Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Continual 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 865 records · Page 48

Bayesian sequential optimal experimental design for nonlinear models using policy gradient reinforcement learning

We present a mathematical framework and computational methods for optimally designing a finite sequence of experiments. This sequential optimal experimental design (sOED) problem is formulated as a finite-horizon partially observable Markov decision process (POMDP) under a Bayesian setting and with information-theoretic utilities. The formulation is general and may accommodate continuous random variables, non-Gaussian posteriors, and nonlinear forward models. The sOED design policy incorporates elements of feedback and lookahead simultaneously, and we show it to generalize the commonly-used batch and greedy design strategies. We solve for the sOED policy using the policy gradient (PG) method from reinforcement learning, and provide a derivation for the PG expression in the sOED context. Adopting an actor-critic approach, the policy and value functions are parameterized using deep neural networks and improved via PG estimates produced from simulated episodes of designs and observations. The new PG-sOED algorithm is first validated on a linear-Gaussian benchmark, and then compared against other design baselines on a sensor movement problem for contaminant source inversion in a convection-diffusion field. As a result, we provide explanation for the policy behaviors using knowledge of the underlying physical process.

97 MATHEMATICS AND COMPUTING↗

Volcano infrasound: progress and future directions

Over the past two decades (2000–2020), volcano infrasound (acoustic waves with frequencies less than 20 Hz propagating in the atmosphere) has evolved from an area of academic research to a useful monitoring tool. As a result, infrasound is routinely used by volcano observatories around the world to detect, locate, and characterize volcanic activity. It is particularly useful in confirming subaerial activity and monitoring remote eruptions, and it has shown promise in forecasting paroxysmal activity at open-vent systems. Fundamental research on volcano infrasound is providing substantial new insights on eruption dynamics and volcanic processes and will continue to do so over the next decade. The increased availability of infrasound sensors will expand observations of varied eruption styles, and the associated increase in data volume will make machine learning workflows more feasible. More sophisticated modeling will be applied to examine infrasound source and propagation effects from local to global distances, leading to improved infrasound-derived estimates of eruption properties. Future work will use infrasound to detect, locate, and characterize moving flows, such as pyroclastic density currents, lahars, rockfalls, lava flows, and avalanches. Infrasound observations will be further integrated with other data streams, such as seismic, ground- and satellite-based thermal and visual imagery, geodetic, lightning, and gas data. The volcano infrasound community should continue efforts to make data and codes accessible and to improve diversity, equity, and inclusion in the field. In summary, the next decade of volcano infrasound research will continue to advance our understanding of complex volcano processes through increased data availability, sensor technologies, enhanced modeling capabilities, and novel data analysis methods that will improve hazard detection and mitigation.

58 GEOSCIENCES↗

Expanding NASA and Roscosmos Scientific Collaboration on the International Space Station

The International Space Station (ISS) is a world-class laboratory orbiting in space. NASA and Roscosmos have developed a strong relationship through the ISS Program Partnership, working together and with the other ISS Partners for more than twenty years. Since 2013, based on a framework agreement between the Program Managers, NASA and Roscosmos are building a joint program of collaborative research on ISS. This international collaboration is developed and implemented in phases. Initially, members of the ISS Program Science Forum from NASA and TsNIIMash (representing Roscosmos) identified the first set of NASA experiments that could be implemented in the "near term". The experiments represented the research categories of Technology Demonstration, Microbiology, and Education. Through these experiments, the teams from the "program" and "operations" communities learned to work together to identify collaboration opportunities, establish agreements, and jointly plan and execute the experiments. The first joint scientific activity on ISS occurred in January 2014, and implementation of these joint experiments continues through present ISS operations. NASA and TsNIIMash have proceeded to develop "medium term" collaborations, where scientists join together to improve already-proposed experiments. A major success is the joint One-Year Mission on ISS, with astronaut Scott Kelly and cosmonaut Mikhail Kornienko, who returned from ISS in March, 2016. The teams from the NASA Human Research Program and the RAS Institute for Biomedical Problems built on their considerable experience to design joint experiments, learn to work with each other's protocols and processes, and share medical and research data. New collaborations are being developed between American and Russian scientists in complex fluids, robotics, rodent research and space biology, and additional human research. Collaborations are also being developed in Earth Remote Sensing, where scientists will share data from imaging systems mounted on ISS as well as other orbiting spacecraft to improve our understanding of the Earth and its climate. NASA and Roscosmos continue to encourage international scientific cooperation and expanded use of the ISS Laboratory. "Long-term", larger collaborations will achieve scientific objectives that no single national science team or agency can achieve on its own. The joint accomplishments achieved so far have paved the way for a stronger international scientific community and improved results and benefits from ISS.

Hasbrook, Pete↗

Laplacian-level meta-generalized gradient approximation for solid and liquid metals

In this work, we derive and motivate a Laplacian-level, orbital-free meta-generalized-gradient approximation (LL-MGGA) for the exchange-correlation energy, targeting accurate ground-state properties of sp and sd metallic condensed matter, in which the density functional for the exchange-correlation energy is only weakly nonlocal due to perfect long-range screening. Our model for the orbital-free kinetic energy density restores the fourth-order gradient expansion for exchange to the r 2 SCAN meta-GGA [Furness et al., J. Phys. Chem. Lett. 11, 8208 (2020)], yielding a LL-MGGA we call OFR2. OFR2 matches the accuracy of SCAN for prediction of common lattice constants and improves the equilibrium properties of alkali metals, transition metals, and intermetallics that were degraded relative to the PBE GGA values by both SCAN and r 2 SCAN. We compare OFR2 to the r 2 SCAN -L LL-MGGA [Mejia-Rodriguez and Trickey, Phys. Rev. B 102, 121109(R) (2020)] and show that OFR2 tends to outperform r 2 SCAN -L for the equilibrium properties of solids, but r 2 SCAN -L much better describes the atomization energies of molecules than OFR2 does. For best accuracy in molecules and nonmetallic condensed matter, we continue to recommend SCAN and r 2 SCAN. Numerical performance is discussed in detail, and our paper provides an outlook to machine learning.

36 MATERIALS SCIENCE↗

EQ_phase_detection

The EQ_phase_detection software is designed to scan continuous daily waveforms to detect earthquake phase arrivals from local to regional (150 km) events. The detections are made with a deep learning encoder-decoder model. When the model detects an earthquake in the waveforms, a second model is implemented to classify the first arriving motions. Both deep learning models are trained with the Tensorflow package using publicly available benchmark data sets. The software input is a path to a directory that contains waveforms in mseed format and the associated response files in xml format. The output is a data table of time stamped detections, signal amplitude, signal-to-noise ratio, and softmax probability of the detection in a generic format applicable to post-processing association algorithms for event locations. Additionally, the p-wave and s-wave waveforms are saved in a data table for rapid access when producing improved locations using correlation-based techniques. The software is designed for multiprocessing with multiple GPU’s for rapid processing of large data sets. The configuration file provides flexibility in the trained models implemented and allows access to multiple models trained for different sampling rates or input dimensions. This is particularly useful for regions with multiple networks that do not have the same data parameters.

Johnson, Christopher↗

RCT Continuing Training: 3rd Quarter 2022 Online Presentation

This presentation focuses on "Continuing training for Radiological Control Technicians (RCTs) designed to meet the training requirements of DOE-HDBK-1122-2009." The report contains learning objectives and modules with directions on how to navigate through the modules and course.

61 RADIATION PROTECTION AND DOSIMETRY↗

Helios mission support

The successful flight of the Helios-1 spacecraft continues as it approaches its third aphelion. The Helios-2 spacecraft has entered its first superior conjunction and continues in excellent health. Much valuable scientific information about the solar corona and its effects on electromagnetic waves is expected to be learned from data gathered during this superior conjunction.

Goodwin, P. S.↗

Launch Processing System operations with a future look to Operations Analyst (OPERA)

The Launch Processing System architecture and the ground support operations required to provide Shuttle System engineers with the capability to safely process and launch an Orbiter are described. The described ground operations are the culmination of eleven years of experience and redesign. Some of the 'lessons learned' are examined, and problem areas which ground support operations have identified over the years as the Shuttle and Launch Processing Systems continue to grow in complexity are discussed. The Operational Analyst for Distributed Systems (OPERA), a proposed set of expert systems for the Launch Processing System Operational assistance, is discussed along with its extensions to prospective future configurations and components for the Launch Processing System.

Heard, Astrid E.↗

Proposal Improvements That Work

Rocketdyne Propulsion and Power, an operating location of Boeing in Canoga Park, California is under contract with NASA's Marshall Space Flight Center (MSFC) in Huntsville, Alabama for design, development, production, and mission support of Space Shuttle Main Engines (SSMEs). The contract was restructured in 1996 to emphasize a mission contracting environment under which Rocketdyne supports the Space Transportation System launch manifest of seven flights a year without the need for a detailed list of contract deliverables such as nozzles, turbopumps, and combustion devices. This contract structure is in line with the overall Space Shuttle program goals established by the NASA to fly safely, meet the flight manifest, and reduce cost. Rocketdyne's Contracts, Pricing, and Estimating team has worked for the past several years with representatives from MSFC, the local Defense Contract Management Command, and the DCAA to improve the quality of cost proposals to MSFC for contract changes on the SSME. The contract changes on the program result primarily from engineering change proposals for product enhancements to improve safety, maintainability, or operability in the space environment. This continuous improvement team effort has been successful in improving proposal quality, reducing cycle time, and reducing cost. Some of the principal lessons learned are highlighted here to show how proposal improvements can be implemented to enhance customer satisfaction and ensure cost proposals can be evaluated easily by external customers.

Dunn, F.↗

Practical Applications of Cables and Ropes in the ISS Countermeasures System

National Aeronautics and Space Administration (NASA) uses exercise countermeasures on the International Space Station (ISS) to maintain crew health and combat the negative effects of long-duration spaceflight on the human body. Most ISS exercise countermeasures system (CMS) equipment rely heavily on the use of textile and wire ropes to transmit resistive loads and provide stability in a microgravity environment. For a variety of reasons, including challenges in simulating microgravity environments for testing and limits on time available for life cycle testing, the textiles and wire ropes have contributed significantly to on-orbit planned and unplanned maintenance time. As a result, continued ground testing and on-orbit experience since the first expedition on the ISS in 2000 provide valuable data and lessons learned in materials selection, applications, and design techniques to increase service life of these ropes. This paper will present a review of the development and failure history of textile and wire ropes for four exercise countermeasure systems-the Treadmill with Vibration Isolation and Stabilization (TVIS) System, Cycle Ergometer with Vibration Isolation and Stabilization (CEVIS) System, Interim Resistive Exercise Device (IRED), and the Advanced Resistive Exercise Device (ARED)-to identify lessons learned in order to improve future systems. These lessons learned, paired with thorough testing on the ground, offer a forward path towards reduced maintenance time and up-mass for future space missions.

Svetlik, Randall G.↗

Assessing ISS Habitability Training: A Historical Perspective

Over the lifetime of the International Space Station (ISS) training evolved based on Astronaut feedback, system updates, increased mission duration, and shifting operational goals. This training is a mixture of skill-based instruction and mission specific lessons on many topics. Habitability training specifically focuses on preparing astronauts for the day-to-day needs of living in space such as hygiene, food, sleep, restraints/mobility aids, and housekeeping. In this paper, the authors evaluate the effectiveness of habitability training for Astronaut working on the International Space Station (ISS) over the course of its continuously manned operation since 2000. This involved identifying ISS habitability training changes in lessons objectives and skills between revisions. These identified changes were then compared with relevant Astronaut feedback from post mission debriefs to determine the effectiveness of the changes. Habitability training is essential for Astronauts and has changed and continues to evolve over the course of the ISS. Understanding ISS habitability and how to most effectively train it will generate lessons learned that benefit current ISS operations and future exploration outside of Low Earth Orbit (LEO) to the moon and eventually Mars.

Swarmer, Tiffany M.↗

Modeling and Simulation - Virtual

The purpose of this report is to describe the body of work I have produced as a NASA Office of Science Technology Engineering and Math (OSTEM) intern in the Fall 2020 semester. My mentor during this session was Antonio Pego and my main task was to research and develop solutions in augmented and virtual reality technologies for use in training simulations. A main focus of this project was the development of human models for use in the game engine, with the purpose of creating simulations that would help with realistic analysis of tasks that will be performed by personnel. A steep learning curve had to be tackled in order to learn and catch up with current MR technologies. Along the way I created documentation of the different techniques utilized to support future continuation of the project.

Peter Leroy Santana Rodriguez↗

Assessment of the Advanced Very High Resolution Radiometer (AVHRR) for Snowfall Retrieval in High Latitudes Using CloudSat and Machine Learning

Precipitation retrieval is a challenging topic, especially in high latitudes (HL), and current precipitation products face ample challenges over these regions. This study investigates the potential of the Advanced Very High Resolution Radiometer (AVHRR) for snowfall retrieval in HL using CloudSat radar information and machine learning (ML). With all the known limitations, AVHRR observations should be considered for HL snowfall retrieval because 1) AVHRR data have been continuously collected for about four decades on multiple platforms with global coverage, and similar observations will likely continue in the future; 2) current passive microwave satellite precipitation products have several issues over snow and ice surfaces; and 3) good coincident observations between AVHRR and CloudSat are available for training ML algorithms. Using ML, snowfall rate was retrieved from AVHRR’s brightness temperature and cloud probability, as well as auxiliary information provided by numerical reanalysis. The results indicate that the ML-based retrieval algorithm is capable of detection and estimation of snowfall with comparable or better statistical scores than those obtained from the Atmospheric Infrared Sounder (AIRS) and two passive microwave sensors contributing to the Global Precipitation Measurement (GPM) mission constellation. The outcomes also suggest that AVHRR-based snowfall retrievals are spatially and temporally reasonable and can be considered as a quantitatively useful input to the merged precipitation products that require frequent sampling or long-term records.

Mohammad Reza↗

Nexus of technologies : international safeguards, physical protection and arms control.

New technologies have been, and are continuing to be, developed for Safeguards, Arms Control, and Physical Protection. Application spaces and technical requirements are evolving - Overlaps are developing. Lessons learned from IAEA's extensive experience could benefit other communities. Technologies developed for other applications may benefit Safeguards - Inherent cost benefits and improvements in procurement security processes.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

The conduct of the united states department of energy nuclear criticality safety program hands-on training and education courses - 14621

The United States Department of Energy (DOE) Nuclear Criticality Safety Program (NCSP), funded and managed by the National Nuclear Security Administration (NNSA), offers courses to educate nuclear criticality safety (NCS) engineers, process supervisors, and others, and to provide experimental, hands-on training addressing important characteristics of neutron multiplying systems. This training satisfies the American National Standard Institute/American Nuclear Society (ANSI/ANS)-8.26-2007 requirement for participating in hands-on experiments with fissionable materials and provides awareness and understanding of DOE Orders, Guides and Rules, ANS standards, and hazard identification techniques, as well as control design, implementation, and maintenance in criticality safety evaluations. Since the pilot course was developed in 2011, a variety of courses have been developed for NCS practitioners and process supervisors. Attendees have come from several US and international sites. Through NCSP international collaborations and relationships, students from the Atomic Weapons Establishment (AWE) in the United Kingdom, Atomic Energy of Canada, and the Institute for Radiation Protection and Nuclear Safety in France have participated in these courses in the US. Manager courses are available for process supervisors and operations managers with NCS responsibilities in their daily jobs. Manager courses are taught at Sandia National Laboratory (SNL) and the National Criticality Experiments Research Center (NCERC); they offer a combination of hands-on experiments and classroom discussions. A two-week course is also offered for NCS practitioners, with a week of classroom instruction at Los Alamos National Laboratory (LANL) focused on generation of NCS evaluations, and a week of hands-on training utilizing the critical assemblies at either SNL or NCERC. Cleared students can attend the hands-on training at either SNL or NCERC, and uncleared students can attend at SNL. Courses continue to evolve and continuously improve as important elements of NCS evaluations (e.g., human factors, non-destructive assay (NDA) techniques, process criticality accident lessons-learned, and hand calculation methods) are integrated with criticality safety evaluation exercises. Courses include tours of process operations at SNL, NCERC, and LANL, and interaction with instructors experienced in conducting critical experiments and working in NCS. The NNSA NCSP provides management, funding, and technical direction for these courses and makes them available with no tuition cost to NCS practitioners. This paper provides a status report to the NCS community on the conduct of these courses and how they will likely evolve in the future. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Predicting Drug Effects from High-dimensional Asymmetric Drug Data Sets using Graph Neural Networks: A Comprehensive Analysis of Multi-target Drug Effect Prediction

Graph neural networks (GNNs) have emerged as one of the most effective Machine learning (ML) techniques for drug effect prediction from drug molecular graphs. Despite having immense potential, GNN models lack performance when using data sets that contain high dimensional asymmetrically co-occurrent drug effects as targets with complex correlations between them. Training individual learning models for each drug effect and incorporating every prediction result for a wide spectrum of drug effects is beyond practicality. Such an implication provides a testbed to address this challenge as multi-target prediction problems, aiming to predict all drug effects at a time. We develop standard and hybrid graph neural networks (GNNs)to perform two separate tasks that are multi-regression for continuous values and multi-label classification for categorical values contained in our data sets. Since this step makes the target data even more sparse and introduces asymmetric label co-occurrence, the learning of multi-label classification models becomes difficult and heavily impacts the GNN's performance. To address these challenges, we propose a new data oversampling technique to improve multi-label classification performances on all the given imbalanced molecular graph data sets. Using the technique, we improve the data imbalance ratio of the drug effects better than before while protecting the data set's integrity. Finally, we evaluate multi-label classification performance using the best-performant hybrid GNN model on all the oversampled data sets obtained from the proposed oversampling technique. These results outperform those of other ML models including GNN models when they are trained on the original data sets or oversampled data sets using MLSMOTE (a well-known oversampling technique) in all evaluation metrics precision, recall, and F1 score by a significant margin.

Bose, Avishek [ORNL]↗

Thermal Management for FPGA Nodes in HPC Systems

The integration of FPGAs into large-scale computing systems is gaining attention. In these systems, real-time data handling for networking, tasks for scientific computing, and machine learning can be executed with customized datapaths on reconfigurable fabric within heterogeneous compute nodes. At the same time, thermal management, particularly battling the cooling cost and guaranteeing the reliability, is a continuing concern. The introduction of new heterogeneous components into HPC nodes only adds further complexities to thermal modeling and management. The thermal behavior of multi-FPGA systems deployed within large compute clusters is less explored. Here, we first show that the thermal behaviors of different FPGAs of the same generation can vary due to their physical locations in a rack and process variation, even though they are running the same tasks. We present a machine learning–based model to capture the thermal behavior of each individual FPGA in the cluster. We then propose two thermal management strategies guided by our thermal model. First, we mitigate thermal variation and hotspots across the cluster by proactive thermal-aware task placement. Under the tested system and benchmarks, we achieve up to 26.4° C and on average 13.3° C system temperature reduction with no performance penalty. Second, we utilize this thermal model to guide HLS parameter tuning at the task design stage to achieve improved thermal response after deployment.

97 MATHEMATICS AND COMPUTING↗

Retrofit California: Better Buildings Program Overview

Energy efficiency retrofits (also called upgrades) are widely recognized as a critical component to achieving energy savings in the building sector to help lower greenhouse gas (GHG) emissions. To date, however, upgrades have accounted for only a small percentage of aggregate energy savings in building stock, both in California and nationally. Although the measures and technologies to retrofit a building to become energy efficient are readily deployed, establishing this model as a standard practice remains elusive. Retrofit California sought to develop and test new program models to increase participation in the energy upgrade market in California. The Program encompassed 24 pilot projects, conducted between 2010 and mid-2013 and funded through a $30 million American Recovery and Reinvestment Act (ARRA) grant from the U.S. Department of Energy’s (DOE) Better Buildings Neighborhood Program (BBNP). The broad scope of the Program can be seen in the involvement of the following regionally based Grant Partners: Los Angeles County (as prime grantee); Association of Bay Area Governments (ABAG), consisting of: StopWaste.org for Alameda County, Regional Climate Protection Authority (RCPA) for Sonoma County, SF Environment for the City and County of San Francisco, and City of San Jose; California Center for Sustainable Energy (CCSE) for the San Diego region; Sacramento Municipal Utilities District (SMUD). Within these jurisdictions, nine different types of pilots were tested with the common goal of identifying, informing, and educating the people most likely to undertake energy upgrades (both homeowners and contractors), and to provide them with incentives and resources to facilitate the process. Despite its limited duration, Retrofit California undoubtedly succeeded in increasing awareness and education among home and property owners, as well as contractors, realtors, and community leaders. However, program results indicate that a longer timeframe will be needed to transform the market and establish energy retrofits as the new paradigm. Innovations such as Flex Path, which came about because of barriers encountered during the Program, have already shown promise and are enabling increased participation. Together, the pilots represent an unprecedented effort to identify and address market barriers to energy efficiency upgrades and to provide lessons learned to shape future program planning and implementation. The statistics reflects the scope of the marketing and outreach campaigns, which tested a variety of approaches to increase understanding of the benefits of energy upgrades to drive participation in the Program. More traditional methods such as TV and radio advertisements were complimented by innovative community based social marketing campaigns that sought to leverage the trusted status of neighborhood organizations and leaders in order to motivate their constituents to undertake retrofits. The remainder of this report provides an overview of Retrofit California including brief summaries of the pilots’ main components and highlights, followed by the major findings or takeaway lessons from the approaches that were tested. Eleven of the pilots will be continued, with modifications, under the ratepayer-funded Regional Energy Networks. Involvement in the RENS by many of the Retrofit California partners will ensure that early lessons learned are carried forward to guide future programs for energy upgrades in California.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗