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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Gaining Real-Time Water Leak Detection

Devens Reserve Forces Training Area is a United States Army Reserve (USAR) Installation that struggles with severe water leaks, often causing significant damage to the facility and requiring major renovation. Traditional water use is highly dependent on occupancy, so it can be difficult to benchmark a facility’s water use. It can be exceptionally difficult when occupancy is transient and/or varies. Pacific Northwest National Laboratory (PNNL) collaborated with Devens to implement real-time monitoring of their water consumption by utilizing the smart meter data from their existing 23 water meters. PNNL created a simple algorithm to calculate hourly water consumption and trigger an alert to be instantly emailed to Devens’ personnel when there appears to be a water leak in any building with a smart water meter. Here, this approach is expected to save hundreds of thousands of dollars in unnecessary water consumption costs and damages from leaks and was implemented with little-to-no costs or service disruptions. Next steps for this project include slow leak detection through nighttime monitoring and to extrapolate this water leak approach to the remainder 360 water meters on USAR’s Enterprise Building Control System so USAR sites across the country can be instantly notified of potential water leaks.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Efficient Training of Deep Neural Operator Networks via Randomized Sampling

Neural operators (NOs) employ deep neural networks to learn the mappings between infinitedimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex dynamics across various scientific and engineering applications. In this work, we introduce a random sampling technique to be adopted during the training of DeepONet, aimed at improving the generalization ability of the model, while significantly reducing the computational time. The proposed approach targets the trunk network of the DeepONet model that outputs the basis functions corresponding to the spatiotemporal locations of the bounded domain on which the physical system is defined. While constructing the loss function, DeepONet training traditionally considers a uniform grid of spatiotemporal points at which all the output functions are evaluated for each iteration. This approach leads to a larger batch size, resulting in poor generalization and increased memory demands, due to the limitations of the stochastic gradient descent (SGD) optimizer. The proposed random sampling over the inputs of the trunk net mitigates these challenges, improving generalization and reducing the memory requirements during training, resulting in significant computational gains. We validate our hypothesis through three benchmark examples, demonstrating substantial reductions in training time while achieving comparable or lower overall test errors relative to the traditional training approach. Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet, offering a promising avenue for improving the framework’s performance in modeling complex physical systems.

Karumuri, Sharmila [Department of Civil & Systems ↗
DOE OSTI2022

Accelerated Probabilistic Marching Cubes by Deep Learning for Time-Varying Scalar Ensembles

Visualizing the uncertainty of ensemble simulations is challenging due to the large size and multivariate and temporal features of en-semble data sets. One popular approach to studying the uncertainty of ensembles is analyzing the positional uncertainty of the level sets. Probabilistic marching cubes is a technique that performs Monte Carlo sampling of multivariate Gaussian noise distributions for positional uncertainty visualization of level sets. However, the technique suffers from high computational time, making interactive visualization and analysis impossible to achieve. This paper introduces a deep-learning-based approach to learning the level-set uncertainty for two-dimensional ensemble data with a multivariate Gaussian noise assumption. We train the model using the first few time steps from time-varying ensemble data in our workflow. We demonstrate that our trained model accurately infers uncertainty in level sets for new time steps and is up to 170X faster than that of the original probabilistic model with serial computation and 10X faster than that of the original parallel computation.

Han, Mengjiao↗
DOE OSTI2021

Performance Profile of Transformer Fine-Tuning in Multi-GPU Cloud Environments

The study presented here focuses on performance characteristics and trade-offs associated with running machine-learning tasks in multi-GPU environments on both on-site cloud computing resources and commercial cloud services (Azure). Specifically, this study examines these tradeoffs by examining the performance of training and fine-tuning of transformer-based deep-learning (DL) networks on clinical notes and data, a task of critical importance in the medical domain. To this end, we perform DL-related experiments on the widely deployed NVIDIA V100 GPUs and on the newer A100 GPUs connected via NVLink or PCIe. This study analyzes the execution time of major operations to train DL models and investigate popular options to optimize each of them. We examine and present the findings on the impacts that various operations (e.g. data loading into GPUs, training, fine-tuning), optimizations, and system configurations (single vs. multi-GPU, NVLink vs. PCIe) have on the overall training performance.

Begoli, Edmon↗
DOE OSTI2022

Fed-DeepONet: Stochastic Gradient-Based Federated Training of Deep Operator Networks

The Deep Operator Network (DeepONet) framework is a different class of neural network architecture that one trains to learn nonlinear operators, i.e., mappings between infinite-dimensional spaces. Traditionally, DeepONets are trained using a centralized strategy that requires transferring the training data to a centralized location. Such a strategy, however, limits our ability to secure data privacy or use high-performance distributed/parallel computing platforms. To alleviate such limitations, in this paper, we study the federated training of DeepONets for the first time. That is, we develop a framework, which we refer to as Fed-DeepONet, that allows multiple clients to train DeepONets collaboratively under the coordination of a centralized server. To achieve Fed-DeepONets, we propose an efficient stochastic gradient-based algorithm that enables the distributed optimization of the DeepONet parameters by averaging first-order estimates of the DeepONet loss gradient. Then, to accelerate the training convergence of Fed-DeepONets, we propose a moment-enhanced (i.e., adaptive) stochastic gradient-based strategy. Finally, we verify the performance of Fed-DeepONet by learning, for different configurations of the number of clients and fractions of available clients, (i) the solution operator of a gravity pendulum and (ii) the dynamic response of a parametric library of pendulums.

Moya, Christian↗
NASA NTRS1988

Real-time space system control with expert systems

Many aspects of space system operations involve continuous control of real time processes. These processes include electrical power system monitoring, prelaunch and ongoing propulsion system health and maintenance, environmental and life support systems, space suit checkout, onboard manufacturing, and vehicle servicing including satellites, shuttles, orbital maneuvering vehicles, orbital transfer vehicles and remote teleoperators. Traditionally, monitoring of these critical real time processes has been done by trained human experts monitoring telemetry data. However, the long duration of future space missions and the high cost of crew time in space creates a powerful economic incentive for the development of highly autonomous knowledge based expert control procedures for these space systems.

Leinweber, David↗
DOE OSTI2025

Artificial intelligence-based predictive modeling for imaging neutral particle analyzers on the DIII-D tokamak

The Imaging Neutral Particle Analyzer (INPA) at DIII-D is a diagnostic system used to accurately resolve the energy and spatial distributions of fast ions in fusion plasmas. A novel artificial intelligence (AI) technique named INPA-net is based on Reservoir Computing Networks and developed here to predict active and passive signals produced by charge-exchange reactions from injected and edge-cold neutrals, respectively, in magnetically confined fusion plasmas. This model is trained using a set of 21 time domain signals between 0 s to 3.35 s that includes injected beam and thermal plasma information, and 6444 real 2D experimental images of the INPA in 12 plasma discharges at DIII-D. The trained neural network is able to forecast experimental images in real-time. The model achieves an R-squared value of 0.91, which is higher than the 0.83 value achieved by a simple linear regression model. This improvement highlights the model's enhanced predictive accuracy for measured images from the validation set. This AI approach is valuable due to its rapid response times and potential for integration into real-time plasma control systems. A version of this model capable of generating syntehic images would be useful for the real-time monitoring of fast-ion transport. A comprehensive sensitivity study reveals that INPA-net maintains high performance even with variations in the input parameters, indicating the model's robustness and reliability. While developed for the INPA, the underlying architecture is adaptable and may be applied to various 2D imaging diagnostics in fusion research.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1992

Training evaluation final report

In the area of management training, 'evaluation' refers both to the specific evaluation instrument used to determine whether a training effort was considered effective, and to the procedures followed to evaluate specific training requests. This report recommends to evaluate new training requests in the same way new procurement or new projects are evaluated. This includes examining training requests from the perspective of KSC goals and objectives, and determining expected ROI of proposed training program (does training result in improved productivity, through savings of time, improved outputs, and/or personnel reduction?). To determine whether a specific training course is effective, a statement of what constitutes 'good performance' is required. The user (NOT the Training Branch) must define what is 'required level of performance'. This 'model' will be the basis for the design and development of an objective, performance-based, training evaluation instrument.

Sepulveda, Jose A.↗
DOE OSTI2023

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

Brewer, Wes↗
NASA NTRS1965

Human Tracking Performance in Uncoupled and Coupled Two-Axis Systems

This report presents tile results of an experimental and analytical study of human performance in uncoupled and coupled control systems. Human pilot performance in single and two-axis systems was mathematically modeled by linear second-order describing functions. Model parameters were determined using model matching techniques. Analysis of the models showed that the amplitude ratio and phase lead of the describing function increased with training indicating an increase in open loop bandwidth. The phase margin also decreased with training. Increasing the plant lag time constant resulted in an increase in the model lead time constant and a decrease in the zero frequency gain. No significant difference was found to exist in the normalized tracking error per axis between the two-axis tasks and the single-axis tasks. However tile model lead time constant was significantly greater in two-axis tracking. Manual tracking of two-axis systems with cross-coupling was studied experimentally and analytically. Approximate methods for modeling two-axis performance were developed and checked using a precise spectral analysis approach. Coupled and uncoupled, symmetrical and asymmetrical two-axis performance was compared. The results show that modeling of cross-coupled systems is feasible and that trained subjects are capable of decoupling the axes of some systems. A methodology study compared the identification performance of continuous, iterative, and extrapolation model matching techniques. An iterative technique employing sensitivity equations for the generation of influence coefficients was found to be the best technique due to its excellent identification accuracy and ease of implementation. Convergence in iterative techniques can be improved substantially by equalizing the parameter adjustment rates and limiting the maximum correction per iteration.

Todosiev, E. P.↗
DOE OSTI2025

Surrogate models to optimize plasma-assisted atomic layer deposition in high aspect ratio features

In this work, we explore surrogate models to optimize plasma enhanced atomic layer deposition (PEALD) in high aspect ratio features. In plasma-based processes such as PEALD and atomic layer etching (ALE), surface recombination can dominate the reactivity of plasma species with the surface, which can lead to unfeasibly long exposure times to achieve full conformality inside nanostructures like high aspect ratio vias. Using a synthetic dataset based on simulations of PEALD, we train artificial neural networks to predict saturation times based on cross section thickness data obtained for partially coated conditions. The results obtained show that just two experiments in undersaturated conditions contain enough information to predict saturation times within 10% of the ground truth. A surrogate model trained to determine whether surface recombination dominates the plasma–surface interactions in a PEALD process achieves 99% accuracy. This demonstrates that machine learning can provide a new pathway to accelerate the optimization of PEALD processes in areas such as microelectronics. Our approach can be easily extended to ALE and more complex structures.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2009

Using Decision Trees to Detect and Isolate Simulated Leaks in the J-2X Rocket Engine

The goal of this work was to use data-driven methods to automatically detect and isolate faults in the J-2X rocket engine. It was decided to use decision trees, since they tend to be easier to interpret than other data-driven methods. The decision tree algorithm automatically "learns" a decision tree by performing a search through the space of possible decision trees to find one that fits the training data. The particular decision tree algorithm used is known as C4.5. Simulated J-2X data from a high-fidelity simulator developed at Pratt & Whitney Rocketdyne and known as the Detailed Real-Time Model (DRTM) was used to "train" and test the decision tree. Fifty-six DRTM simulations were performed for this purpose, with different leak sizes, different leak locations, and different times of leak onset. To make the simulations as realistic as possible, they included simulated sensor noise, and included a gradual degradation in both fuel and oxidizer turbine efficiency. A decision tree was trained using 11 of these simulations, and tested using the remaining 45 simulations. In the training phase, the C4.5 algorithm was provided with labeled examples of data from nominal operation and data including leaks in each leak location. From the data, it "learned" a decision tree that can classify unseen data as having no leak or having a leak in one of the five leak locations. In the test phase, the decision tree produced very low false alarm rates and low missed detection rates on the unseen data. It had very good fault isolation rates for three of the five simulated leak locations, but it tended to confuse the remaining two locations, perhaps because a large leak at one of these two locations can look very similar to a small leak at the other location.

Schwabacher, Mark A.↗
NASA NTRS1988

Crew activities, science, and hazards of manned missions to Mars

The crew scientific and nonscientific activities that will occur at each stage of a mission to Mars are examined. Crew activities during the interplanetary flight phase will include simulations, maintenance and monitoring, communications, upgrading procedures and operations, solar activity monitoring, cross-training and sharpening of skills, physical conditioning, and free-time activities. Scientific activities will address human physiology, human psychology, sociology, astronomy, space environment effects, manufacturing, and space agriculture. Crew activities on the Martian surface will include exploration, construction, manufacturing, food production, maintenance and training, and free time. Studies of Martian geology and atmosphere, of the life forms that may exist there, and of the Martian moons will occur on the planet's surface. Crew activities and scientific studies that will occur in Mars orbit, and the hazards relevant to each stage of the mission, are also addressed.

Clark, Benton C.↗
DOE OSTI2024

Development of a machine learning model for polyethylene pyrolysis using a detailed reaction mechanism

Waste plastics have recently received significant attention as the issue of waste generation continues to increase. Thermal conversion processes, such as pyrolysis and gasification, are attractive potential technologies for utilizing waste plastics and reducing overall waste generation. Efficient utilization of plastics requires a detailed understanding of the conversion process such as pyrolysis and gasification. However, a mechanistic understanding of these processes lead to large and complex kinetic schemes that are not suited for large-scale and long-time simulation methods. Currently, most modeling approaches for pyrolysis and gasification rely on globally lumped, simplified kinetic schemes that provide results that are classified by their product type and not individual species, which limit the level of fidelity achieved via modeling. A machine learning (ML) model has been developed for the primary reactions of high-density polyethylene (HDPE) in an attempt to increase computational efficiency while still maintaining a high level of detail and accuracy. The ML model is trained on a detailed reaction mechanism containing 42 total species and 737 chemical reactions. A DeepONet branch and trunk architecture was adopted to train the model using time-steps relevant to computational fluid dynamics simulations. The ML used physics-informed loss functions to ensure mass conservation. The surrogate model has been deployed in simple MFiX CFD simulations, single particle and an experimental drop tube reactor, and has shown promising performance compared to the original scheme.

Houston, Ross↗
DOE OSTI2020

Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations

Here we propose a generalized space-time domain decomposition approach for the physics-informed neural networks (PINNs) to solve nonlinear partial differential equations (PDEs) on arbitrary complex-geometry domains. The proposed framework, named eXtended PINNs ( X P I N N s ), further pushes the boundaries of both PINNs as well as conservative PINNs (cPINNs), which is a recently proposed domain decomposition approach in the PINN framework tailored to conservation laws. Compared to PINN, the XPINN method has large representation and parallelization capacity due to the inherent property of deployment of multiple neural networks in the smaller subdomains. Unlike cPINN, XPINN can be extended to any type of PDEs. Moreover, the domain can be decomposed in any arbitrary way (in space and time), which is not possible in cPINN. Thus, XPINN offers both space and time parallelization, thereby reducing the training cost more effectively. In each subdomain, a separate neural network is employed with optimally selected hyperparameters, e.g., depth/width of the network, number and location of residual points, activation function, optimization method, etc. A deep network can be employed in a subdomain with complex solution, whereas a shallow neural network can be used in a subdomain with relatively simple and smooth solutions. We demonstrate the versatility of XPINN by solving both forward and inverse PDE problems, ranging from one-dimensional to three-dimensional problems, from time-dependent to time-independent problems, and from continuous to discontinuous problems, which clearly shows that the XPINN method is promising in many practical problems. The proposed XPINN method is the generalization of PINN and cPINN methods, both in terms of applicability as well as domain decomposition approach, which efficiently lends itself to parallelized computation. The XPINN code is available on h t t p s : / / g i t h u b . c o m / A m e y a J a g t a p / X P I N N s .

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2009

Shallow-Water Nitrox Diving, the NASA Experience

NASA s Neutral Buoyancy Laboratory (NBL) contains a 6.2 million gallon, 12-meter deep pool where astronauts prepare for space missions involving space walks (extravehicular activity EVA). Training is conducted in a space suit (extravehicular mobility unit EMU) pressurized to 4.0 - 4.3 PSI for up to 6.5 hours while breathing a 46% NITROX mix. Since the facility opened in 1997, over 30,000 hours of suited training has been completed with no occurrence of decompression sickness (DCS) or oxygen toxicity. This study examines the last 5 years of astronaut suited training runs. All suited runs are computer monitored and data is recorded in the Environmental Control System (ECS) database. Astronaut training runs from 2004 - 2008 were reviewed and specific data including total run time, maximum depth and average depth were analyzed. One hundred twenty seven astronauts and cosmonauts completed 2,231 training runs totaling 12,880 exposure hours. Data was available for 96% of the runs. It was revealed that the suit configuration produces a maximum equivalent air depth of 7 meters, essentially eliminating the risk of DCS. Based on average run depth and time, approximately 17% of the training runs exceeded the NOAA oxygen maximum single exposure limits, with no resulting oxygen toxicity. The NBL suited training protocols are safe and time tested. Consideration should be given to reevaluate the NOAA oxygen exposure limits for PO2 levels at or below 1 ATA.

Fitzpatrick, Daniel T.↗
DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

MMMnet: A Neural Network Surrogate for Real-Time Transport Prediction Based on the Updated Multi-Mode Model

The Multi-Mode Model (MMM) is a physics-based anomalous transport model integrated into TRANSP for predicting electron and ion thermal transport, electron and impurity particle transport, and toroidal and poloidal momentum transport. While MMM provides valuable predictive capabilities, its computational cost, although manageable for standard simulations, is too high for real-time control applications. MMMnet, a neural network-based surrogate model, is developed to address this challenge by significantly reducing computation time while maintaining high accuracy. Trained on TRANSP simulations of DIII-D discharges, MMMnet incorporates an updated version of MMM (9.0.10) with enhanced physics, including isotopic effects, plasma shaping via effective magnetic shear, unified correlation lengths for ion-scale modes, and a new physics-based model for the electromagnetic electron temperature gradient mode. A key advancement is MMMnet’s ability to predict all six transport coefficients, providing a comprehensive representation of plasma transport dynamics. MMMnet achieves a two-order-of-magnitude speed improvement while maintaining strong correlation with MMM diffusivities, making it well-suited for real-time tokamak control and scenario optimization.

DIII-D↗