Search NASA⌕ Search

SEARCH · Search NASA

Results for “Active learning”

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 1,045 records · Page 58
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

Considerations for Corridor and Community DC Fast Charging Complex System Design

As auto manufacturers bring vehicles to market with large batteries that provide over 200 miles of driving range, interest in faster charging options for plug-in electric vehicles (PEVs) is intensifying. This report focuses on direct current fast charger (DCFC) systems and how they can be deployed to provide convenient charging for PEV drivers. First, lessons learned from previous DCFC deployment and data collection activities are shared to describe consumer experience with DCFC systems to date. Second, considerations and criteria are established for designing and upgrading DCFC complexes that provide fast-charging opportunities for PEV drivers in urban communities and on rural corridors. Third, cost estimates are shared for hypothetical high-power DCFC complexes that meet simplified design requirements. Finally, results for a business case analysis are presented that shed light on the financial challenges associated with DCFCs.

25 ENERGY STORAGE↗
NASA NTRS1994

An intelligent robotic aid system for human services

The long term goal of our research at the Intelligent Robotic Laboratory at Vanderbilt University is to develop advanced intelligent robotic aid systems for human services. As a first step toward our goal, the current thrusts of our R&D are centered on the development of an intelligent robotic aid called the ISAC (Intelligent Soft Arm Control). In this paper, we describe the overall system architecture and current activities in intelligent control, adaptive/interactive control and task learning.

Kawamura, K.↗
NASA NTRS1992

Composite fuselage shell structures research at NASA Langley Research Center

Fuselage structures for transport aircraft represent a significant percentage of both the weight and the cost of these aircraft primary structures. Composite materials offer the potential for reducing both the weight and the cost of transport fuselage structures, but only limited studies of the response and failure of composite fuselage structures have been conducted for transport aircraft. The behavior of these important primary structures must be understood, and the structural mechanics methodology for analyzing and designing these complex stiffened shell structures must be validated in the laboratory. The effects of local gradients and discontinuities on fuselage shell behavior and the effects of local damage on pressure containment must be thoroughly understood before composite fuselage structures can be used for commercial aircraft. This paper describes the research being conducted and planned at NASA LaRC to help understand the critical behavior or composite fuselage structures and to validate the structural mechanics methodology being developed for stiffened composite fuselage shell structure subjected to combined internal pressure and mechanical loads. Stiffened shell and curved stiffened panel designs are currently being developed and analyzed, and these designs will be fabricated and then tested at Langley to study critical fuselage shell behavior and to validate structural analysis and design methodology. The research includes studies of the effects of combined internal pressure and mechanical loads on nonlinear stiffened panel and shell behavior, the effects of cutouts and other gradient-producing discontinuities on composite shell response, and the effects of local damage on pressure containment and residual strength. Scaling laws are being developed that relate full-scale and subscale behavior of composite fuselage shells. Failure mechanisms are being identified and advanced designs will be developed based on what is learned from early results from the LaRC research activities. Results from combined load tests will be used to validate analytical models of critical nonlinear response mechanisms as well as shell scaling laws.

Starnes, James H., Jr.↗
NASA NTRS1995

International Space Station environmental control and life support system. Phase 3: Water Recovery Test Stage 9

A test has been completed at NASA's Marshall Space Flight Center (MSFC) to evaluate the latest water recovery system design for the United States On-Orbit Segment (USOS) of the International Space Station (ISS) with higher fidelity hardware and integration than has been achieved in previous Water Recovery Test (WRT) Stages. This test is referred to as WRT Stage 9. Potable and urine processing assemblies were integrated with end-use equipment and operated for 116 days. The overall integrated configuration of the test system included a single water recovery loop that was automated and controlled from a central computer. This report summarizes the test objectives, system design, test activities and protocols, significant results, anomalies and lessons learned throughout the WRT Stage 9.

D L Carter↗
NASA NTRS1996

Experiences in Interagency and International Interfaces for Mission Support

The Flight Dynamics Division (FDD) of the National Aeronautics and Space Administration (NASA) Goddard Space Flight Center (GFSC) provides extensive support and products for Space Shuttle missions, expendable launch vehicle launches, and routine on-orbit operations for a variety of spacecraft. A major challenge in providing support for these missions is defining and generating the products required for mission support and developing the method by which these products are exchanged between supporting agencies. As interagency and international cooperation has increased in the space community, the FDD customer base has grown and with it the number and variety of external interfaces and product definitions. Currently, the FDD has working interfaces with the NASA Space and Ground Networks, the Johnson Space Center, the White Sands Complex, the Jet propulsion Laboratory (including the Deep Space Network), the United States Air Force, the Centre National d'Etudes Spatiales, the German Spaceflight Operations Center, the European Space Agency, and the National Space Development Agency of Japan. With the increasing spectrum of possible data product definitions and delivery methods, the FDD is using its extensive interagency experience to improve its support of established customers and to provide leadership in adapting/developing new interfaces. This paper describes the evolution of the interfaces between the FDD and its customers, discusses many of the joint activities ith these customers, and summarizes key lessons learned that can be applied to current and future support.

Dell, G. T.↗
NASA NTRS2005

STS-114 Flight Day 13 and 14 Highlights

On Flight Day 13, the crew of Space Shuttle Discovery on the STS-114 Return to Flight mission (Commander Eileen Collins, Pilot James Kelly, Mission Specialists Soichi Noguchi, Stephen Robinson, Andrew Thomas, Wendy Lawrence, and Charles Camarda) hear a weather report from Mission Control on conditions at the shuttle's possible landing sites. The video includes a view of a storm at sea. Noguchi appears in front of a banner for the Japanese Space Agency JAXA, displaying a baseball signed by Japanese MLB players, demonstrating origami, displaying other crafts, and playing the keyboard. The primary event on the video is an interview of the whole crew, in which they discuss the importance of their mission, lessons learned, shuttle operations, shuttle safety and repair, extravehicular activities (EVAs), astronaut training, and shuttle landing. Mission Control dedicates the song "A Piece of Sky" to the Shuttle crew, while the Earth is visible below the orbiter. The video ends with a view of the Earth limb lit against a dark background.

Source record↗
NASA NTRS2010

STEM Education Efforts in the Ares Projects

According to the National Science Foundation, of the more than 4 million first university degrees awarded in science and engineering in 2006, students in China earned about 21%, those in the European Union earned about 19%, and those in the United States earned about 11%. Statistics like these are of great interest to NASA's Ares Projects, which are responsible for building the rockets for the U.S. Constellation Program to send humans beyond low-Earth orbit. Science, technology, engineering, and mathematics students are essential for the long-term sustainability of any space program. Since the Projects creation, the Ares Outreach Team has used a variety of STEM-related media, methods, and materials to engage students, educators, and the general public in Constellation's mission. Like Project Apollo, the nation s exploration destinations and the vehicles used to get there can inspire students to learn more about STEM. Ares has been particularly active in public outreach to schools in Northern Alabama; on the Internet via outreach and grade-specific educational materials; and in more informal social media settings such as YouTube and Facebook. These combined efforts remain integral to America s space program, regardless of its future direction.

Doreswamy, Rajiv↗
NASA NTRSDate not supplied

Localizing Earth Science: The NASA DEVELOP Model of Community Science & Engagement

NASA’s DEVELOP Program conducts rapid feasibility studies that apply Earth observations to address community priorities and needs and enable informed decision making. Part of NASA’s Applied Sciences’ Capacity Building Program, DEVELOP builds skills in both participants (students, recent graduates, and early/transitioning career professionals) who conduct projects on small teams, and partner organizations (state and local governments, federal agencies, non-profit and for-profit organizations, and international organizations) that work closely with DEVELOP to design the project. While only a subset of DEVELOP partner organizations are local municipalities or community-led non-profits, the DEVELOP model is an effective engagement tool and often used by NASA as an introduction for communities to engage in Earth science research and familiarization with satellite remote sensing. This presentation will highlight the DEVELOP model of co-production and community collaboration, lessons learned in partnering with local communities, and evaluation activities that look at the program’s reach and efforts.

Robert Cecil Byles↗
DOE OSTI2017

Technology Basis for Savannah River Tank Closure Cesium Removal Project - 17448

Westinghouse is currently executing a contract, awarded in June 2016 from Savannah River Remediation LLC, to deliver a system capable of removing solids and up to 100,000 curies of Cesium-137 from tank 10H, located in the Savannah River 'tank farm'. Savannah River Remediation currently has the responsibility to perform work for the Savannah River Site Liquid Waste Operations Program at the Savannah River Site for the US government, represented by the US DOE under their Principal contract. The scope of work covers the detailed design, procurement, fabrication, and delivery of the system to the Savannah River Site. It also includes the factory acceptance testing of the system, prior to delivery to site. Before leaving the site, Westinghouse will perform an evaluation of the system assembly and operations training for the incumbent operator. The basis for the technology chosen to accomplish the solids and Cesium-137 removal is unique to the specific feed stream, but is based on well-known and successful technology, Toshiba SARRY water cleanup system. Toshiba is Westinghouse's parent company, allowing us to reach back and incorporate the lessons learned during the water cleanup at Fukushima Daiichi and the integration of various technologies. Another key to the technology basis was the ion exchange media selection. A number of possible ion exchange media for the cesium removal were considered with the final choice being inorganic CST resin. Several criteria were considered and compared, such as the radiation sensitivity of the CST and the cesium specific ion preference. This paper will present the conceptual design of the modular system, noting the key benefits of specific components in the overall technology basis. Along with the design, a look at key technology improvements carried into the design through the Toshiba SARRY system will be incorporated. A first feedback on the implementation of the overall project will be provided. Since this system is a first-of-a-kind in this specific application, interesting lessons learned will be provided for future tank closure activities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2020

Energy-Efficient Self-Organization and Swarm Behavior in Active Matter

Living systems have the unique ability to form hierarchical assemblies, in which individual constituents can perform tasks cooperatively and emergently. Harnessing such properties is a long-standing challenge for the rational design of dynamic materials, that can respond to their environment, communicate with one another, and undergo a rapid, reversible, assembly through the transduction of energy. Recent developments in the design of smart and active colloidal building blocks have led to tremendous breakthroughs, with, for instance, the onset of synthetic photoactivated active assemblies. In this project, we develop a combined experimental, computational, theoretical and Machine Learning framework to shed light on the physical underpinnings of such assembly processes and program the assembly of smart active materials.

36 MATERIALS SCIENCE↗
DOE OSTI2018

Lessons Learned from the Remote Reactor Vessel Internals Segmentation at Barsebaeck 2 - 18231

Westinghouse is performing a decommissioning project at Barsebaeck in Sweden that was awarded in June 2015. Barsebaeck is an ABB-designed boiling water reactor (BWR) plant (2 units of 615 MW) located 30 kilometers from Malmoe. The first reactor, Barsebaeck 1, was permanently shut down on Nov. 30, 1999, and the second one, Barsebaeck 2, ceased operation on May 31, 2005. The scope of work covers the underwater segmentation and packaging of the Reactor Vessel internals at Barsebaeck 1 and 2, including the up-front engineering studies and equipment manufacturing and qualification. The Barsebaeck Unit 2 was selected for starting the site work in August 2016. Cutting was performed with different types of Westinghouse designed cutting equipment (hydraulic shears, band saw, disc saw). All segmentation tools are remotely controlled due to the high radiation levels and ALARA and personal safety is the number one priority during the site work. The cutting equipment proved to be reliable and flexible which is very valuable for the execution of such a challenging project. The Barsebaeck Unit 2 cutting activities have been finished end of October 2018 and its lessons learned will be taken into consideration for the Unit 1 activities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
NASA NTRS2021

Machine Learning the COSMO Model for Predicting Thermodynamics of Electrolyte Mixtures

Bottom-up design of electrolyte mixtures for battery systems requires predicting macro thermodynamic properties from molecular constituents. For instance, molten salt electrolyte batteries require conditions far above room temperature to operate. Therefore, discovering mixtures with increasingly lower eutectic melting points is desirable. A model that can approximate chemical activity is a valuable tool to search through the vast compositional design space. Machine learning can predict properties of materials such as vibrational free energies, electronic energy gaps, and thermal conductivities. Moreover, they can learn physical models such as interatomic potentials. The COSMO-SAC model uses theory and empirical parameterization to predict liquid-vapor and liquid-solid properties using first-principles calculations. However, obtaining activity coefficients required for parameterizing the COSMO-SAC model is costly and limited to a select chemical space. In this work, we explored if machine learning methods could improve the COSMO-SAC model and bridge density functional theory calculations to liquid phase thermodynamic properties. Our data-driven approach uses existing databases for sigma-profiles of organic solvents and reconciles their methodological differences via ensemble averaging. First, an optimal machine learning model is constructed for each dataset. Our machine learning algorithms use the sigma-profile as an input feature to predict binary mixtures' activity coefficients using multi-output regression. Each dataset uses different choices of functionals, methods, and basis sets. Therefore, our ensemble model attempts to predict corrected activity coefficients given the combination of all the model outputs. The activity coefficients used for training are generated using the COSMO-SAC model. This approach enables the extraction of meaningful information from the existing datasets to improve the COSMO-SAC model for obtaining thermodynamic properties of electrolyte mixtures. With the liquid phase activities, we can identify electrolyte mixtures that meet desired phase equilibria conditions.

Thermodynamics↗
DOE OSTI2025

Machine Learning-Assisted Recovery of Delicate Kinetic Information from Transient Reactor Experiments

Identifying active sites and their roles in chemical reaction steps remains a vital challenge in heterogeneous catalysis. Transient experiments offer a unique way to probe active sites and distinguish subtle kinetic features. Although physics-based analysis methods may be well-developed, they can be highly susceptible to experimental noise, and smoothing methods may erase or even distort important features; a smooth curve is not always the best curve. We demonstrate a new workflow for the direct interpretation of intrinsic kinetic information from exit flux curves measured in transient reactor experiments. This workflow contains three artificial neural networks (ANNs), including a noise reducer, a concentration predictor, and a rate predictor to analyze experimental data, followed by the virtual TAP (VTAP) physics-based reactor model and density functional theory (DFT) calculations of adsorption energies on specific sites. We use this workflow to analyze the data from experiments titrating Pt/Al 2 O 3 and Pt/SiO 2 catalysts with carbon monoxide (CO) in the temporal analysis of products (TAP) reactor. Our workflow separates the time-evolving chemical reaction and mass transfer information contained in the TAP pulse response. The existence of strong- and weak-binding sites on the Pt/Al 2 O 3 catalyst is observed in the catalyst titration experiment in the transient reactor. The structures of the strong- and weak-binding sites are then identified by using DFT calculations. We find that the Pt/SiO 2 catalyst has only strong-binding sites, which aligns with the inactive support effect of SiO 2 . We demonstrate how machine learning methods provide unique insights with high-resolution data analysis that cannot be achieved by using state-of-the-art physics-based methods.

Adsorption↗
DOE OSTI2019

Report of the Workshop on Advanced Fusion with Machine Learning, April 30-May 2, 2019

The pursuit of fusion energy has led to extensive activities in both experimental and theoretical science. The central goal of all these activities has been to develop the knowledge necessary for the design of successful fusion power plants. Even today, following decades of research in many key areas including plasma physics and material science, much remains to be learned in order to achieve optimization of the tokamak or other paths to fusion energy. Data science methods from the fields of machine learning and artificial intelligence (ML/AI) offer opportunities for enabling or accelerating progress toward the realization of fusion energy by maximizing the amount and usefulness of information extracted from experimental and simulation output data. From April 30 to May 2 of 2019, a workshop on “Advancing Fusion with Machine Learning Research Needs” was held in Gaithersburg, MD, with joint support from the Fusion Energy Science (FES) and Advanced Scientific Computing Research (ASCR) Programs. The workshop brought together ~ 60 experts in fields spanning fusion science, data science, statistical inference and mathematics, machine learning, and artificial intelligence, along with DOE program managers and technical experts, with the goal of identifying Priority Research Opportunities (PROs) for the application of ML/AI methods to accelerating progress on solving fusion problems. During the workshop, seven key PROs were identified. The description of each PRO includes relevant fusion problems, potentially useful ML/AI approaches, known gaps currently preventing the use of such approaches, and research guidelines to maximize the effective application of ML/AI methods to the PRO. The report containing the full description of the workshop outcomes is available at https://science.osti.gov/-/media/fes/pdf/workshopreports/FES_ASCR_Machine_Learning_Report.pdf

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Developing a Deep Learning-Computer Vision Framework to Monitor Avian Interactions with Solar Energy Facility Infrastructure (Final Technical Report)

The project addressed an inability to monitor avian interactions with photovoltaic (PV) solar energy facilities necessary for understanding PV solar impacts on birds. In the project, machine-vision technology that continuously monitors avian activities at PV solar facilities was developed. The technology includes four machine-learning (ML) models, each of which accomplishes a specific task in detecting birds and classifying their activities in live or recorded videos—detecting and tracking moving objects, differentiating birds from other objects, detecting bird collisions with solar panels, and classifying non-collision bird activities around PV facilities. Major project outcomes include adoption by two of DOE SETO’s SolWEB projects, providing novel observational data on birds to promote co-location of PV solar development and habitat conservation, known as ecovoltaics.

14 SOLAR ENERGY↗
DOE OSTI2023

Machine Learning Based Resilience Testing of an Address Randomization Cyber Defense

Moving target defenses (MTDs) are widely used as an active defense strategy for thwarting cyberattacks on cyber-physical systems by increasing diversity of software and network paths. Recently, machine Learning (ML) and deep Learning (DL) models have been demonstrated to defeat some of the cyber defenses by learning attack detection patterns and defense strategies. It raises concerns about the susceptibility of MTD to ML and DL methods. Here, in this article, we analyze the effectiveness of ML and DL models when it comes to deciphering MTD methods and ultimately evade MTD-based protections in real-time systems. Specifically, we consider a MTD algorithm that periodically randomizes address assignments within the MIL-STD-1553 protocol—a military standard serial data bus. Two ML and DL-based tasks are performed on MIL-STD-1553 protocol to measure the effectiveness of the learning models in deciphering the MTD algorithm: 1) determining whether there is an address assignments change i.e., whether the given system employs a MTD protocol and if it does 2) predicting the future address assignments. The supervised learning models (random forest and k-nearest neighbors) effectively detected the address assignment changes and classified whether the given system is equipped with a specified MTD protocol. On the other hand, the unsupervised learning model (K-means) was significantly less effective. The DL model (long short-term memory) was able to predict the future addresses with varied effectiveness based on MTD algorithm's settings.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗
DOE OSTI2020

Development of neural network force fields for corrosion studies

To fully understand the chemistry and physics of corrosion, novel methods of simulation must be developed. One approach is designing machine learning (ML) algorithms integrated with density functional theory to develop adaptive force fields to gain insight into corrosion behavior namely at the surface of metal oxides. Current methods of modeling corrosion are slow due to the computational cost of resolving both reaction mechanics and mass transport processes. Machine learning methods can be implemented to obtain structure-activity relationships at both the molecular and bulk scale while still retaining the accuracy of density functional theory (DFT) and significantly decreasing the time needed for simulations of complex chemical processes in the various environments of corrosion. Multiscale models are needed for corrosion studies to fully understand its processes not only at the atomic length scale (chemical bonding, energies, and forces), but also at the nano and meso length scales (solid-state physics and material science processes). Current methods of study include DFT, molecular dynamics, and Monte Carlo. The limitation of DFT is that only a small number of atoms or molecules can be simulated at that level of theory. Density functional theory is used to study the electronic structure of atoms and molecules, and calculate the force component of each atom. However, these calculations are limited to about 1000 atoms. Custom periodic boundary conditions (PBC) can be used to describe the various environments and defects that affect the atomic forces to produce a large data set from which a training set can be derived. Machine learning can be utilized to overcome the barrier of modeling macroscopic and multi-scale processes from ab initio calculations through the development of adaptive force fields. Local environments determine the atomic forces of a given system, therefore adaptive force fields must be created to produce reliable quantum mechanical calculations. This can be achieved by developing a learning algorithm that uses the mapped atomic forces or fingerprint as an input to produce energies and magnetic moments as output. A systematic approach was used to begin to build a data set in order to accurately describe the atomic forces in various environments. In Figure 4 below, a simple PBC cell of Fe{sub 2}O{sub 3} was first optimized. A surface optimization was performed next, followed by a hydroxylated surface optimization. Once this calculation has converged, the adsorption of halide species to the hydroxylated surface will be investigated. TensorFlow is an open source platform for machine learning developed by Google. Using a high level application program interface (API) such as Keras allows for building and training ML models easily in a number of different environments and languages. For this project, a neural network was developed within Anaconda in Python. Future Work: Further development of reference data set; Refining neural network and learning algorithm; Fingerprinting atomic environment to enable mapping of atomic force components; Choosing appropriate training set from reference data; Learning from training set and enabling non-linear mapping of training set fingerprints and the atomic forces; Estimation of uncertainty to identify ranges of outside applicability; Testing and analysis of molecular dynamic simulations.

36 MATERIALS SCIENCE↗