Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “train”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields in the last two decades, in part thanks to an increasing culture of open data sharing and reuse. Due to its capability for identifying complex relationships and patterns, AI/ML methodology is particularly well suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are many key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Even with the positive culture of Open Science and data sharing, inexperienced researchers working quickly without proper checks can produce models that perform poorly outside of the immediate training dataset. Lessons learned from biological AI/ML research indicate that Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Andrew Casaletto↗
NASA NTRSDate not supplied

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields, in part due to a culture of open data sharing and reuse. AI/ML methodology is well-suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Inexperienced researchers can produce models that perform poorly outside of the training dataset. Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Casaletto↗
NASA NTRSDate not supplied

Isolator Shock Train Response to Dual-Mode Scramjet Throttling-Like Forcing

Typical dual-mode scramjet designs employ an isolator component situated between the inlet and combustor. The isolator fluidically buffers the inlet from the combustor via the formation of a shock train, an interconnected series of shock-boundary layer interactions. The isolator is required during ramjet-engine operation and at the lower edges of the scramjet operational envelope. In an operational engine, transient behavior imposes fluidic dynamics due to attitude adjustments, combustor throttling, aberrant resonances within the combustor, etc. To accommodate these transients, the shock train adjusts on both temporal and spatial scales. Sufficiently large downstream pressure increases in the combustor play a critical role during unstart, whereby strong compression waves propagate upstream in the isolator to ultimately force the shock train out the inlet, if it cannot stabilize to the pressure increase. This critically reduces the engine mass flow rate, potentially causing a catastrophic reduction in thrust and loss of the vehicle. A nearly instantaneous unstart can, in principle, be predicted by a ratio of the normal shock pressure jump in an inviscid isolator. However, lower-magnitude perturbations, below this bound, also induce unstarts. Understanding the transient behavior inherent in unsteady isolator operation is critical to reducing safety margin in isolator length and refining engine control algorithms to improve engine performance. The Isolator Dynamics Research Lab (IDRL) is a cold-flow, direct-connect isolator facility ideal for assessing the fundamental fluid dynamics of shock trains. The internal flow of a scramjet isolator is modeled using a 2D, symmetric Mach 2.5 nozzle followed by a 695 mm long, 25.4x50.8 mm rectangular isolator test section. A blockage cone on a high-speed ball screw actuator downstream of the isolator is pulsed to simulate the throttling behavior in an operational combustor. Wall flush high-speed static pressure transducers detect the streamwise shock train within the isolator. Time delays between the onset of the throttling and the response motion of the shock train are analyzed to assess the controlling scales and parameters. From this analysis, the response time of the isolator shock train system is found to depend primarily on the isolator back pressure time-rate-of-change but quickly saturates to a maximum propagation speed along the isolator. These results inform dual-mode scramjet engine designers of the critical parameters and limits of an unstart resistant engine.

scramjet↗
DOE OSTI2017

U.S. DOE’s Energy Treasure Hunt Exchange In-Plant Trainings – DOE Resources, Early Results and Lessons Learned

The primary objective of the Department of Energy’s (DOE) Energy Treasure Hunt In-Plant Training (INPLT) is to train Better Plants partner employees to lead and conduct future energy efficiency Treasure Hunts within their facilities without DOE assistance. By taking a “learning-by-doing” approach, this INPLT, like other DOE INPLT trainings, has the added benefit of uncovering real energy and cost-saving opportunities. This INPLT leverages DOE and Better Plants technical staff, resources and tools and the EPA “Energy Treasure Hunt Guide: Simple Steps to Finding Energy Savings” process. While Treasure Hunts are a relatively well-known approach to identifying energy-savings in manufacturing plants, DOE is adding several additional elements in its Treasure Hunt Exchanges. The first element is technical assistance and methodology. DOE provides high-quality technical resources, such as energy efficiency calculators, fact sheets, source books etc., to facilitate the Treasure Hunt process and teaches four fundamentals: 1) how to profile equipment, 2) how to collect data, and 3), data & ROI calculation methodologies. Another element is the “train the trainer” approach wherein the training facilitator will train at least one partner employee to facilitate future treasure hunts. Another element is that DOE provides energy diagnostic equipment and teaches the participants how to use them. Finally, DOE also offers partners the opportunity to exchange teams of employees either within a partners’ enterprise or with other partners to conduct the treasure hunt in each other’s facilities. This exchange of teams is important because each team can bring different insights and uncover energy-saving opportunities that would otherwise be missed. This paper will discuss DOE methodology and the early results and lessons learned from DOE’S Energy Treasure Hunt In-Plant Trainings at Better Plants Partner facilities.

Nimbalkar, Sachin U.↗
DOE OSTI2022

Anderson Acceleration for Distributed Training of Deep Learning Models

Anderson acceleration (AA) is an extrapolation technique that has recently gained interest in the deep learning (DL) community to speed-up the sequential training of DL models. However, when performed at large scale, the DL training is exposed to a higher risk of getting trapped into steep local minima of the training loss function, and standard AA does not provide sufficient acceleration to escape from these steep local minima. This results in poor generalizability and makes AA ineffective. To restore AA’s advantage to speed-up the training of DL models on large scale computing platforms, we combine AA with an adaptive moving average procedure that boosts the training to escape from steep local minima. By monitoring the relative standard deviation between consecutive iterations, we also introduce a criterion to automatically assess whether the moving average is needed. We applied the method to the following DL instantiations for image classification: (i) ResNet50 trained on the open-source CIFAR100 dataset and (ii) ResNet50 trained on the open-source ImageNet1k dataset. Numerical results obtained using up to 1,536 NVIDIA V100 GPUs on the OLCF supercomputer Summit showed the stabilizing effect of the moving average on AA for all the problems above.

Lupo Pasini, Massimiliano↗
DOE OSTI2022

Do Neural Networks Trained with Topological Features Learn Different Internal Representations?

There is a growing body of work that leverages features extracted via topological data analysis to train machine learning models. While this field, sometimes known as topological machine learning (TML), has seen some notable successes, an understanding of how the process of learning from topological features differs from the process of learning from raw data is still limited. In this work, we begin to address one component of this larger issue by asking whether a model trained with topological features learns internal representations of data that are fundamentally different than those learned by a model trained with the original raw data. To quantify ``different'', we exploit two popular metrics that can be used to measure the similarity of the hidden representations of data within neural networks, neural stitching and centered kernel alignment. From these we draw a range of conclusions about how training with topological features does and does not change the representations that a model learns. Perhaps unsurprisingly, we find that structurally, the hidden representations of models trained and evaluated on topological features differ substantially compared to those trained and evaluated on the corresponding raw data. On the other hand, our experiments show that in some cases, these representations can be reconciled (at least to the degree required to solve the corresponding task) using a simple affine transformation. We conjecture that this means that neural networks trained on raw data may extract some limited topological features in the process of making predictions.

McGuire, Sarah L.↗
DOE OSTI2024

Visual feedback and guided balance training in an immersive virtual reality environment for lower extremity rehabilitation

Balance training is essential for physical rehabilitation procedures, as it can improve functional mobility and enhance cognitive coordination. However, conventional balance training methods may have limitations in terms of motivation, real-time objective feedback, and personalization, which a virtual reality (VR) setup may provide a better alternative. In this work, we present an immersive VR training environment for lower extremity balance rehabilitation with real-time guidance and feedback. The VR training environment immerses the user in a 3D ice rink model where a virtual coach (agent) leads them through a series of balance poses, and the user controls a trainee avatar with their own movements. Here we developed two coaching styles: positive-reinforcement and autonomous-supportive, and two viewpoints of the trainee avatar: first-person and third-person. The proposed environment was evaluated in a user study with healthy, non-clinical participants (n = 16, 24.4 ± 5.7 years old, 9 females). Our results show that participants showed stronger performance in the positive-reinforcement style compared to the autonomous-supportive style. Additionally, in the third-person viewpoint, the participants exhibited more stability in the positive-reinforcement style compared to the autonomous-supportive style. For viewpoint, participants exhibited stronger performance in the first-person viewpoint compared to third-person in the autonomous-supportive style, while they were comparable in the positive-reinforcement style. We observed no significant effects on the foot height and number of mistakes. Furthermore, we report the analysis of user performance with balance training poses and subjective measures based on questionnaires to assess the user experience, usability, and task load. The proposed VR balance training could offer an interactive, adaptive, and engaging environment and open new potential research directions for lower extremity rehabilitation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism

Here, we present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make training much more costly and even infeasible due to excessive memory usage. We solve these challenges by extensively applying hybrid parallelism throughout the end-to-end training pipeline, including both computations and I/O. Our hybrid-parallel algorithm extends the standard data parallelism with spatial parallelism, which partitions a single sample in the spatial domain, realizing strong scaling beyond the mini-batch dimension with a larger aggregated memory capacity. We evaluate our proposed training algorithms with two challenging 3D CNNs, CosmoFlow and 3D U-Net. Our comprehensive performance studies show that good weak and strong scaling can be achieved for both networks using up to 2K GPUs. More importantly, we enable training of CosmoFlow with much larger samples than previously possible, realizing an order-of-magnitude improvement in prediction accuracy.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Artemis Crewed Surface Operations Training Dust Mitigation Test/Training Facility (DMTF)

Based on several Apollo mission(s) reports and lessons learned1 on lunar dust impacts, it is imperative for successful Artemis missions, to develop dust mitigation methods & train crew in dust cleaning techniques for efficient use of lunar surface time and for crew health. Longer durations and increased number of Extra Vehicular Activities (EVAs) for Artemis need better training. Apollo missions lacked training in a dust facility. Current facilities do not provide adequate fidelity to train crew in dust cleaning operations in suited, pressurized environments. Mimicking dust cleaning actions in existing facilities (eg- Neutral Buoyancy lab) does not provide in depth understanding of actions and time needed to clean suit or positions crew need to take to remove dust from suit. Available dust bins do not support suited/pressurized ops, personnel not trained in suited ops, more overhead/travel. A local facility at Johnson Space Center (JSC) w/ adequate fidelity supporting suited/pressurized ops, personnel in suited ops is a crucial need for rapid development/testing and training. This facility will provide NASA capabilities to: 1. Provide a dust containment bin to perform suited pressurized crewed training/testing activities for dust interaction/mitigation leveraging existing JSC facility infrastructure and 2. Perform end-to-end simulated lunar dust testing of fluid, mechanical, and electrical systems to provide “test like you fly” confidence for industry developed solutions.

EVA training↗
DOE OSTI2020

DeepClone: Lightweight State Replication of Deep Learning Models for Data Parallel Training

Training modern deep neural network (DNN) models involves complex workflows triggered by model exploration, sensitivity analysis, explainability, etc. A key primitive in this context is the ability to clone a model training instance, i.e. “fork” the training process in a potentially different direction, which enables comparisons of different evolution paths using variations of training data and model parameters. However, in a quest improve the training throughput, a mix of data parallel, model parallel, pipeline parallel and layer-wise parallel approaches are making the problem of cloning highly complex. In this paper, we explore the problem of efficient cloning under such circumstances. To this end, we leverage several properties of data-parallel training and layer-wise parallelism to design DeepClone, a cloning approach based on augmenting the execution graph to gain direct access to tensors, which are then sharded and reconstructed asynchronously in order to minimize runtime overhead, standby duration, readiness duration. Compared with state-of-art approaches, DeepClone shows orders of magnitude improvement for several classes of DNN models.

data-parallel training↗
DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗
DOE OSTI2018

Integration of Solar Training into Allied Professional Development Platforms - Final Technical Report

The Interstate Renewable Energy Council (IREC) designed the “Integration of Solar Training into Allied Professional Development Platforms” project to surmount barriers to the expansion of solar technology caused by gaps in knowledge impacting on-the-job performance of allied professionals. At project start, questionnaires deployed nationally indicated that only 9% of firefighters felt certain they could shut down a PV system to the extent possible, and only a third of code officials thought they could even discern the difference between a PV and solar thermal system. Therefore, the project objective was to measurably and significantly increase the number of code officials and fire service professionals with solar knowledge directly applicable to their job function. IREC identified specific gaps in current knowledge, and integrated research-proven adult learning principles and technology solutions to enable a cost-effect but impactful reach. The project design ensured that solar training is a continuing component of the targeted sector professional development toolkit. To this end, the key partners recruited and cultivated were existing, trusted training partners in the targeted sectors: International Code Council Solar Rating and Certification Corporation (ICC-SRCC), International Association of Electrical Inspectors (IAEI), International Association of Fire Fighters (IAFF) and National Association of State Fire Marshals (NASFM). During the project, IREC held 79 courses in 25 states that trained 4,156 people, offered a PV in the 2017 National Electric Code webinar attended by 787 people, developed on-line training for code officials with 2,298 on-line learners, and developed an on-line training for firefighters with 4,930 on-line learners. In addition, the project participated in 28 conferences and reached over 537,000 professionals with solar information.

14 SOLAR ENERGY↗
DOE OSTI2023

Proposed Subcritical Assembly for Nuclear Criticality Safety Training at the Oak Ridge National Laboratory

The design of a new subcritical assembly at Oak Ridge National Laboratory (ORNL) has been finalized. This design takes the feasibility study of the subcritical assembly performed in August 2020 to an implementable design. This subcritical assembly will support the Nuclear Criticality Safety Program (NCSP) training and education program. The addition of this subcritical assembly into the NCSP training and education will enhance the program by providing backup capacity for training if nuclear facility operations are disrupted at Sandia National Laboratories or the National Criticality Experiments Research Center; providing a new location that is more accessible to students in the Eastern portion of the United States; providing flexibility to support students from a diverse background (e.g., university students, foreign nationals). The proposed subcritical assembly uses legacy AGN-201M research reactor fuel plates that are available at the Y-12 National Security Complex. The final design of this subcritical assembly contains approximately 617 grams of 235 U as UO 2 powder distributed homogeneously in polyethylene. The fuel plates will have a graphite neutron reflector to obtain a core multiplication, M, from 10 to 20, corresponding to a $k_{eff}$ of 0.90 to 0.95, respectively. The subcritical assembly will be able to support at least four experiments for the training courses: (1) the addition of fissile material to the core (mass), (2) a core separation experiment (interaction), (3) the addition of moderators to the core (moderation), and (4) the addition of neutron absorbers to the core (poison/absorption). The subcritical assembly will be designed to be inherently safe—subcritical under all normal and abnormal conditions— and will provide the capability to conduct hands-on training to support NCSP and general nuclear criticality safety staff training and qualification goals.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS1993

Effect of exercise training on cardiopulmonary baroreflex control of forearm vascular resistance in humans

We studied the stimulus-response characteristics of cardiopulmonary baroreflex control of forearm vascular resistance (FVR) in four groups of male volunteer subjects: i) unfit, ii) physically fit, iii) before and after 10 wk of endurance training (chronic blood volume expansion), and iv) before and after acute blood volume expansion. We assessed the relationship between reflex stimulus, i.e., changes in central venous pressure and response, i.e., FVR, during unloading of cardiopulmonary mechanoreceptors with lower body negative pressure (LBNP, 0 to -20 mm Hg). The slope of the linear relationship between FVR and CVP, the index of the responsiveness of this baroreflex, was significantly diminished (> 50%) in the fit subjects compared with the unfit. The slope of the FVR-CVP relationship was inversely correlated with the subject's total blood volume, suggesting that blood volume expansion was related to the attenuated CP baroreflex. In the exercise training study, maximal oxygen consumption and blood volume increased following 10 wk of endurance training (N = 14) but were unchanged in the time control group (N = 7). The slope of the FVR-CVP relationship was significantly reduced (32%) following 10 wk of training but was unchanged in the time control group. The reduction in slope of the FVR-CVP relationship was inversely related to the increase in blood volume associated with exercise training. Acute blood volume expansion 8 ml.kg-1 body weight with 5% human serum albumin solution) significantly reduced the slope of the FVR-CVP relationship. These data support the hypothesis that the attenuated forearm vascular reflex in physically fit individuals is related to a training-induced hypervolemia.(ABSTRACT TRUNCATED AT 250 WORDS).

Review↗
NASA NTRS2017

Training, Retention, and Transfer of Data Entry Perceptual and Motoric Processes Over Long Retention Intervals

Subjects trained in a standard data entry task, which involved typing numbers (e.g., 5421) using their right hands. At test (6 months post-training), subjects completed the standard task, followed by a left-hand variant (typing with their left hands) that involved the same perceptual, but different motoric, processes as the standard task. At a second test (8 months post-training), subjects completed the standard task, followed by a code variant (translating letters into digits, then typing the digits with their right hands) that involved different perceptual, but the same motoric, processes as the standard task. For each of the three tasks, half the trials were trained numbers (old) and half were new. Repetition priming (faster response times to old than new numbers) was found for each task. Repetition priming for the standard task reflects retention of trained numbers; for the left-hand variant reflects transfer of perceptual processes; and for the code variant reflects transfer of motoric processes. There was thus evidence for both specificity and generalizability of training data entry perceptual and motoric processes over very long retention intervals.

dat↗
NASA NTRS2019

Training, Retention, and Transfer of Data Entry Perceptual and Motor Processes Over Short and Long Retention Intervals

In 2 experiments, subjects trained in a standard data entry task, which involved typing numbers (e.g., 2147) using their right hands. At an initial test (20 min or 6 months after training), subjects completed the standard task, followed by a left-hand variant (typing with their left hands) that involved the same perceptual, but different motoric, processes as the standard task. At a second test (2 days or 8 months after training), subjects completed the standard task, followed by a code variant (translating letters into digits, then typing the digits with their right hands) that involved different perceptual, but the same motoric, processes as the standard task. At test, for each of the three tasks, half the trials were trained numbers (old) and half were new. Repetition priming (faster response times to old than new numbers) was found for each task, with extended delays only slightly decreasing the magnitude of the effect. Repetition priming for the standard task reflects retention of trained numbers, for the left-hand variant reflects transfer of perceptual processes, and for the code variant reflects transfer of motoric processes. There was, thus, evidence for both specificity and generalizability of training data entry perceptual and motoric processes even over very long retention intervals.

transfer↗
NASA NTRSDate not supplied

Training Airline Pilots for Improved Flight Path Monitoring: The Sensemaking Model Framework

The importance and benefit of improved monitoring is increasingly recognized. Improved training may be a valuable intervention. Our study (conducted 2019) assessed and trained airline First Officers on flight path monitoring skills. The exploratory study assessed monitoring pre-training in a simulator session that included monitoring challenges (8 or 7 events). A 1-hour interactive training followed, based on the Sensemaking Model of Monitoring; it presented concepts and examples using a slide deck, discussion, and simple activities. Post-training assessment used scenarios with analogous monitoring challenges (7 or 8 events) but a different setting. Performance showed significant and relatively consistent improvement. Training monitoring as sensemaking merits further investigation.

training↗
NASA NTRSDate not supplied

Virtual International Satellite Training Experiences for Weather, Marine, Climate, and Environmental Applications

Since January 2020, National Oceanic and Atmospheric Administration, its Cooperative Institutes, and international partners provided over 15,000 hours of virtual satellite focused on user engagement. The training provides and guides users to analyze a large variety of satellite data for weather, climate, and environmental applications and decision support. The training team reached users in over 50 countries via monthly Regional Focus Group and special topic sessions, World Meteorological Organization Regional Association III and IV Workshops, and American Meteorological Society Short Courses. The training sessions were offered in both English and Spanish covering such themes as GOES-R, JPSS and other satellite capabilities, data access using GEONET Cast, data display, and user applications. The training also emphasized the operational application of satellite observations for cross-disciplinary topics like heavy rain and hail events, aviation hazards, fire and smoke detection, volcanic eruptions and ash monitoring, climate indices, monitoring coral reef health, and in tsunami preparedness. The presentation will highlight the methods used and challenges posed by the various training approaches and future modifications to adapt to the virtual environment during training sessions planned for the next year.

Satellite Training↗