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.

SourceResearch connectionFrom yearThrough year

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

At least 1,081 records · Page 60

All sources NASA NTRS DOE OSTI

DOE OSTI2020

FALCON: Framework for Anomaly Detection in Industrial Control Systems

Industrial Control Systems (ICS) are used to control physical processes in critical infrastructure. These systems are used in a wide variety of operations such as water treatment, power generation and distribution, and manufacturing. While the safety and security of these systems are of serious concern, recent reports have shown an increase in targeted attacks aimed at manipulating physical processes to cause catastrophic consequences. This trend emphasizes the need for algorithms and tools that provide resilient and smart attack detection mechanisms to protect ICS. In this paper, we propose an anomaly detection framework for ICS based on a deep neural network. The proposed methodology uses dilated convolution and long short-term memory (LSTM) layers to learn temporal as well as long term dependencies within sensor and actuator data in an ICS. The sensor/actuator data are passed through a unique feature engineering pipeline where wavelet transformation is applied to the sensor signals to extract features that are fed into the model. Additionally, this paper explores four variations of supervised deep learning models, as well as an unsupervised support vector machine (SVM) model for this problem. The proposed framework is validated on Secure Water Treatment testbed results. This framework detects more attacks in a shorter period of time than previously published methods.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2022

A Novel Method for Controlling Crud Deposition in Nuclear Reactors Using Optimization Algorithms and Deep Neural Network Based Surrogate Models

This work presents the use of a high-fidelity neural network surrogate model within a Modular Optimization Framework for treatment of crud deposition as a constraint within light-water reactor core loading pattern optimization. The neural network was utilized for the treatment of crud constraints within the context of an advanced genetic algorithm applied to the core design problem. This proof-of-concept study shows that loading pattern optimization aided by a neural network surrogate model can optimize the manner in which crud distributes within a nuclear reactor without impacting operational parameters such as enrichment or cycle length. Several analysis methods were investigated. Analysis found that the surrogate model and genetic algorithm successfully minimized the deviation from a uniform crud distribution against a population of solutions from a reference optimization in which the crud distribution was not optimized. Strong evidence is presented that shows boron deposition in crud can be optimized through the loading pattern. This proof-of-concept study shows that the methods employed provide a powerful tool for mitigating the effects of crud deposition in nuclear reactors.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Deep learning models for interpretation of point of care ultrasound in military working dogs

Introduction: Military working dogs (MWDs) are essential for military operations in a wide range of missions. With this pivotal role, MWDs can become casualties requiring specialized veterinary care that may not always be available far forward on the battlefield. Some injuries such as pneumothorax, hemothorax, or abdominal hemorrhage can be diagnosed using point of care ultrasound (POCUS) such as the Global FAST® exam. This presents a unique opportunity for artificial intelligence (AI) to aid in the interpretation of ultrasound images. In this article, deep learning classification neural networks were developed for POCUS assessment in MWDs. Methods: Images were collected in five MWDs under general anesthesia or deep sedation for all scan points in the Global FAST® exam. For representative injuries, a cadaver model was used from which positive and negative injury images were captured. A total of 327 ultrasound clips were captured and split across scan points for training three different AI network architectures: MobileNetV2, DarkNet-19, and ShrapML. Gradient class activation mapping (GradCAM) overlays were generated for representative images to better explain AI predictions. Results: Performance of AI models reached over 82% accuracy for all scan points. The model with the highest performance was trained with the MobileNetV2 network for the cystocolic scan point achieving 99.8% accuracy. Across all trained networks the diaphragmatic hepatorenal scan point had the best overall performance. However, GradCAM overlays showed that the models with highest accuracy, like MobileNetV2, were not always identifying relevant features. Conversely, the GradCAM heatmaps for ShrapML show general agreement with regions most indicative of fluid accumulation. Discussion: Overall, the AI models developed can automate POCUS predictions in MWDs. Preliminarily, ShrapML had the strongest performance and prediction rate paired with accurately tracking fluid accumulation sites, making it the most suitable option for eventual real-time deployment with ultrasound systems. Further integration of this technology with imaging technologies will expand use of POCUS-based triage of MWDs.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1983

Description and overview of an instrument designed to measure line-of-sight delay due to water vapor

Eight dual channel microwave radiometers were constructed as a research and development effort for the Crustal Dynamics Project and the Deep Space Network. These instruments, known as water vapor radiometers, are primarily intended to demonstrate that the variable path delay imposed by atmospheric water vapor can be calibrated in microwave tracking and distance measuring systems but could also be used in other applications involving moist air meteorology and propagation studies. They are being deployed to various stations and observatories that participate in Very Long Baseline Interferometry experiments. The development history of these instruments are reviewed, the theory of operation and overall design considerations are outlined, and the instrumental parameters and performance characteristics are described.

Resch, G. M.↗

NASA NTRS1993

Optical subnet concepts for the deep space network

This article describes potential enhancements to the Deep Space Network, based on a subnet of receiving stations that will utilize optical communications technology in the post-2010 era. Two optical subnet concepts are presented that provide full line-of-sight coverage of the ecliptic, 24 hours a day, with high weather availability. The technical characteristics of the optical station and the user terminal are presented, as well as the effects of cloud cover, transmittance through the atmosphere, and background noise during daytime or nighttime operation on the communications link. In addition, this article identifies candidate geographic sites for the two network concepts and includes a link design for a hypothetical Pluto mission in 2015.

Shaik, K.↗

NASA NTRS2008

Optical Communications from Planetary Distances

Future planetary campaigns, including human missions, will require data rates difficult to realize by microwave links. Optical channels not only provide an abundance of bandwidth, they also allow for significant size, weight, and power reduction. Moreover, optical-based tracking may enhance spacecraft navigation with respect to microwave-based tracking. With all its advantages, optical communications from deep space is not without its challenges. Due to the extreme distance between the two ends of the link, specialized technologies are needed to enable communications in the deep space environment. Although some of the relevant technologies have been developed in the last decade, they remain to be validated in an appropriate domain. The required assets include efficient pulsed laser sources, modulators, transmitters, receivers, detectors, channel encoders, precise beam pointing technologies for the flight transceiver and large apertures for the ground receiver. Clearly, space qualification is required for the systems that are installed on a deep space probe. Another challenge is atmospheric effects on the optical beam. Typical candidate locations on the ground have a cloud-free line of sight only on the order of 60-70% of the time. Furthermore, atmospheric losses and background light can be problematic even during cloud-free periods. Lastly, operational methodologies are needed for efficient and cost effective management of optical links. For more than a decade, the National Aeronautics and Space Administration (NASA) has invested in relevant technologies and procedures to enable deep space optical communications capable of providing robust links with rates in the order of 1 Gb/s from Mars distance. A recent publication indicates that potential exists for 30-dB improvement in performance through technology development with respect to the state-of-the-art in the early years of this decade. The goal is to fulfill the deep space community needs from about 2020 to the foreseeable future. It is envisioned that, at least initially, optical links will be complemented by microwave assets for added robustness, especially for human missions. However, it is expected that as optical techniques mature, laser communications may be operated without conventional radio frequency links. The purpose of this paper is to briefly review the state-of-the-art in deep space laser communications and its challenges and discuss NASA-supported technology development efforts and plans for deep space optical communications at JPL.

Laser Communications↗

DOE OSTI2022

Dynamic Role-Based Access Control Policy for Smart Grid Applications: An Offline Deep Reinforcement Learning Approach

Role-based access control (RBAC) is adopted in the information and communication technology domain for authentication purposes. However, due to a very large number of entities within organizational access control (AC) systems, static RBAC management can be inefficient, costly, and can lead to cybersecurity threats. In this paper, a novel hybrid RBAC model is proposed, based on the principles of offline deep reinforcement learning (RL) and Bayesian belief networks. The considered framework utilizes a fully offline RL agent, which models the behavioral history of users as a Bayesian belief-based trust indicator. Thus, the initial static RBAC policy is improved in a dynamic manner through off-policy learning while guaranteeing compliance of the internal users with the security rules of the system. By deploying our implementation within the smart grid domain and specifically within a Distributed Energy Resources (DER) ecosystem, we provide an end-to-end proof of concept of our model. Finally, detailed analysis and evaluation regarding the offline training phase of the RL agent are provided, while the online deployment of the hybrid RL-based RBAC model into the DER ecosystem highlights its key operation features and salient benefits over traditional RBAC models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA NTRS2017

NASA Near Earth Network (NEN) Support for Lunar and L1/L2 CubeSats

The NASA Near Earth Network (NEN) consists of globally distributed tracking stations, including NASA, commercial, and partner ground stations, that are strategically located to maximize the coverage provided to a variety of orbital and suborbital missions, including those in LEO, GEO, HEO, lunar and L1/L2 orbits. The NENs future mission set includes and will continue to include CubeSat missions. The first NEN supported CubeSat mission will be the Cubesat Proximity Operations Demonstration (CPOD) launching into low earth orbit (LEO) in early 2017. The majority of the CubeSat missions destined to fly on EM-1, launching in late 2018, many in a lunar orbit, will communicate with ground based stations via X-band and will utilize the NASA Jet Propulsion Laboratory (JPL) developed IRIS radio. The NEN recognizes the important role CubeSats are beginning to play in carrying out NASAs mission and is therefore investigating the modifications needed to provide IRIS radio compatibility. With modification, the NEN could potentially expand support to the EM-1 lunar CubeSats. The NEN could begin providing significant coverage to lunar CubeSat missions utilizing three to four of the NENs mid-latitude sites. This coverage would supplement coverage provided by the JPL Deep Space Network (DSN). The NEN, with smaller apertures than DSN, provides the benefit of a larger beamwidth that could be beneficial in the event of uncertain ephemeris data. In order to realize these benefits the NEN would need to upgrade stations targeted based on coverage ability and current configurationease of upgrade, to ensure compatibility with the IRIS radio.In addition, the NEN is working with CubeSat radio developers to ensure NEN compatibility with alternative CubeSat radios for Lunar and L1/L2 CubeSats. The NEN has provided NEN compatibility requirements to several radio developers who are developing radios that offer lower cost and, in some cases, more capabilities with fewer constraints. The NEN is ready to begin supporting CubeSat missions. The NEN is considering network upgrades to broaden the types of CubeSat missions that can be supported and is supporting both the CubeSat community and radio developers to ensure future CubeSat missions have multiple options when choosing a network for their communications support.

Global Tracking Network Ground Station↗

DOE OSTI2021

Polarimetric Signatures in Landfalling Tropical Cyclones

Polarimetric radar observations from the NEXRAD WSR-88D operational radar network in the contiguous United States, routinely available since 2013, are used to reveal three prominent microphysical signatures in landfalling tropical cyclones: 1) hydrometeor size sorting within the eyewall convection, 2) vertical displacement of the melting layer within the inner core, and 3) dendritic growth layers within stratiform regions of the inner core. Size sorting signatures within eyewall convection are observed with greater frequency and prominence in more intense hurricanes, and are observed predominantly within the deep-layer environmental wind shear vector-relative quadrants that harbor the greatest frequency of deep convection (i.e., downshear and left-of-shear). Melting-layer displacements are shown that exceed 1 km in altitude compared to melting-layer altitudes in outer rainbands and are complemented by analyses of archived dropsonde data. Dendritic growth and attendant snow aggregation signatures in the inner core are found to occur more often when echo-top altitudes are low (≤10 km MSL), nearer the -15°C isotherm commonly associated with dendritic growth. These signatures, uniquely observed by polarimetric radar, provide greater insight into the physical structure and thermodynamic characteristics of tropical cyclones, which are important for improving rainfall estimation and the representation of tropical cyclones in numerical models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Semi-automatic image annotation using 3D LiDAR projections and depth camera data

Efficient image annotation is necessary to utilize deep learning object recognition neural networks in nuclear safeguards, such as for the detection and localization of target objects like nuclear material containers (NMCs). This capability can help automate the inventory accounting of different types of NMCs within nuclear storage facilities. The conventional manual annotation process is labor-intensive and time-consuming, hindering the rapid deployment of deep learning models for NMC identifications. This paper introduces a novel semi-automatic method for annotating 2D images of nuclear material containers (NMCs) by combining 3D light detection and ranging (LiDAR) data with color and depth camera images collected from a handheld scan system. The annotation pipeline involves an operator manually marking new target objects on a LiDAR-generated map, and projecting these 3D locations to images, thereby automatically creating annotations from the projections. The semi-automatic approach significantly reduces manual efforts and the expertise in image annotation that is required to perform the task, allowing deep learning models to be trained on-site within a few hours. The paper compares the performance of models trained on datasets annotated through various methods, including semi-automatic, manual, and commercial annotation services. The evaluation demonstrates that the semi-automatic annotation method achieves comparable or superior results, with a mean average precision (mAP) above 0.9, showcasing its efficiency in training object recognition models. Additionally, the paper explores the application of the proposed method to instance segmentation, achieving promising results in detecting multiple types of NMCs in various formations.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

DOE OSTI2025

Securing Smart Manufacturing: Detection of Cyber-Physical Attacks in CNC-Based Systems

As Industry 4.0 advances, the integration of computer numerical control (CNC) machines and advanced manufacturing technologies is transforming production into smart manufacturing systems that blend physical and digital processes as cyber-physical systems. However, this increased cyber-physical connectivity exposes manufacturing systems to cyber threats that can cause severe operational and financial disruptions. This paper presents a comparative study on cyber attacks and anomaly detection techniques in manufacturing, focusing on network traffic from CNC machines. The data extracted from network packets includes machine commands and control signals exchanged between the machine's interface and control system, crucial for maintaining operational integrity. We explore two types of cyber attacks, design modification and command injection, which pose substantial risks to CNC machine productivity and system integrity. Our investigation involves experiments on a real CNC system, highlighting the urgent need for effective detection mechanisms. To address these threats, we evaluate three anomaly detection methods: dynamic time warping (DTW), rolling average, and a deep learning, long short-term memory (LSTM) time-series-based autoencoder. Each is assessed for its effectiveness in identifying anomalous behaviors caused by the attacks. Our findings demonstrate the unique strengths and limitations of each detection technique, providing a deeper understanding of their applicability in realworld manufacturing environments. The comparative analysis indicates that while certain methods are highly effective against specific attack types, others offer broader applicability across different attacks. This study contributes to the accurate detection of anomalies in CNC machining processes, thereby enhancing the reliability and security of smart manufacturing systems against diverse cyber threats.

Williams, Bethanie [Tennessee Technological Univer↗

NASA NTRS1993

Cost and reliability study for a large array of small reflector antennas for JPL/NASA Deep Space Network (DSN)

A study performed to estimate the cost of an array of small aperture reflector antennas to be used instead of or in conjunction with the current large reflector antennas of the JPL/NASA Deep Space Network (DSN) is described. The arrays are used for servicing present and future NASA missions that involve smaller spacecraft with limited power and smaller, lower-gain antennas. The advantages of the array configuration in terms of cost and reliability are discussed. A probabilistic determination of the reliability and availability of the array as a function of the number of array elements and the availability of individual array elements is made. The impact of additional marginal elements on the operational availability of the array is studied. Parametric cost and reliability plots are presented and directions for further investigation are outlined.

Jamnejad, Vahraz↗

NASA NTRSDate not supplied

Updating the Thermal Vacuum Chambers at the NASA Johnson Space Center

Chambers A and B are two large thermal vacuum chambers at Johnson Space Center which enable space simulation for unmanned and human-rated missions, respectively. With the resurgence in deep space missions for scientific research and various private commercial ventures, these chambers are expected to be used frequently for at least the next decade. For qualifying the James Webb Space Telescope, upgrades to Chamber A were performed which included the addition of a 12.5 kW refrigeration system with helium shrouds capable of simulating deep space environment and an efficient and reliable LN2 natural flow thermosiphon system for the thermal shield. Continuous improvements since then have focused on ensuring operational readiness by modernizing the data acquisition, recording, controls, and visualization systems for both chambers and clean room. These upgrades will be the focus of this paper. Controlling the Cryochambers was enhanced by moving from a 32-bit SCADA system to a 64-bit architected system. Infrastructural changes involved installing redundant power circuits, adding new servers, network switches, and including load balancing with fail-over between servers to minimize downtime. Instead of distributed servers, 3 redundant servers are used to share configurations. Configurations are now kept in a shared SQL instance making it easy to deploy and maintain. During this upgrade process many sub-systems (PLCs and NI PXI interfaces to sensors) were upgraded from the prior OPC-DA to the more secure OPC-UA protocol. Cryo-system PLCs were updated to allow Ganni cycle floating pressure calculations from any cold box to be sent to any compressor. During the project, the team recreated over 70,000 live data points, 50000 historical data points, and 4000 alarms. Finally, the graphical interfaces were upgraded to support HTML 5 in conjunction shared pages were implemented reducing the total number of webpages by over 75%. These system updates reinvigorated the previous SCADA system which had reached its end of life. The same look and feel was maintained while providing operators with an updated interface to control, troubleshoot, and record. The new system architecture is more robust and easier to maintain creating a path forward to address remaining problem points and implement additional features.

Cody Schaefer↗

NASA NTRSDate not supplied

Updating the Thermal Vacuum Chambers at the NASA Johnson Space Center

Cody Schaefer↗

NASA NTRS2011

High-Efficiency Ka-Band Waveguide Two-Way Asymmetric Power Combiner

NASA is planning a number of Space Exploration, Earth Observation and Space Science missions where Ka-band solid-state power amplifiers (SSPAs) could have a role. Monolithic microwave integrated circuit (MMIC) based SSPAs with output powers on the order of 10 W at Ka-band frequencies would be adequate to satisfy the data transmission rate requirements at the distances involved. MMICs are a type of integrated circuit fabricated on a GaAs wafer, which operates at micro wave frequencies and performs the function of signal amplification. The highest power Ka-band (31.8 to 32.3 GHz) SSPA to have flown in space had an output power of 2.6 W with an overall efficiency of 14.3 percent. This SSPA was built around discrete GaAs pHEMT (high electron mobility transistor) devices and flew aboard the Deep Space One spacecraft. State-of-the-art GaAs pHEMT-based MMIC power amplifiers (PAs) can deliver RF power at Ka-band frequencies anywhere from 3 W with a power added efficiency (PAE) of 32 percent to 6 W with a PAE of 26 percent. However, to achieve power levels higher than 6 W, the output of several MMIC PAs would need to be combined using a high-efficiency power combiner. Conventional binary waveguide power combiners, based on short-slot and magic-T circuits, require MMIC PAs with identical amplitude and phase characteristics for high combining efficiency. However, due to manufacturing process variations, the output powers of the MMIC PAs tend to be unequal, and hence the need to develop unequal power combiners. A two-way asymmetric magic-T based power combiner for MMIC power amplifiers, which can take in unequal inputs, has been successfully designed, fabricated, and characterized over NASA s Deep Space Network (DSN) frequency range of 31.8 to 32.3 GHz. The figure is a transparent view of the a sym - metric combiner that shows the 4-port configuration and the internal structure. The rod, post, and iris are positioned by design to achieve the desired asymmetric power ratio, phase equality, and port isolation. Although the combiner was designed for an input power ratio of 2:1, it can be custom-designed for any arbitrary power ratio and frequency range. The manufactured prototype combiner was precision machined from aluminum and is less than 2 in.3 (32.8 cm3). Previously investigated rectangular waveguide unequal power combiners were based on shunt/series coupling slots, E-plane septums, or H-plane T-junctions. All the prior art unequal power combiners operated at or below X-band (10 GHz) frequencies and were primarily used in the feed network of antenna arrays. The only reported asymmetric magic-T was developed as a 2:1 power divider for operation at a much lower frequency, around 500 MHz. The measured power ratio when tested as a power divider was very close to 2 and the phase balance was within 2.6, resulting in near ideal performance. When tested as a combiner using two MMIC SSPAs with a 2:1 power output ratio, an efficiency greater than 90 percent was demonstrated over the 500 MHz DSN frequency range. The return loss at the combiner output port (1) was greater than 18 dB and the input port (2 and 3) isolation was greater than 22 dB. The results show the asymmetric combiner to be a good candidate for high-efficiency power combining of two or more SSPAs needed to achieve the 6 to 10 W required by space communications systems of future NASA missions.

Wintucky, E. G.↗

DOE OSTI2025

Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem

Three-dimensional target identification using scattering techniques requires high accuracy solutions and very fast computations for real-time predictions in some critical applications. We first train a deep neural operator (DeepONet) to solve wave propagation problems described by the Helmholtz equation in a domain without scatterers but at different wavenumbers and with a complex absorbing boundary condition. We then design two classes of fast meta-solvers by combining DeepONet with either relaxation methods, such as Jacobi and Gauss-Seidel, or with Krylov methods, such as GMRES and BiCGStab, using the trunk basis of DeepONet as a coarse-scale preconditioner. We leverage the spectral bias of neural networks to account for the lower part of the spectrum in the error distribution while the upper part is handled inexpensively using relaxation methods or fine-scale preconditioners. The meta-solvers are then applied to solve scattering problems with different shape of scatterers, at no extra training cost. We first demonstrate that the resulting meta-solvers are shape-agnostic, fast, and robust, whereas the standard standalone solvers may even fail to converge without the DeepONet. We then apply both classes of meta-solvers to scattering from a submarine, a complex three-dimensional problem. We achieve very fast solutions, especially with the DeepONet-Krylov methods, which require orders of magnitude fewer iterations than any of the standalone solvers.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Neural Lyapunov Control for Power System Transient Stability: A Deep Learning-Based Approach

We report that power system control and transient stability analysis play essential roles in secure system operation. Control of power systems typically involves highly nonlinear and complex dynamics. Most of the existing works address such problems with additional assumptions in system dynamics, leading to a requirement for a complete and general solution. This paper, therefore, proposes a novel control framework for various power system control and stability problems leveraging a learning-based approach. The proposed framework includes a two-module structure that iteratively and jointly learns the candidate Lyapunov function and control law via deep neural networks in a learning module. Meanwhile, it guides the learning procedure towards valid results satisfying Lyapunov conditions in a falsification module. The introduced termination criteria ensure provable system stability. This control framework is verified through several studies handling different types of power system control problems. The results show that the proposed framework is generalizable and can simplify the control design for complex power systems with the stability guarantee and enlarged region of attraction.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

A Deep Learning Filter for the Intraseasonal Variability of the Tropics

Abstract This paper presents a novel application of convolutional neural network (CNN) models for filtering the intraseasonal variability of the tropical atmosphere. In this deep learning filter, two convolutional layers are applied sequentially in a supervised machine learning framework to extract the intraseasonal signal from the total daily anomalies. The CNN-based filter can be tailored for each field similarly to fast Fourier transform filtering methods. When applied to two different fields (zonal wind stress and outgoing longwave radiation), the index of agreement between the filtered signal obtained using the CNN-based filter and a conventional weight-based filter is between 95% and 99%. The advantage of the CNN-based filter over the conventional filters is its applicability to time series with the length comparable to the period of the signal being extracted. Significance Statement This study proposes a new method for discovering hidden connections in data representative of tropical atmosphere variability. The method makes use of an artificial intelligence (AI) algorithm that combines a mathematical operation known as convolution with a mathematical model built to reflect the behavior of the human brain known as artificial neural network. Our results show that the filtered data produced by the AI-based method are consistent with the results obtained using conventional mathematical algorithms. The advantage of the AI-based method is that it can be applied to cases for which the conventional methods have limitations, such as forecast (hindcast) data or real-time monitoring of tropical variability in the 20–100-day range.

Stan, Cristiana↗