtained from the solution of a two-body relativistic equation in which one particle is kept on its mass-shell. Results at 200 MeV are presented for two sets of NN amplitudes, one with pure pseudo-vector coupling for the pion and another with a 25 percent admixture of pseudo-scaling coupling. Both give a very good fit to the positive energy on-shell NN data. Differences between the predictions of these two models (which are shown to be due only to the differences in their corresponding negative energy amplitudes) provide a measure of the uncertainty in contructing Dirac optical potentials from NN amplitudes.

Gross, Franz↗
NASA NTRS2000

Neural Network and Response Surface Methodology for Rocket Engine Component Optimization

The goal of this work is to compare the performance of response surface methodology (RSM) and two types of neural networks (NN) to aid preliminary design of two rocket engine components. A data set of 45 training points and 20 test points obtained from a semi-empirical model based on three design variables is used for a shear coaxial injector element. Data for supersonic turbine design is based on six design variables, 76 training, data and 18 test data obtained from simplified aerodynamic analysis. Several RS and NN are first constructed using the training data. The test data are then employed to select the best RS or NN. Quadratic and cubic response surfaces. radial basis neural network (RBNN) and back-propagation neural network (BPNN) are compared. Two-layered RBNN are generated using two different training algorithms, namely solverbe and solverb. A two layered BPNN is generated with Tan-Sigmoid transfer function. Various issues related to the training of the neural networks are addressed including number of neurons, error goals, spread constants and the accuracy of different models in representing the design space. A search for the optimum design is carried out using a standard gradient-based optimization algorithm over the response surfaces represented by the polynomials and trained neural networks. Usually a cubic polynominal performs better than the quadratic polynomial but exceptions have been noticed. Among the NN choices, the RBNN designed using solverb yields more consistent performance for both engine components considered. The training of RBNN is easier as it requires linear regression. This coupled with the consistency in performance promise the possibility of it being used as an optimization strategy for engineering design problems.

Vaidyanathan, Rajkumar↗
NASA NTRS2002

Effects of Lateral Plasma Density and Temperature Diffusion on VCSEL Performance

The hydrodynamic model is further verified by applying to a gain-guided single mode VCSEL. DC effects of D(sub NN): (1) increase threshold current J(sub th) and decrease slope efficiency; (2) within the studied range (50% pumping within threshold and realistic diffusion coefficient for a single mode), the L-I relation scales with the relative Injection current (J/J(sub th) - 1). AC effects of D(sub NN): (1) decrease spectral bandwidth and responsivity of direct-current modulation; (2) within the studied range, the frequency response follows the same formal dependence as predicted without diffusion and under a linear gain model, while the resonant frequency position similarly scales with the relative injection current; (3) therefore, it is concluded that the AC effects of D(sub NN) is purely of static nature and reflected via its influence on ot and J(sub th). Within this study, the nonlinear effects of D(sub NN) are mostly reproducible with an equivalent constant diffusion coefficient.

Li, Jian-Zhong↗
NASA NTRS1998

Predicting lettuce canopy photosynthesis with statistical and neural network models

An artificial neural network (NN) and a statistical regression model were developed to predict canopy photosynthetic rates (Pn) for 'Waldman's Green' leaf lettuce (Latuca sativa L.). All data used to develop and test the models were collected for crop stands grown hydroponically and under controlled-environment conditions. In the NN and regression models, canopy Pn was predicted as a function of three independent variables: shootzone CO2 concentration (600 to 1500 micromoles mol-1), photosynthetic photon flux (PPF) (600 to 1100 micromoles m-2 s-1), and canopy age (10 to 20 days after planting). The models were used to determine the combinations of CO2 and PPF setpoints required each day to maintain maximum canopy Pn. The statistical model (a third-order polynomial) predicted Pn more accurately than the simple NN (a three-layer, fully connected net). Over an 11-day validation period, average percent difference between predicted and actual Pn was 12.3% and 24.6% for the statistical and NN models, respectively. Both models lost considerable accuracy when used to determine relatively long-range Pn predictions (> or = 6 days into the future).

Non-NASA Center↗
NASA NTRS2005

Entry Abort Determination Using Non-Adaptive Neural Networks for Mars Precision Landers

The 2009 Mars Science Laboratory (MSL) will attempt the first precision landing on Mars using a modified version of the Apollo Earth entry guidance program. The guidance routine, Entry Terminal Point Controller (ETPC), commands the deployment of a supersonic parachute after converging the range to the landing target. For very dispersed cases, ETPC may not converge the range to the target and safely command parachute deployment within Mach number and dynamic pressure constraints. A full-lift up abort can save 85% of these failed trajectories while abandoning the precision landing objective. Though current MSL requirements do not call for an abort capability, an autonomous abort capability may be desired, for this mission or future Mars precision landers, to make the vehicle more robust. The application of artificial neural networks (NNs) as an abort determination technique was evaluated by personnel at the National Aeronautics and Space Administration (NASA) Johnson Space Center (JSC). In order to implement an abort, a failed trajectory needs to be recognized in real time. Abort determination is dependent upon several trajectory parameters whose relationships to vehicle survival are not well understood, and yet the lander must be trained to recognize unsafe situations. Artificial neural networks (NNs) provide a way to model these parameters and can provide MSL with the artificial intelligence necessary to independently declare an abort. Using the 2009 Mars Science Laboratory (MSL) mission as a case study, a non-adaptive NN was designed, trained and tested using Monte Carlo simulations of MSL descent and incorporated into ETPC. Neural network theory, the development history of the MSL NN, and initial testing with severe dust storm entry trajectory cases are discussed in Reference 1 and will not be repeated here. That analysis demonstrated that NNs are capable of recognizing failed descent trajectories and can significantly increase the survivability of MSL for very dispersed cases. NN testing was then broadened to evaluate fully dispersed entry trajectories. The NN correctly classified 99.7% of descent trajectories as abort or nonabort and reduced the probability of an unsafe parachute deployment by 83%. This second, broader testing phase is discussed in this paper.

Graybeal, Sarah R.↗
NASA NTRS2019

Sea Surface Salinity Retrievals from Aquarius Using Neural Networks

Even though the Sea Surface Salinity (SSS) retrieved from Aquarius are generally very close to in-situ measurements, the level of similarity varies with the region and with the circumstances of the observations (wind speed, sea surface temperature, etc.). SSS is currently retrieved from the brightness temperatures measured by Aquarius and applying the current theoretical model for the propagation and emission of the natural thermal radiation. In this contribution we consider an alternative retrieval approach based on a Neural Network (NN) with the goal of improving the subsets of Aquarius SSS data that are in poorer agreement within-situ measurements. The subset considered here are the SSS retrieved at latitudes higher than 30 ̊. The output of the NN approach are compared against in-situ measurements using four statistical metrics (correlation coefficient, bias, RMSD and 5% trimmed range). The output of the NN and the nominal Aquarius SSS are compared against SSS values from in-situ measurements and from ocean models. From these comparisons it appears that the output of the NN matches the in-situ measurements better than the nominal Aquarius SSS.

Soldo, Yan↗
NASA NTRSDate not supplied

An Online Reinforcement Learning Controller Design For Mars Ascent Vehicle

This paper presents a neural network (NN) approximator-based online reinforcement learning (ORL) controller design for Mars Ascent Vehicle (MAV) under parametric variation and significant external disturbances. The ORL controller, which does not require any offline training, involves two NNs where an action NN produces optimal short-term control performance while a critic NN evaluates the performance of the action NN using an approximated cost function. The simulation example with comparisons against baseline Proportional-Integral-Derivative (PID) and gain scheduled pole-placement PID (GS-PP-PID) controllers show the proposed controller’s effectiveness and robustness under parametric variation and high external disturbances.

Han Woong Bae↗