Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep Operator Network”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Digital signal processing in the radio science stability analyzer

The Telecommunications Division has built a stability analyzer for testing Deep Space Network installations during flight radio science experiments. The low-frequency part of the analyzer operates by digitizing wave signals with bandwidths between 80 Hz and 45 kHz. Processed outputs include spectra of signal, phase, amplitude, and differential phase; time series of the same quantities; and Allan deviation of phase and differential phase. This article documents the digital signal-processing methods programmed into the analyzer.

Greenhall, C. A.↗
NASA NTRS1995

Automated Consultation for the Diagnosis of Interplanetary Telecommunications

SHARP (Spacecraft Health Automated Reasoning Program) is a knowledge-based system for the diagnosis of problems in NASA's Deep Space Network (DSN) telecommunications system. This system provides the means of communication between a spacecraft and operations personnel at Jet Propulsion Laboratory. SHARP analyzes problems that occur in both the on-board spacecraft telecom subsystem, and the DSN.

SHARP spacecraft health automated reasoning progra↗
NASA NTRS1998

NASA's Deep Space Telecommunications Roadmap

This paper will present this roadmap, describe how it will support an increasing mission set while also providing significantly increased science data return, summarize the current state of key Ka-band and optical communications technologies, and identify critical path items in terms of technology developments, demonstrations, and mission users.

roadmap↗
NASA NTRS2014

Preparing for Crew-Control of Surface Robots from Orbit

Since 2010, the European Space Agency (ESA) and the National Aeronautics and Space Administration (NASA) have been developing robots that can be remotely operated on planetary surfaces by astronauts in orbiting spacecraft. A primary objective of this work has been to test telerobotic technologies that are needed for future deep-space human exploration missions. Specifically, ESA's Multi-Purpose End-To-End Robotic Operations Network (METERON) project and NASA's Human Exploration Telerobotics (HET) project are complementary initiatives that aim to validate communications, operations and robotic systems through a range of ground and flight experiments with humans and robots in the loop. Several experiments have already been successfully completed and others are now in preparation for flight.

telerobotics↗
NASA NTRSDate not supplied

Assumption Generation for the Verification of Learning-Enabled Autonomous Systems

Providing safety guarantees for autonomous systems is difficultas these systems operate in complex environments that require the use of learning-enabled components, such as deep neural networks (DNNs) for visual perception. DNNs are hard to analyze due to their size (they can have thousands or millions of parameters), lack of formal specifications (DNNs are typically learnt from labeled data, in the absence of any formal or informal requirements), and sensitivity to small changes in the environment. We present an assume-guarantee style compositional approach for the formal verification of system-level safety properties of such autonomous systems. Our insight is that we can analyze the system in the absence of the DNN perception components by automatically synthesizing assumptions on the DNN behaviour that guarantee the satisfaction of the required safety properties. The synthesized assumptions are the weakest in the sense that they characterize the output sequences of all the possible DNNs that, plugged into the autonomous system, guarantee the required safety properties. The assumptions can be leveraged as run-time monitors over a deployed DNN to guarantee the safety of the overall system; they can also be mined to extract local specifications for use during training and testing of DNNs. We illustrate our approach on a case study taken from the autonomous airplanes domain that uses a complex DNN for perception

Autonomous systems↗
DOE OSTI2022

Solving Newton’s equations of motion with large timesteps using recurrent neural networks based operators

Classical molecular dynamics simulations are based on solving Newton’s equations of motion. Using a small timestep, numerical integrators such as Verlet generate trajectories of particles as solutions to Newton’s equations. We introduce operators derived using recurrent neural networks that accurately solve Newton’s equations utilizing sequences of past trajectory data, and produce energy-conserving dynamics of particles using timesteps up to 4000 times larger compared to the Verlet timestep. We demonstrate significant speedup in many example problems including 3D systems of up to 16 particles.

Newton’s equations↗
DOE OSTI2020

Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems

This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (DRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions in the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DRL environment. The proposed method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.

41 EE - Solar Energy Technologies Office (EE-4S)↗
NASA NTRSDate not supplied

Lunar Node 1 and Beyond

Lunar Node 1 (LN-1) is an S-band Navigation beacon for lunar applications that was recently designed and built at MSFC. As part of NASA's Commercial Lunar Payload Services initiative, this beacon will be delivered to the moon's surface on Intuitive Machine's NOVA-C lunar lander in November 2021. During this mission, LN-1’s goal will be to demonstrate navigation technologies that can support local surface and orbital operations around the moon, enabling autonomy which would decrease dependency on heavily utilized Earth based assets like the Deep Space Network. To do this, LN-1’s design leverages Cubesat components as well as the Multi-spacecraft Autonomous Positioning System (MAPS) algorithms, which enable the autonomous spacecraft positioning through communication-integrated navigation measurements. In addition to demonstrating the MAPS payload, the radio will also be used in standard tone-based non-coherent ranging and Doppler tracking to provide an alternate approaches and comparisons for navigation performance. LN-1 will represent a single node in a potential greater MAPS network of assets. While LN-1 awaits launch to demonstrate this initial use of one-way navigation, designs are already under way for proposed subsequent missions like LN-2 to enable expanded capability. The next steps in these missions seek to include a receive capability to allow two-way ranging support with other operational spacecraft in the lunar vicinity, and to provide some component upgrades related to the radio, power, and thermal systems that will improve the longevity of the payload in the harsh lunar environment. The LN-1 design details, status, and potential forward work with mission like LN-2 will be outlined in this presentation.

Evan John Anzalone↗
DOE OSTI2022

Deep Reinforcement Learning based Model-free On-line Dynamic Multi-Microgrid Formation to Enhance Resilience

Multi-microgrid formation (MMGF) is a promising solution for enhancing power system resilience. This paper proposes a new deep reinforcement learning (RL) based model-free on-line dynamic MMGF scheme. Additionally, the dynamic MMGF problem is formulated as a Markov decision process, and a complete deep RL framework is specially designed for the topologytransformable micro-grids. In order to reduce the large action space caused by flexible switch operations, a topology transformation method is proposed and an action-decoupling Q-value is applied. Then, a convolutional neural network (CNN) based multi-buffer double deep Q-network (CM-DDQN) is developed to further improve the learning ability of the original DQN method. The proposed deep RL method provides real-time computing to support the on-line dynamic MMGF scheme, and the scheme handles a long-term resilience enhancement problem using an adaptive on-line MMGF to defend changeable conditions. The effectiveness of the proposed method is validated using a 7-bus system and the IEEE 123-bus system. The results show strong learning ability, timely response for varying system conditions and convincing resilience enhancement.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRSDate not supplied

Facility engineering and operations

Flight project support for Surveyor III, Lunar Orbiter, Pioneer VII, and Mariner IV MISSIONS, facility construction and equipment for deep space network, and system reliability

MISSION PLANNING↗
DOE OSTI2023

Deep Reinforcement Learning Based Smart Water Heater Control for Reducing Electricity Consumption and Carbon Emission

Water heating is the third largest electricity consumer in U.S. households, after space heating and cooling. Thus, water heaters represent a significant potential for reducing electricity consumption and associated CO2 emissions of residential buildings. To this end, this study proposes a model-free deep reinforcement learning (RL) approach that aims to minimize the electricity consumption and the CO2 emissions of a heat pump water heater without affecting user comfort. In this approach, a set of RL agents focusing on either electricity saving or emission reduction, with different look ahead periods, were trained using the deep Q-networks (DQN) algorithm and their performance was tested on different hot water usage and Marginal Operating Emissions Rate (MOER) profiles. The testing results showed that the RL agents that focus on electricity saving can save electricity in the range of 12–22% by operating the water heater with maximum heat pump efficiency and minimum electric element utilization. On the other hand, the RL agents that focus on emission reduction reduced emissions in the range of 18–37% by making use of the variable MOER values. These RL agents used the heat pump and/or an element when the MOER values are low due to the availability of renewable energy sources (e.g., solar and wind) and mostly avoided the periods of carbon-intensive periods. Overall, these results showed that the proposed RL approach can help minimize the electricity consumption and the CO2 emissions of a heat pump water heater without having any prior knowledge about the device.

Amasyali, Kadir↗
DOE OSTI2022

AI-enabled traveling wave protection for microgrids

Grid forming inverters provide voltage and frequency regulations for microgrids; in the meantime, new challenges are introduced for microgrid protections. For instance, inverters’ control strategies can affect protection behaviors, and low short-circuit ratios and bi-directional power flows also make protection operations complex. Protection schemes based on conventional principles such as overcurrent and distance relays do not always provide reliable, sensitive, or selective operations. Here, we devise a traveling wave protection approach for microgrids using a wavelet-driven deep neural network named WaveletKernelNet (WKN). Compared with conventional methods, the presented approach provides enhanced sensitivity, higher selectivity, and better identification of various faults in microgrids. Extensive case studies validate the efficacy and excellent performance of the devised approach.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2020

Quantum adiabatic machine learning by zooming into a region of the energy surface

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. Here, we propose QAML-Z, an algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the receiver operating characteristic curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS1967

Television observations from Surveyor III

Surveyor III landed on the lunar surface at 00:04 GMT, on Day 110, 1967, approximately 23 hr after local sunrise on the Moon. The first pictures were taken by the television camera at 01:02 GMT. The camera was operated extensively for the first period of lunar visibility from the Goldstone Tracking Station of the Deep Space Network and, except on Day 115, on each successive Goldstone pass of the Moon until the Sun set over the Surveyor III landing site on Day 123. During this period, the Sun rose from an elevation angle of 11° in the east to within 3° of the zenith and then sank almost due west of the spacecraft. Many pictures were obtained of the illuminated eastern horizon in the period immediately preceding sunset. In addition to those received at the Goldstone Station, some were obtained at the Canberra, Australia, station of the Deep Space Network. There were 6315 television pictures taken during the first lunar day of the Surveyor III mission.

Surveyor III spacecraft↗
NASA NTRS1976

Microwave spectrum compatibility in planetary research

The paper presents an overview of solar system exploration, basic functions of the Deep Space Network (DSN), deep space microwave links, space research compatibility problems, and DSN's interference susceptibility. To maintain the operational integrity of competing radio systems using the microwave spectrum, the technology must extend to make possible the shared use of the spectral ranges without the ill effects of interferences. Suggestions are given which are only examples of many possible techniques that can eliminate or reduce interferences.

Siegmeth, A. J.↗
NASA NTRS1982

The role of the deep space network's frequency and timing system in the detection of gravitational waves

A review of the Deep Space Network's (DSN) use of precision Doppler-tracking of deep space vehicles is presented. The review emphasizes operational and configurational aspects and considers: the projected configuration of the DSN's frequency and timing system; the environment within the DSN provided by the precision atomic standards within the frequency and timing system--both current and projected; and the general requirements placed on the DSN and the frequency and timing system for both the baseline and the nominal gravitational wave experiments. A comment is made concerning the current probability that such an experiment will be carried out in the foreseeable future.

Mankins, J. C.↗
NASA NTRS1983

Telecommunications and data acquisition systems support for Voyager missions to Jupiter and Saturn, 1972-1981, prelaunch through Saturn encounter

The Deep Space Network has supported the Voyager Project for approximately nine years, during which time implementation, testing, and operational support was provided. Four years of this time involved testing prior to launch; the final five years included network operations support and additional network implementation. Intensive and critical support intervals included launch and four planetary encounters. The telecommunications and data acquisition support for the Voyager Missions to Jupiter and Saturn are summarized.

Traxler, M. R.↗