Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network acceleration”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
NASA NTRS1993

Radial basis function network learns ceramic processing and predicts related strength and density

Radial basis function (RBF) neural networks were trained using the data from 273 Si3N4 modulus of rupture (MOR) bars which were tested at room temperature and 135 MOR bars which were tested at 1370 C. Milling time, sintering time, and sintering gas pressure were the processing parameters used as the input features. Flexural strength and density were the outputs by which the RBF networks were assessed. The 'nodes-at-data-points' method was used to set the hidden layer centers and output layer training used the gradient descent method. The RBF network predicted strength with an average error of less than 12 percent and density with an average error of less than 2 percent. Further, the RBF network demonstrated a potential for optimizing and accelerating the development and processing of ceramic materials.

Cios, Krzysztof J.↗
DOE OSTI2023

Distribution Grid Management in the Presence of Distributed Energy Resources

The global concerns over climate change, government policies, and incentives in support of distributed energy resources (DERs) are accelerating the growth of DERs in distribution networks. The growth in DER penetration levels can create various issues such as over/under voltages, reverse power flows, overloading, and protection miscoordination. State-of-the-art grid automation solutions such as advanced distribution management systems (ADMS) and distributed energy resource management systems (DERMS) can leverage the DERs to improve distribution grid operations. The ADMS offers advanced grid management functions such as Volt-VAR optimization (VVO), fault management, and outage management to the distribution operator to improve situational awareness and optimize network operations. The DERMS solutions aggregate the small-scale BTM DERs to provide grid services including demand response, voltage regulation, and situational awareness. In this presentation, distribution grid management approaches in the presence of DERs using ADMS and DERMS will be discussed.

ADMS↗
DOE OSTI2024

Non-Electricity Based Renewable Fuels: Theory and Computation for Solar Thermochemical Hydrogen

Dominated by photovoltaics and wind, current renewable energy sources generate mostly electricity, but 80% of the global final energy consumption occurs in form of fuels. Therefore, direct solar fuel generation would be a major breakthrough for the energy transition. Solar thermochemical hydrogen (STCH) is one of the very few potential routes towards scalable renewable fuels, but currently suffers from lack of an oxide working material that could optimally perform energy conversion within the thermodynamic boundary conditions. Theory and computation can contribute in two distinct ways, through materials search and discovery, but also by providing detailed mechanistic models for specific systems so to advance our understanding of possible design strategies. To enable high-throughput materials screening, we developed a defect graph neural network (dGNN) machine learning approach,[1] which accelerates the prediction of defect formation energies by replacing the tedious density functional theory (DFT) supercell calculations for all possible defect sites. This approach enables high-throughput database screening of oxides, which was integrated with thermodynamic modeling to extract the reduction entropies as additional selection criterion for STCH. Once potential candidate materials are identified, detailed models can guide materials design by predicting performance characteristics. One challenge is to quantitatively predict thermochemical equilibria at high concentrations when the redox active defects start to interact with each other, thereby impeding the formation of additional defects. Introducing a model for the free energy of defect interaction, parametrized on the basis of DFT data, we simulated the complete STCH redox cycle for (Sr,Ce)MnO3 alloys, achieving near-quantitative agreement with experimental data.[2] The analysis of these simulations reveals how defect interactions diminish the reduction entropy and H2 yield, suggesting to include these interactions in design considerations. Finally, we revisit the popular van't Hoff method for analyzing reduction enthalpies and entropies. This method is not ideal, as it involves a temperature-dependent convolution of gas-phase and solid-state entropies, causing uncertainties in the same order of magnitude as the physical quantities of interest. To avoid this problem, we suggest a simple alternative approach which can be applied to experimental and simulated data alike.

first-principles calculations↗
DOE OSTI2024

Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks and Operators in Scientific Computing: Fluid and Solid Mechanics

Abstract Advancements in computing power have recently made it possible to utilize machine learning and deep learning to push scientific computing forward in a range of disciplines, such as fluid mechanics, solid mechanics, materials science, etc. The incorporation of neural networks is particularly crucial in this hybridization process. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data are sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multiphysics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multiphysics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities are presented in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers.

Computer Science↗
DOE OSTI2022

Tensor Network Quantum Virtual Machine for Simulating Quantum Circuits at Exascale

The numerical simulation of quantum circuits is an indispensable tool for development, verification, and validation of hybrid quantum-classical algorithms intended for near-term quantum co-processors. The emergence of exascale high-performance computing (HPC) platforms presents new opportunities for pushing the boundaries of quantum circuit simulation. Here, we present a modernized version of the Tensor Network Quantum Virtual Machine (TNQVM) that serves as the quantum circuit simulation backend in the eXtreme-scale ACCelerator (XACC) framework. The new version is based on the scalable tensor network processing library ExaTN (Exascale Tensor Networks). It provides multiple configurable quantum circuit simulators that perform either an exact quantum circuit simulation via the full tensor network contraction or an approximate simulation via a suitably chosen tensor factorization scheme. Upon necessity, stochastic noise modeling from real quantum processors is incorporated into the simulations by modeling quantum channels with Kraus tensors. By combining the portable XACC quantum programming frontend and the scalable ExaTN numerical processing backend, we introduce an end-to-end virtual quantum development environment that can scale from laptops to future exascale platforms. We report initial benchmarks of our framework, which include a demonstration of the distributed execution, incorporation of quantum decoherence models, and simulation of the random quantum circuits used for the certification of quantum supremacy on Google’s Sycamore superconducting architecture.

Nguyen, Thien↗
NASA NTRSDate not supplied

Large-Scale Space Network Simulator for Performance-Optimized DTNs

High-rate Delay Tolerant Networking (HDTN) is a performance-optimized Delay Tolerant Networking (DTN) implementation that can provide multigigabit per second data rates in disruptive and high-latency space networks. Routing, especially in large-scale space networks, remains challenging due to network topologies that evolve over time. This paper presents a simulation tool that enables HDTN implementation testing at accelerated speeds, which is key for routing in large-scale space networks.

High data-rate Delay Tolerant Networking↗
DOE OSTI2021

GPU-Accelerated Machine Learning Inference as a Service for Computing in Neutrino Experiments

Machine learning algorithms are becoming increasingly prevalent and performant in the reconstruction of events in accelerator-based neutrino experiments. These sophisticated algorithms can be computationally expensive. At the same time, the data volumes of such experiments are rapidly increasing. The demand to process billions of neutrino events with many machine learning algorithm inferences creates a computing challenge. We explore a computing model in which heterogeneous computing with GPU coprocessors is made available as a web service. The coprocessors can be efficiently and elastically deployed to provide the right amount of computing for a given processing task. With our approach, Services for Optimized Network Inference on Coprocessors (SONIC), we integrate GPU acceleration specifically for the ProtoDUNE-SP reconstruction chain without disrupting the native computing workflow. With our integrated framework, we accelerate the most time-consuming task, track and particle shower hit identification, by a factor of 17. This results in a factor of 2.7 reduction in the total processing time when compared with CPU-only production. For this particular task, only 1 GPU is required for every 68 CPU threads, providing a cost-effective solution.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Encoder–decoder neural network for solving the nonlinear Fokker–Planck–Landau collision operator in XGC

An encoder–decoder neural network has been used to examine the possibility for acceleration of a partial integro-differential equation, the Fokker–Planck–Landau collision operator. This is part of the governing equation in the massively parallel particle-in-cell code XGC, which is used to study turbulence in fusion energy devices. The neural network emphasizes physics-inspired learning, where it is taught to respect physical conservation constraints of the collision operator by including them in the training loss, along with the ℓ 2 loss. In particular, network architectures used for the computer vision task of semantic segmentation have been used for training. A penalization method is used to enforce the ‘soft’ constraints of the system and integrate error in the conservation properties into the loss function. During training, quantities representing the particle density, momentum and energy for all species of the system are calculated at each configuration vertex, mirroring the procedure in XGC. This simple training has produced a median relative loss, across configuration space, of the order of 10 –4 , which is low enough if the error is of random nature, but not if it is of drift nature in time steps. The run time for the current Picard iterative solver of the operator is O(n 2 ), where n is the number of plasma species. As the XGC1 code begins to attack problems including a larger number of species, the collision operator will become expensive computationally, making the neural network solver even more important, especially since its training only scales as O(n). Here, a wide enough range of collisionality has been considered in the training data to ensure the full domain of collision physics is captured. An advanced technique to decrease the losses further will be subject of a subsequent report. Eventual work will include expansion of the network to include multiple plasma species.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Surrogate modeling of Monte Carlo radiation transport with convolutional neural networks for shielding optimization

Here, we present a machine learning (ML)-based surrogate model using convolutional neural networks (CNN) designed to emulate the attenuation of neutron fields as they pass through various shielding materials. This model can compute the outgoing neutron flux almost instantaneously and achieves reasonable accuracy compared to traditional Monte Carlo (MC)-based codes, which are computationally intensive. This emulator alleviates the complexity of neutron radiation transport through shielding materials by reducing the dimensionality and enables shielding optimization for a known radiation environment. This optimization process, which would have taken an unrealistic timeline due to several complex radiation transport simulations, can now be achieved in minutes, thus increasing computational capabilities in radiation shielding assessment. We demonstrate the applications of this emulator in computing effective dose rates and optimizing shielding solutions for a heavy-ion accelerator facility, such as the Facility for Rare Isotope Beams, where secondary neutrons produced via beam interactions dominate the radiation environment.

accelerator shielding↗
DOE OSTI2025

Twinac: A Universal Framework for Virtual Accelerator Controls

We propose a universal framework for a system of virtual accelerator controls (Twinac), a standard toolkit for research institutions to design, maintain, and use a real-time, end-to-end "digital twin" of their particle accelerator facility. This virtual counterpart will mirror any physical accelerator to provide (1) predictive maintenance; (2) surveillance of hidden environmental factors, such as seasonal temperature variations, which could impact performance of power supplies, magnets, and other instruments; and (3) a capability to model novel ways to operate the accelerator without risking equipment damage. Twinac is envisioned as accelerator facility agnostic, allowing institutions to share and reuse myriad simulation approaches (analytics-based, A.I.-driven, or combinations of the like) across facilities. The Twinac system lays the groundwork for a collaborative network of institutions to maintain and update this shared virtual accelerator technology.

Miceli, Tia M. [Fermilab] (ORCID:0000000265577789)↗
DOE OSTI2021

A graph-based network for predicting chemical reaction pathways in solid-state materials synthesis

Abstract Accelerated inorganic synthesis remains a significant challenge in the search for novel, functional materials. Many of the principles which enable “synthesis by design” in synthetic organic chemistry do not exist in solid-state chemistry, despite the availability of extensive computed/experimental thermochemistry data. In this work, we present a chemical reaction network model for solid-state synthesis constructed from available thermochemistry data and devise a computationally tractable approach for suggesting likely reaction pathways via the application of pathfinding algorithms and linear combination of lowest-cost paths in the network. We demonstrate initial success of the network in predicting complex reaction pathways comparable to those reported in the literature for YMnO 3 , Y 2 Mn 2 O 7 , Fe 2 SiS 4 , and YBa 2 Cu 3 O 6.5 . The reaction network presents opportunities for enabling reaction pathway prediction, rapid iteration between experimental/theoretical results, and ultimately, control of the synthesis of solid-state materials.

36 MATERIALS SCIENCE↗
NASA NTRS1992

Seeing the forest for the trees: Networked workstations as a parallel processing computer

Unlike traditional 'serial' processing computers in which one central processing unit performs one instruction at a time, parallel processing computers contain several processing units, thereby, performing several instructions at once. Many of today's fastest supercomputers achieve their speed by employing thousands of processing elements working in parallel. Few institutions can afford these state-of-the-art parallel processors, but many already have the makings of a modest parallel processing system. Workstations on existing high-speed networks can be harnessed as nodes in a parallel processing environment, bringing the benefits of parallel processing to many. While such a system can not rival the industry's latest machines, many common tasks can be accelerated greatly by spreading the processing burden and exploiting idle network resources. We study several aspects of this approach, from algorithms to select nodes to speed gains in specific tasks. With ever-increasing volumes of astronomical data, it becomes all the more necessary to utilize our computing resources fully.

Breen, J. O.↗
DOE OSTI2023

Distributed Optimal Power Management for Battery Energy Storage Systems: A Novel Accelerated Tracking ADMM Approach

Optimal power management (OPM) is critical for large-scale battery energy storage systems. Today’s methods often require formidable computational effort due to the design based on centralized numerical optimization. Thus, this paper investigates computationally distributed OPM where the agents based on the cells communicate over a network to cooperatively solve the OPM problem. We propose an accelerated tracking alternating direction method of multipliers (ADMM) algorithm to solve the distributed OPM. The proposed algorithm embeds dynamic average consensus and Nesterov’s acceleration technique in the ADMM algorithm. Not only is the proposed algorithm fully distributed without a need for fusion or aggregating nodes, but it also accelerates convergence. The paper formulates the OPM in a model predictive control framework where it seeks to regulate the charging/discharging power of each battery cell to minimize the total power losses and promote balanced use of the constituent cells while complying with the safety constraints. The paper provides ample simulation results to demonstrate the effectiveness and advantages of the proposed distributed OPM in terms of computation and convergence.

Farakhor, Amir↗
DOE OSTI2025

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗
DOE OSTI2026

Kinetic Monte Carlo Framework for Coupled Degradation and Dehydration of Anion Exchange Membranes

Kinetic Monte Carlo (kMC) simulations, augmented with temporal-acceleration schemes, can efficiently handle stiff reaction-transport networks when fast processes rapidly relax to quasi-equilibrium on a fixed lattice. However, in glassy anion-exchange membranes (AEM), rare and irreversible chemical degradation events continuously reshape the nanoscale morphology, and the associated hydration and transport degrees of freedom remain far from a well-defined local equilibrium. This combination of evolving state space and nonequilibrated fast dynamics lies outside the scope of existing kMC acceleration frameworks. Here, to address this challenge, we introduce an auxiliary-particle kinetic Monte Carlo (AP-kMC) scheme. In AP-kMC, short-lived mobile particles spawned at degradation sites execute hop, water-elimination, and decay moves, enforcing rapid local relaxation of the hydration structure while preserving the stochastic rules of kMC. Parameterized with molecular-dynamics morphologies and experimental solution degradation kinetics, AP-kMC reproduces the evolution of ion-exchange capacity, water uptake, and conductivity, and reveals a feedback loop in which poorly hydrated sites degrade first and each degradation event induces further local dehydration. The resulting thinning and fragmentation of water channels cause loss of hydrophilic percolation and abrupt conductivity collapse well before complete charge loss. AP-kMC thus reframes AEM durability as a coupled degradation–drying–percolation problem and provides a transferable strategy to simulate reactive, out-of-equilibrium polymer electrolytes where local solvation controls reactivity.

organic↗
NASA NTRS1999

Unsupervised classification of Space Acceleration Measurement System (SAMS) data using ART2-A

The Space Acceleration Measurement System (SAMS) has been developed by NASA to monitor the microgravity acceleration environment aboard the space shuttle. The amount of data collected by a SAMS unit during a shuttle mission is in the several gigabytes range. Adaptive Resonance Theory 2-A (ART2-A), an unsupervised neural network, has been used to cluster these data and to develop cause and effect relationships among disturbances and the acceleration environment. Using input patterns formed on the basis of power spectral densities (psd), data collected from two missions, STS-050 and STS-057, have been clustered.

STS-57 Shuttle Project↗
DOE OSTI2025

Rational Regulation of Layer‐by‐Layer Processed Active Layer via Trimer‐Induced Pre‐Swelling Strategy for Efficient and Robust Thick‐Film Organic Solar Cells

Thick-film (>300 nm) organic solar cells (OSCs) have garnered intensifying attention due to their compatibility with commercial roll-to-roll printing technology for the large-scale continuous fabrication process. However, due to the uncontrollable donor/acceptor (D/A) arrangement in thick-film condition, the restricted exciton splitting and severe carrier traps significantly impede the photovoltaic performance and operability. For this work, combined with layer-by-layer deposition technology, a twisted 3D star-shaped trimer (BTT-Out) is synthesized to develop a trimer-induced pre-swelling (TIP) strategy, where the BTT-Out is incorporated into the buried D18 donor layer to enable the fabrication of thick-film OSCs. The integrated approach characterizations reveal that the exceptional configuration and spontaneous self-organization behavior of BTT-Out trimer could pre-swell the D18 network to facilitate the acceptor's infiltration and accelerate the formation of D/A interfaces. This enhancement triggers the elevated polarons formation with amplified hole-transfer kinetics, which is essential for the augmented exciton splitting efficiency. Furthermore, the regulated swelling process can initiate the favorable self-assembly of L8-BO acceptors, which would ameliorate carrier transport channels and mitigate carrier traps. As a result, the TIP-modified thin-film OSC devices achieve the champion performance of 20.3% (thin-film) and 18.8% (thick-film) with upgraded stability, among one of the highest performances reported of thick-film OSCs.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Neural network-based control of an ultrafast laser

With the recent advances in machine learning (ML) and data science (DS), the control, modeling, and analysis of these complex systems continues to improve. In this work, we report on the optimization of the intensity of a femtosecond laser using feedforward neural networks (FFNN) that model the input–output relationships of the data. The input parameters of the system were optimized to achieve the required performance of the femtosecond laser. We propose a neural network-based control system to model the relationship between the spectral amplitude and phase of the input laser pulse at the amplifier input and the shape of the output pulse. Low-jitter laser parameter inputs and the resulting laser pulse duration were modeled, and the resulting correlation between the input and output data was used to optimize the laser pulse. Here, we demonstrate improved processing and laser control performance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗