Search NASA⌕ Search

SEARCH · Search NASA

Results for “Augmented”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS2005

Thrust Augmentation Measurements for a Pulse Detonation Engine Driven Ejector

Thrust augmentation results of an ongoing study of pulse detonation engine driven ejectors are presented and discussed. The experiments were conducted using a pulse detonation engine (PDE) setup with various ejector configurations. The PDE used in these experiments utilizes ethylene (C2H4) as the fuel, and an equi-molar mixture of oxygen and nitrogen as the oxidizer at an equivalence ratio of one. High fidelity thrust measurements were made using an integrated spring damper system. The baseline thrust of the PDE engine was first measured and agrees with experimental and modeling results found in the literature. Thrust augmentation measurements were then made for constant diameter ejectors. The parameter space for the study included ejector length, PDE tube exit to ejector tube inlet overlap distance, and straight versus rounded ejector inlets. The relationship between the thrust augmentation results and various physical phenomena is described. To further understand the flow dynamics, shadow graph images of the exiting shock wave front from the PDE were also made. For the studied parameter space, the results showed a maximum augmentation of 40%. Further increase in augmentation is possible if the geometry of the ejector is tailored, a topic currently studied by numerous groups in the field.

Pal, S.↗
NASA NTRS2003

Utilization of the Space Vision System as an Augmented Reality System For Mission Operations

Augmented reality is a technique whereby computer generated images are superimposed on live images for visual enhancement. Augmented reality can also be characterized as dynamic overlays when computer generated images are registered with moving objects in a live image. This technique has been successfully implemented, with low to medium levels of registration precision, in an NRA funded project entitled, "Improving Human Task Performance with Luminance Images and Dynamic Overlays". Future research is already being planned to also utilize a laboratory-based system where more extensive subject testing can be performed. However successful this might be, the problem will still be whether such a technology can be used with flight hardware. To answer this question, the Canadian Space Vision System (SVS) will be tested as an augmented reality system capable of improving human performance where the operation requires indirect viewing. This system has already been certified for flight and is currently flown on each shuttle mission for station assembly. Successful development and utilization of this system in a ground-based experiment will expand its utilization for on-orbit mission operations. Current research and development regarding the use of augmented reality technology is being simulated using ground-based equipment. This is an appropriate approach for development of symbology (graphics and annotation) optimal for human performance and for development of optimal image registration techniques. It is anticipated that this technology will become more pervasive as it matures. Because we know what and where almost everything is on ISS, this reduces the registration problem and improves the computer model of that reality, making augmented reality an attractive tool, provided we know how to use it. This is the basis for current research in this area. However, there is a missing element to this process. It is the link from this research to the current ISS video system and to flight hardware capable of utilizing this technology. This is the basis for this proposed Space Human Factors Engineering project, the determination of the display symbology within the performance limits of the Space Vision System that will objectively improve human performance. This utilization of existing flight hardware will greatly reduce the costs of implementation for flight. Besides being used onboard shuttle and space station and as a ground-based system for mission operational support, it also has great potential for science and medical training and diagnostics, remote learning, team learning, video/media conferencing, and educational outreach.

Maida, James C.↗
NASA NTRS2005

Stability-Augmentation Devices for Miniature Aircraft

Non-aerodynamic mechanical devices are under consideration as means to augment the stability of miniature autonomous and remotely controlled aircraft. Such aircraft can be used for diverse purposes, including military reconnaissance, radio communications, and safety-related monitoring of wide areas. The need for stability-augmentation devices arises because adverse meteorological conditions generally affect smaller aircraft more strongly than they affect larger aircraft: Miniature aircraft often become uncontrollable under conditions that would not be considered severe enough to warrant grounding of larger aircraft. The need for the stability-augmentation devices to be non-aerodynamic arises because there is no known way to create controlled aerodynamic forces sufficient to counteract the uncontrollable meteorological forces on miniature aircraft. A stability-augmentation device of the type under consideration includes a mass pod (a counterweight) at the outer end of a telescoping shaft, plus associated equipment to support the operation of the aircraft. The telescoping shaft and mass pod are stowed in the rear of the aircraft. When deployed, they extend below the aircraft. Optionally, an antenna for radio communication can be integrated into the shaft. At the time of writing this article, the deployment of the telescoping shaft and mass pod was characterized as passive and automatic, but information about the deployment mechanism(s) was not available. The feasibility of this stability-augmentation concept was demonstrated in flights of hand-launched prototype aircraft.

Wood, RIchard M.↗
NASA NTRSDate not supplied

Evaluating Sensory Augmentation as A Non-Pharmaceutical Tool to Mitigate Motion Sickness and Enhance Sensorimotor Task Performance: A Pilot Study Using Simulated Capsule Wave Motion

Wave motion during capsule recovery operations can result in motion sickness and performance decrements exacerbating reentry sickness following long duration spaceflight. The purpose of this pilot study was (1) to validate a capsule wave motion simulation as a platform to evaluate motion sickness countermeasures and (2) to evaluate a sensory augmentation belt providing vibrotactile feedback of gravitational upright. Ten healthy subjects ages 38.0 ± 10.1 (6M|4F) were exposed to complex wave motions on a six degree-of-freedom platform that included pitch, roll, and heave at provocative stimulus frequencies (0.1-0.25 Hz) while seated in an illuminated cabin deprived of external visual cues. Subjects reported acute symptoms for up to three consecutive 15 min trials or until they reached a motion sickness endpoint of 8 pts on the Pensacola Diagnostic Index (PDI). Five subjects were randomly assigned to the Sensory Augmentation (SA) group while the other five served as controls (CN group). Based on a Motion Sickness Susceptibility Questionnaire, the two groups had similar motion sickness histories (susceptibility percentile ranking of CN group = 27.5 ± 63.6 in the CN group versus 27.5 ± 37.0 in the SA group, median ± IQR). The vibrotactile feedback consisted of a single array of 8 electromechanical tactors positioned around the torso on an adjustable belt (Engineering Acoustics, Inc) that utilized an integrated inertial measurement unit (IMU) to indicate the direction of upright (e.g., subject’s back tactor on during forward tilt). During each wave motion trial subjects performed a battery of four different tasks: tracking Earth vertical using a joystick with and without a secondary task (Paced Auditory Serial Addition Test), an eye-hand target acquisition task on a cabin-fixed tablet, and the psychomotor vigilance test (PVT). All ten subjects reported varying levels of motion sickness with 6 of 10 reaching a symptom endpoint. Interestingly, subjects anecdotally reported that engagement in the joystick tracking task was less provocative than tasks involving the cabin-fixed tablet or periods of no activity. Sensory augmentation appeared to delay symptom onset, with 2 of 5 subjects reaching an endpoint within the first 15 min trial in the CN group versus none in the SA group (PDI after 15 min = 6.0 ± 2.5 in the CN group versus 3.4 ± 2.5 in the SA group, mean ±std). Sensory augmentation also improved performance on the joystick tracking task at lower stimulus frequencies (0.1 Hz in roll and 0.2 Hz in pitch). Both CN and SA groups maintained a consistent level of performance on the eye-hand target acquisition and PVT throughout the baseline (no motion) and wave motion periods. Our results validated that the simulated capsule wave motion paradigm provides an effective motion sickness stressor. This paradigm is currently being used to investigate the efficacy of intranasal scopolamine to mitigate motion sickness. Sensory augmentation using vibrotactile feedback appears to improve spatial awareness and delay symptom onset during complex passive motion. One advantage of this portable belt design is that it incorporates all tactor drive and IMU circuitry and therefore could continue to be worn by crewmembers and serve as a balance aid during egress and ambulation with recovery operations.

A M Bollinger↗
DOE OSTI2022

Classification of animal sounds in a hyperdiverse rainforest using convolutional neural networks with data augmentation

To protect tropical forest biodiversity, we need to be able to detect it reliably, cheaply, and at scale. Automated detection of sound producing animals from passively recorded soundscapes via machine-learning approaches is a promising technique towards this goal, but it is constrained by the necessity of large training data sets. Using soundscapes from a tropical forest in Borneo and a Convolutional Neural Network model (CNN), we investigate i) the minimum viable training data set size for accurate prediction of call types (‘sonotypes’), and ii) the extent to which data augmentation and transfer learning can overcome the issue of small and imbalanced training data sets. We found that even relatively high sample sizes (>80 per sonotype) lead to mediocre accuracy, which however improved significantly with data augmentation and transfer learning, including at extremely small sample sizes (3 per sonotype), regardless of taxonomic group or call characteristics. Neither transfer learning nor data augmentation alone achieved high accuracy. Our results suggest that transfer learning and data augmentation could make the use of CNNs to classify species’ vocalizations feasible even for small soundscape-based projects with many rare species. Retraining our open-source model requires only basic programming skills which makes it possible for individual conservation initiatives to match their local context, in order to enable more evidence-informed management of biodiversity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation

The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.

Bayesian neural network↗
NASA NTRS2012

Percussive Augmenter of Rotary Drills (PARoD)

Increasingly, NASA exploration mission objectives include sample acquisition tasks for in-situ analysis or for potential sample return to Earth. To address the requirements for samplers that could be operated at the conditions of the various bodies in the solar system, a piezoelectric actuated percussive sampling device was developed that requires low preload (as low as 10N) which is important for operation at low gravity. This device can be made as light as 400g, can be operated using low average power, and can drill rocks as hard as basalt. Significant improvement of the penetration rate was achieved by augmenting the hammering action by rotation and use of a fluted bit to provide effective cuttings removal. Generally, hammering is effective in fracturing drilled media while rotation of fluted bits is effective in cuttings removal. To benefit from these two actions, a novel configuration of a percussive mechanism was developed to produce an augmenter of rotary drills. The device was called Percussive Augmenter of Rotary Drills (PARoD). A breadboard PARoD was developed with a 6.4 mm (0.25 in) diameter bit and was demonstrated to increase the drilling rate of rotation alone by 1.5 to over 10 times. Further, a large PARoD breadboard with 50.8 mm diameter bit was developed and its tests are currently underway. This paper presents the design, analysis and preliminary test results of the percussive augmenter.

percussive augmenter↗
DOE OSTI2025

Utilization of Data Augmentation Techniques in Automated Inspection Systems for Defect Detection in Metals With Limited Data

Accurate identification of defects on metal surfaces is of great interest to many industry sectors, such as the automotive and aerospace industries. In contrast to conventional manual inspection techniques, recent automated inspection systems employ deep learning models trained to detect defects rapidly and precisely. The development of these models often requires a substantial image dataset to acquire adequate knowledge of defect features and enhance their predictive accuracy. When data is limited, augmentation techniques are often used to improve the precision and accuracy of defect detection systems. This study examined the prediction performance of two object detection models, namely Faster Region‐based Convolutional Neural Network (Faster R‐CNN) and You Only Look Once version 8 (YOLOv8), to identify dent defects in limited images of cast iron cylinder head surfaces. The original image set contains 46 images with 563 dents. To overcome limited data availability, common image augmentation techniques along with a copy‐paste method were applied. Results show that standard augmentation improved YOLOv8 accuracy by 8.00% and average precision (AP) by 3.00%. On the other hand, the copy‐paste technique achieved a 20.00% increase in accuracy and a 1% increase in AP with just 200 synthetic dents. Furthermore, these results provide support for using the copy‐paste augmentation strategy to enhance defect detection performance, with a limited dataset, contributing to more accurate defect identification in remanufacturing processes.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks

Integrating photovoltaics (PV) into electricity grids is challenged by potentially large fluctuations in power generation. In recent years, sky image-based PV output prediction using convolutional neural networks (CNNs) has emerged as a promising approach to forecasting fluctuations. A key challenge is imbalanced sky image datasets: because of the geography of solar PV system installations, sky image datasets are often rich in sunny condition data but deficient in cloudy condition data. This imbalance contrasts with the fact that model errors are dominated by cloudy condition performance. In this study, we attempt to remedy this by exploring the enrichment and augmentation of an imbalanced sky images dataset for two PV output prediction tasks: nowcasting (predicting concurrent PV output) and forecasting (predicting 15-minute-ahead future PV output). We empirically examine the efficacy of using different resampling and data augmentation approaches to create a rebalanced dataset for model development. A three-stage greedy search is used to determine the optimal resampling approach, data augmentation techniques and over-sampling rate. The results show that for the nowcast problem, resampling and data augmentation can effectively enhance the model performance, reducing overall root mean squared error (RMSE) by an average of 4%, or a 15 std. (standard deviation) of improvement compared to the variability of the baseline model. In contrast, the treatment RMSE for the forecast problem nearly always overlaps the baseline performance at the ± 2 std. level. The optimal resampling approach expands on the original dataset by over-sampling the minority cloudy data, with the best results from large over-sampling rate (e.g., 4 ~ 6 times over-sampling of cloudy images).

14 SOLAR ENERGY↗
DOE OSTI2024

Framework for custom event sample augmentations for ATLAS analysis data

For HEP event processing, data is typically stored in column-wise synchronized containers, such as most prominently ROOT’s TTree, which have been used for several decades to store by now over 1 exabyte. These containers can combine row-wise association capabilities needed by most HEP event processing frameworks (e.g. Athena for ATLAS) with column-wise storage, which typically results in better compression and more efficient support for many analysis use-cases. One disadvantage is that these containers, TTree in the HEP use-case, require to contain the same attributes for each entry/row (representing events), which can make extending the list of attributes very costly in storage, even if those are only required for a small subsample of events. Since the initial design, the ATLAS software framework features powerful navigational infrastructure to allow storing custom data extensions for subsamples of events in separate, but synchronized containers. This allows adding event augmentations to ATLAS standard data products (such as DAOD-PHYS or PHYSLITE) avoiding duplication of those core data products, while limiting their size increase. For this functionality, the framework does not rely on any associations made by the I/O technology (i.e. ROOT), however it supports TTree friends and builds the associated index to allow for analysis outside of the ATLAS framework. A prototype based on the Long-Lived Particle search is implemented and preliminary results with this prototype will be presented. At this point, augmented data are stored within the same file as the core data. Storing them in separate files will be investigated in future, as this could provide more flexibility, e.g. certain sites may only want a subset of several augmentations or augmentations can be archived to tape once their analysis is complete.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Improve Learning from Crowds via Generative Augmentation

Crowdsourcing provides an efficient label collection schema for supervised machine learning. However, to control annotation cost, each instance in the crowdsourced data is typically annotated by a small number of annotators. This creates a sparsity issue and limits the quality of machine learning models trained on such data. In this paper, we study how to handle sparsity in crowdsourced data using data augmentation. Specifically, we propose to directly learn a classifier by augmenting the raw sparse annotations. We implement two principles of high-quality augmentation using Generative Adversarial Networks: 1) the generated annotations should follow the distribution of authentic ones, which is measured by a discriminator; 2) the generated annotations should have high mutual information with the ground-truth labels, which is measured by an auxiliary network. Extensive experiments and comparisons against an array of state-of-the-art learning from crowds methods on three real-world datasets proved the effectiveness of our data augmentation framework. It shows the potential of our algorithm for low-budget crowdsourcing in general.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2019

Augmented Reality for Enabling Smart Nuclear Infrastructure

This work presents a novel, comprehensive framework that leverages emerging augmented reality headset technology to enable smart nuclear industrial infrastructure that a human can easily interact with to improve their performance in terms of safety, security, and productivity. Nuclear industrial operations require some of the most complicated infrastructure that must be managed today. Nuclear infrastructure and their associated industrial operations typically features stringent requirements associated with seismic, personnel management (e.g., access control, equipment access), safety (e.g., radiation, criticality, mechanical, electrical, spark, and chemical hazards), security (cyber/physical), and sometimes international treaties for nuclear non-proliferation. Furthermore, a wide variety of manufacturing and maintenance operations take place within these facilities further complicating their management. Nuclear facilities require very thorough and stringent documentation of the operations occurring within these facilities as well as maintaining a tight chain-of-custody for the materials being stored within the facility. The emergence of augmented reality and a variety of Internet of Things (IoT) devices offers a possible solution to help mitigate these challenges. This work provides a demonstration of a prototype smart nuclear infrastructure system that leverages augmented reality to illustrate the advantages of this system. It will also present example augmented reality tools that can be leveraged to create the next generation of smart nuclear infrastructure. The discussion will layout future directions of research for this class of work.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Improving Photometric Redshift Estimates with Training Sample Augmentation

Abstract Large imaging surveys will rely on photometric redshifts (photo- z 's), which are typically estimated through machine-learning methods. Currently planned spectroscopic surveys will not be deep enough to produce a representative training sample for Legacy Survey of Space and Time (LSST), so we seek methods to improve the photo- z estimates that arise from nonrepresentative training samples. Spectroscopic training samples for photo- z 's are biased toward redder, brighter galaxies, which also tend to be at lower redshift than the typical galaxy observed by LSST, leading to poor photo- z estimates with outlier fractions nearly 4 times larger than for a representative training sample. In this Letter, we apply the concept of training sample augmentation, where we augment simulated nonrepresentative training samples with simulated galaxies possessing otherwise unrepresented features. When we select simulated galaxies with ( g - z ) color, i -band magnitude, and redshift outside the range of the original training sample, we are able to reduce the outlier fraction of the photo- z estimates for simulated LSST data by nearly 50% and the normalized median absolute deviation (NMAD) by 56%. When compared to a fully representative training sample, augmentation can recover nearly 70% of the degradation in the outlier fraction and 80% of the degradation in NMAD. Training sample augmentation is a simple and effective way to improve training samples for photo- z 's without requiring additional spectroscopic samples.

Moskowitz, Irene (ORCID:0000000222068589)↗
NASA NTRS1978

Pilot-optimal augmentation synthesis

An augmentation synthesis method usable in the absence of quantitative handling qualities specifications, and yet explicitly including design objectives based on pilot-rating concepts, is presented. The algorithm involves the unique approach of simultaneously solving for the stability augmentation system (SAS) gains, pilot equalization and pilot rating prediction via optimal control techniques. Simultaneous solution is required in this case since the pilot model (gains, etc.) depends upon the augmented plant dynamics, and the augmentation is obviously not a priori known. Another special feature is the use of the pilot's objective function (from which the pilot model evolves) to design the SAS.

Schmidt, D. K.↗
NASA NTRS1979

An overview of current Navy programs to develop thrust augmenting ejectors

The primary objective of Navy sponsored research in thrust augmentation is the development of an improved augmenter for V/STOL application. In support of this goal, a data base is being established to provide an accurate prediction capability for use in ejector design. A general technology development of ejectors and associated effects presently is split into the more specific areas of lift and control, since thrust augmenting ejectors may be suitable for both. Research areas examined include advanced diffuser and end wall design; advanced primary nozzles; analytic studies; augmenting reaction controls; and nozzle design.

Green, K. A.↗
NASA NTRS1981

A flight investigation of static stability, control augmentation, and flight director influences on helicopter IFR handling qualities

A flight experiment was conducted using the NASA-Army V/STOLAND UH-1H variable-stability helicopter to investigate the influence of several longitudinal-static-stability, control-augmentation, and flight-director parameters on helicopter flying qualities during terminal area operations in instrument conditions. This experiment, which was part of a joint NASA/FAA program pertaining to helicopter IFR airworthiness, was designed to corroborate and extend previous ground simulation results obtained in this program. Variations examined included stable and neutral longitudinal control position gradients, rate-damping and attitude-command augmentation, and raw data versus flight-director displays. Pilot rating results agreed excellently with the ground simulation data, indicating an adequate instrument capability with rate-damping augmentation and neutral statics and the need for pitch-roll attitude augmentation to achieve a satisfactory system.

Lebacqz, J. V.↗
NASA NTRS1961

Effects of Geometric Variations on Lift Augmentation of Simple-plenum-chamber Ground-effect Models

Considerable interest has been shown during recent years in ground-effect vehicles. Of the various types proposed, the simple-plenum-chamber vehicle has indicated promise because, although the lift augmentation obtainable appears to be less than that of an annular jet, it may be somewhat less complicated structurally. The present investigation was undertaken to study the effects of some geometric variations upon lift augmentation of a simple plenum chamber within ground proximity. The variables included the ratio inlet area to exit area, plenum-chamber depth, and entrance configuration. An optimum plenum-chamber depth appeared to be between 3 and 10 percent of the plenum-chamber diameter with a ratio of inlet diameter to plenum-chamber diameter of 0.15 for the range of plenum-chamber depths investigated. The most important effect of multiple inlets was the elimination of negative lift augmentation, which was experienced with single sharp-edged inlets, at intermediate heights. Installation of a flared inlet and a turning-vane assembly improved lift augmentation of a single-inlet configuration at intermediate heights.

Davenport, Edwin E.↗
NASA NTRS1948

Theoretical Comparison of Several Methods of Thrust Augmentation for Turbojet Engines

A theoretical investigation has been made of various methods of thrust augmentation for turbojet engines. The method investigated were tail-pipe burning, water injection at the compressor inlet, a combination of tail-pipe burning and water injection, bleedoff in conjunction with water injection at the compressor inlet, and rocket assist. The effect of ratio of augmented-to-normal total liquid consumption, flight conditions, and design compressor pressure ratio on the augmentation produced by each method were determined. A comparison was also made for a given time of operation of the weight of an augmented engine plus fuel and additional liquids to the weight of a standard engine plus fuel producing the same thrust.

Hall, Eldon W.↗