hls4ml: Deploying Deep Learning on FPGAs for L1 trigger and Data Acquisition [PowerPoint]
Abstract not provided.
SEARCH · Search NASA
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.
Abstract not provided.
Abstract not provided.
Explore the source record for details and available documents.
The nuclear industry is experiencing a steady increase in maintenance costs even though plants are maintained under high levels of safety, capability and reliability. Nuclear power plants are expected to run every unit at maximum capacity at all times, efficiently utilizing assets with minimal downtime. Surveillance and maintenance of nuclear decommissioning infrastructure provides lot challenges with respect to maintenance or decommissioning of the buildings. There is a need for a framework to analyze the huge amount of data generated by the sensors on the nuclear reactor components as well as structures, to monitor the conditions of these building over a period of time. Emerging technologies such as big data analytics have become a requirement in the nuclear industry to improve structural health monitoring and diagnostics. FIU will make use of existing mature technologies in the areas of imaging, robotics, big data, and machine learning/deep learning to assess the structural integrity of aging facilities at DOE sites. As these facilities await decommissioning, there is a need to understand the structural health of these structures. Many of these facilities were built over 50 years ago and in some cases these facilities have gone beyond the operational life expectancy. In other cases, the facilities have been placed in a state of 'cold and dark' and they are sitting unused, awaiting decommissioning. Finally, some older facilities are one-of-a-kind operational/production facilities supporting critical DOE missions and cannot be shut down. In any of these scenarios, the structural integrity of these facilities may be compromised, so it is imperative that adequate inspections and data collection/analysis be performed on a continuous and ongoing basis. The primary goals of the research include collecting various formats of data such as structured, unstructured and streaming data from the various sensors deployed in buildings, collect videos/pictures from various imaging sources, ingest them using a Hadoop distributed file system and process the data using Spark to perform batch processing and real time analytics. Research and development on various machine learning/deep learning algorithms will also be performed to analyze the heterogeneous data collected from nuclear decommission infrastructure. FIU will design the big data framework to ingest, store and process huge amounts of heterogeneous data collected from many sources and optimize the algorithms to provide insights into the data and predict anomalies observed when compared against baseline conditions. Various modules of this framework will include heterogeneous data sources, message broker, Hadoop distributed file system, Spark for stream and batch processing, machine learning/ deep learning, Cassandra - persistent data store and visualization. (authors)
Explore the source record for details and available documents.
In this paper we will present the results of monitored annual energy use data from eight residential Deep Energy Retrofit (DER) case studies using a variety of performance metrics. For each home, the details of the retrofits were analyzed, diagnostic tests to characterize the home were performed and the homes were monitored for total and individual end-use energy consumption for approximately one year. Annual performance in site and source energy, as well as carbon dioxide equivalent (CO 2 e) emissions were determined on a per house, per person and per square foot basis to examine the sensitivity to these different metrics. All eight DERs showed consistent success in achieving substantial site energy and CO 2 e reductions, but some projects achieved very little, if any source energy reduction. This problem emerged in those homes that switched from natural gas to electricity for heating and hot water, resulting in energy consumption dominated by electricity use. This demonstrates the crucial importance of selecting an appropriate metric to be used in guiding retrofit decisions. Also, due to the dynamic nature of DERs, with changes in occupancy, size, layout, and comfort, several performance metrics might be necessary to understand a project’s success.
To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach. Instrumental to this framework, Feature Similarity Measurement (FSM) technique was developed for error estimation in two-phase flow simulation using coarse-mesh CFD, to achieve a comparable accuracy as fine-mesh simulations with fast-running feature. In this work, by defining physics-guided parameters and variable gradients as physical features, FSM has the capability to capture the underlying local patterns in the coarse-mesh CFD simulation. Massive low-fidelity data and respective high-fidelity data are used to explore the underlying information relevant to the main simulation errors and the effects of phenomenological scaling. By learning from previous simulation data, a surrogate model using deep feedforward neural network (DFNN) can be developed and trained to estimate the simulation error of coarse-mesh CFD. In a demonstration case of two-phase bubbly flow, the DFNN model well captured and corrected the unphysical “peaks” in the velocity and void fraction profiles near the wall in the coarse-mesh configuration, even for extrapolative predictions. The research documented supports the feasibility of the physics-guided deep learning methods for coarse mesh CFD simulations which has a potential for the efficient industrial design.
We search for z {approx} 10 galaxies over {approx}160 arcmin{sup 2} of Wide-Field Camera 3 (WFC3)/IR data in the Chandra Deep Field South, using the public HUDF09, Early Release Science, and CANDELS surveys, that reach to 5{sigma} depths ranging from 26.9 to 29.4 in H{sub 160} AB mag. z {approx}> 9.5 galaxy candidates are identified via J{sub 125} - H{sub 160} > 1.2 colors and non-detections in any band blueward of J{sub 125}. Spitzer Infrared Array Camera (IRAC) photometry is key for separating the genuine high-z candidates from intermediate-redshift (z {approx} 2-4) galaxies with evolved or heavily dust obscured stellar populations. After removing 16 sources of intermediate brightness (H{sub 160} {approx} 24-26 mag) with strong IRAC detections, we only find one plausible z {approx} 10 galaxy candidate in the whole data set, previously reported in Bouwens et al.. The newer data cover a 3 Multiplication-Sign larger area and provide much stronger constraints on the evolution of the UV luminosity function (LF). If the evolution of the z {approx} 4-8 LFs is extrapolated to z {approx} 10, six z {approx} 10 galaxies are expected in our data. The detection of only one source suggests that the UV LF evolves at an accelerated rate before z {approx} 8. The luminosity density is found to increase by more than an order of magnitude in only 170 Myr from z {approx} 10 to z {approx} 8. This increase is {>=}4 Multiplication-Sign larger than expected from the lower redshift extrapolation of the UV LF. We are thus likely witnessing the first rapid buildup of galaxies in the heart of cosmic reionization. Future deep Hubble Space Telescope WFC3/IR data, reaching to well beyond 29 mag, can enable a more robust quantification of the accelerated evolution around z {approx} 10.
The objective of the Fourth Technical Meeting on Fusion Data Processing, Validation and Analysis was to provide a platform during which a set of topics relevant to fusion data processing, validation and analysis are discussed with the view of extrapolating needs to next step fusion devices such as ITER. The validation and analysis of experimental data obtained from diagnostics used to characterize fusion plasmas are crucial for a knowledge-based understanding of the physical processes governing the dynamics of these plasmas. This paper presents the recent progress and achievements in the domain of plasma diagnostics and synthetic diagnostics data analysis (including image processing, regression analysis, inverse problems, deep learning, machine learning, big data and physics-based models for control) reported at the meeting. The progress in these areas highlight trends observed in current major fusion confinement devices. A special focus is dedicated on data analysis requirements for ITER and DEMO with a particular attention paid to artificial intelligence for automatization and improving reliability of control processes.
We compare sensitive H I data from The H I Nearby Galaxy Survey and deep far-ultraviolet (FUV) data from the Galaxy Evolution Explorer in the outer disk of M83. The FUV and H I maps show a stunning spatial correlation out to almost 4 optical radii (r {sub 25}), roughly the extent of our maps. This underscores that H I traces the gas reservoir for outer-disk star formation (SF), and it implies that massive (at least low level) SF proceeds almost everywhere that H I is observed. Whereas the average FUV intensity steadily decreases with increasing radius before leveling off at {approx}1.7 r {sub 25}, the decline in H I surface density is more subtle. Low H I columns ({approx_lt}2 M {sub sun} pc{sup -2}) contribute most of the mass in the outer disk, which is not the case within r {sub 25}. The time for SF to consume the available H I, inferred from the ratio of H I to FUV intensity, rises with increasing radius before leveling off at {approx}100 Gyr, i.e., many Hubble times, near {approx}1.7 r {sub 25}. Assuming that the relatively short H{sub 2} depletion times observed in the inner parts of galaxies hold in outer disks, the conversion of H I into bound, molecular clouds seems to limit SF in outer galaxy disks. The long consumption times suggest that most of the extended H I observed in M83 will not be consumed by in situ SF. However, even these low SF rates are enough for moderate chemical enrichment in a closed outer disk to be expected.
Laser Powder Bed Fusion (L-PBF) Additive Manufacturing (AM) is among the metal 3D printing technologies most broadly adopted by the manufacturing industry. The current industry qualification paradigm for critical-application L-PBF parts relies heavily on expensive non-destructive inspection techniques such as X-Ray Computed Tomography (XCT), which significantly limits the use-cases of L-PBF. In situ monitoring of the process promises a less expensive alternative to ex situ testing, but existing sensor technologies and data analysis techniques struggle to detect sub-surface flaws (e.g., porosity and cracking) on production-scale L-PBF printers. RTX Technologies Research Center (RTRC) has licensed ORNL’s Peregrine software package – a printer- and camera-agnostic data analytics tool designed specifically for detecting process anomalies using in situ data collected during powder bed printing. The goal of this project was to feed temporally rich, multi-modal sensor data, including visible light, integrated near infrared (NIR), and spatially mapped co-axial melt pool thermal emission data into Peregrine to enable detection of subsurface flaws. XCT data was used as ground truth training data to allow Peregrine’s deep learning algorithms to recognize anomalies in these complex data streams in both test artifacts and industrially relevant geometries. Completion of this program has seen the successful implementation of multi-modal, multi-layer sensor data footprints for training of machine learning models in Peregrine. Flaws detected in XCT data have been successfully detected directly from this in situ data footprint, and initial analyses of the in situ probability-of-detection has been conducted, showing performance levels commensurate with traditional non-destructive evaluation (NDE) methods. The in situ monitoring methodology was then applied to an industrially relevant component that was using post-build NDE, highlighting the utility of the proposed method for hard-to-inspect AM components. As a direct result of this program, two journal manuscripts [1], [2] have been published in Additive Manufacturing, with additional manuscripts planned following program completion.
We report results of a deep all-sky search for periodic gravitational waves from isolated neutron stars in data from the first Advanced LIGO observing run. This search investigates the low frequency range of Advanced LIGO data, between 20 and 100 Hz, much of which was not explored in initial LIGO. The search was made possible by the computing power provided by the volunteers of the Einstein@Home project. We find no significant signal candidate and set the most stringent upper limits to date on the amplitude of gravitational wave signals from the target population, corresponding to a sensitivity depth of 48.7 [1/$\sqrt{Hz}$]. At the frequency of best strain sensitivity, near 100 Hz, we set 90% confidence upper limits of 1.8×10 ₋25 . At the low end of our frequency range, 20 Hz, we achieve upper limits of 3.9×10 ₋24 . At 55 Hz we can exclude sources with ellipticities greater than 10 ₋5 within 100 pc of Earth with fiducial value of the principal moment of inertia of 10 38 kg m 2 .
Studying the biology of sleep requires the accurate assessment of the state of experimental subjects, and manual analysis of relevant data is a major bottleneck. Recently, deep learning applied to electroencephalogram and electromyogram data has shown great promise as a sleep scoring method, approaching the limits of inter-rater reliability. As with any machine learning algorithm, the inputs to a sleep scoring classifier are typically standardized in order to remove distributional shift caused by variability in the signal collection process. However, in scientific data, experimental manipulations introduce variability that should not be removed. For example, in sleep scoring, the fraction of time spent in each arousal state can vary between control and experimental subjects. We introduce a standardization method, mixture z-scoring, that preserves this crucial form of distributional shift. Using both a simulated experiment and mouse in vivo data, we demonstrate that a common standardization method used by state-of-the-art sleep scoring algorithms introduces systematic bias, but that mixture z-scoring does not. We present a free, open-source user interface that uses a compact neural network and mixture z-scoring to allow for rapid sleep scoring with accuracy that compares well to contemporary methods. This work provides a set of computational tools for the robust automation of sleep scoring.
In this paper we discuss recent advances in deep convolutional neural networks (CNN) for sequence learning, which allow identifying long-range, multi-scale phenomena in long sequences, such as those found in fusion plasmas. We point out several benefits of these deep CNN architectures, such as not requiring experts such as physicists to hand-craft input data features, the ability to capture longer range dependencies compared to the more common sequence neural networks (recurrent neural networks like long short-term memory (LSTM) networks), and the comparative computational efficiency. We apply this neural network architecture to the popular problem of disruption prediction in fusion energy tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. Initial results trained on a large ECEi dataset show promise, achieving an F 1 -score of ~91% on individual time-slices using only the ECEi data. This indicates the ECEi diagnostic by itself can be sensitive to a number of pre-disruption markers useful for predicting disruptions on timescales not only for mitigation but also avoidance. Future opportunities for utilizing these deep CNN architectures with fusion data are outlined, including impact of recent upgrades to the ECEi diagnostic.
The Deep Lynx UNC is a small utility written in Python that uses only basic Python libraries and the Deep Lynx Python Software Development Kit (SDK). It queries Deep Lynx for tasks that indicate some data to be run in the UNC's environment. Once a task is acquired, the UNC retrieves the associated data and provides it to some other application for processing, waits for output, and sends the output from the other application to Deep Lynx. As data flows only from the UNC to Deep Lynx, this software solves the problem of connecting Deep Lynx with applications and resources that exist in a network where the network can reach Deep Lynx, but Deep Lynx cannot reach that network (unidirectional network).
We utilize the Sagittarius Window Eclipsing Extrasolar Planet Search Hubble Space Telescope/Advanced Camera for Surveys data set for a Deep Rapid Archival Flare Transient Search to constrain the flare rate toward the older stellar population in the Galactic bulge. During seven days of monitoring 229,293 stars brighter than V = 29.5, we find evidence for flaring activity in 105 stars between V = 20 and V = 28. We divided the sample into non-variable stars and variable stars whose light curves contain large-scale variability. The flare rate on variable stars is {approx}700 times that of non-variable stars, with a significant correlation between the amount of underlying stellar variability and peak flare amplitude. The flare energy loss rates are generally higher than those of nearby well-studied single dMe flare stars. The distribution of proper motions is consistent with the flaring stars being at the distance and age of the Galactic bulge. If they are single dwarfs, then they span a range of Almost-Equal-To 1.0-0.25 M{sub Sun }. A majority of the flaring stars exhibit periodic photometric modulations with P < 3 days. If these are tidally locked magnetically active binary systems, then their fraction in the bulge is enhanced by a factor of {approx}20 compared to the local value. These stars may be useful for placing constraints on the angular momentum evolution of cool close binary stars. Our results expand the type of stars studied for flares in the optical band, and suggest that future sensitive optical time-domain studies will have to contend with a larger sample of flaring stars than the M dwarf flare stars usually considered.
The high frequency dynamics of liquid iodine has been investigated by deep inelastic x-ray scattering at exchanged wave-vectors (q) ranging from 2.5 to 15 A{sup -1}. The experimental data have been analyzed in the frame of the Sachs-Teller theory of the molecular spectrum while accounting for final state corrections to the lineshape. The performed data analysis carries insights on physical quantities as relevant as the mean rototranslational kinetic energy and the mean square Laplacian of the intermolecular potential. In both cases the measured values are consistent with corresponding theoretical expectations.
An experiment that measured the parity violating asymmetries in deep inelastic scattering was completed at the Thomas Jefferson National Accelerator Facility in experimental Hall A. From these asymmetries, a combination of the quark weak axial charge could be extracted with a factor of five improvement in precision over world data. To achieve this, asymmetries at the 10^-4 level needed to be measured at event rates up to 500 kHz and the high pion background typical to deep inelastic scattering experiments needed to be rejected efficiently. A specialized data acquisition (DAQ) system with intrinsic particle identification (PID) was successfully developed and used: The pion contamination in the electron samples was controlled at the order of 2 × 10^-4 or below with an electron efficiency of higher than 91% throughout the production period of the experiment, the systematic uncertainty in the measured asymmetry due to DAQ deadtime was below 0.2%, and the statistical quality of the asymmetry measurement agreed with the Gaussian distribution to over five orders of magnitudes. The DAQ system is presented here with an emphasis on its design scheme, the achieved PID performance, deadtime effect and the capability of measuring small asymmetries.