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 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Transferable Reinforcement Learning for Smart Homes: Preprint

To harness the great amount of untapped resources at the demand side, smart home technology plays a vital role in solving the "last mile" problem in smart grid. Reinforcement learning (RL), which has demonstrated an outstanding performance in solving many sequential decision-making problems, can be a great candidate to be used in smart home control. For instance, many studies have started investigating the load scheduling problem under dynamic pricing scheme. Based on those, this study aims at providing an affordable solution to encourage a higher smart home adoption rate. Specifically, we investigate combining transfer learning (TL) with RL to reduce the training cost of an optimal RL control policy. Given an optimal policy for a benchmark home, TL can jump-start the RL training of a policy for a new home, which has different appliances and user preferences. Simulation results show that by leveraging TL, RL training converges faster and requires much less computing time for new homes that are similar to the benchmark home. In all, this study proposes a cost-effective approach for training RL control policies for homes at scale, which ultimately reduces the controller's implementation costs, increases the adoption rate of RL controllers, and makes more homes grid-interactive.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION,↗
DOE OSTI2021

Characterizing the acceleration time of laser-driven ion acceleration with data-informed neural networks

Peak ion energy is an important figure-of-merit in short-pulse, laser-driven ion acceleration and is dependent on an associated acceleration time. Standard metrics for these quantities depend on analytical results such as the self-similar fluid model or empirical models based on relatively small experimental and simulation datasets. In this work we attempt to use a data-informed neural network (NN) as a surrogate model for a large ensemble of PIC simulations to investigate an effective acceleration time. We explore the application of a stacked convolutional and recurrent NN architecture for improved regression by incorporating the time dependencies of the data into the training process. Of particular note is how pretraining a network on lower fidelity data, e.g. 1D analytical results, greatly improves the network's ability to learn more complex, higher fidelity data. Finally, the dependency of the acceleration time on various laser and plasma parameters is explored.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

An encoder–decoder LSTM-based EMPC framework applied to a building HVAC system

Numerous studies have demonstrated the benefit of economic model predictive control (EMPC) applied to building heating, ventilation, and air conditioning (HVAC) systems. However, the construction and training of predictive models for building HVAC systems are widely recognized as a key technological barrier preventing large-scale adoption of EMPC for buildings. In this work, an encoder–decoder long short-term memory-based EMPC framework is developed. The key advantage of the approach is that a model may be automatically generated from a list of inputs and outputs. From the definition of inputs and outputs, the constructed model may be trained and automatically embedded into the EMPC framework for real-time estimation and control. The overall end-to-end EMPC framework from model training to on-line estimation and control are described. To this end, the encoder–decoder model provides a natural framework for state estimation (encoder), which is required to provide an initial condition for the predictive model of EMPC (decoder). Closed-loop simulations using EnergyPlus are performed to demonstrate the approach. The simulated closed-loop system consists of a building zone from a multi-zone building, which is served by an air handling unit-variable air volume HVAC system. For the HVAC example considered, the trained encoder–decoder model can predict the indoor air temperature and HVAC sensible cooling rate of a building zone over a two-day horizon with high accuracy. Overall, we find that considering a time-of-use electric rate structure, the EMPC, which manipulates the zone temperature setpoint, can reduce the HVAC power consumption cost relative to keeping the zone temperature setpoint at its maximum value (i.e., minimum energy approach).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

PPINN: Parareal physics-informed neural network for time-dependent PDEs

Physics-informed neural networks (PINNs) encode physical conservation laws and prior physical knowledge into the neural networks, ensuring the correct physics is represented accurately while alleviating the need for supervised learning to a great degree. While effective for relatively short-term time integration, when long time integration of the time-dependent PDEs is sought, the time–space domain may become arbitrarily large and hence training of the neural network may become prohibitively expensive. To this end, we develop a parareal physics-informed neural network (PPINN), hence decomposing a long-time problem into many independent short-time problems supervised by an inexpensive/fast coarse-grained (CG) solver. In particular, the serial CG solver is designed to provide approximate predictions of the solution at discrete times, while initiate many fine PINNs simultaneously to correct the solution iteratively. There is a two-fold benefit from training PINNs with small-data sets rather than working on a large-data set directly, i.e., training of individual PINNs with small-data is much faster, while training the fine PINNs can be readily parallelized. Consequently, compared to the original PINN approach, the proposed PPINN approach may achieve a significant speed-up for long-time integration of PDEs, assuming that the CG solver is fast and can provide reasonable predictions of the solution, hence aiding the PPINN solution to converge in just a few iterations. To investigate the PPINN performance on solving time-dependent PDEs, we first apply the PPINN to solve the Burgers equation, and subsequently we apply the PPINN to solve a two-dimensional nonlinear diffusion–reaction equation. Furthermore, our results demonstrate that PPINNs converge in a few iterations with significant speed-ups proportional to the number of time-subdomains employed.

42 ENGINEERING↗
DOE OSTI2025

Fast and Accurate Pixel Calibration of Tof Neutron Diffractometers with Machine Learning

At a spallation neutron source, neutron pulses of varying energies are generated, and the detection of neutrons by instrument detectors is recorded as time-of-flight from the emission of the neutron pulse to its arrival at specific detector pixels with high time resolution. The flight path of neutrons from the moderator to the sample and then to the detector must be precisely calibrated at the detector-pixel level using standard powders, so the neutron events from all pixels can be time-focused to produce high-resolution diffraction patterns. Modern time-of-flight neutron diffractometers at spallation neutron sources are equipped with two-dimensional detectors with millimeter-scale pixelations. The number of pixels in a diffraction instrument can reach millions, which makes a single-pixel-level calibration process time-consuming or even impossible with conventional refinement or fitting approaches. Here we present a machine-learning-aided calibration process using a train-and-predict approach, in which machine learning models are trained on the relationship between an individual pixel time-of-flight diffraction pattern and its diffraction constant. These models use a portion of the available pixels for training, and a good model then predicts the diffraction constants precisely and rapidly for large sets of pixel diffraction patterns.

detector pixel calibration↗
DOE OSTI2025

Online thermal profile prediction for large format additive manufacturing: A hybrid CNN-LSTM based approach

Large format additive manufacturing (LFAM) is an advanced 3D printing technique that efficiently fabricates large-scale components through a layer-by-layer extrusion and deposition process. Accurate surface layer temperature monitoring is essential to prevent manufacturing failures and ensure final product quality. Traditional physics-based offline approaches for simulating thermal behavior are often inefficient and complex, posing challenges on real-time, in-situ monitoring. Here, to address this, we propose a data-driven hybrid CNN-LSTM model to predict sequential thermal images of arbitrary length using real-time infrared thermal imaging. In this approach, a Convolutional Neural Networks (CNN) is trained offline to capture spatial features, reduce dimensional complexity, and enhance time efficiency, while a stacked Long Short-Term Memory (LSTM) is applied online to capture temporal information for improved prediction of future thermal behavior in subsequent printing layers. Model performance is evaluated using MSE, SSIM, and PSNR metrics and is benchmarked against stacked LSTM and convolutional LSTM models, demonstrating superior accuracy and applicability. Additionally, to mitigate noise from moving extruders and gantry backgrounds in thermal images, a fine-tuned semantic segmentation model is implemented offline to extract printing geometry, enabling precise temperature tracking along the tool path for further thermal analysis. The frameworks developed in this study significantly advance temperature monitoring, thermal analysis, and in-situ manufacturing control for LFAM, bridging the gap between theoretical modeling and practical application.

Geometry extraction↗
DOE OSTI2026

Hierarchical semi-Markov models with duration-aware dynamics for activity sequences

Residential electricity demand at granular scales is driven by what people do and for how long. Accurately forecasting this demand for applications like microgrid management and demand response therefore requires generative models for activities that can produce realistic daily activity sequences, capturing both the timing and duration of human behavior. This paper develops a generative model of human activity sequences using nationally representative time-use diaries at a 10-min resolution. We use this model to quantify which demographic factors are most critical for improving predictive performance. We propose a hierarchical semi-Markov framework that addresses two key modeling challenges. First, a time-inhomogeneous Markov router learns the patterns of “which activity comes next.” Second, a semi-Markov hazard component explicitly models activity durations, capturing “how long” activities realistically last. To ensure statistical stability when data are sparse, the model pools information across related demographic groups and time blocks. The entire framework is trained and evaluated using survey design weights to ensure our findings are representative of the U.S. population. On a held-out test set, we demonstrate that explicitly modeling durations with the hazard component provides a substantial and statistically significant improvement over purely Markovian models. Furthermore, our analysis reveals a clear hierarchy of demographic factors: Sex, Day-Type, and Household Size provide the largest predictive gains, while Region and Season, though important for energy calculations, contribute little to predicting the activity sequence itself. The result is an interpretable and robust generator of synthetic activity traces, providing a high-fidelity foundation for downstream energy systems modeling.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Dynamics of Aqueous Electrolyte Solutions: Challenges for Simulations

This Perspective article focuses on recent simulation work on the dynamics of aqueous electrolytes. It is well-established that full-charge, nonpolarizable models for water and ions generally predict solution dynamics that are too slow in comparison to experiments. Models with reduced (scaled) charges do better for solution diffusivities and viscosities but encounter issues describing other dynamic phenomena such as nucleation rates of crystals from solution. Polarizable models show promise, especially when appropriately parametrized, but may still miss important physical effects such as charge transfer. First-principles calculations are starting to emerge for these properties that are in principle able to capture polarization, charge transfer, and chemical transformations in solution. Finally, while direct ab initio simulations are still too slow for simulations of large systems over long time scales, machine-learning models trained on appropriate first-principles data show significant promise for accurate and transferable modeling of electrolyte solution dynamics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Online energy consumption forecast for battery electric buses using a learning-free algebraic method

Accurately predicting the energy consumption plays a vital role in battery electric buses (BEBs) route planning and deployment. Based on the algebraic derivative estimation, we present a novel method to forecast the energy consumption in real time. In contrast to the mainstream machine-learning-based methods, the proposed method does not require access to the historical energy consumption data. It eliminates the time-consuming and computationally expensive offline training. Consequently, its prediction performance is not constrained by the quantity and quality of the training data. Moreover, the method can swiftly adapt to new situations not included in the previous driving cycles, which makes it especially suitable for emerging transport modes, e.g., on-demand transit services. In addition, its online execution only involves algebraic calculations, yielding superior calculation efficiency. Using real-world data, we comprehensively compare the performance of the proposed learning-free algebraic method with multiple representative machine-learning-based methods. Finally, the advantages and limitations of the proposed method are discussed in detail.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2023

DIII-D's role as a national user facility in enabling the commercialization of fusion energy

The path to fusion in the United States requires partnership between public and private sector. While the private sector provides the vigor to take some of the major steps necessary, there is a depth of expertise and capability in the public sector that is vital to resolving feasible approaches. As an open national user facility, DIII-D provides a crucial testbed to develop the required new technologies and approaches in relevant conditions. It has unparalleled potential to meet this challenge, thanks to its extreme flexibility and world leading diagnostics. This provides a basis to rapidly develop solutions that project to future reactors with confidence. The program has thus been redeveloped to enable public and private sector engagement and testing of new concepts. A new technology program has been launched to resolve plasma interacting technologies. With modest heating upgrades, the facility can confront the crucial “Integrated Tokamak Exhaust and Performance” gap, to resolve core, exhaust and technology solutions together. The device is also being redeveloped as a training facility, with dedicated student run time, a mentorship program, and open access to all opportunity roles, part of wider efforts to diversify and open pathways through inclusion, access, and equity. This exciting agenda is enabling scientists and technology researchers to pioneer the solutions needed for a Fusion Pilot Plant (FPP) and ITER this decade. As a national user facility, DIII D has singular potential to provide the tools, teams, and insight necessary, to do its part in moving the United States rapidly toward the commercialization of fusion energy.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

KilonovaNet : Surrogate models of kilonova spectra with conditional variational autoencoders

ABSTRACT Detailed radiative transfer simulations of kilonova spectra play an essential role in multimessenger astrophysics. Using the simulation results in parameter inference studies requires building a surrogate model from the simulation outputs to use in algorithms requiring sampling. In this work, we present kilonovanet, an implementation of conditional variational autoencoders (cVAEs) for the construction of surrogate models of kilonova spectra. This method can be trained on spectra directly, removing overhead time of pre-processing spectra, and greatly speeds up parameter inference time. We build surrogate models of three state-of-the-art kilonova simulation data sets and present in-depth surrogate error evaluation methods, which can in general be applied to any surrogate construction method. By creating synthetic photometric observations from the spectral surrogate, we perform parameter inference for the observed light-curve data of GW170817 and compare the results with previous analyses. Given the speed with which kilonovanet performs during parameter inference, it will serve as a useful tool in future gravitational wave observing runs to quickly analyse potential kilonova candidates.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

DQ Admittance Model Extraction for IBRs via Gaussian Pulse Excitation

While $dq$ admittance models have shown to be very useful for stability analysis, extracting admittance models of inverter-based resources (IBRs) from the electromagnetic transient (EMT) simulation environment using frequency scans takes time. In this letter, a new perturbation method based on Gaussian pulses in combination with the system identification algorithms shows great promise for parametric $dq$ admittance model extraction. We present the $dq$ admittance model extracting method for a type-4 wind turbine. Challenges in implementing Gaussian pulse excitation are also pointed out. In conclusion, the extracted $dq$ admittance model via the new method shows to have a high matching degree with the measurements obtained from frequency scans.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Source Authentication of Distribution Synchrophasors for Cybersecurity of Microgrids

This letter proposes a hybrid approach combining Self-Adaptive Mathematical Morphology (SAMM) and Time-Frequency (TF) techniques to authenticate the source information of Distribution Synchrophasors (DS) within near-range locations. The SAMM can adaptively regulate the synchrophasors variations which are representatives of local environmental characteristics. Subsequently, TF mapping is employed to extract informative signatures from the regulated synchrophasors variation. Finally, Random Forest Classification (RFC) is used to correlate the extracted signatures with the source information based on the derived TF mapping. Experiment results using DS collected at multiple small geographical scales validated the proposed methodology.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Image transformers for classifying acute lymphoblastic leukemia

Cancer is the leading cause of death by disease in American children. Each year, nearly 16,000 children in the United States and over 300,000 children globally are diagnosed with cancer. Leukemia is a form of blood cancer that originates in the bone marrow and accounts for one-third of pediatric cancers. This disease occurs when the bone marrow contains 20% or more immature white blood cell blasts. Acute lymphoblastic leukemia is the most prevalent leukemia type found in children, with half of all annual cases in the U.S. diagnosed for subjects under 20 years of age. To diagnose acute lymphoblastic leukemia, pathologists often conduct a morphological bone marrow assessment. This assessment determines whether the immature white blood cell blasts in bone marrow display the correct morphological characteristics, such as size and appearance of nuclei. Pathologists also use immunophenotyping via multi-channel flow cytometry to test whether certain antigens are present on the surface of blast cells; the antigens are used to identify the cell lineage of acute lymphoblastic leukemia. These manual processes require well-trained personnel and medical professionals, thus being costly in time and expenses. Computerized decision support via machine learning can accelerate the diagnosis process and reduce the cost. Training a reliable classification model to distinguish between mature and immature white blood cells is essential to the decision support system. Here, we adopted the Vision Transformer model to classify white blood cells. The Vision Transformer achieved superb classification performance compared to state-of-the-art convolutional neural networks while requiring less computational resources for training. Additionally, the latent self-attention architecture provided attention maps for a given image, providing clues as to which portion(s) of the image were significant in decision-making. We applied the Vision Transformer model and a convolutional neural network model to an acute lymphoblastic leukemia classification dataset of 12,528 samples and achieved accuracies of 88.4% and 86.2%.

Cho, Priscilla↗
DOE OSTI2024

The military gear microbiome: risk factors surrounding the warfighter

ABSTRACT Combat extremity wounds are highly susceptible to contamination from surrounding environmental material. This bioburden could be partially transferred from materials in immediate proximity to the wound, including fragments of the uniform and gear. However, the assessment of the microbial bioburden present on military gear during operational conditions of deployment or training is relatively unexplored. Opportunistic pathogens that can survive on gear represent risk factors for infection following injury, especially following combat blasts, where fibers and other materials are embedded in wounded tissue. We utilized 16S rRNA sequencing to assess the microbiome composition of different military gear types (boot, trouser, coat, and canteen) from two operational environments (training in Hawai’i and deployed in Indonesia) across time (days 0 and 14). We found that microbiome diversity, stability, and composition were dependent on gear type, training location, and sampling timepoint. At day 14, species diversity was significantly higher in Hawai’i samples compared to Indonesia samples for boot, coat, and trouser swabs. In addition, we observed the presence of potential microbial risk factors, as opportunistic pathogenic species, such as Acinetobacter , Pseudomonas, and Staphylococcus , were found to be present in all sample types and in both study sites. These study outcomes will be used to guide the design of antimicrobial materials and uniforms and for infection control efforts following combat blasts and other injuries, thereby improving treatment guidance during military training and deployment. IMPORTANCE Combat extremity wounds are vulnerable to contamination from environments of proximity to the warfighter, leading to potential detrimental outcomes such as infection and delayed wound healing. Therefore, microbial surveillance of such environments is necessary to aid the advancement of military safety and preparedness through clinical diagnostics, treatment protocols, and uniform material design.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Improving Fission Products at CARIBU: Near Field Detection (Q3/FY21 Quarterly Progress Report)

The overview of our project as well as most recent results have been presented at the NSARD review in April, and more recently during the WoNDRAM workshop. We have been dealing with recent personnel changes in the group. Miguel Bencomo, who has worked with us on this project as a postdoc at LLNL since 2019, will be terminating his appointment within the next two weeks to take a full-time appointment with Raytheon. We continue training our new team member Dan Hoff to take over data analysis from the last experiment we performed, as well as prepare for upcoming measurements. Additionally, we are working with a summer student, John Wilkinson, who is training to perform GEANT4 simulations of beta detector this summer.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Interlaminar Fracture Toughness Testing of Nb3Sn Insulation Systems

Epoxy cracking has been the main suspected contributor to training in Nb3Sn magnets for some time, as it leads to energy release and magnet quenching. Cracking in a superconducting composite can occur from several modes, and the likelihood of these modes is not well understood. Failure has been observed between insulation systems and the superconducting cable itself rather than within the cable or insulation. To target the behavior at the interface, samples have been fabricated and tested for mode I fracture toughness in an adapted version of ASTM D5528. This work seeks to better characterize the fracture toughness of this interface to better understand how to model and design insulation systems.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Demonstrate FARM supervisory capabilities for a thermal energy storage problem for the DETAIL facility: IES Simulation Ecosystem Control System Development

The goal of the power dispatch problem for an Integrated Energy System (IES) is to adjust the power output and the heat flow of each component to maximize the profitability of the whole unit. Facilities that can integrate real-time digital signals, mock nuclear power, thermal energy storage and industrial heat use via high-temperature electrolysis were constructed at INL to support the research activities. The Dynamic Energy Technology and Integration Laboratory (DETAIL) houses the Microreactor Agile Non-nuclear Experimental Test Bed (MAGNET) and the Thermal Energy Distribution System (TEDS). In this report, the hierarchical control system architecture proposed in June 2023 milestone for the flexible operation of DETAIL facility is finalized and demonstrated. A brief description of the components and the corresponding Dymola models from the HYRBID repository is first provided. Then, the current control strategy is presented. In particular, the approach for generating the set-point trajectories to be fed to the PI controllers is analyzed, and its limits were identified. To preserve safe operation over both long-time and real-time horizons, the integration of a Supervisory Control layer embedding a modified version of FARM (Feasible Actuator Range Modifier) module is proposed. FARM is a component of the RAVEN-based FORCE framework designed to support HERON module at optimizing the operation of IES units. The proposed control system for DETAIL foresees FARM to be applied twice, i.e., the original version (“FARM-Validator”) aiding the solution of the power dispatch problem, and a modified version (“FARM-Supervisory”) coordinating the PID controllers. Despite the kernel of the two modules is the same, their tasks are quite different. The former intervenes at the beginning of each hour to prevent constraint violations over long time periods, the latter addresses real-time control tasks and monitors the response of constrained variables at a much finer time resolution. A tentative procedure for training the embedded Digital Twins with the experimental data is also proposed. Finally, the capabilities of the designed architecture and the impact of the added Supervisory Control layer are demonstrated by simulating a representative power dispatch scenario.

25 ENERGY STORAGE↗