Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative 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 379 records · Page 21

Immunity-Based Aircraft Fault Detection System

In the study reported in this paper, we have developed and applied an Artificial Immune System (AIS) algorithm for aircraft fault detection, as an extension to a previous work on intelligent flight control (IFC). Though the prior studies had established the benefits of IFC, one area of weakness that needed to be strengthened was the control dead band induced by commanding a failed surface. Since the IFC approach uses fault accommodation with no detection, the dead band, although it reduces over time due to learning, is present and causes degradation in handling qualities. If the failure can be identified, this dead band can be further A ed to ensure rapid fault accommodation and better handling qualities. The paper describes the application of an immunity-based approach that can detect a broad spectrum of known and unforeseen failures. The approach incorporates the knowledge of the normal operational behavior of the aircraft from sensory data, and probabilistically generates a set of pattern detectors that can detect any abnormalities (including faults) in the behavior pattern indicating unsafe in-flight operation. We developed a tool called MILD (Multi-level Immune Learning Detection) based on a real-valued negative selection algorithm that can generate a small number of specialized detectors (as signatures of known failure conditions) and a larger set of generalized detectors for unknown (or possible) fault conditions. Once the fault is detected and identified, an adaptive control system would use this detection information to stabilize the aircraft by utilizing available resources (control surfaces). We experimented with data sets collected under normal and various simulated failure conditions using a piloted motion-base simulation facility. The reported results are from a collection of test cases that reflect the performance of the proposed immunity-based fault detection algorithm.

Dasgupta, D.↗

Space Infrared Astronomy in the 21st Century

New technology and design approaches have enabled revolutionary improvements in astronomical observations from space. Worldwide plans and dreams include orders of magnitude growth in sensitivity and resolution for all wavelength ranges, and would give the ability to learn our history, from the Big Bang to the conditions for life on Earth. The Next Generation Space Telescope, for example, will be able to see the most distant galaxies as they were being assembled from tiny fragments. It will be 1/4 as massive as the Hubble, with a mirror 3 times as large, cooled to about 30 Kelvin to image infrared radiation. I will discuss plans for NGST and hopes for future large space telescopes, ranging from the Space UV Optical (SUVO) telescope to the Filled Aperture Infrared (FAIR) Telescope, the Space Infrared Interferometric Telescope (SPIRIT), and the Submillimeter Probe of the Evolution of Cosmic Structure (SPECS).

Mather, John C.↗

Spacecraft Design Considerations for Piloted Reentry and Landing

With the end of the Space Shuttle era anticipated in this decade and the requirements for the Crew Exploration Vehicle (CEV) now being defined, an opportune window exists for incorporating 'lessons learned' from relevant aircraft and space flight experience into the early stages of designing the next generation of human spacecraft. This includes addressing not only the technological and overall mission challenges, but also taking into account the comprehensive effects that space flight has on the pilot, all of which must be balanced to ensure the safety of the crew. This manuscript presents a unique and timely overview of a multitude of competing, often unrelated, requirements and constraints governing spacecraft design that must be collectively considered in order to ensure the success of future space exploration missions.

Stroud, Kenneth J.↗

Finite-difference simulation and visualization of elastodynamics in time-evolving generalized curvilinear coordinates

Modeling and simulation of free and forced structural vibrations is essential to an overall structural health monitoring capability. In the various embodiments, a first principles finite-difference approach is adopted in modeling a structural subsystem such as a mechanical gear by solving elastodynamic equations in generalized curvilinear coordinates. Such a capability to generate a dynamic structural response is widely applicable in a variety of structural health monitoring systems. This capability (1) will lead to an understanding of the dynamic behavior of a structural system and hence its improved design, (2) will generate a sufficiently large space of normal and damage solutions that can be used by machine learning algorithms to detect anomalous system behavior and achieve a system design optimization and (3) will lead to an optimal sensor placement strategy, based on the identification of local stress maxima all over the domain.

Kaul, Upender K.↗

3D Printing in Zero G Technology Demonstration Mission: Summary of On-Orbit Operations, Material Testing, and Future Work

Human space exploration to date has been limited to low Earth orbit and the moon. The International Space Station (ISS), an orbiting laboratory 200 miles above the earth, provides a unique and incredible opportunity for researchers to prove out the technologies that will enable humans to safely live and work in space for longer periods of time and venture farther into the solar system. The ability to manufacture parts in-space rather than launch them from earth represents a fundamental shift in the current risk and logistics paradigm for human spaceflight. In particularly, additive manufacturing (or 3D printing) techniques can potentially be deployed in the space environment to enhance crew safety (by providing an on-demand part replacement capability) and decrease launch mass by reducing the number of spare components that must be launched for missions where cargo resupply is not a near-term option. In September 2014, NASA launched the 3D Printing in Zero G technology demonstration mission to the ISS to explore the potential of additive manufacturing for in-space applications and demonstrate the capability to manufacture parts and tools on-orbit. The printer for this mission was designed and operated by the company Made In Space under a NASA SBIR (Small Business Innovation Research) phase III contract. The overarching objectives of the 3D print mission were to use ISS as a testbed to further maturation of enhancing technologies needed for long duration human exploration missions, introduce new materials and methods to fabricate structure in space, enable cost-effective manufacturing for structures and mechanisms made in low-unit production, and enable physical components to be manufactured in space on long duration missions if necessary. The 3D print unit for fused deposition modeling (FDM) of acrylonitrile butadiene styrene (ABS) was integrated into the ISS Microgravity Science Glovebox (MSG) in November 2014 and phase I printing operations took place from November through December of that year. Phase I flight operations yielded 14 unique parts (21 total specimens) that could be directly compared against ground-based prints of identical geometry manufactured using the printer prior to its launch to ISS. The 3DP unit functioned safely and produced specimens necessary to advance the understanding of the critical design and operational parameters for the FDM process as affected by the microgravity environment. From the standpoint of operations, 3DP demonstrated the ability to remove parts from the build-tray on-orbit, teleoperate the printer from the ground, perform critical maintenance functions within defined human factors limits, produce a functional tool that could be evaluated for form/fit/function, and uplink a new part file from the ground and produce it on the printer. The flight parts arrived at NASA Marshall Space Flight Center in Huntsville, Alabama in April 2015, where they underwent months of testing in the materials and processes laboratory. Ground and flight prints completed the following phases of testing: photographic/visual inspection, mass and density evaluation, structured light scanning, XRay and CT, mechanical testing, optical microscopy, scanning electron microscopy, and chemical analysis. This presentation will discuss the results of this testing as well as phase II operations for the printer, which took place in June and July of 2016. Lessons learned from the tech demo and their impacts on the design and development of the second generation 3D printer for ISS, the Additive Manufacturing Facility (AMF) by Made In Space will also be presented. In addition, progress in other elements of NASA's In Space Manufacturing (ISM) initiative such as the on-demand ISM utilization catalog, in-space Recycler ISS Technology Demonstration development, launch packaging recycling, in-space printable electronics, development of higher strength polymeric materials for 3D printing and Additive Construction by Mobile Emplacement (ACME) will also be addressed.

Prater, Tracie↗

Digital Technologies at NASA for Science and Engineering

While scientific and engineering advancements used to rely primarily on theoretical studies and physical experiments, today digital technology enabled by petaflops-scale supercomputers is an equal, if not a greater, contributor to such achievements. In addition, computational modeling and simulation serves as a predictive tool that is not otherwise available. As a result, the use of high performance computing is integral to NASA's work in all mission areas such as space exploration, aeronautics, and scientific discovery. But traditional supercomputing alone is not sufficient for all of the space agency's needs. The success of many NASA missions depends on solving complex computing challenges, some of which are NP-hard (decision theory) if using classical solution methods. Quantum computing promises an unprecedented ability to solve such intractable problems by harnessing quantum mechanical effects such as tunneling, superposition, and entanglement. Another disruptive digital technology is neuromorphic computing that uses brain-inspired lessons to generate new architectures that are much more energy efficient, and capable of massive parallel processing and learning in-situ. Finally, with large amounts of observational and computational data sets, the opportunities of big data and data analytics can be leveraged to enable deep learning and knowledge discovery - it's all a massive digital transformation. This talk will be an overview how NASA utilizes digital technologies for its science and engineering efforts.

Biswas, Rupak↗

Habitability Lessons Learned from Field Testing of a Small Pressurized Rover

From 2008 to 2010, the NASA Small Pressurized Rover was tested in the Arizona desert in anticipation of human lunar surface missions. These tests were multi-day mission simulations with crew living in and conducting simulated lunar surface EVAs from the rover prototypes for 3, 7, or 14 days. This two-person surface spacecraft represents a departure from most previous lunar architectures, which either featured Apollo-class unpressurized rovers or large pressurized rovers – in some cases up to the scale of being considered mobile outposts. This paper will discuss the history of the Small Pressurized Rover, some of the values of field testing, the rover’s design evolution including the two prototypes tested in the field, key features and advantages of the SPR, the field test site location, the 2008, 2009, and 2010 field tests, habitability lessons learned from the testing, comparisons with follow-on laboratory/high bay testing, and recommendations for third generation rover design and flight vehicle development.

Pressurized Rover↗

Trajectory Design and Early Mission Operations for the Lunar IceCube Mission

The Lunar IceCube (LIC) mission, a Next Space Technologies for Exploration Partnerships (NSTEP) program selection, was launched as a rideshare onboard Artemis-I on November 16th 2022, and deployed into a high energy lunar flyby trajectory. The final destination of the mission was a polar elliptical lunar orbit from which it could conduct spectroscopy observations of the lunar surface; however, a near rectilinear halo orbit (NRHO) was planned to be used as a staging orbit that divided the lunar transfer and low-thrust spiral phases of the mission. This paper presents the process used to design the LIC transfer trajectory from the high-energy deployment state to a 9:2 synodic resonance NRHO. Additional analyses performed, to assess the critical deployment to lunar flyby phase of the trajectory and to generate recovery trajectories following a loss of contact with the spacecraft, are described as well. Lessons learned from working on the LIC mission are presented to inform the design of similar future CubeSat missions.

Robert E Pritchett↗

Piezoelectric impedance-based high-accuracy damage identification using sparsity conscious multi-objective optimization inverse analysis

Two elements are essential in structural health monitoring utilizing dynamic responses: response measurement with high-frequency contents, i.e., small characteristic wavelengths, that can adequately reflect damage features, and effective inverse identification analysis that is however oftentimes under-determined. The advancement of smart structure integration has led to active interrogation through frequency-sweeping piezoelectric impedance measurement at high frequency range. In this research we develop a multi-objective optimization formulation for the identification of damage location and severity utilizing piezoelectric impedance. While one optimization objective is to match the response measurement with finite element model prediction in the damage parametric space, the other is the number of locations of damage, i.e., the sparsity of damage index as the solution vector, since damage usually occurs within a small number of locations. This multi-objective formulation fits well the under-determined nature of damage identification, as it naturally provides multiple solutions as basis for further elucidation. The challenge remaining is how to find a small solution set that can include the actual damage scenario. Here we develop a novel inverse identification framework utilizing the intelligent swarm optimizer which possesses flexibility for enhancement. We first embed a sparsity enforcement process into the population generation of the optimizer, which yields a solution repository intrinsically possessing sparsity. We then apply reinforcement learning so the agents can adaptively opt for local strategies with the aim of enriching the searching patterns to diversify the solutions. Through the incorporation of a Q-table, searching toward more promising directions will be rewarded. Our case analyses employing experimental data indicate that this sparsity-conscious multi-objective particle swarm optimization technique can lead to a small solution set which generally encompasses the true damage scenario. This effectively solves the structural damage identification problem with piezoelectric impedance measurement.

Yang Zhang↗

Launches and the environment - Lessons learned

An evaluation is presented of the consequences of NASA's study of the ways in which the launch of a Space Shuttle generates a plume of HCl and Al2O3; in combination with water from the Shuttle's sound-suppressor cooling water system, these substances can create a corrosive and hard-to-remove Al2O3 coating on nearby surfaces. Attention is given to the site-specific character of such environmental complications, the need to involve environmental-risk specialists in hardware-development teams, and the nonlinearity of many environmental impacts.

Vaughan, William W.↗

Interplanetary Low-Thrust Design Using Proximal Policy Optimization

This paper aims to demonstrate a reinforcement learning technique for developing complex, decision-making policies capable of planning interplanetary transfers.Using Proximal Policy Optimization (PPO), a neural network agent is trained to produce a closed-loop controller capable of transfers between Earth and Mars.The agent is trained in an environment that utilizes a medium fidelity solar electric propulsion model and a real ephemeris model of the Earth and Mars. The results are compared against those generated by the Evolutionary Mission Trajectory Generator (EMTG) tool.

proximal policy optimization↗

NASA Plans for In Situ Resource Utilization (ISRU) Development, Demonstration, and Implementation

The United States (US) National Aeronautics and Space Administration’s (NASA) Artemis Moon to Mars program has four major goals: (1) Returning Americans to the Moon: 1st Woman & 1st Person of Color, (2) Learning to live and work on the Moon, (3) Translating lessons learned so that the United States has capabilities and operational experience for a mission to Mars, and (4) Inspires the next generation of explorers, researchers, scientists, and engineers worldwide. Overarching all of this, the NASA Artemis program also continues to follow Space Policy Directive One (SPD-1) which directs the US to lead an innovative and sustainable exploration program with commercial and international partners. A major objective to achieve the Artemis program goals and SPD-1 is to understand and characterize the resources that exist at these destinations, and to learn how to utilize these resources for sustained human exploration and the commercialization of space. This ability, commonly known as In Situ Resource Utilization (ISRU), involves any hardware or operation that harnesses and utilizes local resources to create products and services for robotic and human explo-ration. The NASA ISRU program is focused on the production of mission consumables and com-modities to enable sustained human exploration, such as rocket propellants, life support consuma-bles, fuel cell reactants, feedstock for manufacturing and construction, and nutrients for food and plant growth. In particular, propellants make up a significant fraction of the mass launched from Earth, are critical to mission success, and can reduce the cost for reusable transportation. Important for enabling long term surface stays, greater independence from Earth, and growing lunar infra-structure are the abilities to perform construction and manufacturing from in situ-derived metals and materials to create and expand on the infrastructure and reduce the logistical resupply needed for sustained surface and space operations. To achieve these ISRU capabilities, NASA, in partner-ship with industry, academia, and international partners has initiated a multi-faceted program which involves (i) Determining Customer Needs (Type and Quantity of Commodities), (ii) supporting ground Development of Hardware and Systems until Ready for Lunar Flight, (iii) utilize Commer-cial Lunar Payload Services (CLPS) flights to fly resource assessment missions with the Science Mission Directorate (SMD), and public-private partnership (PPP) ISRU demonstrations of critical technologies and processes, and (iv) performing commercial-led end-to-end ‘Pilot’ Plant production of commodities and demonstration of usage at a scale and duration that minimizes or eliminates risk for full implementation of ISRU-derived commodities in mission critical applications. This paper will discuss the technologies, mission studies, and accomplishments achieved to date for the ISRU multi-faceted program, and plans for continued ground development and flight missions to reduce the risk of full ISRU implementation.

In situ resource utilization↗

A self-learning rule base for command following in dynamical systems

In this paper, a self-learning Rule Base for command following in dynamical systems is presented. The learning is accomplished though reinforcement learning using an associative memory called SAM. The main advantage of SAM is that it is a function approximator with explicit storage of training samples. A learning algorithm patterned after the dynamic programming is proposed. Two artificially created, unstable dynamical systems are used for testing, and the Rule Base was used to generate a feedback control to improve the command following ability of the otherwise uncontrolled systems. The numerical results are very encouraging. The controlled systems exhibit a more stable behavior and a better capability to follow reference commands. The rules resulting from the reinforcement learning are explicitly stored and they can be modified or augmented by human experts. Due to overlapping storage scheme of SAM, the stored rules are similar to fuzzy rules.

Tsai, Wei K.↗

Laser Tracker Utilization Methodology in Measuring Truth Trajectories for INS Testing on 6 Degree of Freedom Table at the Marshall Space Flight Center's Contact Dynamics Simulation Laboratory with Lessons Learned

When performing Inertial Navigation System (INS) testing at the Marshall Space Flight Center's (MSFC) Contact Dynamics Simulation Laboratory (CDSL) early in 2017, a Leica Geosystems AT901 Laser Tracker system (LLT) measured the twist & sway trajectories as generated by the 6 Degree Of Freedom (6DOF) Table in the CDSL. These LLT measured trajectories were used in the INS software model validation effort. Several challenges were identified and overcome during the preparation for the INS testing, as well as numerous lessons learned. These challenges included determining the position and attitude of the LLT with respect to an INS-shared coordinate frame using surveyed monument locations in the CDSL and the accompanying mathematical transformation, accurately measuring the spatial relationship between the INS and a 6DOF tracking probe due to lack of INS visibility from the LLT location, obtaining the data from the LLT during a test, determining how to process the results for comparison with INS data in time and frequency domains, and using a sensitivity analysis of the results to verify the quality of the results. While many of these challenges were identified and overcome before or during testing, a significant lesson on test set-up was not learned until later in the data analysis process. It was found that a combination of trajectory-dependent gimbal locking and environmental noise introduced non-negligible noise in the angular measurements of the LLT that spanned the evaluated frequency spectrum. The lessons learned in this experiment may be useful for others performing INS testing in similar testing facilities.

Leggett, Jared O.↗

NASA’s Continued Partnerships with High School Students during a Global Pandemic

NASA HUNCH’s mission is to empower students through Project-Based Learning where they learn skills and can launch their careers through participation in the design and fabrication of real-world valued products. Our goal is to mentor the next generation of students to solve NASA’s greatest challenges even during a global pandemic

HUNCH↗

A Robust Hybrid Deep Learning Model for Spatiotemporal Image Fusion

Dense time-series remote sensing data with detailed spatial information are highly desired for the monitoring of dynamic earth systems. Due to the sensor tradeoff, most remote sensing systems cannot provide images with both high spatial and temporal resolutions. Spatiotemporal image fusion models provide a feasible solution to generate such a type of satellite imagery, yet existing fusion methods are limited in predicting rapid and/or transient phenological changes. Additionally, a systematic approach to assessing and understanding how varying levels of temporal phenological changes affect fusion results is lacking in spatiotemporal fusion research. The objective of this study is to develop an innovative hybrid deep learning model that can effectively and robustly fuse the satellite imagery of various spatial and temporal resolutions. The proposed model integrates two types of network models: super-resolution convolutional neural network (SRCNN) and long short-term memory (LSTM). SRCNN can enhance the coarse images by restoring degraded spatial details, while LSTM can learn and extract the temporal changing patterns from the time-series images. To systematically assess the effects of varying levels of phenological changes, we identify image phenological transition dates and design three temporal phenological change scenarios representing rapid, moderate, and minimal phenological changes. The hybrid deep learning model, alongside three benchmark fusion models, is assessed in different scenarios of phenological changes. Results indicate the hybrid deep learning model yields significantly better results when rapid or moderate phenological changes are present. It holds great potential in generating high-quality time-series datasets of both high spatial and temporal resolutions, which can further benefit terrestrial system dynamic studies. The innovative approach to understanding phenological changes’ effect will help us better comprehend the strengths and weaknesses of current and future fusion models.

spatiotemporal fusion↗

Multiple Kernel Learning for Heterogeneous Anomaly Detection: Algorithm and Aviation Safety Case Study

The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. In this paper, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequence of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also discuss results on real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods

Das, Santanu↗