Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network design”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

StressNet - Deep learning to predict stress with fracture propagation in brittle materials

Abstract Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of materials. Existing high-fidelity methods, such as the Finite-Discrete Element Model (FDEM), are limited by their high computational cost. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, StressNet, is proposed to predict the entire sequence of maximum internal stress based on fracture propagation and the initial stress data. More specifically, the Temporal Independent Convolutional Neural Network (TI-CNN) is designed to capture the spatial features of fractures like fracture path and spall regions, and the Bidirectional Long Short-term Memory (Bi-LSTM) Network is adapted to capture the temporal features. By fusing these features, the evolution in time of the maximum internal stress can be accurately predicted. Moreover, an adaptive loss function is designed by dynamically integrating the Mean Squared Error (MSE) and the Mean Absolute Percentage Error (MAPE), to reflect the fluctuations in maximum internal stress. After training, the proposed model is able to compute accurate multi-step predictions of maximum internal stress in approximately 20 seconds, as compared to the FDEM run time of 4 h, with an average MAPE of 2% relative to test data.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Investigating Scientific Workload Acceleration using BlueField SmartNICs [Slides]

Modern computing platforms whose workloads generate large amounts of network traffic, such as cloud and HPC systems, often suffer from performance bottlenecks associated with the network interface. In order to alleviate the effects of this obstacle, a new generation of accelerators known as ‘SmartNICs’, which are designed to offload low level networking tasks from the processor into the NIC, have emerged.

42 ENGINEERING↗
DOE OSTI2022

Data-Driven Optimal Control of Traffic Signals for Urban Road Networks

This paper studies the issue of data-driven optimal control design for traffic signals of oversaturated urban road networks. The signal control system based on the store and forward model is generally uncontrollable for which the controllable decomposition is needed. Instead of identifying the unknown parameters like saturation rates and turning ratios, a finite number of measured trajectories can be used to parametrize the system and help directly construct a transformation matrix for Kalman controllable decomposition through the fundamental lemma of J. C. Willems. On top of that, an infinite-horizon linear quadratic regulator (LQR) problem is formulated considering the constraints of green times for traffic signals. The problem can be solved through a two-phase data-driven learning process, where one solves an infinite-horizon unconstrained LQR problem and the other solves a finite-horizon constrained LQR problem. The simulation result shows the theoretical analysis is effective and the proposed data-driven controller can yield desired performance for reducing traffic congestion.

Liu, Tong↗
DOE OSTI2021

Tailoring Lifetimes and Properties of Carbodiimide-Fueled Covalently Cross-linked Polymer Networks

The mechanical properties of nonequilibrium polymer hydrogels obtained from the transient cross-linking of polymer chains by a chemical fuel were investigated. Aqueous polymers featuring pendant carboxylic acids were treated with a carbodiimide to give anhydride-cross-linked gels. The anhydrides spontaneously hydrolyze back to the polymer solution, and the cycle can be repeated multiple times. Oscillatory rheology was employed to study the effects of temperature, fuel concentration, chain length, and polymer composition on the storage and loss moduli of the polymeric materials as well as the time taken for the polymers to undergo decross-linking. Regardless of the temperature used, at constant carbodiimide concentration, degelation times are more sensitive to experimental temperature than are the peak storage moduli. Decross-linking times decrease with increasing temperature. As carbodiimide concentration decreases, there is a decrease in moduli and decross-linking times. Within the scope of materials studied, the polymer structure was found to have a relatively small impact on the transient properties of gel networks compared to the fuel concentration and temperature. Furthermore, these findings facilitate the design of tunable on-demand networks and gels.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Joint Estimation of Topology and Injection Statistics in Distribution Grids with Missing Nodes

Optimal operation of distribution grid resources relies on accurate estimation of its state and topology. Practical estimation of such quantities is complicated by the limited presence of real-time meters. This article discusses a theoretical framework to jointly estimate the operational topology and statistics of injections in radial distribution grids under limited availability of nodal voltage measurements. In particular, we show that our proposed algorithms are able to provably learn the exact grid topology and injection statistics at all unobserved nodes as long as they are not adjacent. The algorithm design is based on novel ordered trends in voltage magnitude fluctuations at node groups, that are independently of interest for radial physical flow networks. The complexity of the designed algorithms is theoretically analyzed and their performance is validated using both linearized and nonlinear ac power flow samples in test distribution grids.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Fast GPU-Based Generation of Large Graph Networks From Degree Distributions

Synthetically generated, large graph networks serve as useful proxies to real-world networks for many graph-based applications. The ability to generate such networks helps overcome several limitations of real-world networks regarding their number, availability, and access. Here, we present the design, implementation, and performance study of a novel network generator that can produce very large graph networks conforming to any desired degree distribution. The generator is designed and implemented for efficient execution on modern graphics processing units (GPUs). Given an array of desired vertex degrees and number of vertices for each desired degree, our algorithm generates the edges of a random graph that satisfies the input degree distribution. Multiple runtime variants are implemented and tested: 1) a uniform static work assignment using a fixed thread launch scheme, 2) a load-balanced static work assignment also with fixed thread launch but with cost-aware task-to-thread mapping, and 3) a dynamic scheme with multiple GPU kernels asynchronously launched from the CPU. The generation is tested on a range of popular networks such as Twitter and Facebook, representing different scales and skews in degree distributions. Results show that, using our algorithm on a single modern GPU (NVIDIA Volta V100), it is possible to generate large-scale graph networks at rates exceeding 50 billion edges per second for a 69 billion-edge network. GPU profiling confirms high utilization and low branching divergence of our implementation from small to large network sizes. For networks with scattered distributions, we provide a coarsening method that further increases the GPU-based generation speed by up to a factor of 4 on tested input networks with over 45 billion edges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Bayesian Entropy Neural Networks for physics-aware prediction

This article addresses the need for deep learning models to integrate well-defined constraints into their outputs, driven by their application in surrogate models, learning with limited data and partial information, and scenarios requiring flexible model behavior to incorporate non-data sample information. We introduce Bayesian Entropy Neural Networks (BENN), a framework grounded in Maximum Entropy (MaxEnt) principles, designed to impose constraints on Bayesian Neural Network (BNN) predictions. BENN is capable of constraining not only the predicted values but also their derivatives and variances, ensuring a more robust and reliable model output. To achieve simultaneous uncertainty quantification and constraint satisfaction, we employ the method of multipliers approach. This allows for the concurrent estimation of neural network parameters and the Lagrangian multipliers associated with the constraints. Our experiments, spanning diverse applications such as beam deflection modeling and microstructure generation, demonstrate the effectiveness of BENN. The results highlight significant improvements over traditional BNNs and showcase competitive performance relative to contemporary constrained deep learning methods.

14 SOLAR ENERGY↗
DOE OSTI2020

Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs

We develop and study FPGA implementations of algorithms for charged particle tracking based on graph neural networks. The two complementary FPGA designs are based on OpenCL, a framework for writing programs that execute across heterogeneous platforms, and hls4ml, a high-level-synthesis-based compiler for neural network to firmware conversion. We evaluate and compare the resource usage, latency, and tracking performance of our implementations based on a benchmark dataset. We find a considerable speedup over CPU-based execution is possible, potentially enabling such algorithms to be used effectively in future computing workflows and the FPGA-based Level-1 trigger at the CERN Large Hadron Collider.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Interpretable design of Ir-free trimetallic electrocatalysts for ammonia oxidation with graph neural networks

The electrochemical ammonia oxidation to dinitrogen as a means for energy and environmental applications is a key technology toward the realization of a sustainable nitrogen cycle. The state-of-the-art metal catalysts including Pt and its bimetallics with Ir show promising activity, albeit suffering from high overpotentials for appreciable current densities and the soaring price of precious metals. Herein, the immense design space of ternary Pt alloy nanostructures is explored by graph neural networks trained on ab initio data for concurrently predicting site reactivity, surface stability, and catalyst synthesizability descriptors. Among a few Ir-free candidates that emerge from the active learning workflow, Pt 3 Ru-M (M: Fe, Co, or Ni) alloys were successfully synthesized and experimentally verified to be more active toward ammonia oxidation than Pt, Pt 3 Ir, and Pt 3 Ru. More importantly, feature attribution analyses using the machine-learned representation of site motifs provide fundamental insights into chemical bonding at metal surfaces and shed light on design strategies for high-performance catalytic systems beyond the d-band center metric of binding sites.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Characterizing Quantum Classifier Utility in Natural Language Processing Workflows

Quantum Natural Language Processing (QNLP) develops natural language processing (NLP) models for deployment on quantum computers. We explore feature and data prototype selection techniques to address challenges posed by encoding high dimensional features. Our study builds quantum circuit classifiers that includes classical feature pre-processing, quantum embedding and quantum model training. The quantum models are built on 4 or 6 qubits and the quantum neural network (QNN) uses the established bricklayer design. We compare the dependence of model performance (in terms of accuracy and F1 scores) on feature length, embedding gates and parameterized unitary design. We compare the performance of quantum machine learning models to classical convolution neural network model (CNN) on binary and multi-class classification tasks using two datasets of synthetic features and labels. The first is the ECP-CANDLE P3B3 dataset a corpus of synthetically generated cancer pathology reports. The second dataset is extracted from well-known benchmark dataset (MADELON) - features are generated with a combination of informative, repeated and uninformative features. Both datasets are used for binary classification and multi-class classification with 3 classes. We observe robust, accurate performance from all models on the binary classification tasks, but multiclass classification is a challenge for the quantum models-there is a notable decrease in accuracy when using 3 classes. Overall the performance is comparable in terms of recall and accuracy between QNNs and CNNs, even with large datasets. These results provide a point of comparison between quantum and classical models on real-world datasets.

Hamilton, Kathleen↗
DOE OSTI2023

Development of fracture diagnostic methods for fluid distribution based on quantitative interpretation of distributed acoustic sensing and distributed temperature sensing

Multistage hydraulic fracturing design on horizontal wells has significantly evolved with larger fluid volume, more fracturing stages, and tighter perforation cluster spacing to efficiently stimulate unconventional reservoirs. From the published field observations, the recent fracturing design results in complex fracture networks or swarm of fractures. Fracture treatment evaluation is extremely challenging in such a case because of the large amount of variables in well completion and stimulation design. Combined measurements from different technologies can help in fracture diagnosis. Fluid distribution, either during fracture injection or during production, directly relates to the stimulation efficiency at the cluster level and at the stage level. Because it is unlikely in the real world to distribute the injected fluid uniformly among all the clusters, we need diagnostic techniques to generate the flow profile along a lateral. Fiber-optic measurements, such as distributed acoustic sensing (DAS) and distributed temperature sensing (DTS), are currently used to diagnose downhole flow conditions. This technology allows us to qualitatively confirm the fluid flow profile and other issues occurring downhole during fracturing such as leakage through plugs. For optimizing a fracturing design, we also need to understand how the design parameters are correlated with the stimulation efficiency. In this study, we combine two sets of models of DAS and DTS data interpretation for injected fluid volume distribution. The DAS is interpreted based on an empirical correlation between fluid flow rates and frequency band energy from the acoustic signals. The DTS is interpreted by performing temperature history match-based thermal energy conservation. Because of the completely different physics behind the interpretations, the confirmation of two interpretations provides confidence in fluid distribution.

Geochemistry & Geophysics↗
DOE OSTI2024

Angular Dependence of Drell-Yan in the SeaQuest Experiment using Deep Neural Network-Based Reconstruction

The SeaQuest and SpinQuest experiments at Fermilab were designed to probe the internal dynamics of protons and neutrons via the angular dependence of muons created by colliding 120 GeV protons into stationary targets. To do this, it is necessary to translate the detector data into coherent information about the particles detected in the experiment. This dissertation describes the development and implementation of QTracker, a neural network-based algorithm designed to reconstruct muons. The application of QTracker to experimental data yields improved reconstruction of muon tracks, allowing for a more precise investigation of the transverse momentum distributions and angular modulations in the Drell-Yan process. This work highlights the potential of neural network-based methods to advance particle tracking and enhance our understanding of nucleon structure.

Conover, Arthur↗
DOE OSTI2025

Direct NeTS sampling of nuclear graphite $S(α, β, T)$ in Serpent

For advanced reactor applications, Neural Thermal Scattering (NeTS) modules were developed to predict the thermal scattering law (TSL or $S(α, β, T)$) of a nuclear graphite neutron moderator. NeTS are multi-layer, feedforward artificial neural networks, which act as universal function approximators designed for TSL datasets. In this case, a 4-layer neural network with 164 neurons per layer is trained using FLASSH evaluated data in PyTorch and serialized as a torchscript dictionary to predict $S(α, β, T)$ on-the-fly. Relative, absolute and maximum percent deviations of NeTS from File 7 data generated using the FLASSH code are on the order of 0.01%, 0.1% and 1%, respectively, with low inference latencies of 0.000172 s per $S(α, β, T)$ at a given temperature. Capturing the full dimensionality of possible inelastic neutron-lattice interactions, NeTS functionality is embedded in the Serpent Monte Carlo code, where $S(α, β, T)_{NeTS}$ sampling is conducted on-the-fly and compared to ACE look-up-tables for predicting TREAT criticality. k-eff differences between sampling algorithms of 6 pcm are observed and are within the order of Monte Carlo uncertainty. Compared to discrete and continuous-energy ACE files (30 MB and 131 MB per temperature), the NeTS format is on the order of 200–300 kB for a continuous-temperature, interpolation-free representation of $S(α, β, T)$ and cross sections. NeTS-in-Serpent runtimes comparable with ACE look-up tables are achieved by scaling NeTS for high performance computing architectures with hybrid OpenMP + MPI parallelization. This work validates a novel, self-contained reactor physics framework for predictive cross sections, and demonstrates a general methodology for embedding modern machine learning libraries within existing neutronic analysis frameworks.

Nuclear Criticality Safety Program (NCSP)↗
DOE OSTI2024

Generating synthetic signaling networks for in silico modeling studies

Predictive models of signaling pathways have proven to be difficult to develop. Reasons include the uncertainty in the number of species, the complexity in species’ interactions, and the sparseness and uncertainty in experimental data. Traditional approaches to developing mechanistic models rely on collecting experimental data and fitting a single model to that data. This approach works for simple systems but has proven unreliable for complex systems such as biological signaling networks. For example, uncertainty and sparseness of the data often result in overfitted models that have little predictive value beyond recapitulating the experimental data itself. Thus, there is a need to develop new approaches to create predictive mechanistic models of complex systems. However, to determine the effectiveness of any new algorithm, a baseline model is needed to test its performance. To meet this need, we developed a method for generating artificial synthetic networks that are reasonably realistic and thus can be treated as ground truth models. These synthetic models can then be used to generate synthetic data for developing and testing algorithms designed to recover the underlying network topology and associated parameters. Here, we describe a simple approach for generating synthetic signaling networks that can be used for this purpose.

42 ENGINEERING↗
DOE OSTI2022

Tailoring thermal insulation architectures from additive manufacturing

Abstract Tailoring thermal transport by structural parameters could result in mechanically fragile and brittle networks. An indispensable goal is to design hierarchical architecture materials that combine thermal and mechanical properties in a continuous and cohesive network. A promising strategy to create such a hierarchical network targets additive manufacturing of hybrid porous voxels at nanoscale. Here we describe the convergence of agile additive manufacturing of porous hybrid voxels to tailor hierarchically and mechanically tunable objects. In one strategy, the uniformly distributed porous silica voxels, which form the basis for the control of thermal transport, are non-covalently interfaced with polymeric networks, yielding hierarchic super-elastic architectures with thermal insulation properties. Another additive strategy for achieving mechanical strength involves the versatile orthogonal surface hybridization of porous silica voxels retains its low thermal conductivity of 19.1 mW m −1 K −1 , flexible compressive recovery strain (85%), and tailored mechanical strength from 71.6 kPa to 1.5 MPa. The printed lightweight high-fidelity objects promise thermal aging mitigation for lithium-ion batteries, providing a thermal management pathway using 3D printed silica objects.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Automatic Extraction of Network Configurations for Realistic Simulation and Validation

Popular HPC network interconnection simulators such as SST Macro provide a variety of configurable parameters to explore the design space of hardware components such as network links and switches. While such knobs provide flexibility to explore design trade-offs for novel hardware, manually configuring simulations for existing hardware to focus on topology exploration can be cumbersome and error-prone, leading to widely inaccurate simulations. This challenge is compounded when specifications of various (proprietary) technologies are not readily available or are intentionally omitted. In this work, we provide a methodology to automatically tune the simulation configuration of the multiple network models running within SST Macro using Bayesian optimization. We perform this optimization in the context of multiple messaging regimes (i.e., small to large and latency to bandwidth-bound messages) and provide a detailed analysis of the simulation error for four systems. With our automated framework, we achieve a 5x improvement in accuracy over best-effort configurations based on available hardware specifications.

Suetterlein, Joshua D.↗
DOE OSTI2024

HPC Network Simulation Tuning via Automatic Extraction of Hardware Parameters

Popular HPC network interconnection simulators such as SST/macro provide a variety of configurable parameters to explore the design space of hardware components such as network interface cards (NIC), switches, and links among them. While such knobs provide flexibility to explore design trade-offs for novel hardware, manually configuring simulations for matching configurations of the existing hardware to focus on topology exploration can be cumbersome and error-prone, leading to widely inaccurate simulations. This challenge is compounded when specifications of various (proprietary) technologies are not readily available or intentionally omitted. In this work, we propose a framework to autotune the multiple network models’ simulation configurations within SST/macro using Tree-structured Parzen Estimator-based Bayesian optimization to observe the effect on simulation accuracy across different message regimes. These regimes consist of small to large message sizes and latency to bandwidth-bound messages. We provide a detailed analysis of the simulation error for four representative HPC systems. Our Bayesian optimization based autotuning framework for network models achieves a maximum of 5x improvement in accuracy over best-effort manual configurations based on available hardware specifications.

Simulation, autotuning↗