Search NASA⌕ Search

SEARCH · Search NASA

Results for “Information Fusion”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

On Feature, Classifier and Detector Fusers for 235U Signatures Using Gamma Spectral Counts

Three types of information fusion strategies are studied to assess the performance of classifiers for detecting low-level 235 U radiation sources, using features obtained from gamma spectra of NaI detectors. These three strategies are based on using two spectral region features, fusing eight classifiers of diverse designs, and fusing multiple detectors located at different positions around the source. The inner, middle and outer groups of detectors, within a formation of two concentric circles and a spiral of 21 detectors, are identified based on their distance to the source, which is located at the center. This study provides two main qualitative insights into this classification task. First, the fusion of detectors leads to an overall improved classification performance, least in the inner group, most in the outer group, and in between for the middle group. Second, several classifiers and fusers achieve lower training error which does not translate to lower generalization error, indicating their over-fitting to training data.

Rao, Nageswara↗
DOE OSTI2020

Sensor Drift Estimation for Reactor Systems by Fusing Multiple Sensor Measurements

A nuclear power plant is instrumented with a variety of sensors that monitor its variables to estimate the state and initiate safety actions, if needed. We address the problem of estimating drifts or errors in sensor measurements due to factors such as calibration changes. We propose an information fusion method that uses measurements from other sensors to generate an estimate of a sensor measurement, and its difference from an actual measurement provides an error estimate. We present two fusers based on the ensemble of trees and support vector machine that are trained using sensor measurements collected at an emulated test loop of a pressurized water reactor under no-drift conditions. We present error estimates for a differential pressure sensor of the heat exchanger of the primary coolant system, under twenty controlled scenarios using the test loop. Both positive and negative errors are captured by both methods in scenarios involving calibration drifts, blocking, air gap and electromagnetic interference. The root mean square errors of estimated drifts are typically within 2% percent of the maximum.

Rao, Nageswara↗
DOE OSTI2020

AI-Science for Performance Optimization and Diagnosis of Science Instrument Federations

Next generation of science workflows are expected to be executed over complex federations composed of supercomputers, science instruments, storage systems and networks, with new additions of the edge and cloud systems and services. The sheer complexity of these multi-domain federations makes it hard to manage them and optimize their performance, as small impedance mismatches (that can dynamically develop between systems) could drastically degrade the entire federation performance. Recent proliferation of Software Defined Everything (SDX) technologies combined with containerization frameworks provide custom instruments that can monitor and collect critical measurements at various levels to support diagnoses and performance optimization; but their data too enormous for human operators and analysts to process and generate decisions. Machine Learning (ML) methods that extract critical parameters, relationships and trends from the data offer general solutions. Artificial Intelligence (AI) and ML methods must be custom-developed for these problems based on solid, rigorous foundations, since black-box approaches are often ineffective and unsound.We propose to develop comprehensive AI-Science for the performance of science federations to (i) monitor and control storage, networks, experiments, and computing systems across multiple domains via softwarization layers, at speeds and scales orders of magnitude superior to current practice, (ii) optimally realize and orchestrate complex workflows with high performance by using dynamic state and performance estimation methods, and (iii) aggregate measurements across sites and time to develop infrastructure-level profiles, optimizations and diagnoses using AI-Science based on foundational principles from ML, game theory, and information fusion areas.

Rao, Nageswara↗
DOE OSTI2022

On Feature, Classifier and Detector Fusers for U-235 Signatures Using Gamma Spectral Counts

Three types of information fusion strategies are studied to assess the performance of classifiers for detecting low-level U-235 radiation sources, using features obtained from gamma spectra of NaI detectors. These three strategies are based on using two spectral region features, fusing eight classifiers of diverse designs, and fusing multiple detectors located at different positions around the source. The inner, middle and outer groups of detectors, within a formation of two concentric circles and a spiral of 21 detectors, are identified based on their distance to the source, which is located at the center. This study provides two main qualitative insights into this classification task. First,the fusion of detectors leads to an overall improved classification performance, least in the inner group, most in the outer group, and in between for the middle group. Second, several classifiers and fusers achieve lower training error which does not translate to lower generalization error, indicating their over-fitting to training data.

Rao, Nageswara↗
DOE OSTI2021

Observation of Hydrodynamic Flows in Imploding Fusion Plasmas on the National Ignition Facility [plus supplemental information]

Inertial confinement fusion implosions designed to have minimal fluid motion at peak compression often show significant linear flows in the laboratory, attributable per simulations to percent-level imbalances in the laser drive illumination symmetry. In this work, we present experimental results which intentionally varied the mode 1 drive imbalance by up to 4% to test hydrodynamic predictions of flows and the resultant imploded core asymmetries and performance, as measured by a combination of DT neutron spectroscopy and high-resolution x-ray core imaging. Neutron yields decrease by up to 50%, and anisotropic neutron Doppler broadening increases by 20%, in agreement with simulations. Furthermore, a tracer jet from the capsule fill-tube perturbation that is entrained by the hot-spot flow confirms the average flow speeds deduced from neutron spectroscopy.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

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

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

36 MATERIALS SCIENCE↗
DOE OSTI2023

Development of compact tokamak fusion reactor use cases to inform future transport studies

The OMFIT STEP (Meneghini et al. , Nucl. Fusion , vol. 10, 2020, p. 1088) workflow has been used to develop inductive and steady-state H-mode core plasma scenario use cases for a $B_0 = 8 \, {\rm T}$ , $R_0 = 4 \, {\rm m}$ machine to help guide and inform future higher-fidelity studies of core transport and confinement in compact tokamak reactors. Both use cases are designed to produce 200 MW or more of net electric power in an up-down symmetric plasma with minor radius $a = 1.4 \, {\rm m}$ , elongation $\kappa = 2.0$ , triangularity $\delta = 0.5$ and effective charge $Z_{{\rm eff}} \simeq 2$ . Additional considerations based on the need for compatibility of the core with reactor-relevant power exhaust solutions and external actuators were used to guide and constrain the use case development. An extensive characterization of core transport in both scenarios is presented, the most important feature of which is the extreme sensitivity of the results to the quantitative stiffness level of the transport model used as well as the predicted critical gradients. This sensitivity is shown to arise from different levels of transport stiffness exhibited by the models, combined with the gyroBohm-normalized fluxes of the predictions being an order of magnitude larger than other H-mode plasmas. Additionally, it is shown that although heating in both plasmas is predominantly to the electrons and collisionality is low, the plasmas remain sufficiently well coupled for the ions to carry a significant fraction of the thermal transport. As neoclassical transport is negligible in these conditions, this situation inherently requires long-wavelength ion gyroradius-scale turbulence to be the dominant transport mechanism in both plasmas. These results are combined with other basic considerations to propose a simple heuristic model of transport in reactor-relevant plasmas, along with simple metrics to quantify coupling and core transport properties across burning and non-burning plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Probabilistic data fusion and physics-informed machine learning: A new paradigm for modeling under uncertainty, and its application to accelerating the discovery of new materials

In this report we summarize the work conducted by PI Perdikaris and his group under this Early Career project DE–SC0019116 during the period of 09/01/2018 – 08/31/2023. The central aim of the work was to introduce a new paradigm for scientific data analysis that can seamlessly synthesize rigorous mathematical modeling with data of variable fidelity (e.g., measurements at multiple scales/resolutions or predictions of variable fidelity models) and multiple modalities (e.g., images, time–series, or scattered measurements). The setting we are interested in involves complex systems that are partially observed and whose dynamical behavior could be hard to model or totally unknown. The inherent uncertainty associated with this setting necessitates a departure from the classical deterministic realm of modeling and scientific computation, and, consequently, our main building blocks can no longer be crisp deterministic numbers and governing laws, but instead we must operate with probabilistic models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Charged particle diagnostics for inertial confinement fusion and high-energy-density physics experiments

MeV-range ions generated in inertial confinement fusion (ICF) and high-energy-density physics experiments carry a wealth of information, including fusion reaction yield, rate, and spatial emission profile; implosion areal density; electron temperature and mix; and electric and magnetic fields. Here, the principles of how this information is obtained from data and the charged particle diagnostic suite currently available at the major US ICF facilities for making the measurements are reviewed. Time-integrating instruments using image plate, radiochromic film, and/or CR-39 detectors in different configurations for ion counting, spectroscopy, or emission profile measurements are described, along with time-resolving detectors using chemical vapor deposited diamonds coupled to oscilloscopes or scintillators coupled to streak cameras for measuring the timing of ion emission. A brief description of charged-particle radiography setups for probing subject plasma experiments is also given. The goal of the paper is to provide the reader with a broad overview of available capabilities, with reference to resources where more detailed information can be found.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

A Representation Fusion Framework for Decoupling Diagnostic Information in Multimodal Learning

Modern medicine increasingly relies on multimodal data, ranging from clinical notes to imaging and genomics, to guide diagnosis and treatment. However, integrating these heterogeneous data sources in a principled and interpretable manner remains a major challenge. We present MODES (Multi-mOdal Disentangled Embedding Space), a representation fusion framework that explicitly separates shared and modality-specific factors of variation, offering a structured latent space for multimodal information that improves both prediction and interpretability. By leveraging pre-trained unimodal foundation models, MODES mitigates the dependency on extensive paired datasets, crucial in data-scarce clinical settings. We introduce a masking strategy that optimizes representation dimensionality by eliminating low-information dimensions, to achieve compact, information-rich representations. Our framework demonstrates superior performance in predicting diagnoses and phenotypes compared to unimodal and conventional fusion models. MODES also enables robust diagnostic inference in missing data scenarios, offering an opportunity toward interpretable and efficient multimodal diagnostics in personalized healthcare.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

A Gaussian process guide for signal regression in magnetic fusion

Extracting reliable information from diagnostic data in tokamaks is critical for understanding, analyzing, and controlling the behavior of fusion plasmas and validating models describing that behavior. Recent interest within the fusion community has focused on the use of principled statistical methods, such as Gaussian process regression (GPR), to attempt to develop sharper, more reliable, and more rigorous tools for examining the complex observed behavior in these systems. While GPR is an enormously powerful tool, there is also the danger of drawing fragile, or inconsistent conclusions from naive GPR fits that are not driven by principled treatments. Here we review the fundamental concepts underlying GPR in a way that may be useful for broad-ranging applications in fusion science. We also revisit how GPR is developed for profile fitting in tokamaks. We examine various extensions and targeted modifications applicable to experimental observations in the edge of the DIII-D tokamak. Finally, we discuss best practices for applying GPR to fusion data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Interactions Between Microturbulence and Magnetohydrodynamic Instabilities in Magnetized Plasmas (Final Technical Report)

The overall goal of this project was to develop a better understanding between small-scale microturbulence and large-scale magnetohydrodynamic (MHD) instabilities, particularly magnetic islands and tearing modes, in fusion relevant magnetically confined plasmas. This project advanced understanding through numerical simulations of different model equations. Questions addressed included how the magnitudes, spatial structures, and scalings of turbulent forcings and drags impact island dynamics, as well as what the "region of influence" of a tearing mode on the turbulence dynamics. A key finding of the project is that the microturbulence (and associated transport) exhibits spatial asymmetries for sufficiently large islands. The results have improved our fundamental understanding of plasma dynamics, motivated new experimental investigations, and will help inform future fusion predictive modeling efforts.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Interactions Between Microturbulence and Magnetohydrodynamic Instabilities in Magnetized Plasmas (Final Technical Report)

This document details the work accomplished during the period 04/15/2012-01/31/2020 for the collaborative project “Interactions Between Microturbulence and Magnetohydrodynamic Instabilities in Magnetized Plasmas,” and serves as the final report on the University of California, San Diego part of this collaborative project for Department of Energy Office of Science - Fusion Energy Sciences Grant No. DE- SC0007783. This project focused on the development of analytic and computational tools, seeking to better understand the mutual interactions between small-scale temperature-gradient driven microturbulence and macroscopic magnetohydrodynamic (MHD) instabilities, particularly tearing modes, in magnetically confined plasmas relevant for the generation of fusion energy. This project advanced understanding through numerical simulations of different sets of model equations, corresponding to different microturbulence instabilities. Questions addressed included how the magnitudes, spatial structures, and scaling's of turbulent forcing's and drags impact magnetic island dynamics, as well as quantifying the “region of influence” of an island on the microturbulence dynamics. A key finding of the project is that the microturbulence fluctuations and associated cross-field particle and energy fluxes exhibit spatial asymmetries for sufficiently large islands. The results have improved our fundamental understanding of plasma dynamics, motivated new experimental investigations, and will help inform future fusion predictive modeling efforts.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Absolute Neutron Rate Measurement and Non-Thermal/Thermonuclear Fusion Differentiation

The goal of fusion energy is to produce significantly more energy from fusion reactions than is input into the device. One of the products of fusion reactions is neutrons, which, due to their lack of charge, provide a unique view into the parameters of the device. Lawrence Livermore National Laboratory (LLNL) in collaboration with the University of California, Berkeley (UCB) have designed, assembled, and fielded a robust and portable neutron detection system known as PANDA (Portable and Adaptable Neutron Diagnostics for ARPA-E). This detector suite consists of three LaBr activation detectors that are calibrated to give a total neutron yield on shot, and twenty-four scintillators coupled to photo-multiplier tubes (SPMT). The SPMTs can be configured to attain spatial, temporal and/or energy information from fusion neutrons. The system was designed to be portable and is compartmentalized so that individual components can be used at different fusion facilities. During the duration of this work, part of the system was installed at the FuZE facility, a part of Zap Energy. Another component was installed that the CESZAR facility at the University of California, San Diego (UCSD) to support experiments by Magneto-Inertial Fusion Technologies, Inc. (MIFTI). The diagnostics were successful at both locations and the LLNL/UCB team supported the data analysis by creating and running analysis scripts and Monte-Carlo calculations. At Zap Energy the diagnostics demonstrated that the fusion from the FuZE device is thermonuclear in nature, a result that resulted in an invited talk at the American Physical Society Division of Plasma Physics and an invited paper. Additionally, temporal and spatial data was taken using the SPMTs to understand the duration and length of fusion production. At UCSD the neutron yield from the diagnostics was used to show improvements to fusion yields on their gas puff Z-pinch when using a gas shell surrounding the fuel. The success in this diagnostic has led to continued work at both Zap Energy and MIFTI, as well as follow on funding and interest at other fusion energy companies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Latent code-based fusion: A Volterra neural network approach

We propose a deep structure encoder using Volterra Neural Networks (VNNs) to seek a latent representation of multi-modal data whose features are jointly captured by a union of subspaces. The so-called self-representation embedding of the latent codes leads to a simplified fusion which is driven by a similarly constructed decoding. The Volterra Filter architecture achieved reduction in parameter complexity is primarily due to controlled non-linearities being introduced by the higher-order convolutions in lieu of generalized activation functions. Experimental results on two different datasets have shown a significant improvement in the clustering performance for VNNs auto-encoder over conventional Convolutional Neural Networks (CNNs) auto-encoder. In addition, we also show that the proposed approach demonstrates a much-improved sample complexity over CNN-based auto-encoder with a robust classification performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Machine Learning Methods for Connection RTT and Loss Rate Estimation Using MPI Measurements Under Random Losses

Scientific computations are expected to be increasingly distributed across wide-area networks, and Message Passing Interface (MPI) has been shown to scale to support their communications over long distances. Application-level measurements of MPI operations reflect the connection Round-Trip Time (RTT) and loss rate, and machine learning methods have been previously developed to estimate them under deterministic periodic losses. In this paper, we consider more complex, random losses with unform, Poisson and Gaussian distributions. We study five disparate machine leaning methods, with linear and non-linear, and smooth and non-smooth properties, to estimate RTT and loss rate over 10Gbps connections with 0-366ms RTT. The diversity and complexity of these estimators combined with the randomness of losses and TCP’s non-linear response together rule out the selection of a single best among them; instead, we fuse them to retain their design diversity. Overall, the results show that accurate estimates can be generated at low loss rates but become inaccurate at loss rates 10% and higher, thereby illustrating both their strengths and limitations.

Generalization Bounds↗