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 1,531 records · Page 85

Reduced Order Model for Guided Wave Propagation on Gas Pipelines to Enable Real-Time Simulation

Reduced order model for simulation of Guided wave propagation is presented here. The utilization of reduced order models ensures efficient data generation for a variety of parameters where it takes huge computational effort to simulate, crucial for timely monitoring and decision-making. Autoencoder based reduced order models are proposed here, which are trained on simulated data from open-source finite element framework, Firedrake.

Bukka, Sandeep Reddy↗

Predicting Mechanical Properties from Microstructure Images in Fiber-Reinforced Polymers Using Convolutional Neural Networks

Evaluating the mechanical response of fiber-reinforced composites can be extremely time-consuming and expensive. Machine learning (ML) techniques offer a means for faster predictions via models trained on existing input–output pairs and have exhibited success in composite research. This paper explores a fully convolutional neural network modified from StressNet, which was originally used for linear elastic materials, and extended here for a non-linear finite element (FE) simulation to predict the stress field in 2D slices of segmented tomography images of a fiber-reinforced polymer specimen. The network was trained and evaluated on data generated from the FE simulations of the exact microstructure. The testing results show that the trained network accurately captures the characteristics of the stress distribution, especially on fibers, solely from the segmented microstructure images. The trained model can make predictions within seconds in a single forward pass on an ordinary laptop, given the input microstructure, compared to 92.5 h to run the full FE simulation on a high-performance computing cluster. These results show promise in using ML techniques to conduct fast structural analysis for fiber-reinforced composites and suggest a corollary that the trained model can be used to identify the location of potential damage sites in fiber-reinforced polymers.

Sun, Yixuan (ORCID:0000000311093380)↗

DeepZipper. II. Searching for Lensed Supernovae in Dark Energy Survey Data with Deep Learning

Gravitationally lensed supernovae (LSNe) are important probes of cosmic expansion, but they remain rare and difficult to find. Current cosmic surveys likely contain 5–10 LSNe in total while next-generation experiments are expected to contain several hundred to a few thousand of these systems. We search for these systems in observed Dark Energy Survey (DES) five year SN fields—10 3 sq. deg. regions of sky imaged in the griz bands approximately every six nights over five years. To perform the search, we utilize the DeepZipper approach: a multi-branch deep learning architecture trained on image-level simulations of LSNe that simultaneously learns spatial and temporal relationships from time series of images. We find that our method obtains an LSN recall of 61.13% and a false-positive rate of 0.02% on the DES SN field data. DeepZipper selected 2245 candidates from a magnitude-limited (m i < 22.5) catalog of 3,459,186 systems. We employ human visual inspection to review systems selected by the network and find three candidate LSNe in the DES SN fields.

79 ASTRONOMY AND ASTROPHYSICS↗

Climate-driven deterioration of future ozone pollution in Asia predicted by machine learning with multi-source data

Ozone (O 3 ) is a secondary pollutant in the atmosphere formed by photochemical reactions that endangers human health and ecosystems. O 3 has aggravated in Asia in recent decades and will vary in the future. In this study, to quantify the impacts of future climate change on O 3 pollution, near-surface O 3 concentrations over Asia in 2020–2100 are projected using a machine learning (ML) method along with multi-source data. The ML model is trained with combined O 3 data from a global atmospheric chemical transport model and real-time observations. The ML model is then used to estimate future O 3 with meteorological fields from multi-model simulations under various climate scenarios. The near-surface O 3 concentrations are projected to increase by 5 %–20 % over South China, Southeast Asia, and South India and less than 10 % over North China and the Gangetic Plains under the high-forcing scenarios in the last decade of 21st century, compared to the first decade of 2020–2100. The O 3 increases are primarily owing to the favorable meteorological conditions for O 3 photochemical formation in most Asian regions. We also find that the summertime O 3 pollution over eastern China will expand from North China to South China and extend into the cold season in a warmer future. Our results demonstrate the important role of a climate change penalty on Asian O 3 in the future, which provides implications for environmental and climate strategies of adaptation and mitigation.

54 ENVIRONMENTAL SCIENCES↗

Coupled dynamics analysis of wind energy systems

A qualitative description of all key elements of a complete wind energy system computer analysis code is presented. The analysis system addresses the coupled dynamics characteristics of wind energy systems, including the interactions of the rotor, tower, nacelle, power train, control system, and electrical network. The coupled dynamics are analyzed in both the frequency and time domain to provide the basic motions and loads data required for design, performance verification and operations analysis activities. Elements of the coupled analysis code were used to design and analyze candidate rotor articulation concepts. Fundamental results and conclusions derived from these studies are presented.

Hoffman, J. A.↗

Intelligent guidance and control for wind shear encounter

The principal objective is to develop methods for assessing the likelihood of wind shear encounter, for deciding what flight path to pursue, and for using the aircraft's full potential for combating wind shear. This study requires the definition of both deterministic and statistical techniques for fusing internal and external information, for making go/no-go decisions, and for generating commands to the aircraft's cockpit displays and autopilot for both manually controlled and automatic flight. The program has begun with the development of a real-time expert system for pilot aiding that is based on the results of the FAA Windshear Training Aids Program. A two-volume manual that presents an overview, pilot guide, training program, and substantiating data provides guidelines for this initial development. The Expert System to Avoid Wind Shear (ESAWS) currently contains over 140 rules and is coded in the LISP programming language for implementation on a Symbolics 3670 LISP machine.

Stengel, Robert F.↗

Network management tools for a GPS datalink network

The availability of GPS (Global Position Satellite) information in real-time via a datalink system is shown to significantly increase the capacity of flight test and training ranges in terms of missions supported. This increase in mission activity. imposes demands on mission planning in the range-operations environment. In this context, network management tools which can improve the capability of range personnel to plan, monitor, and control network resources, are of significant interest. The application of both simulation and artificial intelligence techniques is described to develop such network managements tools.

Smyth, Padhraic↗

Computational Tools and Facilities for the Next-Generation Analysis and Design Environment

This document contains presentations from the joint UVA/NASA Workshop on Computational Tools and Facilities for the Next-Generation Analysis and Design Environment held at the Virginia Consortium of Engineering and Science Universities in Hampton, Virginia on September 17-18, 1996. The presentations focused on the computational tools and facilities for analysis and design of engineering systems, including, real-time simulations, immersive systems, collaborative engineering environment, Web-based tools and interactive media for technical training. Workshop attendees represented NASA, commercial software developers, the aerospace industry, government labs, and academia. The workshop objectives were to assess the level of maturity of a number of computational tools and facilities and their potential for application to the next-generation integrated design environment.

Noor, Ahmed K.↗

Generalized Predictive and Neural Generalized Predictive Control of Aerospace Systems

The research work presented in this thesis addresses the problem of robust control of uncertain linear and nonlinear systems using Neural network-based Generalized Predictive Control (NGPC) methodology. A brief overview of predictive control and its comparison with Linear Quadratic (LQ) control is given to emphasize advantages and drawbacks of predictive control methods. It is shown that the Generalized Predictive Control (GPC) methodology overcomes the drawbacks associated with traditional LQ control as well as conventional predictive control methods. It is shown that in spite of the model-based nature of GPC it has good robustness properties being special case of receding horizon control. The conditions for choosing tuning parameters for GPC to ensure closed-loop stability are derived. A neural network-based GPC architecture is proposed for the control of linear and nonlinear uncertain systems. A methodology to account for parametric uncertainty in the system is proposed using on-line training capability of multi-layer neural network. Several simulation examples and results from real-time experiments are given to demonstrate the effectiveness of the proposed methodology.

Kelkar, Atul G.↗

Balance System

TherEx Inc.'s AT-1 Computerized Ataxiameter precisely evaluates posture and balance disturbances that commonly accompany neurological and musculoskeletal disorders. Complete system includes two-strain gauged footplates, signal conditioning circuitry, a computer monitor, printer and a stand-alone tiltable balance platform. AT-1 serves as assessment tool, treatment monitor, and rehabilitation training device. It allows clinician to document quantitatively the outcome of treatment and analyze data over time to develop outcome standards for several classifications of patients. It can evaluate specifically the effects of surgery, drug treatment, physical therapy or prosthetic devices.

Source record↗

Pulse Detonation Engine Test Bed Developed

A detonation is a supersonic combustion wave. A Pulse Detonation Engine (PDE) repetitively creates a series of detonation waves to take advantage of rapid burning and high peak pressures to efficiently produce thrust. NASA Glenn Research Center's Combustion Branch has developed a PDE test bed that can reproduce the operating conditions that might be encountered in an actual engine. It allows the rapid and cost-efficient evaluation of the technical issues and technologies associated with these engines. The test bed is modular in design. It consists of various length sections of both 2- and 2.6- in. internal-diameter combustor tubes. These tubes can be bolted together to create a variety of combustor configurations. A series of bosses allow instrumentation to be inserted on the tubes. Dynamic pressure sensors and heat flux gauges have been used to characterize the performance of the test bed. The PDE test bed is designed to utilize an existing calorimeter (for heat load measurement) and windowed (for optical access) combustor sections. It uses hydrogen as the fuel, and oxygen and nitrogen are mixed to simulate air. An electronic controller is used to open the hydrogen and air valves (or a continuous flow of air is used) and to fire the spark at the appropriate times. Scheduled tests on the test bed include an evaluation of the pumping ability of the train of detonation waves for use in an ejector and an evaluation of the pollutants formed in a PDE combustor. Glenn's Combustion Branch uses the National Combustor Code (NCC) to perform numerical analyses of PDE's as well as to evaluate alternative detonative combustion devices. Pulse Detonation Engine testbed.

Breisacher, Kevin J.↗

Brain-Computer Interfaces for 1-D and 2-D Cursor Control: Designs Using Volitional Control of the EEG Spectrum or Steady-State Visual Evoked Potentials

We have developed and tested two EEG-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target Practice, is a system for one-dimensional device control, in which participants use biofeedback to learn voluntary control of their EEG spectra. Target Practice uses a KF LS classifier to map power spectra of 30-electrode EEG signals to rightward or leftward position of a moving cursor on a computer display. Three subjects learned to control motion of a cursor on a video display in multiple blocks of 60 trials over periods of up to six weeks. The best subject s average skill in correct selection of the cursor direction grew from 58% to 88% after 13 training sessions. Target Practice also implements online control of two artifact sources: a) removal of ocular artifact by linear subtraction of wavelet-smoothed vertical and horizontal EOG signals, b) control of muscle artifact by inhibition of BCI training during periods of relatively high power in the 40-64 Hz band. The second BCI, Think Pointer, is a system for two-dimensional cursor control. Steady-state visual evoked potentials (SSVEP) are triggered by four flickering checkerboard stimuli located in narrow strips at each edge of the display. The user attends to one of the four beacons to initiate motion in the desired direction. The SSVEP signals are recorded from eight electrodes located over the occipital region. A KPLS classifier is individually calibrated to map multichannel frequency bands of the SSVEP signals to right-left or up-down motion of a cursor on a computer display. The display stops moving when the user attends to a central fixation point. As for Target Practice, Think Pointer also implements wavelet-based online removal of ocular artifact; however, in Think Pointer muscle artifact is controlled via adaptive normalization of the SSVEP. Training of the classifier requires about three minutes. We have tested our system in real-time operation in three human subjects. Across subjects and sessions, control accuracy ranged from 80% to 100% correct with lags of 1-5 seconds for movement initiation and turning.

Trejo, Leonard J.↗

Walking the Walk/Talking the Talk: Mission Planning with Speech-Interactive Agents

The application of simulation technology to mission planning and rehearsal has enabled realistic overhead 2-D and immersive 3-D "fly-through" capabilities that can help better prepare tactical teams for conducting missions in unfamiliar locales. For aircrews, detailed terrain data can offer a preview of the relevant landmarks and hazards, and threat models can provide a comprehensive glimpse of potential hot zones and safety corridors. A further extension of the utility of such planning and rehearsal techniques would allow users to perform the radio communications planned for a mission; that is, the air-ground coordination that is critical to the success of missions such as close air support (CAS). Such practice opportunities, while valuable, are limited by the inescapable scarcity of complete mission teams to gather in space and time during planning and rehearsal cycles. Moreoever, using simulated comms with synthetic entities, despite the substantial training and cost benefits, remains an elusive objective. In this paper we report on a solution to this gap that incorporates "synthetic teammates" - intelligent software agents that can role-play entities in a mission scenario and that can communicate in spoken language with users. We employ a fielded mission planning and rehearsal tool so that our focus remains on the experimental objectives of the research rather than on developing a testbed from scratch. Use of this planning tool also helps to validate the approach in an operational system. The result is a demonstration of a mission rehearsal tool that allows aircrew users to not only fly the mission but also practice the verbal communications with air control agencies and tactical controllers on the ground. This work will be presented in a CAS mission planning example but has broad applicability across weapons systems, missions and tactical force compositions.

Bell, Benjamin↗

Gas Dynamic Spray Technology Demonstration Project Management

The standard practice for protecting metallic substrates in atmospheric environments is the use of an applied coating system. Current coating systems used across AFSPC and NASA contain volatile organic compounds (VOCs) and hazardous air pollutants (HAPs). These coatings are sUbject to environmental regulations at the Federal and State levels that limit their usage. In addition, these coatings often cannot withstand the high temperatures and exhaust that may be experienced by Air Force Space Command (AFSPC) and NASA structures. In response to these concerns, AFSPC and NASA have approved the use of thermal spray coatings (TSCs). Thermal spray coatings are extremely durable and environmentally friendly coating alternatives, but utilize large cumbersome equipment for application that make the coatings difficult and time consuming to repair. Other concerns include difficulties coating complex geometries and the cost of equipment, training, and materials. Gas Dynamic Spray (GOS) technology (also known as Cold Spray) was evaluated as a smaller, more maneuverable repair method as well as for areas where thermal spray techniques are not as effective. The technology can result in reduced maintenance and thus reduced hazardous materials/wastes associated with current processes. Thermal spray and GOS coatings also have no VOCs and are environmentally preferable coatings. The primary objective of this effort was to demonstrate GDS technology as a repair method for TSCs. The aim was that successful completion of this project would result in approval of GDS technology as a repair method for TSCs at AFSPC and NASA installations to improve corrosion protection at critical systems, facilitate easier maintenance activity, extend maintenance cycles, eliminate flight hardware contamination, and reduce the amount of hazardous waste generated.

Lewis, Pattie↗

Joint Test Plan for Gas Dynamic Spray Technology Demonstration

Air Force Space Command (AFSPC) and NASA have similar missions, facilities, and structures located in similar harsh environments. Both are responsible for a number of facilities/structures with metallic structural and non-structural components in highly and moderately corrosive environments. Regardless of the corrosivity of the environment, all metals require periodic maintenance activity to guard against the insidious effects of corrosion and thus ensure that structures meet or exceed design or performance life. The standard practice for protecting metallic substrates in atmospheric environments is the use of an applied coating system. Current coating systems used across AFSPC and NASA contain volatile organic compounds (VOCs) and hazardous air pollutants (HAPs). These coatings are subject to environmental regulations at the Federal and State levels that limit their usage. In addition, these coatings often cannot withstand the high temperatures and exhaust that may be experienced by AFSPC and NASA structures. In response to these concerns, AFSPC and NASA have approved the use of thermal spray coatings (TSCs). Thermal spray coatings are extremely durable and environmentally friendly coating alternatives, but utilize large cumbersome equipment for application that make the coatings difficult and time consuming to repair. Other concerns include difficulties coating complex geometries and the cost of equipment, training, and materials. Gas Dynamic Spray (GDS) technology (also known as Cold Spray) will be evaluated as a smaller, more maneuverable repair method as well as for areas where thermal spray techniques are not as effective. The technology can result in reduced maintenance and thus reduced hazardous materials/wastes associated with current processes. Thermal spray and GDS coatings also have no VOCs and are environmentally preferable coatings. To achieve a condition suitable for the application of a coating system, including GDS coatings, the substrate must undergo some type of surface preparation and/or depainting operation to ensure adhesion of the new coating system. The GDS unit selected for demonstration has a powder feeding system that can be used for surface preparation or coating application. The surface preparation feature will also be examined. The primary objective of this effort is to demonstrate GDS technology as a repair method for TSCs. The project will also determine the optimal GDS coating thickness for acceptable performance. Successful completion of this project will result in approval of GDS technology as a repair method for TSCs at AFSPC and NASA installations and will improve corrosion protection at critical systems, facilitate easier maintenance activity, extend maintenance cycles, eliminate flight hardware contamination, and reduce the amount of hazardous waste generated.

Lewis, Pattie↗

Affordability Approaches for Human Space Exploration

The design and development of historical NASA Programs (Apollo, Shuttle and International Space Station), have been based on pre-agreed missions which included specific pre-defined destinations (e.g., the Moon and low Earth orbit). Due to more constrained budget profiles, and the desire to have a more flexible architecture for Mission capture as it is affordable, NASA is working toward a set of Programs that are capability based, rather than mission and/or destination specific. This means designing for a performance capability that can be applied to a specific human exploration mission/destination later (sometime years later). This approach does support developing systems to flatter budgets over time, however, it also poses the challenge of how to accomplish this effectively while maintaining a trained workforce, extensive manufacturing, test and launch facilities, and ensuring mission success ranging from Low Earth Orbit to asteroid destinations. NASA Marshall Space Flight Center (MSFC) in support of Exploration Systems Directorate (ESD) in Washington, DC has been developing approaches to track affordability across multiple Programs. The first step is to ensure a common definition of affordability: the discipline to bear cost in meeting a budget with margin over the life of the program. The second step is to infuse responsibility and accountability for affordability into all levels of the implementing organization since affordability is no single person s job; it is everyone s job. The third step is to use existing data to identify common affordability elements organized by configuration (vehicle/facility), cost, schedule, and risk. The fourth step is to analyze and trend this affordability data using an affordability dashboard to provide status, measures, and trends for ESD and Program level of affordability tracking. This paper will provide examples of how regular application of this approach supports affordable and therefore sustainable human space exploration architecture.

Holladay, Jon↗

Pre-Mission Input Requirements to Enable Successful Sample Collection by A Remote Field/EVA Team

The FINESSE (Field Investigations to Enable Solar System Science and Exploration) team, part of the Solar System Exploration Virtual Institute (SSERVI), is a field-based research program aimed at generating strategic knowledge in preparation for human and robotic exploration of the Moon, near-Earth asteroids, Phobos and Deimos, and beyond. In contract to other technology-driven NASA analog studies, The FINESSE WCIS activity is science-focused and, moreover, is sampling-focused with the explicit intent to return the best samples for geochronology studies in the laboratory. We used the FINESSE field excursion to the West Clearwater Lake Impact structure (WCIS) as an opportunity to test factors related to sampling decisions. We examined the in situ sample characterization and real-time decision-making process of the astronauts, with a guiding hypothesis that pre-mission training that included detailed background information on the analytical fate of a sample would better enable future astronauts to select samples that would best meet science requirements. We conducted three tests of this hypothesis over several days in the field. Our investigation was designed to document processes, tools and procedures for crew sampling of planetary targets. This was not meant to be a blind, controlled test of crew efficacy, but rather an effort to explicitly recognize the relevant variables that enter into sampling protocol and to be able to develop recommendations for crew and backroom training in future endeavors.

FINESSE↗

Southern Colorado Disasters: Using NASA Observations to Map Aspen Extent and Recovery Due to Wildfire

Quaking aspen (Populus tremuloides) is an important species for wildlife, watershed health, and ecosystem resilience across its range. Heavy ungulate browsing and factors influenced by a changing climate including seasonal temperature changes and moisture deficit have led to reduced post-fire aspen regeneration rates in southern Colorado. This project partnered with Trinchera Ranch and the Colorado State Forest Service to estimate aspen recovery after the Spring Creek Fire, which ignited in June of 2018. The Southern Colorado Disasters team utilized field measurements and satellite imagery from Landsat Operational Land Imager (OLI), Sentinel-2 MultiSpectral Instrument (MSI), and the Shuttle Radar Topography Mission (SRTM) to train and run several random forest models that detect pre- and post-fire aspen extent. Ocular sampling of over 500 points on high-resolution pre-fire and post-fire images identified percentage aspen cover in 30 x 30-meter grid cells. This process provided training data for regression models, which were able to detect aspen across the landscape for both time periods using multiple remote sensing vegetation health indices. In addition, landscape suitability for aspen regeneration was modeled to provide a guide for managers on where to monitor for aspen regeneration post-fire.

DEVELOP Project Summary↗