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 865 records · Page 48
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Decentralised Reinforcement Learning for Dynamic Cyberattack Response in Microgrid Networks

Microgrids rely on communication networks for reliable operation, which makes them inherently vulnerable to cyberattacks. Such attacks can destabilise system dynamics and drive states away from their nominal operating trajectories. Although several physics-informed and machine learning-based strategies have been developed to counter these threats, the rapidly evolving cyber landscape enables adversaries to bypass static defences or rules-based mitigation approaches. This paper proposes a dynamic, online-trained and fully decentralised reinforcement learning (RL)-based cyberattack response framework to protect microgrids from evolving cyberattacks. The proposed framework deploys multiple deep Q-networks (DQNs), each associated with a distributed energy resource (DER), to enable localised and adaptive attack mitigation. In this framework, each DQN processes local voltage and frequency measurements—combined with intrusion detection system (IDS) alerts—as observations and rewards to guide decision-making. Extensive simulation studies demonstrate the robustness of the proposed framework under diverse attack scenarios and varying IDS-induced detection delays. Comparative analysis highlights its superiority over existing static or preexisting rules-based mitigation approaches. Finally, we present an analysis that shows the framework's scalability to real-life microgrids with more interacting agents.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1976

Use of load and go countdowns by the DSN deep space stations

The Level-4 Prepass Readiness Test (PRT) (the load and go countdown) provides an effective and low risk method of improving network productivity. A carefully controlled trial period preceded the full-scale application of the Level-4 PRTS to Pioneer, Helios, and Viking cruise tracking operations. Use of this load and go concept to count down a station brings about a substantial increase in the proportion of total station hours devoted to spacecraft tracking.

Hatch, J. T.↗
NASA NTRS2005

Data-Rate Estimation for Autonomous Receiver Operation

In this article, we present a series of algorithms for estimating the data rate of a signal whose admissible data rates are integer base, integer powered multiples of a known basic data rate. These algorithms can be applied to the Electra radio currently used in the Deep Space Network (DSN), which employs data rates having the above relationship. The estimation is carried out in an autonomous setting in which very little a priori information is assumed. It is done by exploiting an elegant property of the split symbol moments estimator (SSME), which is traditionally used to estimate the signal-to-noise ratio (SNR) of the received signal. By quantizing the assumed symbol-timing error or jitter, we present an all-digital implementation of the SSME which can be used to jointly estimate the data rate, SNR, and jitter. Simulation results presented show that these joint estimation algorithms perform well, even in the low SNR regions typically encountered in the DSN.

Tkacenko, A.↗
NASA NTRS1977

Helios mission support

Deep Space Network coverage of Helios-1 and Helios-2 from Feb. 1 through Apr. 15, 1977 is presented in tabular form. Mark III data system (MDS) performance and station modifications for MDS configuration are discussed. Cross support for Helios operations by DSN and STDN is described and their downlink performances compared.

Goodwin, P. S.↗
DOE OSTI2020

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classication is found to be easily misled by increasingly complex image features due to the usage of pooling operations, hence unable to preserve accurate position and pose information of the objects. To address this challenge, a novel neural network structure called Capsule Network has been proposed, which introduces equivariance through capsules to signicantly enhance the learning ability for image segmentation and object detection. Due to its requirement of performing a high volume of matrix operations, CapsNets have been generally accelerated on modern GPU platforms that provide highly optimized software library for common deep learning tasks. However, based on our performance characterization on modern GPUs, CapsNets exhibit low effciency due to the special program and execution features of their routing procedure, including massive unshareable intermediate variables and intensive syn- chronizations, which are very dicult to optimize at software level. To address these challenges, we propose a hybrid computing architecture design named PIM-CapsNet. It preserves GPU's on-chip computing capability for accelerating CNN types of layers in CapsNet, while pipelining with an off-chip in-memory acceleration solution that effectively tackles routing procedure's ineffciency by leveraging the processing-in-memory capability of today's 3D stacked memory. Using routing procedure's inherent parallellization feature, our design enables hierarchical improvements on CapsNet inference effciency through minimizing data movement and maximizing parallel processing in memory. Evaluation results demonstrate that our proposed design can achieve substantial improvement on both performance and energy savings for CapsNet inference, with almost zero accuracy loss. The results also suggest good performance scalability in optimizing the routing procedure with increasing network size.

Zhang, Xingyao↗
DOE OSTI2020

Deep learning model to detect various synchrophasor data anomalies

High-density synchrophasors provide valuable information for power grid situational awareness, operation and control. Unfortunately, due to factors including communication instability and hardware failure, their data quality can be greatly deteriorated by anomalies. Since the anomalies can impact the performance of the synchrophasor applications, it is of paramount significance to propose a model to detect anomalies in synchrophasor. In this study, a convolutional neural network model is established to detect and classify the anomalies in the synchrophasor measurements. Additionally, four types of anomalies observed in actual synchrophasors including erroneous patterns, random spikes, missing points and high-frequency interferences are considered in this study. The proposed model is extensively evaluated via field-collected measurements from the synchrophasor network in Jiangsu grid, China. The superior performance of the proposed model indicates the great potential of using deep learning for the detection of abnormal synchrophasor measurements.

42 ENGINEERING↗
DOE OSTI2023

Compute in‐Memory with Non‐Volatile Elements for Neural Networks: A Review from a Co‐Design Perspective

Abstract Deep learning has become ubiquitous, touching daily lives across the globe. Today, traditional computer architectures are stressed to their limits in efficiently executing the growing complexity of data and models. Compute‐in‐memory (CIM) can potentially play an important role in developing efficient hardware solutions that reduce data movement from compute‐unit to memory, known as the von Neumann bottleneck. At its heart is a cross‐bar architecture with nodal non‐volatile‐memory elements that performs an analog multiply‐and‐accumulate operation, enabling the matrix‐vector‐multiplications repeatedly used in all neural network workloads. The memory materials can significantly influence final system‐level characteristics and chip performance, including speed, power, and classification accuracy. With an over‐arching co‐design viewpoint, this review assesses the use of cross‐bar based CIM for neural networks, connecting the material properties and the associated design constraints and demands to application, architecture, and performance. Both digital and analog memory are considered, assessing the status for training and inference, and providing metrics for the collective set of properties non‐volatile memory materials will need to demonstrate for a successful CIM technology.

36 MATERIALS SCIENCE↗
DOE OSTI2026

U-net architected deep material network training with microstructure local field information

The Deep Material Network (DMN) has recently emerged as a powerful reduced-order modeling framework for simulating the mechanical response of heterogeneous materials such as composites. Unlike most data-driven approaches that directly learn a material’s response under prescribed loading, the DMN acts as a homogenization operator, learning the kinematic constraints and mechanical interactions of the underlying microstructure. However, traditional DMN training relies exclusively on homogenized effective properties derived from Direct Numerical Simulations (DNS), discarding the rich local field data that govern microstructural interactions. In this work, we extend the DMN framework to incorporate such local field information into the offline training process. Utilizing a U-Net architecture, we augment the DMN training objective to include the first and second statistical moments of the local stress fields obtained from linear DNS. This ensures that the learned network topology not only fits the effective stiffness but also accurately reflects the internal local stress and strain partitioning of the microstructure. The results confirm that supervising the localization process during training yields a superior surrogate model, reducing local prediction errors by an order of magnitude and significantly improving generalization to unseen nonlinear constitutive behaviors compared to traditional DMNs.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Exploring the Use of Novel Spatial Accelerators in Scientific Applications

Driven by the need to find alternative accelerators which can viably replace GPUs in next-generation Supercomputing systems, this paper proposes a methodology to enable agile application/hardware co-design. The application-first methodology provides the ability to come up with design of accelerators while working with real-world workloads, available accelerators, and system software. The iterative design process targets a set of kernels in a workload for performance estimates that can prune the design space for later phases of detailed architectural evaluations. To this effect, in this paper, a novel data-parallel device model is introduced that simulates the latency of performance-sensitive operations in an accelerator including data transfers and kernel computation using multi-core CPUs. The use of off-the-shelf simulators, such as pre-RTL simulator Aladdin or multiple tools available for exploring the design of deep neural network accelerators (e.g., Timeloop) is demonstrated for evaluation of various accelerator designs using applications with realistic inputs. Examples of multiple device configurations that are instantiable in a system are explored to evaluate the performance benefit of deploying novel accelerators. The proposed device is integrated with a programming model and system software to potentially explore the impacts of high-level programming languages/compilers and low-level effects such as task scheduling on multiple accelerators. We analyze our methodology for a set of applications that represent high-performance computing (HPC) and graph analytics. The applications include a computational chemistry kernel realized using tensor contractions, triangle counting, GraphSAGE and Breadth-first Search. These applications include kernels such as dense matrix-dense matrix multiplication, sparse matrix-spare matrix multiplication, and sparse matrix-dense vector multiplication. Our results indicate potential performance benefits and insights for system design by including accelerators that realize these kernels along-side general purpose accelerators.

AI, codesign, Accelerated Computing, Modeling and ↗
DOE OSTI2023

NRAP-Open-IAM Multisegmented Wellbore Reduced-Order Model: Improvement and Quality Assurance

The multisegmented wellbore model (MSW) semi-analytically estimates the amount of CO 2 and brine leakage from a leaking legacy well by segmenting it into intervals to simulate site-specific stratigraphic and hydrogeologic properties. The model is a component of the National Risk Assessment Partnership Open-Source Integrated Assessment Model (NRAP-Open-IAM), which was developed to perform risk assessment for geologic CO 2 storage. The new wellbore leakage model, which uses deep learning networks for a caprock segment, was developed to enhance the analytical MSW. The model was trained and validated using a synthetic data set of Subsurface Transport Over Multiple Phases (STOMP) multiphase flow simulations from various geological, well attribute, and operational conditions to ensure its quality. The results demonstrate that the model is more accurate than the existing model in predicting the transport of two-phase fluids (brine and injected CO 2 ) through the well. This report provides a detailed explanation of the model development and quality assurance.

58 GEOSCIENCES↗
NASA NTRS1987

An overview of the Mark 4A monitor and control system

The Deep Space Network (DSN) Monitor and Control System was completely changed during the conversion from Mark 3 to the Mark 4A configuration. The configuration employs shared data processing equipment between several co-located antennas, and incorporates much greater centralization of operations functions. The configuration is described and its performance is compared to that of the Mark 3 era.

Leflang, J. G.↗
NASA NTRS1988

The JPL trapped mercury ion frequency standard

In order to provide frequency standards for the Deep Space Network (DSN) which are more stable than present-day hydrogen masers, a research task was established under the Advanced Systems Program of the TDA to develop a Hg-199(+) trapped ion frequency standard. The first closed-loop operation of this kind is described. Mercury-199 ions are confined in an RF trap and are state-selected through the use of optical pumping with 194 nm UV light from a Hg-202 discharge lamp. Absorption of microwave radiation at the hyperfine frequency (40.5 GHz) is signaled by atomic fluorescence of the UV light. The frequency of a 40.5 GHz oscillator is locked to a 1.6 Hz wide atomic absorption line of the trapped ions. The measured Allan variance of this locked oscillator is currently gamma sub y (pi) = 4.4 x 10 to the minus 12th/square root of pi for 20 is less than pi is less than 320 seconds, which is better stability than the best commercial cesium standards by almost a factor of 2. This initial result was achieved without magnetic shielding and without regulation of ion number.

Prestage, J. D.↗
NASA NTRS2017

DSN Wide Area Network Architecture, Capacity and Performance

This paper discusses the architecture of the wide area network that connects key communications facilities within the National Aeronautic and Space Administration (NASA) Deep Space Network (DSN). Several considerations are given to the design of this wide area network to ensure a timely, reliable, and secure data delivery between the mission users and their spacecraft. The network star configuration simplifies data delivery to users and minimizes operational cost. The dual-path connections maximize the system reliability, with geographical diversity in data routing to avoid single point of failure. Data encryption enhances the protection of mission users’ data. The system bandwidth is determined by balancing the needs to minimize the operating bandwidth cost and to have sufficient bandwidth to be able to deliver data to all users within the required. The DSN uses a class base weighted fair queuing (CBWFQ) method in its data delivery. This scheme guarantees a minimum bandwidth to each class of users and allows users to also access any unused bandwidth by other groups. The paper will also show performance of system reliability and bandwidth margin.

Liao, Jason↗
NASA NTRS2010

Moving Toward Space Internetworking via DTN: Its Operational Challenges, Benefits, and Management

The international space community has begun to recognize that the established model for management of communications with spacecraft - commanded data transmission over individual pair-wise contacts - is operationally unwieldy and will not scale in support of increasingly complex and sophisticated missions such as NASA's Constellation project. Accordingly, the international Inter-Agency Operations Advisory Group (IOAG) ichartered a Space Internetworking Strategy Group (SISG), which released its initial recommendations in a November 2008 report. The report includes a recommendation that the space flight community adopt Delay-Tolerant Networking (DTN) to address the problem of interoperability and communication scaling, especially in mission environments where there are multiple spacecraft operating in concert. This paper explores some of the issues that must be addressed in implementing, deploying, and operating DTN as part of a multi-mission, multi-agency space internetwork as well as benefits and future operational scenarios afforded by DTN-based space internetworking.

Delay Tolerant Networking↗
DOE OSTI2025

Exact block encoding of imaginary time evolution with universal quantum neural networks

We develop a constructive approach to generate quantum neural networks capable of representing the exact thermal states of all many-body qubit Hamiltonians. The Trotter expansion of the imaginary time propagator is implemented through an exact block encoding by means of a unitary, restricted Boltzmann machine architecture. Marginalization over the hidden-layer neurons (auxiliary qubits) creates the nonunitary action on the visible layer. Then, we introduce a unitary deep Boltzmann machine architecture in which the hidden-layer qubits are allowed to couple laterally to other hidden qubits. We prove that this wave-function is closed under the action of the imaginary time propagator and, more generally, can represent the action of a universal set of quantum gate operations. We provide analytic expressions for the coefficients for both architectures, thus enabling exact network representations of thermal states without stochastic optimization of the network parameters. In the limit of large imaginary time, the yields the ground state of the system. The number of qubits grows linearly with the number of interactions and total imaginary time for a fixed interaction order. Both networks can be readily implemented on quantum hardware via midcircuit measurements of auxiliary qubits. If only one auxiliary qubit is measured and reset, the circuit depth scales linearly with imaginary time and number of interactions, while the width is constant. Alternatively, one can employ a number of auxiliary qubits linearly proportional to the number of interactions, and circuit depth grows linearly with imaginary time only. Every midcircuit measurement has a postselection success probability, and the overall success probability is equal to the product of the probabilities of the midcircuit measurements.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Neural-based time series forecasting of loss of coolant accidents in nuclear power plants

During the last few years, deep learning in neural networks has demonstrated impressive successes in the areas of computer vision, speech and image recognition, text generation, and many others. However, sensitive engineering areas such as nuclear engineering benefited less from these efficient techniques. In this work, deep learning expert systems are utilized to model and predict time series progression of a design-basis nuclear accident, featuring a loss of coolant accident. Two major findings are accomplished in this work. First, the ability to train expert systems with high accuracy, which could help nuclear power plant operators to figure out plant responses during the accident. Second, building fast, efficient, and accurate deep models to simulate nuclear phenomena, which could be valuable to nuclear computational science. In this work, large amount of time series data is obtained from simulation tools by simulating different conditions of the base-case/nominal accident scenario. Four critical outputs/responses are monitored during the accident (e.g. temperature, pressure, break flow rate, water level). Two approaches are adopted in this work. The first approach is to use feedforward deep neural networks (DNN) to fit all time steps and outputs in a single model. The second approach is to use long short-term memory (LSTM) to fit all time steps together for each reactor response separately. Both DNN and LSTM demonstrate very good performance in predicting the test and base-case scenarios, with accuracy as low as 92% and as high as 99%, where these test scenarios are unknown to the expert systems and are not included in the model training. In addition, both approaches demonstrate a significant reduction in computational costs, as the deep expert system is able to accurately predict the accident 100,000 times faster than the original simulation tool. Given sufficient data, the methodology adopted in this study demonstrates that DNN/LSTM expert systems can be used as a decision support system to model advanced time series phenomena within nuclear power plants with high accuracy and negligible computational costs.

42 ENGINEERING↗
NASA NTRS1980

Block 1, phase 1 very long baseline interferometry implementation

The Block 1, phase 1 VBLI System, implemented in the Deep Space Network and currently undergoing system testing, is discussed. The system can be characterized as the modification of existing equipment and the addition of new software in the 64 m subnet and the addition of new hardware and software in the Network Operations and Control Center. It is to be operational to support Voyager project navigation requirements and is to provide, on a weekly basis, the information related to station clock synchronization, UT1, and polar motion.

Wilcher, J. H.↗