Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “limited 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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Some research topics belonging to classification problems in the nuclear industry, such as fault diagnosis and accident identification, can be solved by feature extraction and subsequent application of statistical machine learning classifiers. Recently, deep neural network-based methods with automatic feature extraction and high accuracy have gained wide attention. They usually require large-scale training data, however, plant fault or accident data are scarce or difficult to obtain. Here this paper proposes a convolutional network (CNN)-based transfer learning method to solve this problem. The network's shallow layer is derived from a pre-trained CNN based on the ImageNet database to automatically extract features, and the deep layer is customized to match the classification problem. Data in non-image formats are converted to image formats and subsequently used to train the network. Case studies of rotating machines fault diagnosis show that the proposed method requires only limited training data to achieve high accuracy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

A deep learning-based direct forecasting of CO 2 plume migration

Accurate and timely forecasts of CO 2 plume evolution in geological reservoirs are crucial for CO 2 migration detection, leakage risk assessment, and operation decision support. Conventional forecasting usually adopts a two-step strategy, first calibrating reservoir model parameters against observations using iterative inverse modeling (or history matching) and then applying the calibrated model for predictions. This method impedes real-time forecasts due to the heavy computational demand in inverse modeling and may suffer from poor prediction accuracy because of the limited observation data. In this work, we propose a deep learning-based latent space mapping framework to forecast CO 2 plume migration directly by avoiding the inverse modeling. We first use the convolutional autoencoder to map the high-dimensional complex plume extents onto low-dimensional latent space. Next, we use neural networks to learn the relationship between the observation variables and the prediction latent variables. And then for given observation data, we infer the prediction values directly. This one-step direct forecasting is computationally efficient which requires a few number of parallelizable reservoir simulations and it can provide accurate predictions with limited observations by learning the observation-prediction relationship in the reduced dimension. Therefore, our proposed method enables an in-time forecast of dynamic CO 2 plume distributions. In this work, we demonstrate the effectiveness and accuracy of our method in predicting the CO 2 plume migration using four metrics such as plume area, centroid movement distance, and plume spreading in the primary and secondary directions. And the spatio-temporal evolution patterns of plume migration under diverse geological complexities are also accurately quantified.

15 GEOTHERMAL ENERGY↗
DOE OSTI2024

ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability

Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 684 petaFLOPS to 1.6 exaFLOPS sustained throughput, with scaling efficiency maintained at 41% to 85% across 49,152 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

Wang, Xiao↗
DOE OSTI2022

Snowmass Topical Group Summary Report: IF04 -- Trigger and Data Acquisition Systems

A trend for future high energy physics experiments is an increase in the data bandwidth produced from the detectors. Datasets of the Petabyte scale have already become the norm, and the requirements of future experiments -- greater in size, exposure, and complexity -- will further push the limits of data acquisition technologies to data rates of exabytes per seconds. The challenge for these future data-intensive physics facilities lies in the reduction of the flow of data through a combination of sophisticated event selection in the form of high-performance triggers and improved data representation through compression and calculation of high-level quantities. These tasks must be performed with low-latency (i.e. in real-time) and often in extreme environments including high radiation, high magnetic fields, and cryogenic temperatures.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Snowmass Topical Group Summary Report: IF04 -- Trigger and Data Acquisition Systems

A trend for future high energy physics experiments is an increase in the data bandwidth produced from the detectors. Datasets of the Petabyte scale have already become the norm, and the requirements of future experiments -- greater in size, exposure, and complexity -- will further push the limits of data acquisition technologies to data rates of exabytes per seconds. The challenge for these future data-intensive physics facilities lies in the reduction of the flow of data through a combination of sophisticated event selection in the form of high-performance triggers and improved data representation through compression and calculation of high-level quantities. These tasks must be performed with low-latency (i.e. in real-time) and often in extreme environments including high radiation, high magnetic fields, and cryogenic temperatures.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

PeakDecoder enables machine learning-based metabolite annotation and accurate profiling in multidimensional mass spectrometry measurements

Multidimensional measurements using state-of-the-art separations and mass spectrometry provide advantages in untargeted metabolomics analyses for studying biological and environmental bio-chemical processes. However, the lack of rapid analytical methods and robust algorithms for these heterogeneous data has limited its application. Here, we develop and evaluate a sensitive and high-throughput analytical and computational workflow to enable accurate metabolite profiling. Our workflow combines liquid chromatography, ion mobility spectrometry and data-independent acquisition mass spectrometry with PeakDecoder, a machine learning-based algorithm that learns to distinguish true co-elution and co-mobility from raw data and calculates metabolite identification error rates. We apply PeakDecoder for metabolite profiling of various engineered strains of Aspergillus pseudoterreus, Aspergillus niger, Pseudomonas putida and Rhodosporidium toruloides. Results, validated manually and against selected reaction monitoring and gas-chromatography platforms, show that 2683 features could be confidently annotated and quantified across 116 microbial sample runs using a library built from 64 standards.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

An Evaluated, Transient Experiment based on Simultaneous, 3-D Neutron-Flux and Temperature Measurements

There is substantial interest in the validation of transient models for reactor physics, particularly in support of next-generation, high-fidelity tools like those developed by the U.S. DOE and other institutions. However, much existing data is limited largely to sparse or integral measurements in very large, complicated reactor systems. Moreover, meaningful transients are almost always driven by the complex coupling between neutronics and thermal-hydraulics. To address this data gap, a series of steady-state and transient experiments was conducted at the University of Wisconsin Nuclear Reactor that used several probes containing micro-pocket fission detectors (MPFDs) to measure neutron fluxes or resistance temperature detectors (RTDs) to measure coolant temperatures. Here, an overview of the experimental campaign is provided, as is a preliminary look of selected measurements.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2026

Development of Data-Driven Models for Performance Prediction and Chemical Dosing of a Full-Scale Controlled Phosphorus Precipitation Reactor

This study evaluated the use of data-driven models to improve control of a struvite precipitation reactor that removes phosphorus from wastewater while producing a fertilizer product. The researchers developed predictive models for influent orthophosphate concentration, effluent orthophosphate concentration, and phosphorus removal using operational data from a full-scale MagPrex™ reactor at a water resource recovery facility in Denver, Colorado. Model predictions were used to recommend magnesium chloride dosing adjustments needed to achieve a target effluent phosphorus concentration. Several machine learning approaches were tested, with ridge regression providing the best predictions for influent orthophosphate concentration and phosphorus removal, and XGBoost providing the best predictions for effluent orthophosphate concentration. Simulation results indicated that the decision-support approach could correctly identify dosing adjustments in most cases and reduce chemical use. Full-scale implementation achieved lower accuracy due to changing operating conditions and limited historical data in some operating ranges. Here, the results demonstrate the potential of data-driven tools to support phosphorus recovery process control while also identifying practical limitations that affect deployment in full-scale systems.

42 ENGINEERING↗
DOE OSTI2024

Probabilistic Programming for Transportable Source Characterization and Uncertainty Quantification of the North Korean Nuclear Tests 2006–2017

Here, we introduce a transportable technique to determine the yield and depth of burial (DOB) from seismic source spectra of underground nuclear explosions. We demonstrate this technique on the six declared North Korean nuclear tests. This approach derives source spectra in absolute units from regional phase (Pg) amplitudes by correcting the observations for geometric spreading, attenuation, and site amplification. We couple the source spectra and explosion source models with a probabilistic programming framework that integrates deep learning techniques and Bayesian modeling. This approach permits the exchange of information across various data categories to quantify both the data and model uncertainty. This technique stands out as an innovative use of broad‐area propagation models, making it transportable across various geologic settings. This method proves to be effective in scenarios with diverse and/or limited observational data, even when the source depth is unknown. We present new independent estimates of absolute yield and DOB that are consistent with the prior assessments, underscoring the potential of this method in enhancing transportable nuclear explosion monitoring capabilities.

58 GEOSCIENCES↗
DOE OSTI2022

Report on Data Quality Required for Modeling an MSR

Calculations were performed to assess how uncertainties in molten salt property values impact the results of behavior models of molten salt reactor systems under steady-state conditions. The thermophysical and thermochemical properties of salt mixtures being considered for use in molten salt reactors are not yet well characterized and methods used to measure property values to molten salts are not yet well established. The limited property data for salts of interest that are available in the literature are inconsistent and unreliable. Many methods used to measure property values remain developmental in the sense that not all variables affecting measured values have been identified or controlled during the measurement and not all aspects of the measurements affecting data quality are calibrated. A prior report described the repeatability of measurements made at Argonne and the reproducibility of measurements made with the same salts at several institutions is being evaluated. There is significant uncertainty in measured property values due to instrumental limitations and the effects of contaminants in the salts used to make the measurements that impacts predictions of salt behavior in a reactor. Most salts of interest are multicomponent eutectic or near-eutectic mixtures and both uncertainty in the salt composition and uncertainty in measured values. Furthermore, the salt composition evolves over time due to the uptake of impurities from the atmosphere and corrosion of containment vessels. More significantly, fission products will accumulate during operation that change the salt compositions and property values. MSR developers need to understand how this uncertainty in the basic property data of the fuel will impact modeling predictions for normal reactor operation as well was in transient scenarios that will impact the safety basis. The calculations and analyses in this report address the impact of uncertainty in measured property values under steady-state conditions through a generalized parametric study. The pooled uncertainty from contributions by a number of factors were considered and quantified, including varying composition due to impurities and fission products, imprecision in the measured values, and uncontrolled aspects of the measurement. In this way, we can begin to gain an understanding of the magnitude of the impact uncertainty will have in modeling MSR systems.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

Galaxy Cruise: Deep Insights into Interacting Galaxies in the Local Universe

Abstract We present the first results from GALAXY CRUISE, a community (or citizen) science project based on data from the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP). The current paradigm of galaxy evolution suggests that galaxies grow hierarchically via mergers, but our observational understanding of the role of mergers is still limited. The data from HSC-SSP are ideally suited to improve our understanding with improved identifications of interacting galaxies thanks to the superb depth and image quality of HSC-SSP. We launched a community science project, GALAXY CRUISE, in 2019 and have collected over two million independent classifications of 20686 galaxies at z < 0.2. We first characterize the accuracy of the participants’ classifications and demonstrate that it surpasses previous studies based on shallower imaging data. We then investigate various aspects of interacting galaxies in detail. We show that there is a clear sign of enhanced activities of super-massive black holes and star formation in interacting galaxies compared to those in isolated galaxies. The enhancement seems particularly strong for galaxies undergoing violent mergers. We also show that the mass growth rate inferred from our results is roughly consistent with the observed evolution of the stellar mass function. The second season of GALAXY CRUISE is currently underway and we conclude with future prospects. We make the morphological classification catalog used in this paper publicly available at the GALAXY CRUISE website, which will be particularly useful for machine-learning applications.

Tanaka, Masayuki↗
DOE OSTI2024

Countering Weapons of Mass Destruction Office (CWMD) Data Categorization Study: Chemical, Biological, Radiological, and Nuclear (CBRN) Detection Device Data

Pacific Northwest National Laboratory (PNNL) seeks to address critical questions related to chemical, biological, radiological, and nuclear (CBRN) detection devices. This research aims to enhance the security and understanding of these devices by investigating various aspects of their identification, communication, and functionality. The primary focus is on network security, malware detection, device identification, and intelligence gathering. CBRN data can be categorized in various ways depending on the purpose of CBRN detection devices and the specific context of the applications for analysis. Criteria that can be used to assist in this effort include but are not limited to data type, data protocol, source/destination, application, time, security, and content. This study will inform additional paths for data classification, data profiling, data mapping, and data modeling. This will help the Countering Weapons of Mass Destruction Office (CWMD) better understand their data and make informed decisions based on the insights gained from this study and their application. The CBRN Data Categorization study will include the identification of 5–10 different CBRN detection devices with unique characteristics for assessing and analyzing the data that is being produced by and transmitted from these devices.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2020

Deep learning to generate in silico chemical property libraries and candidate molecules for small molecule identification in complex samples

Comprehensive and unambiguous identification of small molecules in complex samples will revolutionize our understanding of the role of metabolites in biological systems. Existing and emerging technologies have enabled measurement of chemical properties of molecules in complex mixtures and, in concert, are sensitive enough to resolve even stereoisomers. Despite these experimental advances, small molecule identification is inhibited by (i) chemical reference libraries (e.g. mass spectra, collision cross section, and other measurable property libraries) representing <1% of known molecules, limiting the number of possible identifications, and (ii) the lack of a method to generate candidate matches directly from experimental features (i.e. without a library). To this end, we developed a variational autoencoder (VAE) to learn a continuous numerical, or latent, representation of molecular structure to expand reference libraries for small molecule identification. We extended the VAE to include a chemical property decoder, trained as a multitask network, in order to shape the latent representation such that it assembles according to desired chemical properties. The approach is unique in its application to metabolomics and small molecule identification, with its focus on properties that can be obtained from experimental measurements (m/z, CCS) paired with its training paradigm, which involved a cascade of transfer learning iterations. First, molecular representation is learned from a large dataset of structures with m/z labels. Next, in silico property values are used to continue training, as experimental property data is limited. Finally, the network is further refined by being trained with the experimental data. This allows the network to learn as much as possible at each stage, enabling success with progressively smaller datasets without overfitting. Once trained, the network can be used to predict chemical properties directly from structure, as well as generate candidate structures with desired chemical properties. Our approach is orders of magnitude faster than first-principles simulation for CCS property prediction. Additionally, the ability to generate novel molecules along manifolds, defined by chemical property analogues, positions DarkChem as highly useful in a number of application areas, including metabolomics and small molecule identification, drug discovery and design, chemical forensics, and beyond.

Colby, Sean M.↗
DOE OSTI2021

On the Rate Constant for NH 2 +HO 2 and Third-Body Collision Efficiencies for NH 2 +H(+M) and NH 2 +NH 2 (+M)

In low-temperature flash photolysis of NH 3 /O 2 /N 2 mixtures, the NH 2 consumption rate and the product distribution is controlled by the reactions NH 2 + HO 2 → products (R1), NH 2 + H (+M) → NH 3 (+M) (R2), and NH 2 + NH 2 (+M) → N 2 H 4 (+M) (R3). In the present work, published flash photolysis experiments by, among others, Cheskis and co-workers, are re-interpreted using recent direct measurements of NH 2 + H (+N 2 ) and NH 2 + NH 2 (+N 2 ) from Altinay and Macdonald. To facilitate analysis of the FP data, relative third-body collision efficiencies compared to N 2 for R2 and R3 were calculated for O 2 and NH 3 as well as for other selected molecules. We report results were in good agreement with the limited experimental data. Based on reported NH 2 decay rates in flash photolysis of NH 3 /O 2 /N 2 , a rate constant for NH 2 + HO 2 → NH 3 + O 2 (R1a) of $k_{1\text{a}}$ = 1.5(±0.5) × 10 14 cm 3 mol –1 s –1 at 295 K was derived. This value is higher than earlier determinations based on the FP results but in good agreement with recent theoretical work. Kinetic modeling of reported N 2 O yields indicates that NH 2 + HO 2 → H 2 NO + O (R1c) is competing with R1a, but perturbation experiments with addition of CH4 indicate that it is not a dominating channel. Measured HNO profiles indicate that this component is formed directly by NH 2 + HO 2 → HNO + H 2 O (R1b), but theoretical work indicates that R1b is only a minor channel. Based on this analysis, we estimate $k_{1\text{c}}$ = 2.5 × 10 13 cm 3 mol –1 s –1 and $k_{1\text{b}}$ = 2.5 × 10 12 cm 3 mol –1 s –1 at 295 K, with significant uncertainty margins.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

In-situ optical monitoring of gas turbine blade coatings under operational extreme environments

High temperature material systems consisting of thermal barrier coatings and the underlying superalloys are key to achieving higher gas temperatures which in turn control engine efficiencies and reduce emissions. With engine temperatures in excess of the limits that metallic blades and vanes can endure, advanced monitoring techniques that ensure the integrity and durability of these coatings are paramount to continuous and safe operation. Optical methods have the benefit of being non-invasive and are able to capture data under limited access available for monitoring the hot-section of turbines. Addressing Topic 5 on Advanced Instrumentation, the research and development effort for this project titled “In situ optical monitoring of gas turbine blade coatings under operational extreme environments” was completed by University of Central Florida researchers, including Raghavan (PI) and Ghosh (co-PI). In this project, the research team leveraged intrinsic properties of coatings and rare-earth dopants as active and intelligent “sensors” through their optical properties. The outcomes of this project pave the way for diagnostics of turbine blade coatings, under operating environments, through the development of the sensing thermal barrier coating configurations, calibration and associated instrumentation while ensuring coating integrity and durability goals are concurrently met.

42 ENGINEERING↗
DOE OSTI2021

Deep-freeze graph training for latent learning

Scientific and engineering advances are primarily driven by multi-tier conceptual constructs and conditional theoretical frameworks. The theories allow predictions of hypothetical system responses, given a set of approximate conditions (ranges of applicability) imposed on latent parameters that cannot be measured directly. Learning to estimate the latent variables (Latent Learning) helps to pinpoint the anticipated range-edge anomalies and improves the confidence in interpretation, interpolation and extrapolation of limited experimental data. Due to high dimensionality and extreme non-linearity of the materials science problems, very large datasets are typically required for conventional data-driven model development. The vital experimental data collection, particularly on microstructural phases, is very challenging, which makes it difficult to compile a high-quality database. Incorporation of the domain knowledge into the computational graph structure, initialization and optimization processes presents a viable mechanism for developing accurate models, with limited datasets. Furthermore, this study successfully utilized the approach to build the Deep Freeze Graph (DeepFreG) by mapping known causality relationships and by digitizing empirical domain knowledge for Latent Learning (LL), with specific applications in materials science.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Computational Fluid Dynamics Simulations to Support Efficiency Improvements in Aluminum Smelting Process

Smelting is broadly described as the extraction of a metal from its ore. In the United States, aluminum is commonly produced by smelting alumina in bauxite using the Hall-Héroult process. Optimization of equipment and processes in conventional smelting is crucial to enhancing process efficiency and productivity, is necessary for improving the techno-economic feasibility, which directly manifests as the growth of the American economy. To achieve optima, insightful data on the multiphysics phenomena that are inherent to the process must be obtained through physical investigation or high-fidelity numerical simulations. The resolution of relevant scales in time and space for smelting operations requires intensive, high-performance computing (HPC) simulations. Hostile operating conditions limit physical data acquisition to specific techniques; therefore, these data do not describe the multiscale interaction of simultaneous effects. Fortunately, in recent decades, significant advancements in computing hardware and computational methods have made the numerical resolution of such a complex process possible. In this study, a high-fidelity simulation of aluminum smelting was performed using an open-source tool, OpenFOAM, which analyzed many parameters characteristic to underlying phenomena. A multiphysics model based on the Eulerian-Eulerian multifluid approach was adopted. This model can resolve critical issues in the electrolytic smelting of aluminum, such as bubbling of carbon dioxide from the anode(s), magnetohydrodynamics from electromagnetic effects, ionic dissolution of the alumina in the electrolyte, and the evolution of thermal profiles. This study provides valuable connectivity for characteristic data that can direct the future designs of efficient smelters. A basic framework to model and simulate the smelting process using OpenFOAM is presented for user modification in keeping with process development. Of relevance to the flow field, a detailed investigation of vortices produced by bubble motion and electromagnetics is discussed, along with their impact on the evolution of thermal profiles. The predictions show small-scale vortices in the clearance between the anode and cathode caused by magnetic forces. Predictions also indicate relatively large-scale vortices in the inter-anode space resulting from carbon dioxide rising through the electrolytic flow field. The formation of vortices at the edges of anodes was shown to direct alumina charged by the feeder to the bottom of the anodes, thus preventing the entrapment of gas bubbles in the periphery of the bottom of the anode. Symmetry was observed in the location of cold spots in the electrolytic mixture in the vicinity of the feeder. Cold spots were also observed in the clearance between the anode and cathode due to the flow’s transmission of unconverted alumina to this region.

36 MATERIALS SCIENCE↗