Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network slicing”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Measuring the electron temperature and identifying plasma detachment using machine learning and spectroscopy

A machine learning approach has been implemented to measure the electron temperature directly from the emission spectra of a tokamak plasma. This approach utilized a neural network (NN) trained on a dataset of 1865 time slices from operation of the DIII-D tokamak using extreme ultraviolet/vacuum ultraviolet emission spectroscopy matched with high-accuracy divertor Thomson scattering measurements of the electron temperature, T e . This NN is shown to be particularly good at predicting T e at low temperatures (T e < 10 eV) where the NN demonstrated a mean average error of less than 1 eV. Trained to detect plasma detachment in the tokamak divertor, a NN classifier was able to correctly identify detached states (T e < 5 eV) with a 99% accuracy (an F 1 score of 0.96) at an acquisition rate 10× faster than the Thomson scattering measurement. The performance of the model is understood by examining a set of 4800 theoretical spectra generated using collisional radiative modeling that was also used to predict the performance of a low-cost spectrometer viewing nitrogen emission in the visible wavelengths. Furthermore, these results provide a proof-of-principle that low-cost spectrometers leveraged with machine learning can be used to boost the performance of more expensive diagnostics on fusion devices and be used independently as a fast and accurate T e measurement and detachment classifier.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Twice upon a time: timelike-separated quantum extremal surfaces

The Python’s Lunch conjecture for the complexity of bulk reconstruction involves two types of nonminimal quantum extremal surfaces (QESs): bulges and throats, which differ by their local properties. The conjecture relies on the connection between bulk spatial geometry and quantum codes: a constricting geometry from bulge to throat encodes the bulk state nonisometrically, and so requires an exponentially complex Grover search to decode. However, thus far, the Python’s Lunch conjecture is only defined for spacetimes where all QESs are spacelike-separated from one another. Here we explicitly construct (time-reflection symmetric) spacetimes featuring both timelike-separated bulges and timelike-separated throats. Interestingly, all our examples also feature a third type of QES, locally resembling a de Sitter bifurcation surface, which we name a bounce. By analyzing the Hessian of generalized entropy at a QES, we argue that this classification into throats, bulges and bounces is exhaustive. We then propose an updated Python’s Lunch conjecture that can accommodate general timelike-separated QESs and bounces. Notably, our proposal suggests that the gravitational analogue of a tensor network is not necessarily the time-reflection symmetric slice, even when one exists.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Porosity evolution under increasing tension in wire-arc additively manufactured aluminum using in-situ micro-computed tomography and convolutional neural network

Internal defects such as porosities are often formed in additively manufactured metal components. The pores nucleate, grow, and coalesce to form cracks under loads, leading to eventual catastrophic failure. Here, in this paper, the full-field porosity evolution, including pore growth and coalescence in a wire-arc additively manufactured (WAAM) aluminum alloy cylinder under tension is observed with in-situ X-ray micro-computed tomography (μCT). The pore size distribution, density, and tensile stress are calculated from the volumetric images analyzed by a convolutional neural network (CNN) algorithm, which provides rapid analysis of 12,950 slice images from μCT volumetric images at the reference state and 13 tensile strains. The results show the quantitative evolution of the growth and coalescence of macropores under tension. A strong correlation is found between the local pore volume fraction and the true tensile stress when the tensile strain is larger than 5%.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Predicting Mechanical Properties from Microstructure Images in Fiber-Reinforced Polymers Using Convolutional Neural Networks

Evaluating the mechanical response of fiber-reinforced composites can be extremely time-consuming and expensive. Machine learning (ML) techniques offer a means for faster predictions via models trained on existing input–output pairs and have exhibited success in composite research. This paper explores a fully convolutional neural network modified from StressNet, which was originally used for linear elastic materials, and extended here for a non-linear finite element (FE) simulation to predict the stress field in 2D slices of segmented tomography images of a fiber-reinforced polymer specimen. The network was trained and evaluated on data generated from the FE simulations of the exact microstructure. The testing results show that the trained network accurately captures the characteristics of the stress distribution, especially on fibers, solely from the segmented microstructure images. The trained model can make predictions within seconds in a single forward pass on an ordinary laptop, given the input microstructure, compared to 92.5 h to run the full FE simulation on a high-performance computing cluster. These results show promise in using ML techniques to conduct fast structural analysis for fiber-reinforced composites and suggest a corollary that the trained model can be used to identify the location of potential damage sites in fiber-reinforced polymers.

Sun, Yixuan (ORCID:0000000311093380)↗
DOE OSTI2022

Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-informed Deep Generative Models

Here, we propose a new method for inferring the governing stochastic ordinary differential equations (SODEs) by observing particle ensembles at discrete and sparse time instants, i.e., multiple “snapshots.” Particle coordinates at a single time instant, possibly noisy or truncated, are recorded in each snapshot but are unpaired across the snapshots. By training a physics-informed generative model that generates “fake” sample paths, we aim to fit the observed particle ensemble distributions with a curve in the probability measure space, which is induced from the inferred particle dynamics. We employ different metrics to quantify the differences between distributions, e.g., the sliced Wasserstein distances and the adversarial losses in generative adversarial networks. We refer to this method as generative “ensemble-regression” (GER), in analogy to the classic “point-regression,” where we infer the dynamics by performing regression in the Euclidean space. We illustrate the GER by learning the drift and diffusion terms of particle ensembles governed by SODEs with Brownian motions and Lévy processes up to 100 dimensions. We also discuss how to treat cases with noisy or truncated observations. Apart from systems consisting of independent particles, we also tackle nonlocal interacting particle systems with unknown interaction potential parameters by constructing a physics-informed loss function. Finally, we investigate scenarios of paired observations and discuss how to reduce the dimensionality in such cases by proving a convergence theorem that provides theoretical support.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Tribal Engagement in Transmission Planning

The purpose of this white paper is to provide Tribes with information that (a) helps assess whether transmission access is important for their energy goals, and (b) provides guidance on how to engage in transmission planning, if and when doing so would help the Tribe achieve its energy goals. DOE's Office of Indian Energy notes that "Indian Country contains vast untapped energy resources" (OIE 2023). Individual tribes express a wide array of energy needs and goals, ranging from simple access to basic electricity service and energy efficiency tools, to the development of utility-scale generating plants. Access to transmission is a key part of this multifaceted tribal energy picture. About 2.3 percent of the nation's transmission miles are on tribal lands (OIE 2023). Even within that slice, however, circumstances vary widely. Much of that transmission is for local network delivery (138kV or less). There are some large-capacity 500kV lines, but in many cases the Tribe has limited access to them even when they run across the reservation. Some of the Tribes with the largest land area have little transmission, and some such as Navajo Nation and Hopi Tribe have many homes with no access to electricity. This white paper begins with a high-level summary of transmission issues that can affect a Tribe's energy goals. The discussion includes findings from major transmission-related studies, including the 2023 National Transmission Needs Study (GDO 2023). It then discusses strategies that could help a Tribe safeguard its interests when those interests intersect transmission infrastructure planning.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2020

Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices

The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series generated by diagnostic instruments observing fusion plasmas. Here we apply this neural network architecture to the popular problem of disruption prediction in fusion tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. ECEi measures a fundamental plasma quantity (electron temperature) with high temporal resolution over the entire plasma discharge, making it sensitive to a number of potential pre-disruptions markers with different temporal and spatial scales. Promising, initial disruption prediction results are obtained training a deep CNN with large receptive field ({$\sim$}30k), achieving an $F_1$-score of {$\sim$}91\% on individual time-slices using only the ECEi data.

convolutional neural networks↗
DOE OSTI2020

CP-DSSS: A Novel Waveform for Multiple Access in IoT

Cyclic prefix direct sequence spread spectrum (CPDSSS) is a novel waveform with versatile characteristics that positions itself well as a secondary network to relieve the congested wireless spectrum. The underlying structure of CPDSSS allows for efficient and effective multi-access capabilites through frequency and time division schemes in a given system. The sum-rate capacity of the system is maximized when the spectrum is divided and allocated to users with the best signal-to-noise (SNR) ratio for the given channel slice. We propose an algorithm for dividing and allocating portions of the spectrum to multiple users with the final goal of maximizing the sumrate capacity of the network. We also propose and develop a precoding/equalization technique that reduces the length of the channel impulse response. This, when used along with a matched filter detector, leads to some improvement in the sum-rate capacity of the network

5G and Beyond Communications↗
DOE OSTI2025

Real Time implementation of Artificial Intelligence compression algorithm for High-Speed Streaming Readout signals

The new generation of high-energy physics experiments plans to acquire data in streaming mode. With this approach, it is possible to access the information of the whole detector (organized in time slices) for optimal and lossless triggering of data acquisitions. With this approach, data rates, especially in large detectors, are often very high, and the network is likely to be the bottleneck for the entire Streaming Read Out system. The aim of this work is to study the implementation of a lossy compression algorithm based on Artificial Intelligence: an Autoencoder. With Machine Learning it is possible to achieve a high compression ratio and fast inference time with only a small degradation of the signals, almost negligible for the specific application. This work explores different configurations of the Autoencoder and the implementation on different hardware. Different Autoencoder configurations are explored to find the best trade-off between compression ratio and reconstruction loss, both for signals and energy spectrum. Different hardware implementations are also explored to find the best platform to achieve real-time performance for the specific application.

Rossi, Fabio (ORCID:0009000385713885)↗
DOE OSTI2026

Patch-Based Convolutional Neural Networks for Multiple Microstructural Features Detection in FIB-SEM Micrographs of Irradiated Nuclear Fuel

Focused ion beam scanning electron microscopy (FIB-SEM) tomography has increasingly been utilized for acquiring three-dimensional (3D) microstructure features at the sub-micron scale in irradiated nuclear materials. This technique involves sequential ion beam slicing followed by electron beam imaging and compositional mapping using energy dispersive spectroscopy (EDS). Despite its growing use, several challenges persist. These include the time-intensive nature of data collection of EDS data, difficulties in distinguishing between various microstructures, and issues with image alignment. These challenges currently limit the broader application of FIB-SEM tomography in the field. To overcome these limitations, we propose using convolutional neural networks (CNNs) to automate microstructure identification in SEM images. Our study introduces a new framework for identifying microstructures in irradiated U-10Zr (wt. %) metallic fuel with limited annotated data. The framework includes the creation of a reliable annotated dataset with paired SEM and ground truth data from EDS maps, the applications of CNNs for microstructure identification, and the validation of model performance. Specifically, we employed the Segment Anything Model (SAM) to align SEM images with corresponding EDS maps and focused ion beam (FIB) tomography SEM data. We evaluate several models, including Patch-based U-Net, Attention U-Net, and Residual U-Net, finding that patch-based U-Net exhibits superior segmentation performance and consistency. This approach reduces reliance on EDS detectors and aids in accelerating nuclear material analysis process, highlighting the potential of advanced deep learning techniques to improve microstructural understanding in nuclear material. This is the first framework to integrate SAM and Patch-based CNN models for semantic segmentation of irradiated nuclear materials, with potential applicability to other tomography datasets.

36 - MATERIALS SCIENCE↗
DOE OSTI2026

Coarse-grained fixed-point tensor networks and holographic reflected entropy in 3D gravity

We use the framework of fixed-point BCFT tensor networks to present a microscopic CFT derivation of the correspondence between reflected entropy (RE) and entanglement wedge cross section (EW) in AdS 3 /CFT 2 , for both bipartite and multipartite settings. These fixed-point tensor networks, obtained by triangulating Euclidean CFT path integrals, allow us to explicitly construct the canonical purification via cutting-and-gluing CFT path integrals. Employing modular flow in the large-c limit, we demonstrate that these intrinsic CFT manipulations reproduce bulk geometric prescriptions, without assuming the AdS/CFT dictionary. The emergence of bulk geometry is traced to coarse-graining over heavy states in the large-c limit. Universal coarse-grained BCFT data for compact 2D CFTs, through the relation to Liouville theory with ZZ boundary conditions, yields hyperbolic geometry on the Cauchy slice. The corresponding averaged replica partition functions reproduce all candidate EWs, arising from different averaging patterns, with the dominant one providing the correct RE and EW. In this way, many heuristic tensor-network intuitions in toy models are made precise and established directly from intrinsic CFT data.

AdS-CFT correspondence↗
DOE OSTI2022

Computational microscopy for fast widefield deep-tissue fluorescence imaging using a commercial dual-cannula probe

A solid-glass cannula serves as a micro-endoscope that can deliver excitation light deep inside tissue while also collecting emitted fluorescence. Then, we utilize deep neural networks to reconstruct images from the collected intensity distributions. By using a commercially available dual-cannula probe, and training a separate deep neural network for each cannula, we effectively double the field of view compared to prior work. We demonstrated ex vivo imaging of fluorescent beads and brain slices and in vivo imaging from whole brains. We clearly resolved 4 µm beads, with FOV from each cannula of 0.2 mm (diameter), and produced images from a depth of ∼1.2 mm in the whole brain, currently limited primarily by the labeling. Since no scanning is required, fast widefield fluorescence imaging limited primarily by the brightness of the fluorophores, collection efficiency of our system, and the frame rate of the camera becomes possible.

42 ENGINEERING↗
DOE OSTI2020

Machine learning for endoleak detection after endovascular aortic repair

Diagnosis of endoleak following endovascular aortic repair (EVAR) relies on manual review of multi-slice CT angiography (CTA) by physicians which is a tedious and time-consuming process that is susceptible to error. We evaluate the use of a deep neural network for the detection of endoleak on CTA for post-EVAR patients using a novel data efficient training approach. 50 CTAs and 20 CTAs with and without endoleak respectively were identified based on gold standard interpretation by a cardiovascular subspecialty radiologist. The Endoleak Augmentor, a custom designed augmentation method, provided robust training for the machine learning (ML) model. Predicted segmentation maps underwent post-processing to determine the presence of endoleak. The model was tested against 3 blinded general radiologists and 1 blinded subspecialist using a held-out subset (10 positive endoleak CTAs, 10 control CTAs). Model accuracy, precision and recall for endoleak diagnosis were 95%, 90% and 100% relative to reference subspecialist interpretation (AUC = 0.99). Accuracy, precision and recall was 70/70/70% for generalist1, 50/50/90% for generalist2, and 90/83/100% for generalist3. The blinded subspecialist had concordant interpretations for all test cases compared with the reference. In conclusion, our ML-based approach has similar performance for endoleak diagnosis relative to subspecialists and superior performance compared with generalists.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

El-CID: a filter for gravitational-wave electromagnetic counterpart identification

ABSTRACT As gravitational-wave (GW) interferometers become more sensitive and probe ever more distant reaches, the number of detected binary neutron star mergers will increase. However, detecting more events farther away with GWs does not guarantee corresponding increase in the number of electromagnetic counterparts of these events. Current and upcoming wide-field surveys that participate in GW follow-up operations will have to contend with distinguishing the kilonova (KN) from the ever increasing number of transients they detect, many of which will be consistent with the GW sky-localization. We have developed a novel tool based on a temporal convolutional neural network architecture, trained on sparse early-time photometry and contextual information for Electromagnetic Counterpart Identification (El-CID). The overarching goal for El-CID is to slice through list of new transient candidates that are consistent with the GW sky localization, and determine which sources are consistent with KNe, allowing limited target-of-opportunity resources to be used judiciously. In addition to verifying the performance of our algorithm on an extensive testing sample, we validate it on AT2017gfo – the only EM counterpart of a binary neutron star merger discovered to date – and AT2019npv – a supernova that was initially suspected as a counterpart of the GW event, GW190814, but was later ruled out after further analysis.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM

The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Additionally, numerous special-purpose architectures have been proposed to accelerate training: both digital and hybrid digital-analog using resistive RAM (ReRAM) crossbars. ReRAM-based accelerators have demonstrated the effectiveness of ReRAM crossbars at performing matrix-vector multiplication operations that are prevalent in training. However, they still suffer from inefficiency due to the use of serial reads and writes for performing the weight gradient and update step. A few works have demonstrated the possibility of performing outer products in crossbars, which can be used to realize the weight gradient and update step without the use of serial reads and writes. However, these works have been limited to low precision operations which are not sufficient for typical training workloads. Moreover, they have been confined to a limited set of training algorithms for fully-connected layers only. To address these limitations, we propose a bit-slicing technique for enhancing the precision of ReRAM-based outer products, which is substantially different from bit-slicing for matrix-vector multiplication only. We incorporate this technique into a crossbar architecture with three variants catered to different training algorithms. To evaluate our design on different types of layers in neural networks (fully-connected, convolutional, etc.) and training algorithms, we develop PANTHER, an ISA-programmable training accelerator with compiler support. Our design can also be integrated into other accelerators in the literature to enhance their efficiency. Our evaluation shows that PANTHER achieves up to 8.02×, 54.21×, and 103× energy reductions as well as 7.16×, 4.02×, and 16× execution time reductions compared to digital accelerators, ReRAM-based accelerators, and GPUs, respectively.

42 ENGINEERING↗
DOE OSTI2023

Three-dimensional nanoscale reduced-angle ptycho-tomographic imaging with deep learning (RAPID)

X-ray ptychographic tomography is a nondestructive method for three dimensional (3D) imaging with nanometer-sized resolvable features. The size of the volume that can be imaged is almost arbitrary, limited only by the penetration depth and the available scanning time. Here we present a method that rapidly accelerates the imaging operation over a given volume through acquiring a limited set of data via large angular reduction and compensating for the resulting ill-posedness through deeply learned priors. The proposed 3D reconstruction method “RAPID” relies initially on a subset of the object measured with the nominal number of required illumination angles and treats the reconstructions from the conventional two-step approach as ground truth. It is then trained to reproduce equal fidelity from much fewer angles. After training, it performs with similar fidelity on the hitherto unexamined portions of the object, previously not shown during training, with a limited set of acquisitions. In our experimental demonstration, the nominal number of angles was 349 and the reduced number of angles was 21, resulting in a x140 aggregate speedup over a volume of 4.48 x 93.18 x 3.92 μm 3 and with (14nm) 3 feature size, i.e. ~ 10 8 voxels. RAPID’s key distinguishing feature over earlier attempts is the incorporation of atrous spatial pyramid pooling modules into the deep neural network framework in an anisotropic way. We found that adjusting the atrous rate improves reconstruction fidelity because it expands the convolutional kernels’ range to match the physics of multi-slice ptychography without significantly increasing the number of parameters.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Challenges in spatial metabolomics and proteomics for functional tissue unit and single-cell resolution

While transcriptomics is the most broadly applied technology for global spatial and single cell measurements in healthy and diseased tissues. Transcripts are often used as a proxy for protein and even metabolite measurements, but it has become commonly accepted that extrapolating this kind of information is a poor proxy and not a substitute for direct measurement. Within the last decade advanced developments of mass spectrometry-based assays have made these direct measurements not only possible, but routine. Where mass spectrometry has become an enabling technology, and various methods can now detect hundreds of metabolites and thousands of proteins from samples. Not only can this be performed within bulk measurements, but much effort has been directed into translating these measurements to single cells and tissues at cellular resolution. The information obtained from mass spectrometry is now able to trace metabolic events and decipher feedback loops across anatomical regions, connecting genetic and metabolic networks that define phenotypes. Herein, we will broadly overview developments in the field over the past decade, leading into several case studies which highlight the direct measurement of metabolites, proteins, and proteoforms from thinly sliced tissues. Much of this work is feasible due to multidisciplinary team science, and we offer brief perspective on paths forward and the challenges that persist with adoption and application of spatial omics.

59 BASIC BIOLOGICAL SCIENCES↗