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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS1991

Real Time Data System (RTDS)

Information is given in viewgraph form on the Real Time Data System (RTDS). The goals are to increase the quality of flight decision making, reduce and enhance flight controller training time, and serve as a near-operations technology test-bed. Information is given on the growth of RTDS; flight control disciplines; RTDS technology deployment in 1987-1989 and 1990-91; a functionality comparison of mainframes and workstations; and technology transfer activities.

Heindel, Troy A.↗
DOE OSTI2021

Noise Robustness and Experimental Demonstration of a Quantum Generative Adversarial Network for Continuous Distributions

Abstract The potential advantage of machine learning in quantum computers is a topic of intense discussion in the literature. Theoretical, numerical, and experimental explorations will most likely be required to understand its power. There have been different algorithms proposed to exploit the probabilistic nature of variational quantum circuits for generative modeling. In this paper, a hybrid architecture for quantum generative adversarial networks (QGANs) is employed and their robustness in the presence of noise is studied. A simple way of adding different types of noise to the quantum generator circuit is devised, and the noisy hybrid QGANs (HQGANs) are simulated numerically to learn continuous probability distributions, and to show that the performance of HQGANs remains unaffected. The effect of different parameters on the training time is also investigated to reduce the computational scaling of the algorithm and simplify its deployment on a quantum computer. The training on Rigetti's Aspen‐4‐2Q‐A quantum processing unit is then performed, and the results from the training are presented. The authors' results pave the way for experimental exploration of different quantum machine learning algorithms on noisy intermediate‐scale quantum devices.

Anand, Abhinav↗
DOE OSTI2021

Federated Quantum Machine Learning

Distributed training across several quantum computers could significantly improve the training time and if we could share the learned model, not the data, it could potentially improve the data privacy as the training would happen where the data is located. One of the potential schemes to achieve this property is the federated learning (FL), which consists of several clients or local nodes learning on their own data and a central node to aggregate the models collected from those local nodes. However, to the best of our knowledge, no work has been done in quantum machine learning (QML) in federation setting yet. In this work, we present the federated training on hybrid quantum-classical machine learning models although our framework could be generalized to pure quantum machine learning model. Specifically, we consider the quantum neural network (QNN) coupled with classical pre-trained convolutional model. Our distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training. It demonstrates a promising future research direction for scaling and privacy aspects.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Fault-Tolerant Deep Learning Cache with Hash Ring for Load Balancing in HPC Systems

Large-scale DL on HPC systems like Frontier and Summit uses distributed node-local caching to address scalability and performance challenges. However, as these systems grow more complex, the risk of node failures increases, and current caching approaches lack fault tolerance, jeopardizing large-scale training jobs. We analyzed six months of SLURM job logs from Frontier and found that over 30% of jobs failed after an average of 75 minutes. To address this, we propose fault-tolerance strategies that recache data lost from failed nodes using a hash ring technique for balanced data recaching in the distributed node-local caching, reducing reliance on the PFS. Our extensive evaluations on Frontier showed that the hash ring-based recaching approach reduced training time by approximately 25% compared to the approach that redirects I/O to the PFS after node failures and demonstrated effective load balancing of training data across nodes.

Lee, Seoyeong↗
DOE OSTI2025

Optimizing transmit field inhomogeneity of parallel RF transmit design in 7T MRI using deep learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) provides a higher signal-to-noise ratio and, thereby, higher spatial resolution. However, UHF MRI introduces challenges such as transmit radiofrequency (RF) field (B+1) inhomogeneities, leading to uneven flip angles and image intensity anomalies. These issues can significantly degrade imaging quality and its medical applications. This study addresses B+1 field homogeneity through a novel deep learning-based strategy. Traditional methods like Magnitude Least Squares (MLS) optimization have been effective but are time-consuming and dependent on the patient’s presence. Recent machine learning approaches, such as RF Shim Prediction by Iteratively Projected Ridge Regression and deep learning frameworks, have shown promise but face limitations like extensive training times and oversimplified architectures. We propose a two-step deep learning strategy. First, we obtain the desired reference RF shimming weights from multi-channel B+1 fields using random-initialized Adaptive Moment Estimation. Then, we employ Residual Networks (ResNets) to train a model that maps B+1 fields to target RF shimming outputs. Our approach does not rely on pre-calculated reference optimizations for the testing process and efficiently learns residual functions. Comparative studies with traditional MLS optimization demonstrate our method’s advantages in terms of speed and accuracy. The proposed strategy achieves a faster and more efficient RF shimming design, significantly improving imaging quality at UHF. This advancement holds potential for broader applications in medical imaging and diagnostics.

Lu, Zhengyi [Vanderbilt University]↗
DOE OSTI2022

WinnowML: Stable feature selection for maximizing prediction accuracy of time-based system modeling

Online deep learning (ODL) has become an important methodology for modeling time-based performance of computer systems. An open problem is the intelligent selection of features from raw workload traces of computer systems. The best methods are overly sensitive to noisy data, causing frequent feature changes and re-training. Using all available features inflates training time and introduces model artifacts if some features should have been dropped. We present WinnowML, a method for automatically determining the most relevant feature subset for a predictive time-series model. WinnowML combines existing feature ranking algorithms and a history of each feature's ranking to iteratively rank a feature set to lower prediction error and maximize long term relevance. From this ranked feature set, the most relevant and stable subset is selected to train a model. Experimentally, we show how WinnowML can lower a model's mean absolute relative error up to 42% on average compared to the closest performing approach. Additionally, we lower the fluctuation in feature ranking and selection up to 65%. We also demonstrate how to combine WinnowML and a model search tool to provide improvements in performance of up to 14.5% when compared to using all the feature available.

Bel, Oceane MS↗
NASA NTRSDate not supplied

Manual Crew Override of Vehicle Landings Following G-Transitions

BACKGROUND Manual control during exploration spaceflight consists of both planned automated supervisory control and unplanned crew override. This crew override capability is critical to enable overall mission success during landing contingencies. However, the introduction of manual override capabilities must be implemented to enable crews to mitigate risks introduced by human error. Adaptive changes in the sensorimotor system can manifest during g-transitions as spatial disorientation. While training and landing aids enable successful landing through disorientation, these adaptive changes may increase cognitive demand that needs to be accounted for in the manual control strategy. It is important to characterize these effects as soon as possible following the G-transition to develop appropriate countermeasures. METHODS The following study seeks to inform the risk associated with altered sensorimotor and vestibular function impacting critical mission tasks. We aim to characterize the effects of short and long-duration weightlessness on manual control following G-transitions using simulated lunar landing on a six-degree-of-freedom (6DOF) motion base, a fixed base simulation, and a supervisory control tablet task. The primary goal is to understand the impact of spaceflight on crew ability to perform manual crew override and supervisory control. This aim will be assessed by comparing pre- versus postflight simulation performance in crewmembers assigned to either short duration (< 30 day) or long duration (~6- month) missions to the International Space Station (ISS). We hypothesize there will be postflight increases in the percent time that pilots are outside of the acceptable range for recommended vehicle state parameters and the reaction time for secondary cognitive tasks. Ground-based control subjects, who are demographically matched to the crew considering age (± 5 years) and gender, will undergo the same testing schedule as the crew to examine the effects of flight phase independent of microgravity exposure. The second aim is to examine how adaptive changes in vestibular and cognitive function relate to changes in manual crew override proficiency. Crew performance for a sensorimotor perceptual test battery will evaluate motion perception tracking, roll nulling, and/or vection sensitivity using the 6DOF motion base. We hypothesize that a higher severity of vestibular alterations will be associated with increased percent time outside of guidance limits. Motion sickness severity and sleepiness will also be evaluated. To determine the impact of “just-in-time” training, the third aim seeks to compare performance during on-board lunar landing tasks conducted late in-flight to early postflight. We hypothesize that proficiency on the “just-in-time” laptop trainer late in mission will be positively correlated with early postflight proficiency on the same task. The final aim will establish assessments of performance, training protocols, and the learning progression in a ground-control cohort of first-time users. RESULTS The assessment of the learning progression associated with the piloting task on the motion base system with thirty ground subjects will be reported. Learning curves will be established across four distinct sessions and within session considering trial difficulty. The difficulty of the landing task can be modulated with the landing divert distance and cross or downrange difficulty. Results may include changes in performance across multiple trials of a multi-attribute lunar tablet supervisory control task. Preliminary investigations of eighteen subjects who completed vestibular threshold and motion perception tasks offer expected performance ranges for upcoming preflight crew evaluations. The results yielded an average roll threshold of 0.46 ± 0.30 deg/s and an average roll nulling root mean square error performance of 2.52 ± 0.52 deg/s. RELEVANCE This project will deliver an operational demonstration of crew monitoring capability following spaceflight and identify potential deficits that may require remediation. Comparison of individual vestibular and cognitive changes with crew performance will help better characterize the manual control risks associated with sensorimotor alterations. Ground testing will evaluate learning progression, refine training protocols, and serve as a control cohort for comparisons to crew performance. ACKNOWLEDGEMENTS: The authors acknowledge contributions from Draper, the Dynamic Skills Trainer (DST) Lab, and the Software, Robotics, and Simulation Division toward the development of the lunar landing simulation platforms. This project is funded by the Human Health Countermeasures Element.

Hannah M. Weiss↗
DOE OSTI2021

A practical extension of the recursive multi-fidelity model for the emulation of hole closure experiments

We report in regimes of high strain rate, the strength of materials often cannot be measured directly in experiments. Instead, the strength is inferred based on an experimental observable, such as a change in shape, that is matched by simulations supported by a known strength model. In hole closure experiments, the rate and degree to which a central hole in a plate of material closes during a dynamic loading event are used to infer material strength parameters. Due to the complexity of the experiment, many computationally expensive, three-dimensional simulations are necessary to train an emulator for calibration or other analyses. These simulations can be run at multiple grid resolutions, where dense grids are slower but more accurate. In an effort to reduce the computational cost, a combination of simulations with different resolutions can be combined to develop an accurate emulator within a limited training time. We explore the novel design and construction of an appropriate functional recursive multi-fidelity emulator of a strength model for tantalum in hole closure experiments that can be applied to arbitrarily large training data. Hence, by formulating a multi-fidelity model to employ low-fidelity simulations, we were able to reduce the error of our emulator by approximately 81% with only an approximately 1.6% increase in computing resource utilization.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Separable physics-informed DeepONet: Breaking the curse of dimensionality in physics-informed machine learning

The deep operator network (DeepONet) has shown remarkable potential in solving partial differential equations (PDEs) by mapping between infinite-dimensional function spaces using labeled datasets. However, in scenarios lacking labeled data, the physics-informed DeepONet (PI-DeepONet) approach, which utilizes the residual loss of the governing PDE to optimize the network parameters, faces significant computational challenges, particularly due to the curse of dimensionality. This limitation has hindered its application to high-dimensional problems, making even standard 3D spatial with 1D temporal problems computationally prohibitive. Additionally, the computational requirement increases exponentially with the discretization density of the domain. Here, to address these challenges and enhance scalability for high-dimensional PDEs, we introduce the Separable physics-informed DeepONet (Sep-PI-DeepONet). This framework employs a factorization technique, utilizing sub-networks for individual one-dimensional coordinates, thereby reducing the number of forward passes and the size of the Jacobian matrix required for gradient computations. By incorporating forward-mode automatic differentiation (AD), we further optimize computational efficiency, achieving linear scaling of computational cost with discretization density and dimensionality, making our approach highly suitable for high-dimensional PDEs. We demonstrate the effectiveness of Sep-PI-DeepONet through three benchmark PDE models: the viscous Burgers’ equation, Biot’s consolidation theory, and a parameterized heat equation. Our framework maintains accuracy comparable to the conventional PI-DeepONet while reducing training time by two orders of magnitude. Notably, for the heat equation solved as a 4D problem, the conventional PI-DeepONet was computationally infeasible (estimated 289.35 h), while the Sep-PI-DeepONet completed training in just 2.5 h. These results underscore the potential of Sep-PI-DeepONet in efficiently solving complex, high-dimensional PDEs, marking a significant advancement in physics-informed machine learning.

Neural operator↗
NASA NTRS1991

A neural network for the identification of measured helicopter noise

The results of a preliminary study of the components of a novel acoustic helicopter identification system are described. The identification system uses the relationship between the amplitudes of the first eight harmonics in the main rotor noise spectrum to distinguish between helicopter types. Two classification algorithms are tested; a statistically optimal Bayes classifier, and a neural network adaptive classifier. The performance of these classifiers is tested using measured noise of three helicopters. The statistical classifier can correctly identify the helicopter an average of 67 percent of the time, while the neural network is correct an average of 65 percent of the time. These results indicate the need for additional study of the envelope of harmonic amplitudes as a component of a helicopter identification system. Issues concerning the implementation of the neural network classifier, such as training time and structure of the network, are discussed.

Cabell, R. H.↗
DOE OSTI2025

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗
DOE OSTI2024

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

42 ENGINEERING↗
DOE OSTI2024

Temporal dynamics of the multi-omic response to endurance exercise training

Regular exercise promotes whole-body health and prevents disease, but the underlying molecular mechanisms are incompletely understood. Here, the Molecular Transducers of Physical Activity Consortium profiled the temporal transcriptome, proteome, metabolome, lipidome, phosphoproteome, acetylproteome, ubiquitylproteome, epigenome and immunome in whole blood, plasma and 18 solid tissues in male and female Rattus norvegicus over eight weeks of endurance exercise training. The resulting data compendium encompasses 9,466 assays across 19 tissues, 25 molecular platforms and 4 training time points. Thousands of shared and tissue-specific molecular alterations were identified, with sex differences found in multiple tissues. Temporal multi-omic and multi-tissue analyses revealed expansive biological insights into the adaptive responses to endurance training, including widespread regulation of immune, metabolic, stress response and mitochondrial pathways. Many changes were relevant to human health, including non-alcoholic fatty liver disease, inflammatory bowel disease, cardiovascular health and tissue injury and recovery. The data and analyses presented in this study will serve as valuable resources for understanding and exploring the multi-tissue molecular effects of endurance training and are provided in a public repository (https://motrpac-data.org/).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Hvac: Removing I/O Bottleneck for Large-Scale Deep Learning Applications

Scientific communities are increasingly adopting deep learning (DL) models in their applications to accelerate scientific discovery processes. However, with rapid growth in the computing capabilities of HPC supercomputers, large-scale DL applications have to spend a significant portion of training time performing I/O to a parallel storage system. Previous research works have investigated optimization techniques such as prefetching and caching. Unfortunately, there exist non-trivial challenges to adopting the existing solutions on HPC supercomputers for large-scale DL training applications, which include non-performance and/or failures at extreme scale, lack of portability and generality in design, complex deployment methodology, and being limited to a specific application or dataset. To address these challenges, we propose High-Velocity AI Cache (HVAC), a distributed read-cache layer that targets and fully exploits the node-local storage or near node-local storage technology. HVAC seamlessly accelerates read I/O by aggregating node-local or near node-local storage, avoiding metadata lookups and file locking while preserving portability in the application code. We deploy and evaluate HVAC on 1,024 nodes (with over 6000 NVIDIA V100 GPUS) of the Summit supercomputer. In particular, we evaluate the scalability, efficiency, accuracy, and load distribution of HVAC compared to GPFS and XFS-on-NVMe. With four different DL applications, we observe an average 25 % performance improvement atop GPFS and 9% drop against XFS-on-NVMe, which scale linearly and are considered the performance upper bound. We envision HVAC as an important caching library for upcoming HPC supercomputers such as Frontier.

Khan, Awais↗
DOE OSTI2026

VRN3P: Variational Recurrent Neural Network Based Net-Load Prediction under High Solar Penetration

This is the final technical report for the SETO-funded VRN3P project (PNNL# 76914). The goal of this project, led by Pacific Northwest National Laboratory (PNNL), in collaboration with Lawrence Livermore National Laboratory (LLNL) and Portland General Electric (PGE), was to develop and validate a deep variational recurrent neural network-based net-load prediction (VRN3P) framework for probabilistic time-series forecasting of day-ahead net-load under high solar penetration scenarios. The project team reports successful design of a novel probabilistic net-load forecasting architecture, comprising of a variational autoencoder and a recurrent neural network, which demonstrates 30% improvement in forecast performance, 60% improvement in training time, and consumes 44% less memory, when compared with conventional baseline models. The team tested the VRN3P model performance on GridLAB-D test-cases representing varying BTM solar penetration levels of 20%, 30%, and 50%, with integrated time-series net-load profiles provided by the utility partner (PGE). The VRN3P model demonstrate <2% hourly MAPE (averaged over the year) for day- ahead net-load forecast on the test scenario with 20% BTM solar. Transfer learning extension of the VRN3P model has demonstrated 8.33× speed-up in training, while still achieving acceptable forecast performance of 2.24% hourly MAPE on the 30% BTM solar penetration test-scenario. A preliminary version of the VRN3P GridAPPS-D™has been developed, along with a web-based interactive user-interface (named ‘Forte’) which has made available on GitHub for public use.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Geometrical defect detection for additive manufacturing with machine learning models

This study proposed a scheme based on Machine Learning (ML) models to detect geometric defects of additively manufactured objects. The ML models are trained with synthetic 3D point clouds with defects and then applied to detect defects in actual production. Using synthetic 3D point clouds rather than experimental data could save a huge amount of training time and costs associated with many prints for each design. Besides distance differences of individual points between source and target point clouds, this scheme uses a new concept called “patch” to capture macro-level information about nearby points for ML training and implementation. Numerical comparisons of prediction results on experimental data with different shapes showed that the proposed scheme outperformed the existing Z-difference method in the literature. Five ML methods (Bagging of Trees, Gradient Boosting, Random Forest, K-nearest Neighbors and Linear Supported Vector Machine) were compared under various conditions, such as different point cloud densities and defect sizes. Bagging and Random Forest were found the two best models regarding predictability; and the right patch size was found to be at 20. The proposed ML-based scheme is applicable to in-situ defect detection during additive manufacturing with the aid of a proper 3D data acquisition system.

Additive manufacturing↗
DOE OSTI2021

Autonomous nondestructive evaluation of resistance spot welded joints

The application of non-destructive evaluation approaches has attracted strong interests in modern automotive industries. Here, we present an autonomous deep-computing framework to analyze raw videos from infrared systems and to predict weld nugget shape and size with unprecedented accuracy and speed. In a comprehensive training and testing experiment with 90 videos (seven sets of welding material stack-ups), a new method was developed to assemble sufficient datasets for neural network training. Our framework successfully predicts all the nugget shapes with F1 scores that range from 0.84 to 0.92. The total training time on Nvidia DGX station takes less than 10 min for each set of welding material stack-up. The real inference time of an individual dataset (with 30 video frames) takes about 0.005 s. The procedure and methods developed in the study can be applied to other image-based weld property prediction, as well as other manufacturing processes. Furthermore, our well-trained neural networks take limited memory resources (2.3 MB) and are suitable for embedded microprocessors for in-situ welding quality control as edge computing within an intelligent welding framework.

42 ENGINEERING↗
DOE OSTI2026

Multiscale Neural Networks for Approximating Green’s Functions

Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green’s functions. However, Green’s functions are notoriously difficult to learn due to their poor regularity, which typically requires larger NNs and longer training times. In this work, we address these challenges by leveraging multiscale NNs to learn Green’s functions. Through theoretical analysis using multiscale Barron space methods and experimental validation, we show that the multiscale approach significantly reduces the necessary NN size and accelerates training.

97 MATHEMATICS AND COMPUTING↗