Search NASA⌕ Search

SEARCH · Search NASA

Results for “velocity data”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

The Sixth Data Release of the Radial Velocity Experiment (RAVE). I. Survey Description, Spectra, and Radial Velocities

The Radial Velocity Experiment (Rave) is a magnitude-limited (9 < I < 12) spectroscopic survey of Galactic stars randomly selected in Earth’s southern hemisphere. The Rave medium-resolution spectra (R ~ 7500) cover the Ca-triplet region (8410–8795 Å). The sixth and final data release (DR6) is based on 518,387 observations of 451,783 unique stars. Rave observations were taken between 2003 April 12 and 2013 April 4. Here we present the genesis, setup, and data reduction of Rave as well as wavelength-calibrated and flux-normalized spectra and error spectra for all observations in Rave DR6. Furthermore, we present derived spectral classification and radial velocities for the Rave targets, complemented by cross-matches with Gaia DR2 and other relevant catalogs. A comparison between internal error estimates, variances derived from stars with more than one observing epoch, and a comparison with radial velocities of Gaia DR2 reveals consistently that 68% of the objects have a velocity accuracy better than 1.4 km s{sup –1}, while 95% of the objects have radial velocities better than 4.0 km s{sup –1}. Stellar atmospheric parameters, abundances and distances are presented in a subsequent publication. The data can be accessed via the Rave website (http://rave-survey.org) or the Vizier database.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Coupled Experimental and High-Temperature Discrete-Element Method Modeling Studies of Aluminosilicate Particle Handling in Concentrated Solar Power Environments

Chemically inert, aluminosilicate based particles have been investigated as both a thermal transport and sensible energy storage medium for concentrated solar power facilities. These particles will experience a wide range of operating temperatures (300-1000 K) and handling conditions (dense to dilute falling particle curtains, dense granular flows, or dense structures), requiring specially-designed and optimized infrastructures. The relative influence of collisional and frictional interactions between particles varies based on temperature-dependent particulate properties and greatly impacts the bulk, granular flow behavior. These underlying physics are captured using discrete element method modeling tools. However, this modeling method is computationally expensive as each particle position and interaction is tracked during the simulation. These modeling methods are further complicated by introducing temperature-dependent particle properties, high-temperature radiative exchange, and directional irradiation sources experienced by granular flows in concentrated solar power environments. Coupled experimental and numerical studies of aluminosilicate particles in rotary kilns and dense particle curtains were performed for bulk temperatures up to 1073 K. The three particle types investigated included Carbobead HSP 30 /60, Carbobead CP 30/60, and Granusil 4030. Temperature, spatial, and velocity profile data were extracted from experimental runs using embedded K-type thermocouple probes and particle image velocimetry techniques. Experimental and numerical studies were compared using spatial temperature profiles, velocity fields, and shape profiles of the bulk, granular flows. Numerical models were developed using commercially available discrete element method modeling software, Aspherix®. Existing Aspherix® functionality was expanded by introducing coupled radiative exchange modeling tools. The laboratory-scale rotary kiln was developed to investigate the steady-state heat and mass transfer performance of aluminosilicate particles based on particle type, bulk handling temperature, and wall roughness. The rotational speed of the rotary kiln was varied to control the relative impact of collisional and frictional effects upon the granular flow behavior. Heat and mass transfer performance was categorized based on the Froude number and the observed flow regimes of slipping, rolling, cascading, and centrifuging. Coupled discrete element method modeling studies were used to evaluate the effects of temperature-dependent, particulate mechanical properties upon bulk flow behavior and upon the relative effects of radiative, advective, and/or conductive heat transfer. A high-temperature (< 1073 K) falling particle curtain was similarly fabricated to investigate the heat and mass transfer performance of aluminosilicate particles in particle handling situations dominated by inter-particle collisions. The impact of particle type, flow preheat temperatures (< 1073K), and bulk mass flow rates were investigated upon the particle curtain shape, temperature, and velocity profiles. Coupled discrete element method modeling studies were performed to evaluate the varying impact of temperature-dependent, particulate mechanical properties on the bulk flow behavior and the temperature profile of the particle curtain.

14 SOLAR ENERGY↗
DOE OSTI2024

Efficient Anomaly Detection Driven By Different Machine Learning Architectures And Models

The rapid growth and ubiquitous adoption of the internet and cyber-physical systems (CPS) have fundamentally transformed modern communication, work, and human-system interactions. While networks now form the backbone of critical digital ecosystems, enabling seamless data transmission across diverse, interconnected systems, this increased connectivity also expands the attack surface, making real-time detection of network intrusions and anomalies a pressing challenge. Detecting unusual activities within network infrastructure requires advanced data traffic analysis to differentiate between legitimate and malicious interactions. Traditional approaches to network anomaly detectionâ??such as rule-based and signature-based systemsâ??often depend on predefined patterns to identify known anomalies, limiting their effectiveness against emerging, stealthy, or previously unseen threats. These conventional methods suffer from high false alarm rates and fail to adapt to the ever-evolving nature of network traffic, particularly in large-scale, decentralized environments where data volume, velocity, and variety are constantly increasing. This dissertation presents artificial intelligence (AI)-driven approaches to anomaly detection that leverage graphics processing unit (GPU)-enabled high-performance computing (HPC) platforms for processing massive network traffic data and monitoring the components of cyber-physical systems (CPS) for potentially hazardous conditions. The research advances several key contributions: (1) Designing efficient machine learning techniques for CPS condition monitoring and anomaly detection; (2) enabling federated learning (FL) frameworks that enable distributed detection while preserving data privacy and system resilience; (3) exploring graph-based methodologies combining graph neural networks (GNN) and graph machine learning (ML) approaches for the Internet of Things (IoT) and automotive network security, and (4) performing distributed edge computing optimizations that integrate FL with scalable technologies for reduced communication overhead. Through extensive experiments, these methodologies demonstrate that complex anomaly detection and condition monitoring tasks can be achieved while balancing computational efficiency and detection accuracy through fine-grained network information processing. The frameworks developed in this research establish a robust foundation for network anomaly detection, providing scalable, adaptive, and privacy-preserving solutions for safeguarding CPS and IoT networks in an increasingly interconnected digital landscape. The practical implications of these research findings are significant, as they can inform the development of next-generation network security systems and contribute to the protection of critical infrastructure against sophisticated cyber attacks.

Marfo, William↗
DOE OSTI2021

Bayesian calibration of a physics-based crystal plasticity and damage model

In this work, we present a model parameter calibration procedure for a physics-based crystal plasticity model. The calibration process utilizes a powerful statistics-based Bayesian calibration method. Calibration of the crystal plasticity parameters makes use of experimentally-measured data, i.e. compressive stress–strain response, from $\langle$100$\rangle$ and $\langle$123$\rangle$ single crystal copper dynamically loaded via Kolsky bar tests. The calibration of damage parameters is achieved using experimentally-measured free-surface velocity history data from plate impact test on $\langle$100$\rangle$ and $\langle$110$\rangle$ single crystal copper, which generates shock compression followed by dynamic tensile failure. A validation assessment is then carried out by comparing the calibrated model predictions and experimental measurements of the dynamic tensile damage generated in an impacted bicrystal copper plate. Lastly, a model-informed rationale for the experimentally-observed dependence of the spatial distribution of ductile damage (porosity) on crystallography is provided.

42 ENGINEERING↗
DOE OSTI2020

Data Federation Challenges in Remote Near-Real-Time Fusion Experiment Data Processing

Fusion energy experiments and simulations provide critical information needed to plan future fusion reactors. As next-generation devices like ITER move toward long-pulse experiments, analyses, including AI and ML, should be performed in a wide range of time and computing constraints, from near-real-time constraints, between-shot analysis, and to campaign-wide long-term analysis. However, the data volume, velocity, and variety make it extremely challenging for analyses using only local computational resources. Researchers need the ability to compose and execute workflows spanning edge resources to large-scale high-performance computing facilities.We present Delta, a system to address data analysis challenges, including AI/ML, in fusion science, by leveraging the ADIOS I/O library and middleware, to support executing science workflows over the wide area network for near-real-time streaming. We discuss the data federation challenges in performing remote workflows, focusing on on-going research work in (1) managing, reducing, and streaming data to minimize I/O and data movement overheads, (2) decompressing and reorganizing data for analysis, and (3) executing workflows for automated data analysis. We introduce examples for deep-learning based data analysis for the fusion domain and demonstrate how we use Delta to construct end-to-end workflows for a fusion device in Korea, connecting a remote DOE facility in the USA. The capability demonstrated by this project is the basis for improving the state of the art for near-real-time data federation amongst remote facilities.

Choi, Jong Youl↗
DOE OSTI2020

The Manufacturing Data and Machine Learning Platform: Enabling Real-time Monitoring and Control of Scientific Experiments via IoT

IoT devices and sensor networks present new opportunities for measuring, monitoring, and guiding scientific experiments. Sensors, cameras, and instruments can be combined to provide previously unachievable insights into the state of ongoing experiments. However, IoT devices can vary greatly in the type, volume, and velocity of data they generate, making it challenging to fully realize this potential. Indeed, synergizing diverse IoT data streams in near-real time can require the use of machine learning (ML). In addition, new tools and technologies are required to facilitate the collection, aggregation, and manipulation of sensor data in order to simplify the application of ML models and in turn, fully realize the utility of IoT devices in laboratories. Here we will demonstrate how the use of the Argonne-developed Manufacturing Data and Machine Learning (MDML) platform can analyze and use IoT devices in a manufacturing experiment. MDML is designed to standardize the research and operational environment for advanced data analytics and AI-enabled automated process optimization by providing the infrastructure to integrate AI in cyber-physical systems for in situ analysis. We will show that MDML is capable of processing diverse IoT data streams, using multiple computing resources, and integrating ML models to guide an experiment.

Machine Learning↗
DOE OSTI2020

Using Deep Learning to Derive Shear-Wave Velocity Models from Surface-Wave Dispersion Data

We present a new algorithm for derivations of 1D shear-wave velocity models from surface-wave dispersion data using convolutional neural networks (CNNs). The technique is applied for continental China and the plate boundary region in southern California. Different CNNs are designed for these two regions and are trained using theoretical Rayleigh-wave phase and group velocity images computed from reference 1D VS models. The methodology is tested with 3260 phase–group images for continental China and 4160 phase–group images for southern California. The conversions of these images to velocity profiles take ~23 s for continental China and ~30 s for southern California on a personal laptop with the NVIDIA GeForce GTX 1060 core and a memory of 6 GB. The results obtained by the CNNs show high correlation with previous studies using conventional methods. The effectiveness of the CNN technique makes this fast method an important alternative for deriving shear-wave velocity models from large datasets of surface-wave dispersion data.

Geochemistry & Geophysics↗
DOE OSTI2023

Effects of additively manufactured surface roughness on small diameter plenums with multiple side discharges for high temperature gas turbine blade cooling applications

Combined heat and power (CHP) applications have significant environmental and economic benefits that are consistent with the goals of the U.S. Department of Energy (DOE). One area that is currently being studied includes the potential benefits of CHP turbine operation at higher turbine inlet temperatures. Internal cooling concepts enabled by additive manufacturing (AM) are of primary interest. Here, the effectiveness of internal cooling is hindered by many factors such as velocity distribution of the cooling air to the hot surface considering impingement cooling. To simulate cooling air exiting from a series of orifices for internal cooling in an airfoil, a straight smooth wall tubing with multiple side discharging orifices is used and compared to additively manufactured tubing (Ti6Al4V Grade 23) with orifice size and spacing as well as inner and outer diameters identical to the smooth wall tubing. Similar to flow discharging form perforated pipes, the flow discharged from individual orifices along the tubes in this study is found to be nonuniformly distributed, and the horizontal (axial direction) momentum can be observed from the experimental data. Discharge velocities have been measured with two-dimensional (2D) particle imaging velocimetry (PIV) and single element hot wire anemometry. Numerical analysis has also been conducted to predict the velocity distributions along the orifices in the smooth wall and additive manufacturing (AM) tubing, which are inherited with surface roughness. Numerical and measured results in this study are compared, presented, and discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Did we hear the sound of the Universe boiling? Analysis using the full fluid velocity profiles and NANOGrav 15-year data

Abstract In this paper, we analyse sound waves arising from a cosmic phase transition where the full velocity profile is taken into account as an explanation for the gravitational wave spectrum observed by multiple pulsar timing array groups. Unlike the broken power law used in the literature, in this scenario the power law after the peak depends on the macroscopic properties of the phase transition, allowing for a better fit with pulsar timing array (PTA) data. We compare the best fit with that obtained using the usual broken power law and, unsurprisingly, find a better fit with the gravitational wave (GW) spectrum that utilizes the full velocity profile. Even more importantly, the thermal parameters that produce the best fit are quite different. We then discuss models that can produce the best-fit point and complementary probes using CMB experiments and searches for light particles in DUNE, IceCUBE-Gen2, neutrinoless doubleβ-decay, and forward physics facilities (FPF) at the LHC like FASERν, etc.

Astronomy & Astrophysics↗
DOE OSTI2022

Flow structures of the cross-flow over a five-layer helically coiled steam generator geometry

The helically-coiled heat exchanger (HCSG) offers advantages over straight tubes such as compactness in geometry, increased heat transfer coefficients, and capability to absorb thermal expansion. In this study, the time-resolved velocity field data of shell-side crossflow over a five-layer helically coiled steam generator geometry was obtained using Particle Image Velocimetry (PIV) between adjacent rods in four regions with up to 5000 frames per second (5 kHz) at approximately Re u = 3600. The slant rod bundle created different flow patterns in different regions. Proper Orthogonal Decomposition (POD) revealed high-energy-mode flow structures. Due to the confined flow channel geometry, the large flow structures were not advected resulting in no strong POD mode paring. Continuous Wavelet Transform (CWT) visualized the characteristics of flow fluctuation in time and frequency domain simultaneously, which ranged in Strouhal number, S u , between 0.03 and 1.17. In the wake regions of the rods, flows changed in both pattern and magnitude over time. Once a pattern formed, it continued for relatively shorter than straight tube arrays, before changing the pattern again. The histograms of the POD time coefficients presented this multimodal flow characteristics. The current study focuses more on whole flow field analyses in the selected regions rather than local point-wise analyses. Finally, this study revealed that various Strouhal numbers can exist in the helically coiled heat exchanger geometry, which was not observed in straight tube arrays. In particular, Strouhal numbers smaller than 0.1 do not seem to be caused by vortex shedding but seem to be the result of the combination of complex geometry and possible multimodal trends. Based on the current observation, further works would involve intensive instantaneous point-wise analyses on the interactions between important locations such as separation points, stagnation points, shear layers, etc.

42 ENGINEERING↗
DOE OSTI2020

Scale bridging damage model for quasi-brittle metals informed with crack evolution statistics

Computationally efficient methods for bridging length scales, from highly resolved micro/meso-scale models that can explicitly model crack growth, to macro-scale continuum models that are more suitable for modeling large parts, have been of interest to researchers for decades. In this work, an improved brittle damage model is presented for the simulation of dynamic fracture in continuum scale quasi-brittle metal components. Crack evolution statistics, including the number, length, and orientation of individual cracks, are extracted from high-fidelity, finite discrete element method (FDEM) simulations and used to generate effective material moduli that reflect the material’s damaged state over time. This strategy allows for the retention of small-scale physical behaviors such as crack growth and coalescence in continuum scale hydrodynamic simulations. However, the high-fidelity simulations required to generate the crack statistics are computationally expensive. Thus, steps were taken to produce a flexible constitutive model to reduce the number of costly high-fidelity simulations needed to produce accurate results. A new stress based degradation criterion is introduced for the degradation of individual material zones. This allows for the development of a heterogeneous damage distribution within the bulk material. Then a flow stress model is added to the hydrodynamic simulation to account for plasticity in quasi-brittle materials. As a result, the effective moduli model can be applied to a larger range of materials. The effective moduli constitutive model is used to simulate beryllium flyer plate experiments. The results from the continuum scale simulations using statistics from a single high-fidelity simulation are found to be in excellent agreement with numerical and experimental velocity interferometer data. The same set of crack statistics are used to extrapolate the results of a higher rate flyer plate case using the effective moduli model. In conclusion, the extension of this model to higher rate cases shows promise for further reducing the number of costly high-fidelity simulations needed to generate crack statistics.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Simultaneous 10 kHz three-dimensional CH 2 O and tomographic PIV measurements in a lifted partially-premixed jet flame

High-speed, three-dimensional (3D) scalar-velocity field measurements are demonstrated in a lifted partially-premixed dimethyl-ether/air jet flame using simultaneous laser-induced fluorescence (LIF) of formaldehyde (CH 2 O) and tomographic particle image velocimetry (TPIV). The 3D LIF measurements are performed by raster scanning the laser beam from a 100 kHz pulse-burst laser across the probe volume using an acousto-optic deflector. The volumetric reconstruction of the LIF signal from ten parallel planes provides quasi-instantaneous 3D LIF measurements that are synchronized with 10 kHz TPIV measurements. Here, the temporally resolved CH 2 O-LIF and velocity field data are used to analyze Lagrangian particle trajectories and displacement speeds at the base of the lifted flame. The particle trajectories reveal flow structures that are difficult to observe in an Eulerian reference frame. Positive and negative displacement speeds are observed at the CH 2 O-LIF surfaces at the inner and outer regions of the jet flame with a maximum displacement speed of approximately eight times the laminar flame speed of a stoichiometric dimethyl-ether/air mixture. The observations in present study support formation of lean premixed flames near the flame base whose role in flame stabilization should be investigated in more detail.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Resolving Anodic Current and Temperature Distributions in a Polymer Electrolyte Membrane Water Electrolysis Cell Using a Pseudo-Two-Phase Computational Fluid Dynamics Model

Expanding upon our prior experimental work, we constructed a three-dimensional model of a polymer electrolyte membrane water electrolyzer using computational fluid dynamics. We applied the assumption of pseudo-two-phase flow, the flow of two phases with equal velocity. Experimental data were used to obtain parameters and to determine the conditions under which this model was valid. Anodic distributions of current density, temperature, liquid saturation, and relative humidity were obtained at various flow rates. The overall current density and temperature difference from inlet to outlet at the anode agreed strongly with experimental measurements under most circumstances. This verification allowed us to further examine the apparent gas coverage calculated from experimental and model temperature data. Results suggested a low liquid saturation and low relative humidity at the anode due to the consumption of liquid water and water vapor. However, we questioned the accuracy of the pseudo-two-phase assumption at low water feed rates. We concluded that the model was applicable to systems with liquid water feed rates greater than 0.6 ml min -1 cm -2 . Therefore, it is a fair screening method that can advise which operating conditions lead to excessive temperatures or drying at the anode, thereby promoting the longevity of the membrane and catalyst.

25 ENERGY STORAGE↗
DOE OSTI2023

Annular Metallic Nuclear Fuel Informatics at 50 nm Resolution

U-10wt.% Zr (U-10Zr) based metallic fuel is the leading candidate for next-generation sodium cooled fast reactor in United States. Advanced post-irradiation characterization (from sub-nanometer to micrometer) helps to understand fuel microstructure and property change during irradiation, benefiting fuel qualification for commercial application. With high velocity image data generating method, an automatic way to extract the microstructural information quantitively can better serve the needs from post irradiation characterization. A trained machine learning model, named Decision Tree, is employed to categorize pores caused by fission gas release and to aid phase identification. This work presents a showcase of this approach on different irradiated U-10Zr metallic fuels. This quantitative data offers insights into the fission product migration and potentially thermal conductivity degradation. This information from machine learning will be fed into fuel design code for better prediction of fuel performance.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Understanding Fission Gas Bubble Distribution and Zirconium Redistribution in Neutron-irradiated U-Zr Metallic Fuel Using Machine Learning

U-10wt.% Zr (U-10Zr) based metallic fuel is the leading candidate for next-generation sodium cooled fast reactor in United States. Currently, Idaho National Laboratory (INL) has been the leading national laboratory for research, development, and demonstration (RD&D) on metallic fuel. Advanced post-irradiation characterization will help to understand fuel microstructure and property change during irradiation, benefiting fuel qualification for commercial application. Characterization capabilities ranging from sub-nanometer to micrometer, such as scanning electron microscopy (SEM), focused ion beam (FIB) sampling, transmission electron microscopy (TEM) characterization, and local thermal conductivity microscopy (TCM), have been utilized recently on irradiated U-10Zr fuel samples to gain a better understanding of nuclear fuel microstructure and property evolution inside a reactor. The FIB/SEM coupled with energy dispersive X-ray spectroscopy (EDS) can capture the essential information to achieve better understanding of fuel behaviors. Inside a nuclear reactor, the phase and microstructure of U-10Zr is constantly changing under neutron bombardment. For example, the gaseous fission product atoms have a limited solubility inside fuel matrix and tend to precipitate out in bubble form, which not only contribute to fuel thermal conductivity degradation but also provide a shortcut for movement of fission products, i.e. lanthanides. The resultant deposition of lanthanides at the cladding inner surface will potentially trigger a chemical reaction/interaction between nuclear fuel and cladding at reactor operational conditions, threatening fuel integrity and safety. FIB/SEM coupled with EDS can provide the fission bubble information as well as probe into phase separation or Zr redistribution, which is fundamental to predict the fuel performance. With high velocity image data generating method, such as FIB/SEM, an automatic way to extract the microstructural information quantitively can better serve the needs from post irradiation characterization. A trained machine learning model, named Decision Tree, is employed to generate a bubble classifier and to categorize bubbles into three categories: isolated bubble, connected without lanthanides, and connected with lanthanides bubbles[3]. This work presents a showcase of this approach on six regions of a fuel cross-section along the radial temperature gradient. We obtained distributions of bubble categories and porosity rates along the six regions. Moreover, a secondary phase U-Zr2 was determined and found on regions 5 and 6. The secondary phase fraction was increasing from 15.61% in region 5 to 34.79% in region 6 based on this approach . This quantitative data offers insights into the lanthanide migration and potentially thermal conductivity degradation. This information from machine learning will be fed into fuel design code for better prediction of fuel performance.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

Big Data For Operation and Maintenance Cost Reduction

The purpose of this research is to develop a first-of-a-kind framework for integrating Big Data capability into the daily activities of our current fleet of nuclear power plants. Big Data is traditionally defined as data sets with high volume, velocity, and heterogeneity, and the existing Big Data analytics capabilities are now widely popular in fields such as finance, weather, e-commerce, healthcare and sports. In the nuclear industry, while the volume and velocity of data may present computational challenges for existing analytics capabilities, data heterogeneity are seen to present the major challenge. This research project mainly focuses on incorporating the wide range of data heterogeneities in nuclear power plants into an integrated Big Data Analytics capability. The primary end-product of this project is a Big Data framework that is capable of dealing with the large volume and heterogeneity of the data found in nuclear power plants to extract timely and valuable information on equipment performance. The framework can generate system insights that are actionable relations between measurable impacts and the corresponding maintenance action plans and enable optimization of plant operation and maintenance based on the extracted information. The developed framework is capable of handling heterogeneous data including both image data and time-series sensor data. Specifically, this developed framework includes the following components. The first component is an overarching maintenance ontology which includes system insights required by maintenance optimization. The maintenance ontology interacts with other components in the developed framework. The second component handles Piping & Instrumentation Diagram (P&ID) data. It can be used to extract system components and their relations automatically from the P&IDs. This extracted information is stored in the first component, i.e., maintenance ontology, and is also used as input to the third component, i.e., a tool for generating the fault tree for the corresponding system. The generated fault tree in turn is stored in the ontology for assessing risk that is used as a criterion in maintenance policy optimization. The fourth component is a tool for inferring the parameters in the Markov degradation model for a nuclear system. It uses basic information from the ontology. The fifth component is a tool for assessing the degradation level using sensor measurement data, for example, pressure, flowrate. This tool can be used for determining corrective maintenance actions. The results obtained from components four and five are returned to the ontology. The sixth component of the framework is a tool for optimizing the maintenance policy for a nuclear system of interest. It takes certain basic information from the ontology, e.g., costs of maintenance actions and system failures, as input, and returns the optimal maintenance policy to the ontology. This tool can be used for determining predictive maintenance actions. A set of experiments have also been conducted to verify the algorithms developed in this project for nuclear system degradation monitoring. The experiments are based on four solenoid valves, similar to the ones used in nuclear power plants. The analyses based on the experimental data using two algorithms, i.e., the Randomized Window Decomposition (RWD) algorithm and the particle filtering algorithm, and the results are introduced in the report. The Big Data framework developed in this project can be used as a support tool in daily activities of plant operation and maintenance and will reduce current costs while maintaining or improving safety levels. Overall, the project will not only benefit existing reactors, however it will open new frontiers to realize the long overdue value of Big Data Analytics in the nuclear sphere.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Deep Learning for Full Waveform Inversion of Elastic Active-Source Seismic Data to Estimate P-Wave Velocity Models

Seismic imaging methods are critical for Global Security and Energy & Homeland Security missions and activities that rely on subsurface characterization, but traditional methods remain computationally expensive and require significant labor hours and expertise to execute. Within the past few years, machine learning (ML), namely deep learning (DL), has been used to develop data-driven end-to-end full waveform inversion (FWI) methods to estimate 2D P-wave velocity (Vp) models in a fraction of the time as conventional FWI. These methods, however, are trained on simplistic acoustic wave seismic data and Vp models that are not realistic nor representative of real-world observations, leaving a large gap between the state-of-the-art and deployable, feasible, and practical DL FWI methods. Here, we generate a synthetic active-source, 3D, elastic wave seismic data set and a variety of Vp models with realistic geologic structure for training DL FWI methods. We evaluate six different methods that have performed well for acoustic DL FWI or medical imaging tasks using our more realistic dataset. We find that these six trained models do not match the performance of published acoustic end-to-end DL FWI methods, indicating more training data may be needed, physics may need to be incorporated to achieve good accuracy at the sacrifice of the end-to-end advantage, and/or novel methods need to be developed to enable end-to-end DL FWI methods to perform well for real-world seismic data.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗