SEARCH · Search NASA

Results for “learning dynamics”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

All sources NASA NTRS DOE OSTI

NASA NTRS1992

Learning a trajectory using adjoint functions and teacher forcing

A new methodology for faster supervised temporal learning in nonlinear neural networks is presented which builds upon the concept of adjoint operators to allow fast computation of the gradients of an error functional with respect to all parameters of the neural architecture, and exploits the concept of teacher forcing to incorporate information on the desired output into the activation dynamics. The importance of the initial or final time conditions for the adjoint equations is discussed. A new algorithm is presented in which the adjoint equations are solved simultaneously (i.e., forward in time) with the activation dynamics of the neural network. We also indicate how teacher forcing can be modulated in time as learning proceeds. The results obtained show that the learning time is reduced by one to two orders of magnitude with respect to previously published results, while trajectory tracking is significantly improved. The proposed methodology makes hardware implementation of temporal learning attractive for real-time applications.

Toomarian, Nikzad B.↗

NASA NTRS2002

Rapid Spacecraft Development: Results and Lessons Learned

The Rapid Spacecraft Development Office (RSDO) at NASA's Goddard Space Flight Center is responsible for the management and direction of a dynamic and versatile program for the definition, competition, and acquisition of multiple indefinite delivery and indefinite quantity contracts - resulting in a catalog of spacecraft buses. Five spacecraft delivery orders have been placed by the RSDO and one spacecraft has been launched. Numerous concept and design studies have been performed, most with the intent of leading to a future spacecraft acquisition. A collection of results and lessons learned is recorded to highlight management techniques, methods and processes employed in the conduct of spacecraft acquisition. Topics include working relationships under fixed price delivery orders, price and value, risk management, contingency reserves, and information restrictions.

Watson, William A.↗

NASA NTRS1992

Technology test bed review

The topics are presented in viewgraph form and include the following: (1) Space Shuttle Main Engine (SSME) technology test bed (TTB) history; (2) TTB objectives; (3) TTB major accomplishments; (4) TTB contributions to SSME; (5) major impacts of 3001 testing; (6) some challenges to computational fluid dynamics (CFD); (7) the high pressure fuel turbopump (HPFTP); and (8) 3001 lessons learned in design and operations.

Mcconnaughey, H. V.↗

NASA NTRS2004

Planning for rover opportunistic science

The Mars Exploration Rover Spirit recently set a record for the furthest distance traveled in a single sol on Mars. Future planetary exploration missions are expected to use even longer drives to position rovers in areas of high scientific interest. This increase provides the potential for a large rise in the number of new science collection opportunities as the rover traverses the Martian surface. In this paper, we describe the OASIS system, which provides autonomous capabilities for dynamically identifying and pursuing these science opportunities during longrange traverses. OASIS uses machine learning and planning and scheduling techniques to address this goal. Machine learning techniques are applied to analyze data as it is collected and quickly determine new science gods and priorities on these goals. Planning and scheduling techniques are used to alter the behavior of the rover so that new science measurements can be performed while still obeying resource and other mission constraints. We will introduce OASIS and describe how planning and scheduling algorithms support opportunistic science.

artificial intelligence↗

NASA NTRS2004

Architecture for robot intelligence

An architecture for robot intelligence enables a robot to learn new behaviors and create new behavior sequences autonomously and interact with a dynamically changing environment. Sensory information is mapped onto a Sensory Ego-Sphere (SES) that rapidly identifies important changes in the environment and functions much like short term memory. Behaviors are stored in a DBAM that creates an active map from the robot's current state to a goal state and functions much like long term memory. A dream state converts recent activities stored in the SES and creates or modifies behaviors in the DBAM.

Peters, II, Richard Alan↗

NASA NTRS2008

Architecture for Multiple Interacting Robot Intelligences

An architecture for robot intelligence enables a robot to learn new behaviors and create new behavior sequences autonomously and interact with a dynamically changing environment. Sensory information is mapped onto a Sensory Ego-Sphere (SES) that rapidly identifies important changes in the environment and functions much like short term memory. Behaviors are stored in a database associative memory (DBAM) that creates an active map from the robot's current state to a goal state and functions much like long term memory. A dream state converts recent activities stored in the SES and creates or modifies behaviors in the DBAM.

Peters, Richard Alan, II↗

NASA NTRS2009

Apparatus for multiprocessor-based control of a multiagent robot

Peters, II, Richard Alan↗

NASA NTRS2006

DCS-Neural-Network Program for Aircraft Control and Testing

A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

Jorgensen, Charles C.↗

NASA NTRS2011

Application of the Semi-Empirical Force-Limiting Approach for the CoNNeCT SCAN Testbed

The semi-empirical force-limited vibration method was developed and implemented for payload testing to limit the structural impedance mismatch (high force) that occurs during shaker vibration testing. The method has since been extended for use in analytical models. The Space Communications and Navigation Testbed (SCAN Testbed), known at NASA Glenn Research Center (GRC) as, the Communications, Navigation, and Networking re-Configurable Testbed (CoNNeCT) project utilized force-limited testing and analysis following the semi-empirical approach. This presentation presents the steps in performing a force-limited analysis and then compares the results to test data recovered during the CoNNeCT force-limited random vibration qualification test that took place at NASA Glenn Research Center (GRC) in the Structural Dynamics Laboratory (SDL) December 19, 2010 - January 7, 2011. A compilation of lessons learned and considerations for future force-limited tests is also included.

Staab, Lucas↗

NASA NTRS2018

Initial Calibration Activities and Performance Assessments of NOAA-20 VIIRS

The second VIIRS instrument was launched on-board the NOAA-20 (formerly JPSS-1) satellite onNovember 18, 2017. It was designed and built with the same performance requirements as the first VIIRSon-board the S-NPP launched on October 28, 2011. Currently, the NOAA-20 is orbiting the Earth in thesame plane as the S-NPP but separated in time and space by 50 minutes. The VIIRS observations are made in22 spectral bands, including a day-night band (DNB) that cover wavelengths from visible to long-waveinfrared. The sensor's on-orbit calibration is provided by a set of on-board calibrators (OBCs), which includea solar diffuser (SD), a solar diffuser stability monitor (SDSM), and a blackbody (BB). After turn-on, theVIIRS instrument conducted a series of post-launch testing (PLT) and intensive calibration and validation(ICV) activities, including those performed via spacecraft maneuvers, designed to verify and establishinstrument on-orbit calibration performance baseline. This paper provides an overview of NOAA-20 VIIRSICV activities and an assessment of its initial on-orbit performance with a focus on several key calibrationparameters, such as the detector response (or gain), dynamic range, and signal-to-noise ratio (SNR). Variousissues identified and lessons learned from initial instrument operation and calibration are also discussed insupport of long-term monitoring (LTM) of NOAA-20 VIIRS calibration and data quality.

Calibration↗

NASA NTRSDate not supplied

Leading University Students to the Edge of Space

For over 16 years, the Louisiana Space Grant Consortium (LaSPACE), the NASA Balloon Program Office (BPO), and the NASA Columbia Scientific Balloon Facility (CSBF) have collaborated in a series of high altitude balloon-based programs involving hands-on authentic learning experiences that expose university students and other participants to technical skills, teamwork dynamics, and effective communication methods. Such programs go beyond what is possible to achieve in a normal classroom and help prepare future engineers and scientists for a successful aerospace workforce career. In our collaborative effort, LaSPACE has focused on the program content and student mentoring while NASA BPO and CSBF provide balloon flight support and operations. The entry-level Louisiana Aerospace Catalyst Experiences for Students (LaACES) builds students’ skills in basic electronics, sensor interfacing, real-time programming, mechanical development, and project management. These skills are then applied to the design, development, fabrication, and flight of a small (∼500 gram) balloon payload. Finally, the payloads are flight-tested to an altitude of ∼30 km using a 2 kg latex sounding balloon. The LaACES program includes a set of lectures, activities, and Arduino Mega based electronic kits that are used for skill building and as a core control system for the student payload. The more advanced High Altitude Student Platform (HASP) is designed to carry ∼twelve 3 to 20 kg student payloads to an altitude of about 36 kilometers with flight durations of 10 to 20 hours using a ∼311,500 cubic meter, zero pressure balloon. HASP provides all student payloads with power, downlink telemetry, uplink commanding, and real-time HD video for instrument control and assessment during the flight. While originally developed for university students, these programs have been adapted to projects focused on high school teachers as well as affecting minorities underrepresented in aerospace related science and engineering fields. We are now in the process of adapting the LaACES materials to a pre-engineering curriculum for high school students as well as for widespread access over the internet. During this presentation, we will provide details of both the LaACES and HASP programs, how these programs have engaged participants from all demographic groups, and our current plans for continuing and expanding upon our success.

University↗

NASA NTRS1992

Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning

Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.

Berenji, Hamid R.↗

NASA NTRS1989

Neural learning of constrained nonlinear transformations

Two issues that are fundamental to developing autonomous intelligent robots, namely, rudimentary learning capability and dexterous manipulation, are examined. A powerful neural learning formalism is introduced for addressing a large class of nonlinear mapping problems, including redundant manipulator inverse kinematics, commonly encountered during the design of real-time adaptive control mechanisms. Artificial neural networks with terminal attractor dynamics are used. The rapid network convergence resulting from the infinite local stability of these attractors allows the development of fast neural learning algorithms. Approaches to manipulator inverse kinematics are reviewed, the neurodynamics model is discussed, and the neural learning algorithm is presented.

Barhen, Jacob↗

NASA NTRS1993

Solar dynamic power system development for Space Station Freedom

The development of a solar dynamic electric power generation system as part of the Space Station Freedom Program is documented. The solar dynamic power system includes a solar concentrator, which collects sunlight; a receiver, which accepts and stores the concentrated solar energy and transfers this energy to a gas; a Brayton turbine, alternator, and compressor unit, which generates electric power; and a radiator, which rejects waste heat. Solar dynamic systems have greater efficiency and lower maintenance costs than photovoltaic systems and are being considered for future growth of Space Station Freedom. Solar dynamic development managed by the NASA Lewis Research Center from 1986 to Feb. 1991 is covered. It summarizes technology and hardware development, describes 'lessons learned', and, through an extensive bibliography, serves as a source list of documents that provide details of the design and analytic results achieved. It was prepared by the staff of the Solar Dynamic Power System Branch at the NASA Lewis Research Center in Cleveland, Ohio. The report includes results from the prime contractor as well as from in-house efforts, university grants, and other contracts. Also included are the writers' opinions on the best way to proceed technically and programmatically with solar dynamic efforts in the future, on the basis of their experiences in this program.

Source record↗

NASA NTRS1989

SSME fault monitoring and diagnosis expert system

An expert system, called LEADER, has been designed and implemented for automatic learning, detection, identification, verification, and correction of anomalous propulsion system operations in real time. LEADER employs a set of sensors to monitor engine component performance and to detect, identify, and validate abnormalities with respect to varying engine dynamics and behavior. Two diagnostic approaches are adopted in the architecture of LEADER. In the first approach fault diagnosis is performed through learning and identifying engine behavior patterns. LEADER, utilizing this approach, generates few hypotheses about the possible abnormalities. These hypotheses are then validated based on the SSME design and functional knowledge. The second approach directs the processing of engine sensory data and performs reasoning based on the SSME design, functional knowledge, and the deep-level knowledge, i.e., the first principles (physics and mechanics) of SSME subsystems and components. This paper describes LEADER's architecture which integrates a design based reasoning approach with neural network-based fault pattern matching techniques. The fault diagnosis results obtained through the analyses of SSME ground test data are presented and discussed.

Ali, Moonis↗

NASA NTRS2010

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↗

NASA NTRS1992

Neural network error correction for solving coupled ordinary differential equations

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

Shelton, R. O.↗

NASA NTRS1999

A Strategy for Integrating a Large Finite Element Model Using MSC NASTRAN/PATRAN: X-33 Lessons Learned

The X-33 vehicle is an advanced technology demonstrator sponsored by NASA. For the past 3 years the Structural Dynamics and Loads Branch of NASA's Marshall Space Flight Center has had the task of integrating the X-33 vehicle structural finite element model. In that time, five versions of the integrated vehicle model have been produced and a strategy has evolved that would benefit anyone given the task of integrating structural finite element models that have been generated by various modelers and companies. The strategy that has been presented here consists of six decisions that need to be made: purpose of models, units, common materials list, model numbering, interface control, and archive format. This strategy has been proven and expanded from experience on the X-33 vehicle.

McGhee, D. S.↗