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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Sensitivity of Au + Au collisions to the symmetric nuclear matter equation of state at 2–5 nuclear saturation densities

We demonstrate that proton and pion flow measurements in heavy-ion collisions at incident energies ranging from 1 to 20 GeV per nucleon in the fixed target frame can be used for an accurate determination of the symmetric nuclear matter equation of state at baryon densities equal 2–4 times nuclear saturation density n 0 . We simulate Au + Au collisions at these energies using a hadronic transport model with an adjustable vector mean-field potential dependent on baryon density n B . Here, we show that the mean field can be parametrized to reproduce a given density dependence of the speed of sound at zero temperature $c$$^{2}_{s}$ (n B , T = 0), which we vary independently in multiple density intervals to probe the differential sensitivity of heavy-ion observables to the equation of state at these specific densities. Recent flow data from the STAR experiment at the center-of-mass energies √ s NN = {3.0, 4.5} GeV can be described by our model, and a Bayesian analysis of these data indicates a hard equation of state at n B ϵ (2, 3)n 0 and a possible phase transition at n B ϵ (3, 4)n 0 . More data at √ s NN = 2–5 GeV, as well as a more thorough analysis of the model systematic uncertainties will be necessary for a more precise conclusion.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Role of three-body dynamics in nucleon-deuteron correlation functions

Correlation functions of hadrons can be accessed in high-energy collisions of atomic nuclei, revealing information about the underlying interaction. This work complements experimental efforts to study nucleon-deuteron Nd—with N=p (proton) or N=n (neutron)—correlations with theory evaluations using different techniques. The correlation functions C nd and C pd are calculated based on a scattering wave function, extending previous benchmarks for the Nd scattering matrix to this new observable. We use hyperspherical harmonics and Faddeev techniques with one of the widely used nucleon-nucleon (NN) interactions, the Argonne v18 potential. Moreover, in the low-energy region we perform additional calculations in the framework of pionless effective field theory. The pd correlation function is computed in the large-energy region to make contact with a recent measurement by the ALICE Collaboration. We show that the scattering wave function has the proper dynamical input to describe an initial rise and subsequent oscillations of C pd as a function of the energy. Effects on the observables using different NN and three-nucleon potentials are evaluated with the conclusion that variations of around 2% are observed. Although these effects are small, future measurements can go beyond this accuracy, allowing for new detailed studies of strong interaction in light nuclear systems. Furthermore, the present study supports the current efforts devoted to the measurement of correlation functions in systems dominated by the strong interactions, such as pd, ppp, Λd, and ppΛ.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Neural network emulation of spontaneous fission

Large-scale computations of fission properties are an important ingredient for nuclear reaction network calculations simulating rapid neutron-capture process (the 𝑟 process) nucleosynthesis. Due to the large number of fissioning nuclei potentially contributing to the 𝑟 process, a microscopic description of fission based on nuclear density functional theory (DFT) is computationally challenging. Here, we explore the use of neural networks (NNs) to construct DFT emulators capable of predicting potential energy surfaces and collective inertia tensors across the whole nuclear chart, starting from a minimal set of DFT calculations. We use constrained Hartree-Fock-Bogoliubov (HFB) calculations to predict the potential energy and collective inertia tensor in the axial quadrupole and octupole collective coordinates, for a set of nuclei in the 𝑟-process region. We then employ NNs to emulate the HFB energy and collective inertia tensor across the considered region of the nuclear chart. Least-action pathways characterizing spontaneous fission half-lives and fragment yields are then obtained by means of the nudged elastic band method. The potential energy predicted by NNs agrees with the DFT value to within a root-mean-square error of 500 keV, and the collective inertia components agree to within an order of magnitude. These results are largely independent of the NN architecture. The exit points on the outer turning line are found to be well emulated. For the spontaneous fission half-lives the NN emulation provides values that are found to agree with the DFT predictions within a factor of 10 3 across more than 70 orders of magnitude. Neural networks are able to emulate the potential energy and collective inertia well enough to reasonably predict physical observables. Future directions of study, such as the inclusion of additional collective degrees of freedom and active learning, will improve the predictive power of microscopic theory and further enable large-scale fission studies.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Relativistic diffusion model for hadron production in p -Pb collisions at energies available at the CERN Large Hadron Collider

We investigate charged-hadron production in relativistic heavy-ion collisions of asymmetric systems within a nonequilibrium-statistical framework. Calculated centrality-dependent pseudorapidity distributions for p-Pb collisions at s NN = 5.02 and 8.16 TeV are compared with data from the Large Hadron Collider. Our approach combines a relativistic diffusion model with formulations based on quantum chromodynamics while utilizing numerical solutions of a Fokker-Planck equation to account for the shift and broadening of the fragmentation sources for particle-production with respect to the stopping (net-baryon) rapidity distributions. To represent the centrality dependence of charged-hadron production in asymmetric systems over a broad region of pseudorapidities, the consideration and precise modeling of the fragmentation sources, along with the central gluon-gluon source, is found to be essential. Specifically, this results in an inversion of the particle-production amplitude from backward to forward dominance when transitioning from central to peripheral collisions, in agreement with recent ATLAS and ALICE p-Pb data at s NN = 5.02 T e V . Published by the American Physical Society 2024

Schulz, Philipp (ORCID:0009000266642148)↗
DOE OSTI2025

Inference of response functions with the help of machine-learning algorithms

Response functions are a key quantity to describe the near-equilibrium dynamics of strongly interacting many-body systems. Recent techniques that attempt to overcome the challenges of calculating these ab initio have employed expansions in terms of orthogonal polynomials. We employ a neural network prediction algorithm to reconstruct a response function 𝑆⁡(𝜔) defined over a range in frequencies 𝜔. Here, we represent the calculated response function as a truncated Chebyshev series whose coefficients can be optimized to reduce the representation error. We compare the quality of response functions obtained using coefficients calculated using a neural network (NN) algorithm with those computed using the Gaussian integral transform (GIT) method. In the regime where only a small number of terms in the Chebyshev series are retained, we find that the NN scheme outperforms the GIT method.

Kurkcuoglu, Doga Murat [Fermi National Accelerator↗
DOE OSTI2024

Comprehensive AI-based System for Control, Sensor Estimation, and Fault Detection of Cascaded Multilevel Inverters

In this paper, an Artificial Intelligence-based (AI) system is proposed for an 11-level cascaded H-bridge multilevel inverter (MLI) with the aims of harmonic suppression and reliability enhancement. The system consists of three seamlessly integrated Neural Networks (NNs). First, a multilayer perceptron is used to generalize the optimal switching angles for selective harmonic elimination under non-equal DC voltages. Next, an autoencoder NN estimates the voltage sensor readings to address potential drifting. Finally, a perceptron NN detects inverter faults based solely on the output voltage of the MLI. Simulation scenarios were evaluated, and the results show that the proposed system provides a comprehensive solution for the robust operation of the MLI. The proposed solution is capable of minimizing the targeted harmonics orders with minimal impact on the fundamental voltage, even when the voltage sensor drifts. Furthermore, the inverter under fault conditions was successfully identified.

Rezende da Costa Reis Kimpara, Renata↗
DOE OSTI2022

MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series

In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to detecting anomalies from streams of multivariate time series data is of significant importance. Given the scarcity of anomalies in real-world applications, the majority of literature has been focusing on modeling normality. The learned normal representations can empower anomaly detection as the model has learned to capture certain key underlying data regularities. A typical formulation is to learn a predictive model, i.e., use a window of time series data to predict future data values. In this paper, we propose an alternative self-supervised learning task. By randomly masking a portion of the inputs and training a model to estimate them using the remaining ones, MAD is an improvement over the traditional left-to-right next step prediction (NSP) task. Our experimental results demonstrate that MAD can achieve better anomaly detection rates over traditional NSP approaches when using exactly the same neural network (NN) base models, and can be modified to run as fast as NSP models during test time on the same hardware, thus making it an ideal upgrade for many existing NSP-based NN anomaly detection models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Machine-Learning Architecture for Ultrasonic Thermometry

Temperature distribution in solids can be inverted from the speed of sound (SOS) measurements, as has been shown feasible by timing the propagation of the excitation pulse and the train of echoes in ultrasonically segmented waveguides (WGs) and metal components. However, complicated geometries and closely-space echogenic features (EFs) create complex waveforms, from which the segmental time of flights (TOFs) are impossible to estimate using traditional methods. This work describes a machine learning architecture shown to extract temperature information from complex ultrasonic waveforms without explicit measurements of segmental TOFs. We accomplish this by using an autoencoder neural network (NN) to map ultrasonic waveforms into a low-dimensional latent space. A second NN then maps the latent space into unknown temperature distribution along the WG. The proposed architecture was tested in simulations and experimentally. The autoencoder accurately reconstructs the waveforms from their latent representation, several orders of magnitude lower in dimensionality. The obtained latent space was successfully mapped into the temperature of the propagation path.

John, Mason↗
DOE OSTI2020

A Step Towards Machine Learning-based Coherent Generator Grouping for Emergency Control Applications in Modern Power Grid

A dynamic neural network (NN) based multi-class classifier is proposed for improving online prediction of coherent generator groups (CGGs), following the occurrences of various contingencies in the power grid. This is motivated by the increasing availability of the measurements from phasor measurement units (PMUs) and the number of grouping schemes is limited. The proposed method consists of three steps. First, by performing offline simulations, a library of system dynamic responses characterized by post-contingency rotor angles and speeds of individual generators is obtained. To generate sufficient data, up to N-2 contingencies and the uncertain parameters associated with the power grid including type and location of disturbance and fault clearing times are modeled. Secondly, the training data-set is produced by generating labels for individual contingencies using a hierarchical clustering method based on rotor angle and speed data. Lastly, the dynamic NN models are trained for online applications such as emergency controls and controlled islanding. The proposed method is tested on the standard 16-generator 68-bus system to demonstrate its performance. Furthermore, the impact of the sample data lengths on the CGG numbers is evaluated. It is interesting to observe that the time domain stability behaviors can be determined by examining the changes in the CGG numbers.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Co-Optimization Scheme for Hybrid Electric Vehicles Powertrain and Exhaust Emission Control System Using Future Speed Prediction

Hybrid electric vehicles (HEVs) have been an effective solution for improved vehicle fuel efficiency and reduced emission pollution. In this paper, a co-optimization scheme is proposed to optimize fuel efficiency for HEVs. Here, the proposed optimization scheme uses obtainable future speed prediction as the basis to optimally tune control parameters for the existing powertrain control system. The ramp-up time of the catalyst temperature to reach its light-off level in the exhaust emission system is also considered as an additional optimization constraint to reduce emission. The Toyota Prius Hybrid Simulink model which is an integrated model for a powertrain and exhaust emission system is validated using real data from several real driving cycle scenarios. Then, to simplify the formulation of the proposed algorithm, the model for the optimization for powertrain and exhaust emission systems is represented by a set of equivalent neural network (NN) models learned using the data generated from the well-validated Toyota Prius Hybrid Simulink model. Using NN models, a co-optimization algorithm is established that provides an optimal tuning of some fuel-sensitive powertrain control parameters using future speed prediction, leading to a novel co-optimization algorithm, achieving on average a further 9.22% fuel savings for the Toyota Prius Hybrid Simulink model.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Automatic Generation of High-Performance Convolution Kernels on ARM CPUs for Deep Learning

In this work, we present FastConv, a template-based code auto-generation open source library that can automatically generate high-performance deep learning convolution kernels of arbitrary matrices/tensors shapes. FastConv is based on the Winograd algorithm, which is reportedly the highest performing algorithm for the time-consuming convolution layers of convolutional neural networks. ARM CPUs cover a wide range designs and specifications, from embedded devices to HPC-grade CPUs. The leads to the dilemma of how to consistently optimize Winograd-based convolution solvers for convolution layers of different shapes. FastConv addresses this problem by using templates to auto-generate multiple shapes of tuned kernels variants suitable for skinny tall matrices. As a performance portable library, FastConv transparently searches for the best combination of kernel shapes, cache tiles, scheduling of loop orders, packing strategies, access patterns, and online/offline computations. Auto-tuning is used to search the parameter configuration space for the best performance for a given target architecture and problem size. The experiments with layer-wise evaluation on the VGG--16 model confirms a 1.25x performance gains is got by tuning the Winograd library. Integrated comparison results shows 1.02x to 1.40x, 1.14x to 2.17x, and 1.22x and 2.48x speedup is achieved over NNPACK, Arm NN, and FeatherCNN on the Kunpeng 920 beside few cases. Furthermore, problem size performance portability experiments with various convolution shapes shows that FastConv achieves 1.2x to 1.7x speedup and 2x to 22x speedup over NNPACK and ARM NN inference engine using Winograd on Kunpeng 920 . CPU performance portability evaluation on the VGG--16 show an average speedup over NNPACK of 1.42x, 1.21x, 1.26x, 1.37x, 2.26x, and 11.02x is observed on Kunpeng 920, Snapdragon 835, 855, 888, Apple M1, and AWS Graviton2, respectively.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Improving Trustworthiness of Data-Driven Power Grid Contingency Analysis With Bayesian Residual Graph Neural Networks

The evolving energy landscape requires novel tools to efficiently perform contingency analysis and reliability assessment of power grids, potentially in real-time. The high computational cost of traditional power flow solvers limits their applicability in practice. Machine learning (ML) surrogates such as deep neural networks (NNs) accelerate power flow solvers computations, enabling high-order contingency analysis and real-time decision-making by learning highly nonlinear functions and integrating grid topology via graph architectures. However, (graph) NNs lack predictive power away from training data and do not provide predictive confidence estimates. Here, we present a Bayesian residual graph NN that integrates knowledge from low-fidelity data via residual training and embeds granular quantification of uncertainties, improving trustworthiness critical for high-consequence decision-making. Applying Bayesian concepts to NNs is challenging due to the high-dimensionality of both the parameter space, complicating derivation of a meaningful prior, and the output space in large grid systems, requiring enhanced techniques to assess the predicted high-dimensional uncertainties. Our contributions include: (1) Deriving a prior for fully connected and graph NNs that leverages low-fidelity data to guide mean predictions and appropriately control prior predictive uncertainty. (2) Integrating this prior within an ensembling with anchoring scheme for efficient approximate posterior inference. (3) Deriving enhanced metrics to assess accuracy of both the mean and uncertainty predictions in high dimensions, appropriately accounting for correlations propagated through graph layers. The resulting Bayesian residual graph NN is tested on a contingency analysis task for 14-bus and 118-bus grids.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Learning local and semi-local density functionals from exact exchange-correlation potentials and energies

Finding accurate exchange-correlation (XC) functionals remains the defining challenge in density functional theory (DFT). Despite 40 years of active development, attaining general purpose chemical accuracy is still elusive with existing functionals. We present a data-driven pathway to learn the XC functional by using the exact density, XC energy, and XC potential. While the exact densities are obtained from accurate configuration interaction (CI), the exact XC energies and XC potentials are obtained via inverse DFT calculations on the CI densities. We demonstrate how simple neural network (NN)–based local density approximation (LDA) and generalized gradient approximation (GGA), trained on just five atoms and two molecules, provide remarkable improvement in total energies and densities. Particularly, the NN-based GGA functional attains similar accuracy as the higher rung SCAN meta-GGA on various thermochemistry datasets. These results underscore the promise of using the XC potential in modeling XC functionals and can pave the way for systematic learning of increasingly accurate XC functionals.

Science & Technology - Other Topics↗
DOE OSTI2020

PANDA as midrapidity detector for a future HESR Collider at FAIR

Exciting new scientific opportunities are presented for the PANDA detector at the High Energy Storage Ring in the redefined $$\overline{\text {p}} \text {p}(A)$$ p ¯ p ( A ) collider mode, HESR-C, at the Facility for Antiproton and Ion Research (FAIR) in Europe. The high luminosity, $$L \sim 10^{31}$$ L ~ 10 31 cm $$^{-2}$$ - 2 s $$^{-1}$$ - 1 , and a wide range of intermediate and high energies, $$\sqrt{s_{\text {NN}}}$$ s NN up to 30 GeV for $$\overline{\text {p}} \text {p}(A)$$ p ¯ p ( A ) collisions will allow to explore a wide range of exciting topics in QCD, including the study of the production of excited open charm and bottom states, nuclear bound states containing heavy (anti)quarks, the interplay of hard and soft physics in the dilepton production, probing short-range correlations in nuclei, and the exploration of the early, complete $$\overline{\text {p}}$$ p ¯ -p- annihilation phase, where an initially pure Yang–Mills gluon plasma is formed.

Physics↗
DOE OSTI2023

Study of the p-p-K + and p-p-K - dynamics using the femtoscopy technique

The interactions of kaons (K) and antikaons ($\bar{K}$ ) with few nucleons (N) were studied so far using kaonic atom data and measurements of kaon production and interaction yields in nuclei. Some details of the three-body $\bar{K}$NN and NN dynamics are still not well understood, mainly due to the overlap with multi-nucleon interactions in nuclei. An alternative method to probe the dynamics of three-body systems with kaons is to study the final state interaction within triplet of particles emitted in pp collisions at the Large Hadron Collider, which are free from effects due to the presence of bound nucleons. This Letter reports the first femtoscopic study of p–p–K + and p–p–K - correlations measured in high-multiplicity pp collisions at $\sqrt{s}$ = 13 TeV by the ALICE Collaboration. The analysis shows that the measured p–p–K + and p–p–K - correlation functions can be interpreted in terms of pairwise interactions in the triplets, indicating that the dynamics of such systems is dominated by the two-body interactions without significant contributions from three-body effects or bound states.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Probe nuclear structure using the anisotropic flow at the Large Hadron Collider

Abstract Recent studies have shown that the shape and radial profile of the colliding nuclei have strong influences on the initial condition of the heavy ion collisions and the subsequent development of the anisotropic flow. Using A Multi-Phase Transport model (AMPT) model, we investigated the impact of nuclear quadrupole deformation $$\beta _2$$ β 2 and nuclear diffuseness $$a_0$$ a 0 of $$^{129}$$ 129 Xe on various of flow observables in Xe–Xe collisions at $$\sqrt{s_{\textrm{NN}}}=$$ s NN = 5.44 TeV. We found that $$\beta _2$$ β 2 has a strong influence on central collisions while $$a_0$$ a 0 mostly influences the mid-central collisions. The relative change of flow observables induced by a change in $$\beta _2$$ β 2 and $$a_0$$ a 0 are also found to be insensitive to the values of parameters controlling the strength of the interaction among final state particles. Our study demonstrates the potential for constraining the initial condition of heavy ion collisions using future system scans at the LHC.

Physics↗
DOE OSTI2021

Fireball tomography from bottomonia elliptic flow in relativistic heavy-ion collisions

Abstract We calculate the elliptic flow of bottomonia produced in Pb $$\,+\,$$ + Pb collisions at $$\sqrt{s_{\mathrm{NN}}}=5.02$$ s NN = 5.02 TeV. We consider temperature-dependent decay widths for the anisotropic escape of various bottomonium states and observe that the transverse momentum dependence of bottomonia elliptic flow provides a tomographic information about the QGP fireball at different stages of its evolution. For the space-time evolution of the fireball, we employ simulation results from the 3 + 1 D quasiparticle anisotropic hydrodynamic model. We find that our results for transverse momentum dependence of bottomonia elliptic flow are in reasonable agreement with experimental results from the ALICE and CMS collaborations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Azimuthal dependence of two-particle transverse momentum current correlations

Two-particle transverse momentum correlation functions are a powerful technique for understanding the dynamics of relativistic heavy-ion collisions. Among these, the transverse momentum correlator G 2 (Δη,Δφ) is of particular interest for its potential sensitivity to the shear viscosity per unit of entropy density η/s of the quark-gluon plasma formed in heavy-ion collisions. We use the UrQMD, AMPT, and EPOS models for Au–Au at √ s NN = 200 GeV and Pb–Pb at √ s NN = 2760 GeV to investigate the long range azimuthal dependence of G 2 (Δη,Δφ), and explore its utility to constrain η/s based on charged particle correlations. We find that the three models yield quantitatively distinct transverse momentum Fourier harmonics coefficients $a$ $^{pT}_{n}$. We also observe these coefficients exhibit a significant dependence on η/s in the context of the AMPT model. These observations suggest that exhaustive measurements of the dependence of G 2 (Δφ) with collision energy, system size, collision centrality, in particular, offer the potential to distinguish between different theoretical models and their underlying assumptions. Exhaustive analyses of G 2 (Δφ) obtained in large and small systems should also be instrumental in establishing new constraints for precise extraction of η/s.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗