Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Operator Networks”

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 1,045 records · Page 58
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

Deep Space Optical Link ARQ Performance Analysis

Substantial advancements have been made toward the use of optical communications for deep space exploration missions, promising a much higher volume of data to be communicated in comparison with present-day Radio Frequency (RF) based systems. One or more ground-based optical terminals are assumed to communicate with the spacecraft. Both short-term and long-term link outages will arise due to weather at the ground station(s), space platform pointing stability, and other effects. To mitigate these outages, an Automatic Repeat Query (ARQ) retransmission method is assumed, together with a reliable back channel for acknowledgement traffic. Specifically, the Licklider Transmission Protocol (LTP) is used, which is a component of the Disruption-Tolerant Networking (DTN) protocol suite that is well suited for high bandwidth-delay product links subject to disruptions. We provide an analysis of envisioned deep space mission scenarios and quantify buffering, latency and throughput performance, using a simulation in which longterm weather effects are modeled with a Gilbert-Elliot Markov chain, short-term outages occur as a Bernoulli process, and scheduled outages arising from geometric visibility or operational constraints are represented. We find that both short- and long-term effects impact throughput, but long-term weather effects dominate buffer sizing and overflow losses as well as latency performance.

buffer analysis↗
NASA NTRS2022

Spatial Grid-Based Object Localization from A Single Passive Sensor: A Deep Learning-Integrated Approach

Ongoing efforts at NASA’s Langley Research Center have produced a single passive sensor system for detecting ground objects and pinpointing their real-world location to a desired level of precision. The Langley center serves as a test range for unmanned aerial systems (UAS) and real-time knowledge about the location of people on campus is needed to inform least-risk UAS flight operations. The proposed system provides this knowledge through a camera combined with a convolutional neural network and an algorithm that projects an imaginary grid of square cells from the ground plane onto the perspective view of the camera. The position of detected objects on the camera’s projected grid determines their location in the real-world. The imaginary grid is easily mapped to a universal coordinate system, such as longitude and latitude, to provide both relative and absolute positional information of the detected objects. This simple system is shown to be accurate and effective, with decisive advantages over alternative multi-sensor and active sensor approaches. Extensions to the system are described to allow adaptation to a variety of other use cases.

object localization↗
NASA NTRS2008

DSN Array Simulator

The DSN Array Simulator (wherein 'DSN' signifies NASA's Deep Space Network) is an updated version of software previously denoted the DSN Receive Array Technology Assessment Simulation. This software (see figure) is used for computational modeling of a proposed DSN facility comprising user-defined arrays of antennas and transmitting and receiving equipment for microwave communication with spacecraft on interplanetary missions. The simulation includes variations in spacecraft tracked and communication demand changes for up to several decades of future operation. Such modeling is performed to estimate facility performance, evaluate requirements that govern facility design, and evaluate proposed improvements in hardware and/or software. The updated version of this software affords enhanced capability for characterizing facility performance against user-defined mission sets. The software includes a Monte Carlo simulation component that enables rapid generation of key mission-set metrics (e.g., numbers of links, data rates, and date volumes), and statistical distributions thereof as functions of time. The updated version also offers expanded capability for mixed-asset network modeling--for example, for running scenarios that involve user-definable mixtures of antennas having different diameters (in contradistinction to a fixed number of antennas having the same fixed diameter). The improved version also affords greater simulation fidelity, sufficient for validation by comparison with actual DSN operations and analytically predictable performance metrics.

Tikidjian, Raffi↗
NASA NTRS2016

Deep Space Optical Link ARQ Performance Analysis

Substantial advancements have been made toward the use of optical communications for deep space exploration missions, promising a much higher volume of data to be communicated in comparison with present -day Radio Frequency (RF) based systems. One or more ground-based optical terminals are assumed to communicate with the spacecraft. Both short-term and long-term link outages will arise due to weather at the ground station(s), space platform pointing stability, and other effects. To mitigate these outages, an Automatic Repeat Query (ARQ) retransmission method is assumed, together with a reliable back channel for acknowledgement traffic. Specifically, the Licklider Transmission Protocol (LTP) is used, which is a component of the Disruption-Tolerant Networking (DTN) protocol suite that is well suited for high bandwidth-delay product links subject to disruptions. We provide an analysis of envisioned deep space mission scenarios and quantify buffering, latency and throughput performance, using a simulation in which long-term weather effects are modeled with a Gilbert -Elliot Markov chain, short-term outages occur as a Bernoulli process, and scheduled outages arising from geometric visibility or operational constraints are represented. We find that both short- and long-term effects impact throughput, but long-term weather effects dominate buffer sizing and overflow losses as well as latency performance.

optical space communications↗
NASA NTRSDate not supplied

NASA's Biosentinel Mission: Lessons Learned and What's Next

In the last two years, two BioSentinel payloads were launched to space. The ISS mission launched in December 2021, and returned to the ground in August 2022 after successfully completing eight biological experiments while validating the different instruments. On the other hand, the deep space mission launched onboard Artemis I in November 2022, and is currently in a heliocentric orbit over 20 million kilometers away from the Earth. Even though all hardware subsystems were validated in deep space, the microfluidic subsystems experienced anomalies throughout the initial 6-month mission. The main goals of this presentation are (1) to present flight data from the deep space payload, including biology, fluidics, electronics, data processing, and mission operations, and (2) to discuss the lessons learned – what worked and what did not – from this unique complex mission, and how these lessons are aiding in the development of the Lunar Exploration Instrument for space biology Applications (LEIA) mission, launching to the lunar surface on a commercial lander in 2026. As of the writing of this abstract, the satellite continues to work nominally, communicating to Earth via the Deep Space Network (DSN) twice per week. Importantly, the mission received and extension to continue recording data on the deep space radiation environment on its way to solar maximum (i.e., higher probability of solar particle events). BioSentinel is supported by NASA Exploration Systems Development Mission Directorate (ESDMD).

BioSentinel↗
DOE OSTI2026

Extreme Temperature Cryptography Based On Nitrogen-Incorporated Ultrananocrystalline Diamond

Physical entropy sources that remain stable under extreme temperatures are essential for cryptography in emerging technological frontiers in deep space exploration, geothermal energy harvesting, and nuclear energy. However, conventional semiconductor platforms fail to generate stable and reliable cryptographic keys above 200 degrees C due to performance degradation. Here, we report a diamond-based cryptographic primitive that exploits the defect-rich sp 2 -bonded grain boundary network in nitrogen-incorporated ultrananocrystalline diamond (n-UNCD) film as a robust entropy source to generate cryptographic keys that remain operationally stable even after enduring extreme temperatures of 700 degrees C for 54 h while also surviving thermal cycling between room temperature and 700 degrees C for 48 h. The strength of the generated keys is assessed through several cryptographic metrics such as bit uniformity, entropy, hamming distances, and correlation coefficients, all of which are found to be near their respective ideal values. Moreover, the generated keys pass the NIST SP 800 and SP 800-90B tests and are also resilient to supply bias variations and a regression-based machine learning attack model based on the Fourier series. The robustness of the keys is attributed to the better thermal stability and chemical inertness of the n-UNCD film. This is supported by high-resolution energy-dispersive X-ray spectroscopy (EDS), which shows no significant lateral diffusion of metal atoms into the n-UNCD layer, and by Raman spectroscopy, which reveals no significant changes in the bonding configuration of the n-UNCD structure. Our findings highlight the remarkable potential of n-UNCD film for extreme environment cryptography by expanding the operational limits of conventional hardware security platforms.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Application of deep learning methods for beam size control during user operation at the Advanced Light Source

Past research at the Advanced Light Source (ALS) provided a proof-of-principle demonstration that deep learning methods could be effectively employed to compensate for the significant perturbations to the transverse electron beam size induced by user-controlled adjustments of the insertion devices. However, incorporating these methods into the ALS’ daily operations has faced notable challenges. The complexity of the system’s operational requirements and the significant upkeep demands has restricted their sustained application during user operation. Here, we introduce the development of a more robust neural network (NN)-based algorithm that utilizes a novel online fine-tuning approach and its systematic integration into the day-to-day machine operations. Our analysis emphasizes the process of NN model selection, demonstrates the superior performance of the NN-based method over traditional feedback methods, and examines the effectiveness and resilience of the new algorithm during user-operation scenarios. Published by the American Physical Society 2024

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

Bayesian GAN-Based False Data Injection Attack Detection in Active Distribution Grids With DERs

Advancements in information and communication technologies have revolutionized monitoring and control capabilities within smart grids. However, it also brings new vulnerabilities to data acquisition systems and state estimation functions, which attackers can subtly tamper with the measurement data through compromising the communication network. Moreover, the high penetration of renewable energy sources with the inherited characteristics of uncertainty and variability further complicates the design of effective intrusion detection systems. In this paper, a Bayesian deep learning-based approach is developed to detect cyber attacks and maintain the security of smart grids. Our method specifically addresses the prevalent issue of imbalanced data in real power systems, which arises from the predominance of normal system operations over compromised or attacked states. Employing a novel Bayesian GAN-based technique, our approach successfully discriminates between secure and compromised measurement data, even in scenarios with significant data imbalance. Furthermore, the proposed method accommodates various practical application factors, ensuring accurate intrusion detection despite the presence of measurement noise. The feasibility and effectiveness of the proposed detection mechanism are validated by testing on IEEE 13-node and 123-node test systems. Simulation results and comparisons with literature methods demonstrate the superiority of proposed cybersecurity solutions.

Bayesian GAN↗
NASA NTRS2020

Assessment of Natural and Anthropogenic Aerosol Air Pollution In the Middle East Using MERRA-2, CAMS Data Assimilation Products, and High-Resolution WRF-Chem Model Simulations

Modern-Era Retrospective analysis for Research and Applications v.2 (MERRA-2), Copernicus Atmosphere Monitoring Service Operational Analysis (CAMS-OA), and a high-resolution regional Weather Research and Forecasting model coupled with chemistry (WRF-Chem) were used to evaluate natural and anthropogenic particulate matter (PM) air pollution in the Middle East (ME) during 2015–2016. Two Moderate Resolution Imaging Spectrometer (MODIS) retrievals – combined product Deep Blue and Deep Target (MODIS-DB&DT) and Multi-Angle Implementation of Atmospheric Correction (MAIAC) – and Aerosol Robotic Network (AERONET) aerosol optical depth (AOD) observations as well as in situ PM measurements for 2016 were used for validation of the WRF-Chem output and both assimilation products. MERRA-2 and CAMS-OA assimilate AOD observations. WRF-Chem is a free-running model, but dust emission in WRF-Chem is tuned to fit AOD and aerosol volume size distributions obtained from AERONET. MERRA-2 was used to construct WRF-Chem initial and boundary conditions both for meteorology and chemical and aerosol species. SO2 emissions in WRF-Chem are based on the novel OMI-HTAP SO2 emission dataset. The correlation with the AERONET AOD is highest for MERRA-2 (0.72–0.91), MAIAC (0.63–0.96), and CAMSOA (0.65–0.87), followed by MODIS-DB&DT (0.56–0.84) and WRF-Chem (0.43–0.85). However, CAMS-OA has a relatively high positive mean bias with respect to AERONET AOD. The spatial distributions of seasonally averaged AODs from WRF-Chem, assimilation products, and MAIAC are well correlated with MODIS-DB&DT AOD product. MAIAC has the highest correlation (R = 0.8), followed by MERRA-2 (R = 0.66), CAMS-OA (R = 0.65), and WRF-Chem (R = 0.61). WRF-Chem, MERRA-2, and MAIAC underestimate and CAMS-OA overestimates MODIS-DB&DT AOD. The simulated and observed PM concentrations might differ by a factor of 2 because it is more challenging for the model and the assimilation products to reproduce PM concentration measured within the city. Although aerosol fields in WRF-Chem and assimilation products are entirely consistent, WRF-Chem is preferable for analysis of regional air quality over the ME due to its higher spatial resolution and better SO2 emissions. The WRF-Chem’s PM background concentrations exceed the World Health Organization (WHO) guidelines over the entire ME. Mineral dust is the major contributor to PM (≈ 75%–95%) compared to other aerosol types. Near and downwind from the SO2 emission sources, non-dust aerosols (primarily sulfate) contribute up to 30% to PM(sub 2.5). The contribution of sea salt to PM in coastal regions can reach 5%. The contributions of organic matter, black carbon and organic carbon to PM over the Middle East are insignificant. In the major cities over the Arabian Peninsula, the 90th percentile of PM(sub 10) and PM(sub 2.5) (particles with diameters less than 10 and 2.5 μm, respectively) daily mean surface concentrations exceed the corresponding Kingdom of Saudi Arabia air quality limits. The contribution of the non-dust component to PM(sub 2.5) is < 25%, which limits the emission control effect on air quality. The mitigation of the dust effect on air quality requires the development of environment-based approaches like growing tree belts around the cities and enhancing in-city vegetation cover. The WRF-Chem configuration presented in this study could be a prototype of a future air quality forecast system that warns the population against air pollution hazards.

Alexander Ukhov↗
DOE OSTI2024

Graph neural networks for CO 2 solubility predictions in Deep Eutectic Solvents

Deep Eutectic Solvents (DESs) are a promising class of solvents for CO 2 capture. DESs are complex mixtures that can be designed to optimize CO solubility and overall capture process efficiency. However, the vast design landscape of DES mixtures makes experimental investigation prohibitive; as such, there is a need for computational models that can quickly and efficiently navigate the design space and inform data collection efforts. In this work, we propose Graph Neural Network (GNN) models for predicting CO 2 solubility for DESs; the GNN leverages a mixture graph representation that captures the molecular structure of the DES components as well as their intermolecular interactions. Here, we compare the GNN framework against alternative architectures (neural networks, graph convolution networks, and random forests) and data representations (molecular fingerprints, sigma profiles, and graphs). We show that the proposed approach offers superior predictive performance; specifically, we show that solubility can be predicted reliably directly from molecular structure (without the need of using sigma profiles as proposed in previous studies). This result is important, as obtaining sigma profiles requires expensive density functional theory computations. We also explored the ability of GNNs to predict solubility for new DES mixtures and operating conditions. We found that the model extrapolates across temperature reliably. However, we also found deficiencies in the ability of the model to predict solubility for DES mixtures, pressures, and molar ratio not included in the training sets; we show that this is due to an inherent lack of chemical diversity in datasets available in the literature. The proposed computational capabilities can thus help navigate the design space of DES and inform data collection efforts. Our models, data, and benchmarks are shared as Python code implemented in Jupyter notebooks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Throughput-Oriented and Accuracy-Aware DNN Training with BFloat16 on GPU

Deep Neural Networks (DNNs) have transformed the field of artificial intelligence and achieved extraordinary success in many areas. The training of DNNs is commonly compute and memory-intensive, which has resulted in several optimizations in the training phase. Among them, reduced precision is a typical and widely used technique to accelerate DNN training and reduce memory requirements. However, applying a widely adopted reduced precision format such as Float16 to all involved operations in DNN training is not optimal as the use of Float16 in some operations can hurt model accuracy. Meanwhile, additional optimizations including loss scaling and autocast techniques can mitigate the accuracy loss but lead to inherent overhead and inadequate use of reduced precision. In this work, we leverage another reduced precision format, BFloat16, and introduce a throughput-oriented and accuracy-aware approach to maximize the performance potential of DNN training. Since the high throughput provided by BFloat16 format is accompanied by low precision of the floating-point representation, this approach achieves high throughput by using BFloat16 on all DNN operations and avoids the accuracy loss through a customized accuracy-aware normalization. Results show that our approach outperforms the state-of-the-art mixed-precision training by 1.21x on an NVIDIA A100 GPU.

Xie, Zhen↗
NASA NTRS2011

Emergency Communications for NASA's Deep Space Missions

The ability to communicate with spacecraft during emergencies is a vital service that NASA's Deep Space Network (DSN) provides to all deep space missions. Emergency communications is characterized by low data rates(typically is approximately10 bps) with the spacecraft using either a low-gain antenna (LGA, including omnidirectional antennas) or,in some cases, a medium-gain antenna (MGA). Because of the use of LGAs/MGAs for emergency communications, the transmitted power requirements both on the spacecraft andon the ground are substantially greater than those required for normal operations on the high-gain antenna (HGA) despite the lower data rates. In this paper, we look at currentand future emergency communications capabilities available to NASA's deep-space missions and discuss their limitations in the context of emergency mode operations requirements.These discussions include the use of the DSN 70-m diameter antennas, the use of the 34-m diameter antennas either alone or arrayed both for the uplink (Earth-to-spacecraft) and the downlink (spacecraft-to-Earth), upgrades to the ground transmitters, and spacecraft power requirements both with unitygain (0 dB) LGAs and with antennas with directivity (>0 dB gain, either LGA or MGA, depending on the gain). Also discussed are the requirements for forward-error-correctingcodes for both the uplink and the downlink. In additional, we introduce a methodology for proper selection of a directionalLGA/MGA for emergency communications.

Shambayati, Shervin↗
NASA NTRSDate not supplied

Lunar Optical Communications

Numerous studies have shown that NASA’s Deep Space Network (DSN) is woefully inadequate to support the current pace of space exploration. Proposals are on the table for extensive infrastructure build-out using RF communications, which is ultimately bandwidth constrained. Optical communication offers unregulated, near-infinite bandwidth that can easily support the needs of humans at the Moon and beyond. Although not part of the proposed lunar network architecture, optical communication systems should be considered; these systems are operational now, quickly proliferating near Earth space (e.g. StarLink), and offer very high bandwidths.

lunar↗
NASA NTRS1988

Intelligent Resource Management for Local Area Networks: Approach and Evolution

The Data Management System network is a complex and important part of manned space platforms. Its efficient operation is vital to crew, subsystems and experiments. AI is being considered to aid in the initial design of the network and to augment the management of its operation. The Intelligent Resource Management for Local Area Networks (IRMA-LAN) project is concerned with the application of AI techniques to network configuration and management. A network simulation was constructed employing real time process scheduling for realistic loads, and utilizing the IEEE 802.4 token passing scheme. This simulation is an integral part of the construction of the IRMA-LAN system. From it, a causal model is being constructed for use in prediction and deep reasoning about the system configuration. An AI network design advisor is being added to help in the design of an efficient network. The AI portion of the system is planned to evolve into a dynamic network management aid. The approach, the integrated simulation, project evolution, and some initial results are described.

Meike, Roger↗
NASA NTRS1992

Real-time antenna fault diagnosis experiments at DSS 13

Experimental results obtained when a previously described fault diagnosis system was run online in real time at the 34-m beam waveguide antenna at Deep Space Station (DSS) 13 are described. Experimental conditions and the quality of results are described. A neural network model and a maximum-likelihood Gaussian classifier are compared with and without a Markov component to model temporal context. At the rate of a state update every 6.4 seconds, over a period of roughly 1 hour, the neural-Markov system had zero errors (incorrect state estimates) while monitoring both faulty and normal operations. The overall results indicate that the neural-Markov combination is the most accurate model and has significant practical potential.

Mellstrom, J.↗
NASA NTRS1999

The Future of the Deep Space Network: Technology Development for K2-Band Deep Space Communications

Projections indicate that in the future the number of NASA's robotic deep space missions is likely to increase significantly. A launch rate of up to 4-6 launches per year is projected with up to 25 simultaneous missions active [I]. Future high resolution mapping missions to other planetary bodies as well as other experiments are likely to require increased downlink capacity. These future deep space communications requirements will, according to baseline loading analysis, exceed the capacity of NASA's Deep Space Network in its present form. There are essentially two approaches for increasing the channel capacity of the Deep Space Network. Given the near-optimum performance of the network at the two deep space communications bands, S-Band (uplink 2.025-2.120 GHz, downlink 2.2-2.3 GHz), and X-Band (uplink 7.145-7.19 GHz, downlink 8.48.5 GHz), additional improvements bring only marginal return for the investment. Thus the only way to increase channel capacity is simply to construct more antennas, receivers, transmitters and other hardware. This approach is relatively low-risk but involves increasing both the number of assets in the network and operational costs.

Bhanji, Alaudin M.↗
NASA NTRS2001

Considerations and Architectures for Inter-Satellite Communications in Distributed Spacecraft Systems

This paper will identify the important characteristics and requirements necessary for inter-satellite communications in distributed spacecraft systems and present analysis results focusing on architectural and protocol comparisons. Emerging spacecraft systems plan to deploy multiple satellites in various "distributed" configurations ranging from close proximity formation flying to widely separated constellations. Distributed spacecraft configurations provide advantages for science exploration and operations since many activities useful for missions may be better served by distributing them between spacecraft. For example, many scientific observations can be enhanced through spatially separated platforms, such as for deep space interferometry. operating multiple distributed spacecraft as a mission requires coordination that may be best provided through inter-satellite communications. For example, several future distributed spacecraft systems envision autonomous operations requiring relative navigational calculations and coordinated attitude and position corrections. To conduct these operations, data must be exchanged between spacecraft. Direct cross-links between satellites provides an efficient and practical method for transferring data and commands. Unlike existing "bent-pipe" relay networks supporting space missions, no standard or widely-used method exists for cross-link communications. Consequently, to support these future missions, the characteristics necessary for inter-satellite communications need to be examined. At first glance, all of the missions look extremely different. Some missions call for tens to hundreds of nano-satellites in constant communications in close proximity to each other. Other missions call for a handful of satellites communicating very slowly over thousands to hundreds of thousands of kilometers. The paper will first classify distributed spacecraft missions to help guide the evaluation and definition of cross-link architectures and approaches. Based on this general classification, the paper will examine general physical layer parameters, such as frequency bands and data rates, necessary to support the missions. The paper will also identify classes of communication architectures that may be employed, ranging from fully distributed to centralized topologies. Numerous factors, such as number of spacecraft, must be evaluated when attempting to pick a communications architecture. Also important is the stability of the formation from a communications standpoint. For example, do all of the spacecraft require equal bandwidth and are spacecraft allowed to enter and leave a formation? The type of science mission being attempted may also heavily influence the communications architecture. In addition, the paper will assess various parameters and characteristics typically associated with the data link layer. The paper will analyze the performance of various multiple access techniques given the operational scenario, requirements, and communication topologies envisioned for missions. This assessment will also include a survey of existing standards and their applicability for distributed spacecraft systems. An important consideration includes the interoperability of the lower layers (physical and data link) examined in this paper with the higher layer protocols(network) envisioned for future space internetworking. Finally, the paper will define a suggested path, including preliminary recommendations, for defining and developing a standard for intersatellite communications based on the classes of distributed spacecraft missions and analysis results.

Edwards, Bernard↗
NASA NTRS2001

Ultra Low Power, Radiation Tolerant UHF Radio Technologies for In Situ Communication Applications

For future deep space missions, significant reductions in the mass and power requirements for short-range telecommunication systems will be critical in enabling a wide variety of new mission concepts. These possibilities include penetrators, gliders, miniature rovers, and sensor networks. Under joint funding from NASA's Cross Enterprise and JPL's Telecommunications and Mission technology programs, recent development activity has focused on the design of ultralow mass and power transceiver systems and subsystems suitable for operation in a flight environment. For these efforts, the functionality of the transceiver has been targeted towards a specific Mars communications scenario. However, the overall architecture is well suited to any short or medium range application where a remote probe will aperiodically communicate with a base station, possibly an orbiter, for the eventual purpose of relaying science information back to Earth. In 2001, these sponsors have been augmented with collaborative expertise and funding from JPL's Center for Integrated Space Microsystems in order to migrate existing concepts and designs to a System on a Chip (SOAC) solution. Additional information is contained in the original extended abstract.

Lay, N. E.↗