Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Time”

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 1,153 records · Page 64
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Fusion RF Modeling Machine Learning (FusionML_RF) v1.0

FusionML_RF consists of multiple codes and trained machine learning (ML) models that perform low-cost output modeling from the Genray-CQL3D. Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. For example, completing a single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time. On the other hand, these ML models achieve ~ms of inference time with high accuracy across the input parameter space. This software collection consists of multiple components. (1) codes that use ML methods and precomputed Genray-CQL3D simulation output to build regression models that enable approximate computations of Genray-CLQ3D outputs from arbitrary but physically meaningful input parameters (surrogate modeling); (2) three trained models created by the team, using a database of 16,000+ GENRAY/CQL3D simulations, to study the performance of ML models for surrogate modeling; (3) codes that load the trained models and simulation data, and then compute mean squared error between the models' predictions and the ground truth of simulation output data. This collection is being made available in conjunction with a scientific publication about the work to promote reusability and provide an artifact of the scientific work.

Bai, Zhe↗
DOE OSTI2022

Deep Learning-Assisted Real-Time Forward Modeling of Electromagnetic Logging in Complex Formations

Higher dimensional (i.e., 2-D and 3-D) modeling is indispensable to correctly evaluate the responses of electromagnetic logging tools in complex formation environments. However, limited by the high computational cost of rigorous modeling such as finite difference method and the finite element method, the real-time applications in the well logging industry primarily rely on the 1-D forward solver, which would result in erroneous formation evaluation for complex scenarios. As a result, aiming at realizing fast modeling for electromagnetic logging tools in complex formations, this paper proposes a general framework assisted by deep neural networks (DNNs). The framework consists of three modules: earth model classification, parameter extraction, and surrogate construction. Separate DNNs are trained and tested for different modules. The accuracy and efficiency of the DNN assisted fast modeling are validated by several experiments. Here, this study finds that the fast modeling assisted by DNNs is able to calculate the tool responses and reconstruct the subsurface formations in real-time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Statistical learning for predicting density–matrix-based electron dynamics

In this study, we consider the problem of learning density-dependent molecular Hamiltonian matrices from time series of electron density matrices, all in the context of Hartree–Fock theory. Prior work developed a solution to this problem for small molecular systems with density and Hamiltonian matrices of size at most 6 × 6. Here, using a battery of techniques, we scale prior methods to larger molecular systems with, for example, 29 × 29 matrices. This includes systems that either have more electrons or are expressed in large basis sets such as 6-311++G**. Scaling the method to larger systems enhances its relevance for realistic applications in chemistry and physics. To achieve this scaling, we apply dimensionality reduction, ridge regression and analytic computation of Hessians. Through the combination of these techniques, we are able to learn Hamiltonians by minimizing an objective function that encodes local propagation error. Importantly, these learned Hamiltonians can then be used to predict electron dynamics for thousands of steps: When we use our learned Hamiltonians to numerically solve the time-dependent Hartree–Fock equation, we obtain predicted dynamics that are in close quantitative agreement with ground truth dynamics. This includes field-off trajectories similar to the training data and field-on trajectories outside of the training data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Component-wise reduced order model lattice-type structure design

Lattice-type structures can provide a combination of stiffness with light weight that is desirable in a variety of applications. Design optimization of these structures must rely on approximations of the governing physics to render solution of a mathematical model feasible. In this paper, we propose a topology optimization (TO) formulation that approximates the governing physics using component-wise reduced order modeling as introduced in Huynh et al. (2013); Eftang and Patera (2013), which can reduce solution time by multiple orders of magnitude over a full-order finite element model while providing a relative error in the solution of 1%. In addition, the offline training data set from such component-wise models is reusable, allowing its application to many design problems for only the cost of a single offline training phase, and the component-wise method is nearly embarrassingly parallel. We also show how the parameterization chosen in our optimization allows a simplification of the component-wise reduced order model (CWROM) not noted in previous literature, for further speedup of the optimization process. Furthermore, the sensitivity of the compliance with respect to the particular parameterization is derived solely at the component level. In numerical examples, we demonstrate a 1000x speedup over a full-order FEM model with relative error of 1% and show minimum compliance designs for two different cantilever beam examples, one smaller and one larger. Finally, error bounds for the displacement field, compliance, and compliance sensitivity of the CWROM are derived.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Exact enforcement of temporal continuity in sequential physics-informed neural networks

The use of deep learning methods in scientific computing represents a potential paradigm shift in engineering problem solving. One of the most prominent developments is Physics-Informed Neural Networks (PINNs), in which neural networks are trained to satisfy partial differential equations (PDEs). While this method shows promise, the standard version has been shown to struggle in accurately predicting the dynamic behavior of time-dependent problems. To address this challenge, methods have been proposed that decompose the time domain into multiple segments, employing a distinct neural network in each segment and directly incorporating continuity between them in the loss function of the minimization problem. In this work we introduce a method to exactly enforce continuity between successive time segments via a solution ansatz. This hard constrained sequential PINN (HCS-PINN) method is simple to implement and eliminates the need for any loss terms associated with temporal continuity. The method is tested for a number of benchmark problems involving both linear and non-linear PDEs. Examples include various first order time dependent problems in which traditional PINNs struggle, namely advection, Allen–Cahn, and Korteweg–de Vries equations. Furthermore, second and third order time-dependent problems are demonstrated via wave and Jerky dynamics examples, respectively. Notably, the Jerky dynamics problem is chaotic, making the problem especially sensitive to temporal accuracy. Finally, the numerical experiments conducted with the proposed method demonstrated superior convergence and accuracy over both traditional PINNs and the soft-constrained counterparts.

42 ENGINEERING↗
DOE OSTI2022

DNN-based policies for stochastic AC OPF

We report a prominent challenge to the safe and optimal operation of the modern power grid arises due to growing uncertainties in loads and renewables. Stochastic optimal power flow (SOPF) formulations provide a mechanism to handle these uncertainties by computing dispatch decisions and control policies that maintain feasibility under uncertainty. Most SOPF formulations consider simple control policies such as affine policies that are mathematically simple and resemble many policies used in current practice. Motivated by the efficacy of machine learning (ML) algorithms and the potential benefits of general control policies for cost and constraint enforcement, we put forth a deep neural network (DNN)-based policy that predicts the generator dispatch decisions in real time in response to uncertainty. The weights of the DNN are learnt using stochastic primal–dual updates that solve the SOPF without the need for prior generation of training labels and can explicitly account for the feasibility constraints in the SOPF. The advantages of the DNN policy over simpler policies and their efficacy in enforcing safety limits and producing near optimal solutions are demonstrated in the context of a chance constrained formulation on a number of test cases.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2026

Dynamics of argon metastables in Ar–CH 4 radio frequency capacitively-coupled plasma: real-time monitoring with neural network-augmented broadband optical emission spectroscopy

In moderate-pressure radio frequency (RF) capacitively coupled plasmas generated in argon–methane mixtures, the density of argon metastable atoms (Ar 1 s 5 ) exhibits a non-monotonic dependence on methane (CH 4 ) concentration. Laser-induced fluorescence (LIF) was used to measure and compare local Ar 1 s 5 densities in Ar and Ar–CH 4 plasmas at 2.6 Torr and RF powers of 17–117 W. The addition of 1% CH 4 increases the metastable density, and 2% CH 4 triggers a strong depletion by an order of magnitude, compared to 1% CH 4 case. This non-monotonic behavior demonstrates the sensitivity of metastable populations to small gas admixtures, which is critical for processes where metastables drive precursor dissociation. For real-time monitoring of metastable population, broadband optical emission spectroscopy (OES) is augmented with a feedforward neural network (NN) to predict Ar s1 5 densities from spectral features. When trained on LIF data, the NN replicates the absolute densities and the dynamic trends of Ar 1 s 5 density variation. The NN-augmented broadband OES approach can be used as a simple and cost-effective tool for tracking Ar metastables in Ar-rich plasmas, facilitating industrial-scale optimization.

Yatom, Shurik [Princeton Plasma Physics Laboratory↗
DOE OSTI2026

The macroevolution of filamentation morphology across the Saccharomycotina yeast subphylum

Saccharomycotina is a subphylum of ascomycete fungi with diverse asexual growth morphologies. Filamentous growth can comprise linear and branched budding cells that do not undergo cell separation, termed pseudohyphae, or tubular filaments with septa that perforate allowing movement of organelles, termed true hyphae. We integrated phenotypic, genomic, metabolic, and environmental data on isolation sources from 1051 species to examine the variation and evolutionary history of filamentation across Saccharomycotina and determine whether these data could predict filamentation types. We found that 63.37% of strains can form filaments; 6.56% true hyphae, 42.40% pseudohyphae, and 14.39% both true hyphae and pseudohyphae. The distributions of species that can produce true hyphae or filament were more strongly correlated with the yeast phylogeny than the distribution of species with pseudohyphae. Ancestral state reconstruction suggested that true hyphal and pseudohyphal morphologies evolved several times, that most yeast ancestors likely produced pseudohyphae or lacked filaments, and that the Saccharomycotina last common ancestor likely produced pseudohyphae but not true hyphae. Machine learning models trained on genomic and metabolic features predicted filament morphologies with ∼70% accuracy. Connecting the evolution of morphologies to their genomic, physiological, and ecological characteristics will enrich our understanding of how the diversity of lifestyles evolved in Saccharomycotina.

Saccharomycotina↗
DOE OSTI2026

Realizing the scientific program with polarized ion beams at the future BNL Electron Ion Collider

Polarized ion beams at the Electron Ion Collider (EIC) are essential to address some of the most important open questions at the twenty-first century frontiers of understanding of the fundamental structure of matter. Here, in this work, we summarize the science case and identify polarized 2 H, 3 He, 6 Li, and 7 Li ion beams as critical technology that will enable experiments which address the most important science. Furthermore, we discuss the required ion polarimetry and spin manipulation at the EIC. The current EIC accelerator design is presented. We identify a significant research and development effort across national and international laboratories and universities that is required over about a decade to realize the polarized ion beams and estimate (based on previous experience) that it will require about 20 full-time equivalent (FTE) over 10 years (or a total of about 200 FTE-years) of personnel, including graduate students, postdoctoral researchers, technicians, and engineers. Attracting, educating, and training a new generation of physicists in experimental spin techniques will be essential for the successful realization. Artificial intelligence and machine learning are seen as having significant potential for both acceleration of research and development and amplification of discovery in the optimal realization of this unique quantum technology on a cutting-edge collider. The research and development effort is synergistic with research in atomic physics and fusion energy science.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

Classification of Cloud Particle Imagery from Aircraft Platforms Using Convolutional Neural Networks

Abstract A vast amount of ice crystal imagery exists from a variety of field campaign initiatives that can be utilized for cloud microphysical research. Here, nine convolutional neural networks are used to classify particles into nine regimes on over 10 million images from the Cloud Particle Imager probe, including liquid and frozen states and particles with evidence of riming. A transfer learning approach proves that the Visual Geometry Group (VGG-16) network best classifies imagery with respect to multiple performance metrics. Classification accuracies on a validation dataset reach 97% and surpass traditional automated classification. Furthermore, after initial model training and preprocessing, 10 000 images can be classified in approximately 35 s using 20 central processing unit cores and two graphics processing units, which reaches real-time classification capabilities. Statistical analysis of the classified images indicates that a large portion (57%) of the dataset is unusable, meaning the images are too blurry or represent indistinguishable small fragments. In addition, 19% of the dataset is classified as liquid drops. After removal of fragments, blurry images, and cloud drops, 38% of the remaining ice particles are largely intersecting the image border (≥10% cutoff) and therefore are considered unusable because of the inability to properly classify and dimensionalize. After this filtering, an unprecedented database of 1 560 364 images across all campaigns is available for parameter extraction and bulk statistics on specific particle types in a wide variety of storm systems, which can act to improve the current state of microphysical parameterizations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Godiva Experiments for the Nuclear Criticality Safety Program (NCSP)

Godiva IV is a fast burst critical assembly constructed of approximately 65 kg of highly enriched uranium (HEU) fuel alloyed with 1.5 percent molybdenum for strength. Godiva is one of the last such critical assemblies in the United States, and can be used for studies of super-prompt critical behavior as well as irradiations and demonstrations. A demonstration of a Godiva burst is usually performed as a highlight of the hands-on portion of the Criticality Safety Training Classes taught at the National Criticality Experiment Research Center (NCERC). The Godiva burst is used to demonstrate the concept of super-prompt critical and the time-scale of a criticality accident. In addition, several NCSP projects have been conducted on Godiva IV over the past two years. One experiment focused on collecting data to support multiphysics simulations using Photo-Doppler Velocimetry (PDV) to measure surface movement and gamma detectors to measure the burst output as the burst develops from background to peak over ten orders of magnitude. Another experiment was performed to demonstrate the functionality of the Criticality Accident Alarm System (CAAS) system developed for installation in the Y-12 Uranium Processing Facility (UPF). The system must not only respond to a criticality event and alarm, but must also be shown to operate in a high dose environment.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

The Vault: National Security Then and Now

The employees at Los Alamos National Laboratory have always been the key to our mission success, dating all the way back to our inception in 1939 as Project Y. This was the secret Los Alamos Lab of the Manhattan Project charged with designing and producing the world’s first atomic weapons to help end World War II. Back then, prospective Lab employees received letters that directed them to an office at 109 E. Palace in Santa Fe, New Mexico. There, they were greeted by Dorothy McKibbin, secretary to Lab Director J. Robert Oppenheimer. Before anyone headed up the hill to begin work, Dorothy typed up the new employee’s personal information on what quickly became known as the McKibbin Card. Lab employees also had official badges, the black and white photos of which have become iconic over time. Today’s staff at the National Security Research Center, the Lab’s classified library, are just as vital as the Lab’s first workforce was. Our highly trained experts partner with researchers to solve global challenges.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Smart Methane Emission Detection System Development (Final Report)

Working with the Department of Energy's National Energy Technology Laboratory, Southwest Research Institute® (SwRI®) developed a system to identify methane leaks reliably, accurately, and autonomously at critical midstream sections of the natural gas distribution network in real-time for the purpose of mitigating methane emissions using Optical Gas Imaging (OGI) cameras. SwRI's Smart Leak Detection – Methane (SLED/M) adds a high degree of automation to the process of methane leak detection to minimize sources of human error, minimize response time to a leak event, and maximize midstream visibility. Furthermore, SwRI has been working towards integrating Quantitative OGI (QOGI) capabilities into this existing technology. By leveraging Deep Learning, SwRI now has the capability to estimate fugitive emission leak rates quickly and reliably, which allows operators to detect emissions, quantify leak rate, prioritize repairs, and validate the repairs in a single instrument. The next generation QOGI technology leverages the same cameras used in Leak Detection and Repair (LDAR) programs, with improvements in safety and speed for traditional quantification-based repairs, ultimately leading to less overhead cost for the operators. The goals for this research were to develop two types of models with the following goals: Run in real-time on the edge (≥ 12 Hz), Classification: Achieve less than 5% false positive detection, Classification: Achieve ≥ 95% methane plume detection rate, Regression: achieve ≤ 10 standard cubic feet per hour (scfh) prediction > 70% of the time. In order to achieve these results, multiple infrared (IR) and other sensors were investigated in tandem with the midwave IR (MWIR) OGI to provide additional information to train the underlying models. Information on atmospheric conditions including humidity, temperature, pressure, and solar radiation was provided by a weather station. Several machine learning and deep learning architectures and methods, including looking at quantized classification networks and regressions networks, were explored. As further data was collected, curated, and labeled, it allowed for more refined regressive networks to be adequately trained, leading to better insight into the true flow rates being observed. An important valuable deliverable of this research effort was the development of an advanced network which underwent multiple iterations capable of giving a continuous output. The current network has a predicted mean average percentage error (MAPE) of 12.3% just outside our target goal of 10.00%, but an accuracy of 97.78% at ±50 scfh, well within the overall goal for the Department of Energy (DOE) program. Upon closer inspection, it was observed that more than 10% of datapoints contributing to the MAPE predictions were the result of low flow rate predictions and are beyond the sensitivity of instrument measurement as a result of normal operational variation and noise.

03 NATURAL GAS↗
DOE OSTI2022

UF Industrial Assessment Center - Budget Periods 2017-2021. Final Report

This report summarizes the work performed at the University of Florida’s Industrial Assessment Center (UF-IAC) during the five budget periods (BPs) in the years 2017 through 2021 under DOE Award No. DE-EE0007707. The objective of the work is to perform industrial assessments to small- and medium-sized manufacturing facilities in the State of Florida and to train students in industrial energy management and in performing industrial assessments. Specific details about the activities of the UF-IAC (referred to as the Center) during that time can be found in the 20 quarterly reports that were submitted throughout the duration of the contract. The project start and end dates are September 1, 2016 and August 31, 2021, respectively. The project was granted a six-month no-cost extension till February 28, 2022, to accommodate unexpected delays due to the COVID-19 pandemic. This project was performed by the University of Florida (PI: Dr. SA Sherif). The scope of work includes six milestone whose description and outcomes are listed in the Statement of Project Objectives (SOPO).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Smart Methane Emission Detection System Development (Final Report)

Working with the Department of Energy’s National Energy Technology Laboratory, Southwest Research Institute® (SwRI®) developed a system to identify methane leaks reliably, accurately, and autonomously at critical midstream sections of the natural gas distribution network in real- time for the purpose of mitigating methane emissions using Optical Gas Imaging (OGI) cameras. SwRI’s Smart Leak Detection – Methane (SLED/M) adds a high degree of automation to the process of methane leak detection to minimize sources of human error, minimize response time to a leak event, and maximize midstream visibility. Furthermore, SwRI has been working towards integrating Quantitative OGI (QOGI) capabilities into this existing technology. By leveraging Deep Learning, SwRI now has the capability to estimate fugitive emission leak rates quickly and reliably, which allows operators to detect emissions, quantify leak rate, prioritize repairs, and validate the repairs in a single instrument. The next generation QOGI technology leverages the same cameras used in Leak Detection and Repair (LDAR) programs, with improvements in safety and speed for traditional quantification-based repairs, ultimately leading to less overhead cost for the operators. The goals for this research were to develop two types of models with the following goals: 1. Run in real-time on the edge (≥ 12 Hz) 2. Classification: Achieve less than 5% false positive detection 3. Classification: Achieve ≥ 95% methane plume detection rate 4. Regression: achieve ≤ 10 standard cubic feet per hour (scfh) prediction > 70% of the time In order to achieve these results, multiple infrared (IR) and other sensors were investigated in tandem with the midwave IR (MWIR) OGI to provide additional information to train the underlying models. Information on atmospheric conditions including humidity, temperature, pressure, and solar radiation was provided by a weather station. Several machine learning and deep learning architectures and methods, including looking at quantized classification networks and regressions networks, were explored. As further data was collected, curated, and labeled, it allowed for more refined regressive networks to be adequately trained, leading to better insight into the true flow rates being observed. An important valuable deliverable of this research effort was the development of an advanced network which underwent multiple iterations capable of giving a continuous output. The current network has a predicted mean average percentage error (MAPE) of 12.3% just outside our target goal of 10.00%, but an accuracy of 97.78% at ±50 scfh, well within the overall goal for the Department of Energy (DOE) program. Upon closer inspection, it was observed that more than 10% of datapoints contributing to the MAPE predictions were the result of low flow rate predictions and are beyond the sensitivity of instrument measurement as a result of normal operational variation and noise.

03 NATURAL GAS↗
DOE OSTI2024

From RNNs to Foundation Models: An Empirical Study on Commercial Building Energy Consumption

Accurate short-term energy consumption forecasting for commercial buildings is crucial for smart grid operations. While smart meters and deep learning models enable forecasting using past data from multiple buildings, data heterogeneity from diverse buildings can reduce model performance. The impact of increasing dataset heterogeneity in time series forecasting, while keeping size and model constant, is understudied. We tackle this issue using the ComStock dataset, which provides synthetic energy consumption data for U.S. commercial buildings. Two curated subsets, identical in size and region but differing in building type diversity, are used to assess the performance of various time series forecasting models, including finetuned open-source foundation models (FMs). The results show that dataset heterogeneity and model architecture have a greater impact on post-training forecasting performance than the parameter count. Moreover, despite the higher computational cost, finetuned FMs demonstrate competitive performance compared to base models trained from scratch.

commercial buildings↗
DOE OSTI2025

Exploring the Use of Large Immersive Display Systems in the Nuclear Industry

Large immersive display systems play a critical role in the nuclear industry by enabling advanced training, design reviews, scientific visualization, and safety simulations. These systems, such as CAVE and powerwalls, allow engineers and operators to interact with virtual nuclear environments in real-time, providing a deeper understanding of complex systems. Their ability to simulate real-world scenarios for testing and optimization in a safe, controlled environment ensures that operators and engineers can refine process, enhance safety protocols, and troubleshoot complex challenges. This article outlines key lessons learned from deploying these systems, practical insights into their applications, and considerations for future improvements, aiming to guide their broader adoption and effective use in the nuclear industry.

99 - GENERAL AND MISCELLANEOUS↗