Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Average Accuracy”

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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

A differentiable model of the evolution of dark matter halo concentration

ABSTRACT We introduce a new model of the evolution of the concentration of dark matter haloes, c(t). For individual haloes, our model approximates c(t) as a power law with a time-dependent index, such that at early times, concentration has a nearly constant value of c ≈ 3–4, and as cosmic time progresses, c(t) smoothly increases. Using large samples of halo merger trees taken from the Bolshoi–Planck and MultiDark Planck 2 cosmological simulations, we demonstrate that our three-parameter model can approximate the evolution of the concentration of individual haloes with a typical accuracy of 0.1 dex for $t\gtrsim 2\, {\rm Gyr}$ for all Bolshoi–Planck and MultiDark Planck 2 haloes of present-day peak mass $M_{0}\gtrsim 10^{11.5}\, {\rm M}_{\odot }$. We additionally present a new model of the evolution of the concentration of halo populations, which we show faithfully reproduces both average concentration growth and the diversity of smooth trajectories of c(t), including capturing correlations with halo mass and halo assembly history. Our publicly available source code, diffprof, can be used to generate Monte Carlo realizations of the concentration histories of cosmologically representative halo populations. diffprof is differentiable due to its implementation in the jax autodiff library, which facilitates the incorporation of our model into existing analytical halo model frameworks.

Stevanovich, Dash↗
DOE OSTI2023

Modernist materials synthesis: Finding thermodynamic shortcuts with hyperdimensional chemistry

Synthesis remains a challenge for advancing materials science. A key focus of this challenge is how to enable selective synthesis, particularly as it pertains to metastable materials. This perspective addresses the question: how can “spectator” elements, such as those found in double ion exchange (metathesis) reactions, enable selective materials synthesis? By observing reaction pathways as they happen (in situ) and calculating their energetics using modern computational thermodynamics, we observe transient, crystalline intermediates that suggest that many reactions attain a local thermodynamic equilibrium dictated by local chemical potentials far before achieving a global equilibrium set by the average composition. Furthermore, using this knowledge, one can thermodynamically “shortcut” unfavorable intermediates by including additional elements beyond those of the desired target, providing access to a greater number of intermediates with advantageous energetics and selective phase nucleation. Ultimately, data-driven modeling that unites first-principles approaches with experimental insights will refine the accuracy of emerging predictive retrosynthetic models for complex materials synthesis.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning

Earthquake early warning (EEW) systems aim to forecast the shaking intensity rapidly after an earthquake occurs and send warnings to affected areas before the onset of strong shaking. The system relies on rapid and accurate estimation of earthquake source parameters. However, it is known that source estimation for large ruptures in real-time is challenging, and it often leads to magnitude underestimation. In a previous study, we showed that machine learning, HR-GNSS, and realistic rupture synthetics can be used to reliably predict earthquake magnitude. This model, called Machine-Learning Assessed Rapid Geodetic Earthquake model (M-LARGE), can rapidly forecast large earthquake magnitudes with an accuracy of 99%. Here, we expand M-LARGE to predict centroid location and fault size, enabling the construction of the fault rupture extent for forecasting shaking intensity using existing ground motion models. We test our model in the Chilean Subduction Zone with thousands of simulated and five real large earthquakes. The result achieves an average warning time of 40.5 s for shaking intensity MMI4+, surpassing the 34 s obtained by a similar GNSS EEW model. Our approach addresses a critical gap in existing EEW systems for large earthquakes by demonstrating real-time fault tracking feasibility without saturation issues. This capability leads to timely and accurate ground motion forecasts and can support other methods, enhancing the overall effectiveness of EEW systems. Additionally, the ability to predict source parameters for real Chilean earthquakes implies that synthetic data, governed by our understanding of earthquake scaling, is consistent with the actual rupture processes.

58 GEOSCIENCES↗
DOE OSTI2021

A second order yield-temperature relation for accurate inference of burn-averaged quantities in multi-species plasmas

Measured yields and ion temperatures inferred from the fusion product energy spectra can be used as metrics for the performance of an ICF implosion. This can be to infer species separation, thermal decoupling, flows or other effects that can cause the inferred ion temperatures to deviate from the true underlying thermal temperature and the yield ratio to deviate from the expected value. Direct inference of the impact of these effects on observed temperatures and yields can be difficult to uncover due to underlying dependence on the shape and time evolution of the temperature and density proles of the fusing plasma. Due to differences in the temperature dependence of the reactivities, different fusion products are emitted from different regions and times within the implosion. In order to properly account for this, a second order analytic expression relating the apparent temperatures and yield ratios is developed. This expression can be coupled to models of yield and/or temperature altering effects to infer their burn-averaged impact on an implosion. The second order expression shows significant improvement over lower order expressions in synthetic data studies. Demonstrations of its applications to synthetic data coupled with models of ion thermal decoupling and radial flows are presented. In the case of thermal decoupling both first and second order expressions show reasonable levels of accuracy. To consistently infer the amplitude of radial flow with <10% error the second order equation is required.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

SnSe 2 thermal conductivity from optothermal Raman and Stokes/anti-Stokes thermometry

The optothermal Raman method is useful in determining the in-plane thermal conductivity of two-dimensional (2D) materials that are either suspended or supported on a substrate. We compare this method with the Stokes/anti-Stokes scattering thermometry method, which can play a role in both calibration of Raman peak positions as well as extraction of the local phonon temperature. This work demonstrates that the Stokes/anti-Stokes intensity ratio plays an important role in determining the in-plane thermal conductivity of 2D tin diselenide (SnSe 2 ) dry-transferred onto a polished copper (Cu) substrate. The statistically-averaged thermal conductivity of the 108 ± 24 nm-thick SnSe 2 yielded 5.4 ± 3.5 Wm −1 K −1 for the optothermal Raman method, and 2.40 ± 0.81 Wm −1 K −1 for the Stokes/anti-Stokes thermometry method, indicating that the Stokes/anti-Stokes thermometry method to calculate the thermal conductivity of a material can simultaneously increase both precision and accuracy. The uncertainty value was also lowered by a factor of 1.9 from the traditional optothermal Raman method to the Stokes/anti-Stokes thermometry method. The low in-plane thermal conductivity of 2D SnSe 2 , 1.3–2.9 times lower than bulk, is useful for applications in thermal and electrical energy conversion and thermoelectric devices.

2D materials↗
DOE OSTI2024

SIGHT: Stacked Integration of Geospatial Hierarchical Typologies for Inferring Building Characteristics

Building characteristics are often absent in building stock datasets, particularly in regions most vulnerable to climate change and requiring effective disaster management strategies. Traditional machine learning approaches, while widely used to predict building attributes, typically neglect the spatial context of the data, leading to less accurate and reliable outcomes. To address these challenges, this paper introduces a novel algorithm, the Stacked Integration of Geospatial Hierarchical Typologies. This algorithm adapts a meta-learning framework to incorporate geospatial context into the predictive modeling process. We demonstrate the utility of the algorithm through two primary use cases: building use type classification and building height prediction. The algorithm consistently achieved or exceeded a 0.94 macro average F1 score across five geographically distinct countries for building use type classification. For building height prediction, it accurately predicted heights with a root mean square error of 3.01 in a comprehensive study using roughly 3.6 million buildings in Japan. These results underscore the benefits of integrating spatial hierarchies into machine learning models, enhancing both predictive accuracy and reliability in geospatial modeling. This work introduces a new algorithm to address the pervasive data sparsity issue in existing building stock datasets.

Adams, Daniel [ORNL] (ORCID:0000000196950577)↗
DOE OSTI2022

Impact of Advection Schemes on Tracer Interrelationships in Large-Eddy Simulations of Deep Convection

This study investigates the preservation of tracer interrelationships during advection in large-eddy simulations of an idealized deep convective cloud, which is particularly relevant to chemistry, aerosol, and cloud microphysics models. Employing the Cloud Model 1, advection is represented using third-, fifth-, and seventh-order weighted essentially non-oscillatory schemes. As a simplified analogy for cloud hydrometeors and aerosols, several inert passive tracers following linear and nonlinear relationships are initialized after the cloud reaches ~6-km depth. Numerical mixing in the simulated turbulent convective clouds leads to significant deviations from the initial nonlinear relationships between tracers. In these simulations, a considerable fraction of the grid points where the tracers’ nonlinear relationships are altered from advection are classified as unrealistic (e.g., ~13% for the environmental tracers on average), including errors from range-preserving unmixing and overshooting. Errors in the sum of three tracers are also relatively large, ranging between ~1% and 16% for 5% of the grid points in and near the cloud. The magnitude of unrealistic mixing and errors in the sum of three tracers generally increase with the order of accuracy of the advection scheme. These results are consistent across model grid spacings ranging from 50 to 200 m, and across three different flow realizations for each combination of grid spacing and advection scheme tested. Tests employing a previously proposed scalar normalization procedure show substantially reduced errors in the sum of three tracers with a relatively small negative impact on other tracer relationships. This analysis, therefore, suggests efficacy of the normalization procedure when applied to turbulent three-dimensional cloud simulations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Quantitative 2D thermometry in turbulent sooting non-premixed flames using filtered Rayleigh scattering

This paper demonstrates the application of a thermometry method in turbulent sooting non-premixed flames using filtered Rayleigh scattering (FRS). Fuel tailoring is used to establish a specific C 2 H 2 -based fuel mixture such that temperature can be determined accurately by a single FRS measurement over the entirety of mixture fraction space, or equivalently, for all relevant thermo-chemical states. Evaluation is performed in a hierarchy of flows to establish measurement precision and accuracy. Initial assessments in a series of heated fuel mixtures; non-sooting, near-adiabatic flat flames; and laminar non-premixed sooting flames show accuracy of the approach over a full range of expected temperatures and high single-shot measurement precision (e.g., 65 < <#comment/> S N R < <#comment/> 80 ) for temperatures between 1900 and 2200 K. Subsequently, 2D temperature measurements are evaluated in a turbulent non-premixed sooting flame. For the current fuel mixture, the local mixture-averaged Rayleigh scattering cross section is nearly constant over all composition space, and thus traditional laser Rayleigh scattering (LRS) is used as a measurement standard in the absence of soot. The results show excellent agreement between the proposed FRS thermometry approach and LRS in non-sooting regions. In the presence of soot, the proposed FRS-based approach shows no signs of interference. In addition, 2D temperature imaging shows high SNR (60–74) over all temperature conditions. Thus, we believe the proposed methodology successfully provides a high-resolution 2D temperature method under turbulent sooting flame conditions.

Pu, Jinpeng↗
DOE OSTI2024

Analysis on Evaluations of Monterey Bay Aquarium Research Institute’s Wave Energy Converter’s Field Data Using WEC-Sim and Gazebo: A Simulation Tool Comparison

Although many studies have validated wave energy converter (WEC) numerical models against scaled prototype experimental data, there remains a notable lack of validation using data from full-scale deployed WECs. This paper compares two numerical models of Monterey Bay Aquarium Research Institute’s Wave Energy Converter (MBARI-WEC), a two-body point absorber with an electro-hydraulic power take-off system (PTO). The models are implemented in WEC-Sim/Simscape and Gazebo Simulator. A statistical analysis of the models was performed, and field results were obtained to compare the models’ accuracy in predicting the RMS piston velocity, RMS motor speed, and mean electric power compared to field data for 56 observations across varying sea states. The Gazebo model demonstrated a closer agreement across all three parameters for a majority of the observations. When compared to the field data, the Gazebo and WEC-Sim models exhibited average mean electric power overestimations of 13% and 22%, respectively.

16 TIDAL AND WAVE POWER↗
DOE OSTI2024

Privacy-Preserving Real-Time Action Detection in Intelligent Vehicles Using Federated Learning-Based Temporal Recurrent Network

This study introduces a privacy-preserving approach for the real-time action detection in intelligent vehicles using a federated learning (FL)-based temporal recurrent network (TRN). This approach enables edge devices to independently train models, enhancing data privacy and scalability by eliminating central data consolidation. Our FL-based TRN effectively captures temporal dependencies, anticipating future actions with high precision. Extensive testing on the Honda HDD and TVSeries datasets demonstrated robust performance in centralized and decentralized settings, with competitive mean average precision (mAP) scores. The experimental results highlighted that our FL-based TRN achieved an mAP of 40.0% in decentralized settings, closely matching the 40.1% in centralized configurations. Notably, the model excelled in detecting complex driving maneuvers, with mAPs of 80.7% for intersection passing and 78.1% for right turns. These outcomes affirm the model’s accuracy in action localization and identification. The system showed significant scalability and adaptability, maintaining robust performance across increased client device counts. The integration of a temporal decoder enabled predictions of future actions up to 2 s ahead, enhancing the responsiveness. Our research advances intelligent vehicle technology, promoting safety and efficiency while maintaining strict privacy standards.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Correcting for filter-based aerosol light absorption biases at the Atmospheric Radiation Measurement program's Southern Great Plains site using photoacoustic measurements and machine learning

Abstract. Measurement of light absorption of solar radiation by aerosols is vital for assessing direct aerosol radiative forcing, which affects local and global climate. Low-cost and easy-to-operate filter-based instruments, such as the Particle Soot Absorption Photometer (PSAP), that collect aerosols on a filter and measure light attenuation through the filter are widely used to infer aerosol light absorption. However, filter-based absorption measurements are subject to artifacts that are difficult to quantify. These artifacts are associated with the presence of the filter medium and the complex interactions between the filter fibers and accumulated aerosols. Various correction algorithms have been introduced to correct for the filter-based absorption coefficient measurements toward predicting the particle-phase absorption coefficient (Babs). However, the inability of these algorithms to incorporate into their formulations the complex matrix of influencing parameters such as particle asymmetry parameter, particle size, and particle penetration depth results in prediction of particle-phase absorption coefficients with relatively low accuracy. The analytical forms of corrections also suffer from a lack of universal applicability: different corrections are required for rural and urban sites across the world. In this study, we analyzed and compared 3 months of high-time-resolution ambient aerosol absorption data collected synchronously using a three-wavelength photoacoustic absorption spectrometer (PASS) and PSAP. Both instruments were operated on the same sampling inlet at the Department of Energy's Atmospheric Radiation Measurement program's Southern Great Plains (SGP) user facility in Oklahoma. We implemented the two most commonly used analytical correction algorithms, namely, Virkkula (2010) and the average of Virkkula (2010) and Ogren (2010)–Bond et al. (1999) as well as a random forest regression (RFR) machine learning algorithm to predict Babs values from the PSAP's filter-based measurements. The predicted Babs was compared against the reference Babs measured by the PASS. The RFR algorithm performed the best by yielding the lowest root mean square error of prediction. The algorithm was trained using input datasets from the PSAP (transmission and uncorrected absorption coefficient), a co-located nephelometer (scattering coefficients), and the Aerosol Chemical Speciation Monitor (mass concentration of non-refractory aerosol particles). A revised form of the Virkkula (2010) algorithm suitable for the SGP site has been proposed; however, its performance yields approximately 2-fold errors when compared to the RFR algorithm. To generalize the accuracy and applicability of our proposed RFR algorithm, we trained and tested it on a dataset of laboratory measurements of combustion aerosols. Input variables to the algorithm included the aerosol number size distribution from the Scanning Mobility Particle Sizer, absorption coefficients from the filter-based Tricolor Absorption Photometer, and scattering coefficients from a multiwavelength nephelometer. The RFR algorithm predicted Babs values within 5 % of the reference Babs measured by the multiwavelength PASS during the laboratory experiments. Thus, we show that machine learning approaches offer a promising path to correct for biases in long-term filter-based absorption datasets and accurately quantify their variability and trends needed for robust radiative forcing determination.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Revisiting group contribution theory for estimating fractional free volume of microporous polymer membranes

Fractional free volume (FFV) is a commonly used metric for the development of structure–property relationships for polymer membranes. The most common method to calculate FFV uses Bondi's group contribution method, first introduced in 1964. While updated in 1997, there has not been a significant compilation of new structural motifs since the advent of linear microporous polymers. Here, in this study, we critically examined the assumptions in Bondi's original method and provide four recommendations to streamline and improve the accuracy of calculating van der Waals volume (V W ) for any group. Using these recommendations, we created an updated list of (V W ) values for structural groups commonly present in microporous polymers. The (V W ) and FFV values were then calculated for a database of 123 microporous and high free volume polymers from the literature, showing an average 7% decrease in (V W ) and corresponding increase in FFV by a factor of 24% when compared to prior group contribution correlations in the literature. The significant apparent increase in estimated FFV provides a new perspective to understand and interpret the role of free volume on the separation performance of linear microporous polymers. Additionally, standardization of the group contribution method allows for the direct comparison of FFV values across studies.

42 ENGINEERING↗
DOE OSTI2023

An Appraisal of the Performance and Characteristics of Summary Rays Calculated for the SALSA3D Traveltime Dataset

The SALSA3D tomographic model provides a crucial community resource for improving the quality (in terms of both accuracy and precision) of predictions of the traveltimes of seismic waves and therefore improving our ability to locate anthropogenic or natural seismic events. Constructing the requisite tomographic model requires addressing the challenges implied by a massive and growing dataset of traveltime measurements. This study explores one approach to tackle this challenge: the use of summary rays, which average traveltime measurements from sources within evenly spaced cells, thereby eliminating redundant data.

58 GEOSCIENCES↗
DOE OSTI2020

A Clustering-based biased Monte Carlo Approach to Protein Titration Curve Prediction

We develop and implement a novel approach to computing the ensemble averages in systems characterized by pair-wise interactions between the entities. Methods involving full enumeration of the configuration space result in exponential complexity. Sampling methods such as Markov Chain Monte Carlo (MCMC) algorithms have been proposed to tackle the exponential complexity of these problems. In certain scenarios where significant energetic coupling exists between the entities, the accuracy of the such algorithms can be diminished. We propose a strategy to improve the accuracy of the MCMC runs by taking advantage of the cluster structure in the interaction energy matrix. We propose two different schemes for performing the biased MCMC runs on the partitioned systems and show that they are valid MCMC schemes. We then apply these algorithms to the problem of computing the protonation fractions and hence the titration curves of titratable protein residues that constitute a given protein. We leverage both synthesized and real-world systems and show the improved performance of our biased MCMC methods when compared to the regular MCMC method.

Visweswara Sathanur, Arun↗
DOE OSTI2021

Fossil fuel CO 2 emissions over metropolitan areas from space: A multi-model analysis of OCO-2 data over Lahore, Pakistan

Urban areas, where gathering more than 55% of the global population, alone contributed to more than 70% of anthropogenic fossil fuel carbon dioxide (CO 2ff ) emissions. Accurate quantification of CO 2ff emissions from urban areas is of great importance to the formulation of global warming mitigation policies to achieve carbon neutrality by 2050. Satellite-based inversion techniques are unique among “top-down” approaches, potentially allowing us to track CO 2ff emission changes over cities globally. However, its accuracy is still limited by incomplete background information, cloud blockages, aerosol contaminations, and uncertainties in models and emission inventories used as prior. To evaluate the current potential of space-based quantification techniques, we present the first attempt to monitor long-term changes in CO 2ff emissions based on the OCO-2 satellite measurements of column-averaged dry-air mole fractions of CO 2 (X CO2 ) over a fast-growing Asian metropolitan area: Lahore, Pakistan. We first examined the OCO-2 data availability at global scale. About 17% of OCO-2 soundings are marked as high-quality soundings by quality flags over the global 70 most populated cities over the period 2014-2019. Cloud blockage and aerosol contamination are the two main causes of data loss. As an attempt to recover additional soundings, we evaluated the effectiveness of OCO-2 quality flags at the city level by comparing three flux quantification methods (WRF-Chem, X-STILT, and flux cross-sectional integration method), all based on the Open-Data Inventory for Anthropogenic Carbon dioxide (ODIAC) product. The satellite/bottom-up emissions (OCO-2/ODIAC) ratios of the high-quality tracks better converged across the three methods compared to the all-data tracks with reduced uncertainties in emissions. Thus, OCO-2 quality flags are useful filters of low-quality OCO-2 retrievals at local scales, although originally designed for global-scale studies. All three methods consistently suggested that the ratio medians are greater than 1, which implies that the ODIAC slightly underestimated the CO2ff emissions over Lahore. Additionally, our estimation of the a posteriori CO2ff emission trend was about 734 kt C/year (i.e., an annual 6.7% increase). 10,000 Monte Carlo simulations of the Mann-Kendall upward trend test showed that less than 10% prior uncertainty for 8 tracks (or less than 20% prior uncertainty for 25 tracks) is required to achieve a greater-than-50% trend significant possibility at a 95% confidence level. It implies that the trend is driven by the prior and not due to the assimilation of OCO-2 retrievals. The key to improving the role of satellite data in CO 2 emission trend detection lies in collecting more frequent high-quality tracks near metropolitan areas to achieve significant constraints from X CO2 retrievals.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Boosting Barlow Twins Reduced Order Modeling for Machine Learning‐Based Surrogate Models in Multiphase Flow Problems

Abstract We present an innovative approach called boosting Barlow Twins reduced order modeling (BBT‐ROM) to enhance the reliability of machine learning surrogate models for multiphase flow problems. BBT‐ROM builds upon Barlow Twins reduced order modeling that leverages self‐supervised learning to effectively handle linear and nonlinear manifolds by constructing well‐structured latent spaces of input parameters and output quantities. To address the challenge of high contrast data in multiphase flow problems due to injection wells and faults, we employ a boosting algorithm within BBT‐ROM. This algorithm sequentially trains a set of weak models (i.e., inaccurate models), improving prediction accuracy through ensemble learning. To evaluate the performance of BBT‐ROM, we conduct three three‐dimensional multiphase flow problems, including waterflooding and geologic carbon storage (GCS), with varying numbers of input parameter cases and model domain features. The results demonstrate that BBT‐ROM excels at predicting non‐wetting phase saturation (e.g., oil or saturation) and fluid pressure, with average relative errors ranging from 0.5% to 3%. Importantly, BBT‐ROM showcases robustness when faced with limited input parameter space during GCS testing.

58 GEOSCIENCES↗
DOE OSTI2021

A second order yield-temperature relation for accurate inference of burn-averaged quantities in multi-species plasmas

Measured yields and ion temperatures inferred from the fusion product energy spectra can be used as metrics for the performance of an ICF implosion. This can be used to infer species separation, thermal decoupling, flows, or other effects that can cause the inferred ion temperatures to deviate from the true underlying thermal temperature and the yield ratio to deviate from the expected value. Direct inference of the impact of these effects on observed temperatures and yields can be difficult to uncover due to the underlying dependence on the shape and time evolution of the temperature and density profiles of the fusing plasma. Due to differences in the temperature dependence of the reactivities, different fusion products are emitted from different regions and times within the implosion. In order to properly account for this, a second-order analytical expression relating the apparent temperatures and yield ratios is developed. This expression can be coupled to models of yield and/or temperature altering effects to infer their burn-averaged impact on an implosion. The second-order expression shows significant improvement over lower-order expressions in synthetic data studies. Demonstrations of its applications to synthetic data coupled with models of ion thermal decoupling and radial flows are presented. In the case of thermal decoupling, both first and second-order expressions show reasonable levels of accuracy. To consistently infer the amplitude of radial flow with a <10% error, the second-order equation is required.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

ML-based Real-Time Control at the Edge: An Approach Using hls4ml

This study focuses on implementing a real-time control system for a particle accelerator facility that performs high energy physics experiments. A critical operating parameter in this facility is beam loss, which is the fraction of particles deviating from the accelerated proton beam into a cascade of secondary particles. Accelerators employ a large number of sensors to monitor beam loss. The data from these sensors is monitored by human operators who predict the relative contribution of different sub-systems to the beam loss. Using this information, they engage control interventions. In this paper, we present a controller to track this phenomenon in real-time using edge-Machine Learning (ML) and support control with low latency and high accuracy. We implemented this system on an Intel Arria 10 SoC. Optimizations at the algorithm, high-level synthesis, and interface levels to improve latency and resource usage are presented. Our design implements a neural network, which can predict the main source of beam loss (between two possible causes) at speeds up to 575 frames per second (fps) (average latency of 1.74 ms). The practical deployed system is required to operate at 320 fps, with a 3ms latency requirement, which has been met by our design successfully.

Shi, R.↗