Results for “Continual Learning” — Page 36

NASA NTRS1988

Biomedical support of man in space

In its broadest sense, biomedical support of man in space must not be limited to assisting spacecraft crew during the mission; such support should also ensure that flight personnel be able to perform properly during landing and after leaving the craft. Man has developed mechanisms that allow him to cope with specific stresses in his normal habitat; there is indisputable evidence that, in some cases, the space environment, by relieving these stresses, has also allowed the adaptive mechanisms to lapse, causing serious problems after re-entry. Inflight biomedical support must therefore include means to simulate some of the normal stresses of the Earth environment. In the area of cardiovascular performance, we have come to rely heavily on complex feedback mechanisms to cope with two stresses, often combined: postural changes, which alter the body axis along which gravitational acceleration acts, and physical exercise, which increases the total load on the system. Unless the appropriate responses are reinforced continuously during flight, crew members may be incapacitated upon return. The first step in the support process must be a study of the way in which changes in g, even of short duration, affect these responses. In particular we should learn more about effects of g on the "on" and "off" dynamics, using a variety of approaches: increased acceleration on one hand at recumbency, immersion, lower body positive pressure, and other means of simulating some of the effects of low g, on the other. Once we understand this, we will have to determine the minimal exposure dose required to maintain the response mechanisms. Finally, we shall have to design stresses that simulate Earth environment and can be imposed in the space vehicle. Some of the information is already at hand; we know that several aspects of the response to exercise are affected by posture. Results from a current series of studies on the kinetics of tilt and on the dynamics of readjustment to exercise in different postures will be presented and discussed.

NASA Discipline Cardiopulmonary↗

DOE OSTI2024

Polynomial chaos expansions on principal geodesic Grassmannian submanifolds for surrogate modeling and uncertainty quantification

In this work we introduce a manifold learning-based surrogate modeling framework for uncertainty quantification in high-dimensional stochastic systems. Our first goal is to perform data mining on the available simulation data to identify a set of low-dimensional (latent) descriptors that efficiently parameterize the response of the high-dimensional computational model. To this end, we employ Principal Geodesic Analysis on the Grassmann manifold of the response to identify a set of disjoint principal geodesic submanifolds, of possibly different dimension, that captures the variation in the data. Since operations on the Grassmann require the data to be concentrated, we propose an adaptive algorithm based on Riemannian K-means and the minimization of the sample Fréchet variance on the Grassmann manifold to identify “local” principal geodesic submanifolds that represent different system behavior across the parameter space. Polynomial chaos expansion is then used to construct a mapping between the random input parameters and the projection of the response on these local principal geodesic submanifolds. Here, the method is demonstrated on four test cases, a toy-example that involves points on a hypersphere, a Lotka-Volterra dynamical system, a continuous-flow stirred-tank chemical reactor system, and a two-dimensional Rayleigh-Bénard convection problem.

42 ENGINEERING↗

NASA NTRS1994

New technologies for space avionics

This report reviews a 1994 effort that continued 1993 investigations into issues associated with the definition of requirements, with the practice concurrent engineering and rapid prototyping in the context of the development of a prototyping of a next-generation reaction jet driver controller. This report discusses lessons learned, the testing of the current prototype, the details of the current design, and the nature and performance of a mathematical model of the life cycle of a pilot operated valve solenoid.

Aibel, David W.↗

NASA NTRS2005

Auxiliary Propulsion Activities in Support of NASA's Exploration Initiative

The Space Launch Initiative (SLI) procurement mechanism NRA8-30 initiated the Auxiliary Propulsion System/Main Propulsion System (APS/MPS) Project in 2001 to address technology gaps and development risks for non-toxic and cryogenic propellants for auxiliary propulsion applications. These applications include reaction control and orbital maneuvering engines, and storage, pressure control, and transfer technologies associated with on-orbit maintenance of cryogens. The project has successfully evolved over several years in response to changing requirements for re-usable launch vehicle technologies, general launch technology improvements, and, most recently, exploration technologies. Lessons learned based on actual hardware performance have also played a part in the project evolution to focus now on those technologies deemed specifically relevant to the Exploration Initiative. Formal relevance reviews held in the spring of 2004 resulted in authority for continuation of the Auxiliary Propulsion Project through Fiscal Year 2005 (FY05), and provided for a direct reporting path to the Exploration Systems Mission Directorate. The tasks determined to be relevant under the project were: continuation of the development, fabrication, and delivery of three 870 lbf thrust prototype LOX/ethanol reaction control engines; the fabrication, assembly, engine integration and testing of the Auxiliary Propulsion Test Bed at White Sands Test Facility; and the completion of FY04 cryogenic fluid management component and subsystem development tasks (mass gauging, pressure control, and liquid acquisition elements). This paper presents an overview of those tasks, their scope, expectations, and results to-date as carried forward into the Exploration Initiative.

Best, Philip J.↗

DOE OSTI2024

Performance Prediction of High‐Entropy Perovskites La 0.8 Sr 0.2 Mn x Co y Fe z O 3 with Automated High‐Throughput Characterization of Combinatorial Libraries and Machine Learning

Perovskite oxides form a large family of materials with applications across various fields, owing to their structural and chemical flexibility. Efficient exploration of this extensive compositional space is now achievable through automated high-throughput experimentation combined with machine learning. In this study, we investigate the composition–structure–performance relationships of high-entropy La 0.8 Sr 0.2 Mn x Co y Fe z O 3±𝞭 perovskite oxides (0 < x, y, z <1; x+y+z≈1) for application as oxygen electrodes in Solid Oxide Cells. Following the deposition of a continuous compositional map using thin-film combinatorial pulsed laser deposition, compositional, structural, and performance properties are characterized using six different techniques with mapping capabilities. Random forests effectively model electrochemical performance, consistently identifying Fe-rich oxides as optimal compounds with the lowest area-specific resistance values for oxygen electrodes at 700 °C. Additionally, the models identify a statistical correlation between oxygen sublattice distortion—derived from spectral analysis of Raman-active modes—and enhanced performance.

high entropy oxides↗

NASA NTRS2005

Six Lessons We Learned Applying Six Sigma

As Chief Financial Officer of Kennedy Space Center (KSC), I'm not only responsible for financial planning and accounting but also for building strong partnerships with the CFO customers, who include Space Shuttle and International Space Station operations as well all who manage the KSC Spaceport. My never ending goal is to design, manage and continuously improve our core business processes so that they deliver world class products and services to the CFO's customers. I became interested in Six Sigma as Christa Casleton (KSC's first Six Sigma Black belt) applied Six Sigma tools and methods to our Plan and Account for Travel Costs Process. Her analysis was fresh, innovative and thorough but, even more impressive, was her approach to ensure ongoing, continuous process improvement. Encouraged by the results, I launched two more process improvement initiatives aimed at applying Six Sigma principles to CFO processes that not only touch most of my employees but also have direct customer impact. As many of you know, Six Sigma is a measurement scale that compares the output of a process with customer requirements. That's straight forward, but demands that you not only understand your processes but also know your products and the critical customer requirements. The objective is to isolate and eliminate the causes of process variation so that the customer sees consistently high quality.

Carroll, Napoleon↗

NASA NTRS1985

Productivity improvement in engineering at Rocketdyne

The Rocketdyne Division of Rockwell International has embarked on a productivity improvement program in engineering. This effort included participation in the White Collar Productivity Improvement (WCPI) project sponsored by the American Productivity Center. A number of things have been learned through this project. It seems that any productivity improvement project should be employee driven. The Rocketdyne project was essentially started as a result of a grassroots effort to remove some particular hindrances, and employee enthusiasm was a prime factor in the continuing progress of the effort. A significant result was that awareness of problems at all levels increased. Many issues surfaced in the diagnostic phase, and were then noted and discussed. This process added legitimacy to issues that had previously been merely unspoken concerns. The initial feelings of many members of the pilot group was that significant changes would occur relatively quickly. It is now recognized that this will have to be an ongoing, long-term effort.

Nordlund, R. M.↗

NASA NTRS2007

Enhancing the NASA Expendable Launch Vehicle Payload Safety Review Process Through Program Activities

The safety review process for NASA spacecraft flown on Expendable Launch Vehicles (ELVs) has been guided by NASA-STD 8719.8, Expendable Launch Vehicle Payload Safety Review Process Standard. The standard focused primarily on the safety approval required to begin pre-launch processing at the launch site. Subsequent changes in the contractual, technical, and operational aspects of payload processing, combined with lessons-learned supported a need for the reassessment of the standard. This has resulted in the formation of a NASA ELV Payload Safety Program. This program has been working to address the programmatic issues that will enhance and supplement the existing process, while continuing to ensure the safety of ELV payload activities.

Palo, Thomas E.↗

DOE OSTI2024

Theory for Equivariant Quantum Neural Networks

Quantum neural network architectures that have little to no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by creating models encoding the symmetries of the learning task. This is materialized through the usage of equivariant neural networks the action of which commutes with that of the symmetry. In this work, we import these ideas to the quantum realm by presenting a comprehensive theoretical framework to design equivariant quantum neural networks (EQNNs) for essentially any relevant symmetry group. We develop multiple methods to construct equivariant layers for EQNNs and analyze their advantages and drawbacks. Our methods can find unitary or general equivariant quantum channels efficiently even when the symmetry group is exponentially large or continuous. As a special implementation, we show how standard quantum convolutional neural networks (QCNNs) can be generalized to group-equivariant QCNNs where both the convolution and pooling layers are equivariant to the symmetry group. We then numerically demonstrate the effectiveness of a S U ( 2 ) -equivariant QCNN over symmetry-agnostic QCNN on a classification task of phases of matter in the bond-alternating Heisenberg model. Our framework can be readily applied to virtually all areas of quantum machine learning. Lastly, we discuss about how symmetry-informed models such as EQNNs provide hopes to alleviate central challenges such as barren plateaus, poor local minima, and sample complexity. Published by the American Physical Society 2024

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2024

Deep Reinforcement Learning for Microgrid Cost Optimization Considering Load Flexibility

This paper proposes a novel Soft-Actor-Critic (SAC) based Deep Reinforcement Learning (DRL) method for optimizing the cost of microgrid operation by leveraging load flexibility. The proposed SAC-DRL method is designed to coordinate the control of distributed energy resources (DERs) and flexible load, addressing practical energy billing formation by power distribution utilities. Key contributions include an innovative reward function to mitigate sparse reward challenges and a mixed control strategy for discrete and continuous variables, ensuring radial network topology and minimizing power loss. We evaluate the proposed method on the model of a real microgrid located in Southern California, U.S.. The SAC-DRL model is tested to demonstrate its efficacy in reducing grid dependence, optimizing resource use, and minimizing costs. The results highlight the potential of DRL in modern energy systems, offering a sustainable and economically efficient solution for energy management in microgrids.

deep reinforcement learning↗

NASA NTRS2002

Effects of heavy particle irradiation and diet on amphetamine- and lithium chloride-induced taste avoidance learning in rats

Rats were maintained on diets containing either 2% blueberry or strawberry extract or a control diet for 8 weeks prior to being exposed to 1.5 Gy of 56Fe particles in the Alternating Gradient Synchrotron at Brookhaven National Laboratory. Three days following irradiation, the rats were tested for the effects of irradiation on the acquisition of an amphetamine- or lithium chloride-induced (LiCl) conditioned taste avoidance (CTA). The rats maintained on the control diet failed to show the acquisition of a CTA following injection of amphetamine. In contrast, the rats maintained on antioxidant diets (strawberry or blueberry extract) continued to show the development of an amphetamine-induced CTA following exposure to 56Fe particles. Neither irradiation nor diet had an effect on the acquisition of a LiCl-induced CTA. The results are interpreted as indicating that oxidative stress following exposure to 56Fe particles may be responsible for the disruption of the dopamine-mediated amphetamine-induced CTA in rats fed control diets; and that a reduction in oxidative stress produced by the antioxidant diets functions to reinstate the dopamine-mediated CTA. The failure of either irradiation or diet to influence LiCl-induced responding suggests that oxidative stress may not be involved in CTA learning following injection of LiCl.

Non-NASA Center↗

NASA NTRSDate not supplied

Generation of Continental Scale Percent Tree Cover Product Using Deep-learning and Multi-scale Remote Sensing Data

Spatially explicit percent tree cover (TC) estimation is critical for mapping forest aboveground biomass and its dynamics. While various TC products have been developed, there has not been a generalized framework that can be applied to diverse terrestrial ecosystems due to underlain extreme complexities. Deep learning algorithms can learn a spatial pattern and radiometric characteristics of tree canopy as a robust approximation of physical or empirical models, and thus have emerged as promising and efficient tools for large-scale TC mapping. In this study, we synergistically use very high-resolution aerial imageries (National Agriculture Imagery Program, NAIP) and medium resolution Landsat data to map continental-scale TC (CONUS and Mexico) through a hierarchical deep learning approach (Convolutional Neural Network), i.e., NAIP TC generated from a NAIP model is utilized to train a Landsat model. The produced TC product (hereafter, NEX-TC) is able to capture the spatial pattern of TC distribution and its changes driven by natural disturbance and human land management. We further explore and analyze the reliability and potential uncertainty of the NEX-TC by comparing it to lidar- (lidar-TC), National Land Cover Database (NLCD-TC), and MODIS Vegetation Continuous Field (MODIS-TC). This evaluation practice reveals that TC products based on passive optical sensors tend to underestimate TC across all land cover types while Landsat-based TCs (i.e., NEX-TC & NLCD-TC) perform better than the coarser MODIS TC estimate. Our results show that the NEX-TC is generally comparable to NLCD-TC but it particularly outperforms NLCD-TC and MODIS-TC over the dense forests where lidar-TC indicates >80% TC. These results indicate that our hierarchical deep learning approach and TC product will be effective and useful for characterizing large-scale tree cover and possibly associated carbon dynamics.

Landsat↗

NASA NTRS2002

The IRAC Shutter Mechanism: Residual Magnetism and the Rotary Solenoid

The Infrared Array Camera (IRAC) Shutter mechanism was originally presented in the paper, 'A Low Power Cryogenic Shutter Mechanism for Use on Infrared Imagers' at the 34th Aerospace Mechanisms Symposium, May 2000. At that time, the shutter was believed to be performing flawlessly and there was every indication it would continue to do so. In early spring of 2001, the calibration shutter, a rotary solenoid designed to be fail-safe open, remained in a closed state with no power to the electromagnetic coils. The ensuing investigation, subsequent testing, proposed remedy, and lessons learned are the focus of this paper.

Schwinger, Scott↗

NASA NTRS2010

SSME Engine Controller Development and Evolution

The SSME engine controller is a redundant, micro-processor based control unit. The controller along with its embedded software provides closed loop control of the engine s thrust and mixture ratio during flight as well as configuring the engine state and operations during non-flight activities such as checkouts, and pre-start engine conditioning. It processes orbiter commands into engine actions and provides engine state and health information to the orbiter for immediate action, telemetry and recording. In addition the controller includes functions which continually monitor and manage engine health, and can activate a variety of fault mitigation actions to insure safe engine operation. The objective of this paper is to provide a description of the SSME engine controller as well as its developmental history and lessons learned

Abrams, Russ↗

NASA NTRS2011

Long-Term International Space Station (ISS) Risk Reduction Activities

As the assembly of the ISS nears completion, it is worthwhile to step back and review some of the actions pursued by the Program in recent years to reduce risk and enhance the safety and health of ISS crewmembers, visitors, and space flight participants. While the initial ISS requirements and design were intended to provide the best practicable levels of safety, it is always possible to further reduce risk given the determination, commitment, and resources to do so. The following is a summary of some of the steps taken by the ISS Program Manager, by our International Partners, by hardware and software designers, by operational specialists, and by safety personnel to continuously enhance the safety of the ISS, and to reduce risk to all crewmembers. While years of work went into the development of ISS requirements, there are many things associated with risk reduction in a Program like the ISS that can only be learned through actual operational experience. These risk reduction activities can be divided into roughly three categories: Areas that were initially noncompliant which have subsequently been brought into compliance or near compliance (i.e., Micrometeoroid and Orbital Debris [MMOD] protection, acoustics) Areas where initial design requirements were eventually considered inadequate and were subsequently augmented (i.e., Toxicity hazard level-4 materials, emergency procedures, emergency equipment, control of drag-throughs) Areas where risks were initially underestimated, and have subsequently been addressed through additional mitigation (i.e., Extravehicular Activity [EVA] sharp edges, plasma shock hazards). Due to the hard work and cooperation of many parties working together across the span of more than a decade, the ISS is now a safer and healthier environment for our crew, in many cases exceeding the risk reduction targets inherent in the intent of the original design. It will provide a safe and stable platform for utilization and discovery for years to come.

Forroci, Michael P.↗

NASA NTRSDate not supplied

Markov Decision Process based Trajectory Planning for UAVs under Uncertain Wind Conditions

In this paper we propose a Markov Decision Process (MDP) algorithm for path-planning of Unmanned Aviation Vehicles (UAVs) under varying wind conditions. Solutions to path-planning for UAVs are becoming increasingly necessary as autonomous UAVs continue to enter commercial and government spaces. Path-planning is inherently challenging, as UAVs needs to account for dynamically changing flying conditions such as weather, obstacle or no-fly zones, degraded vehicle health and off-nominal battery power consumption. Machine learning methods such as Markov Decision Process (MDPs) have the potential to revolutionize how vehicles navigate in such uncertain environments. Previous papers have demonstrated the use of MDPs to optimize UAV path-planning for energy consumption under time-varying wind distribution. In this study, UAV trajectories from a pre-determined waypoint to target cell, will be computed on a 7X7 grid environment by optimizing parameters for mission assurance and safety limits in addition to the energy consumption, and operation time. The UAV navigates the grid by taking actions to move in either of the eight cardinal and intercardinal directions, under constant thrust profile. The next state of the UAV is calculated by considering its action, transition probability, obstacle cells and the wind speed magnitude and direction. Both constant and stochastic wind will be considered in this paper, the parameters being extracted from real wind measurements in proximity to an experimental UAV flight. One of the studies to be demonstrated in this paper is that as the unmanned airspace gets more complex with multiple vehicles and environmental uncertainties, trade-offs between energy consumption, operation time, risk tolerance, and mission assurance needs to be made. Further, MDPs are capable of fast computation of UAV trajectories under varying wind, hence making them suitable for in-flight path planners.

decision-making↗

NASA NTRSDate not supplied

Kinematic Sensors Evaluation for Spaceflight Exercise Data Collections

INTRODUCTION: On the International Space Station (ISS), exercise feedback from astronauts is very important to diagnose and mitigate any form-related injuries and ensure efficacious exercise prescriptions and systems. Going forward, exploration exercise efforts seek to gain further quantitative data of human and system performance. Currently, methods of collecting in-flight exercise data on the ISS are limited to marker-based motion capture (MoCap) where astronauts must wear reflective markers over their clothes and specialized cameras are used. The main objective of this work was to investigate the following alternative tracking options: markerless video-based MoCap and inertial measurement units (IMUs). These were compared against traditional marker-based MoCap to evaluate kinematic accuracy and inform feasible methods for future exercise data collections on the ISS, especially in support of future Vibration Isolation and Stabilization (VIS) system development. METHODS: Three test subjects performed a variety of flight-like resistance and aerobic exercises using the Miniature Exercise Device (MED-2), Concept-2 rowing ergometer, barbell mockup, bench (e.g., for bench press, hip thruster, and cycling), and a custom structure for dips. These were intended also to represent exercises which could be performed on the multi-modality European Enhanced Exploration Exercise Device (E4D) [1]. The marker-based MoCap data, collected through a 16-camera OptiTrack MoCap system, was regarded as the gold standard to compare the data against. Passive markers were affixed to each subject according to a modified full body Plug-in Gait marker set [2] with 46 total markers. The markerless MoCap data was collected using two GoPro Hero7 cameras and one GoPro Hero11 camera. For the IMU data, a full body set of 17 Xsens DOTs were placed on the subject: 10 upper body and 7 lower body IMUs. Biomechanical modeling and evaluation was conducted through OpenSim [3] (MoCap), OpenSense [4] (IMU), OpenCap [5] (markerless), ENABLE [6] (markerless), and other modeling software. Secondary objectives included comparing the volume of equipment, reducing mass and crew set-up time. RESULTS AND DISCUSSION: While there were issues with initial processing for the IMUs and markerless MoCap, the results aided in the understanding of each sensor, developing end-to-end processes, and identifying future needs. Some observed concerns with the markerless MoCap approaches included being cognizant of a cluttered background, number of people in field of view, camera number and placement. Some challenges with the IMUs included possible sliding, early deactivation possibly due to exercise pose, and large quantity sensor synchronization. Overall, the markerless MoCap option may be the preferred method of data collection and processing as it provides a solution for certain IMU shortcomings and may be least in equipment volume, upmass, and crew setup time. CONCLUSIONS: While this work was mainly focused on ISS data collection, these sensor data along with continued evaluation and development efforts will help to establish best methods for exercise data collection on Gateway, for other Artemis missions, and beyond. Details on the latest end-to-end processing of the data and results will be presented, along with lessons learned and recommended sensor selection and methods.

S. Faragalla↗

NASA NTRS2024

Kinematic Sensors Evaluation for Spaceflight Exercise Data Collections

INTRODUCTION: On the International Space Station (ISS), exercise feedback from astronauts is very important to diagnose and mitigate any form-related injuries and ensure efficacious exercise prescriptions and systems. Going forward, exploration exercise efforts seek to gain further quantitative data of human and system performance. Currently, methods of collecting in-flight exercise data on the ISS are limited to marker-based motion capture (MoCap) where astronauts must wear reflective markers over their clothes and specialized cameras are used. The main objective of this work was to investigate the following alternative tracking options: markerless video-based MoCap and inertial measurement units (IMUs). These were compared against traditional marker-based MoCap to evaluate kinematic accuracy and inform feasible methods for future exercise data collections on the ISS, especially in support of future Vibration Isolation and Stabilization (VIS) system development. METHODS: Three test subjects performed a variety of flight-like resistance and aerobic exercises using the Miniature Exercise Device (MED-2), Concept-2 rowing ergometer, barbell mockup, bench (e.g., for bench press, hip thruster, and cycling), and a custom structure for dips. These were intended also to represent exercises which could be performed on the multi-modality European Enhanced Exploration Exercise Device (E4D) [1]. The marker-based MoCap data, collected through a 16-camera OptiTrack MoCap system, was regarded as the gold standard to compare the data against. Passive markers were affixed to each subject according to a modified full body Plug-in Gait marker set [2] with 46 total markers. The markerless MoCap data was collected using two GoPro Hero7 cameras and one GoPro Hero11 camera. For the IMU data, a full body set of 17 Xsens DOTs were placed on the subject: 10 upper body and 7 lower body IMUs. Biomechanical modeling and evaluation was conducted through OpenSim [3] (MoCap), OpenSense [4] (IMU), OpenCap [5] (markerless), ENABLE [6] (markerless), and other modeling software. Secondary objectives included comparing the volume of equipment, reducing mass and crew set-up time. RESULTS AND DISCUSSION: While there were issues with initial processing for the IMUs and markerless MoCap, the results aided in the understanding of each sensor, developing end-to-end processes, and identifying future needs. Some observed concerns with the markerless MoCap approaches included being cognizant of a cluttered background, number of people in field of view, camera number and placement. Some challenges with the IMUs included possible sliding, early deactivation possibly due to exercise pose, and large quantity sensor synchronization. Overall, the markerless MoCap option may be the preferred method of data collection and processing as it provides a solution for certain IMU shortcomings and may be least in equipment volume, upmass, and crew setup time. CONCLUSIONS: While this work was mainly focused on ISS data collection, these sensor data along with continued evaluation and development efforts will help to establish best methods for exercise data collection on Gateway, for other Artemis missions, and beyond. Details on the latest end-to-end processing of the data and results will be presented, along with lessons learned and recommended sensor selection and methods.

S Faragalla↗