Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep”

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 91 records · Page 5

The deep-DRT: A deep neural network approach to deconvolve the distribution of relaxation times from multidimensional electrochemical impedance spectroscopy data

Electrochemical impedance spectroscopy (EIS) is an experimental technique ubiquitously used to study electrochemical systems. However, conventional EIS data interpretation through physical and equivalent circuit models is challenging because physical models are problem-specific, and equivalent circuits are often just lumped-element analogs lacking physical meaning. The distribution of relaxation times (DRT) has emerged as a complementary approach to resolve these issues. One drawback of conventional DRT deconvolution is that the EIS data is understood to be (only) a function of frequency (i.e. 1D data) and deconvolved accordingly. This work proposes a novel deconvolution method based on deep neural networks (DNNs), allowing the analysis of multidimensional EIS spectra to bridge data dependency on both frequencies and experimental conditions. Two particularly appealing traits of the deep-DRT method developed in this article are that neither regularization nor specific spacing on the state variables defining the experiment are required. Finally, leveraging DNN to examine complex EIS spectra and their dependence on experimental conditions, this work opens a new research direction in the area of EIS analysis and DRT deconvolution.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

How deep is your soil? Quantifying and spatially analyzing understudied deep soil in the United States

Deep soil is largely understudied and important in understanding biogeochemical processes in soil. Here, understudied soil is defined as the difference between soil studied to a known depth and the estimated bedrock depth. To understand more about deep soil, the understudied soil in the US was quantified and spatially analyzed using soil survey data and model estimates of bedrock depth. An equation was derived to find understudied soil using the dataset parameters “max lower depth studied”, “depth to bedrock”, and “likelihood of bedrock in the top 200 cm”. The survey data and bedrock model revealed that soil has been studied to an average depth of 1-2 meters, and the average depth to bedrock is 20 meters. Soil data density in the soil surveys was greatest in the West Coast, Midwest, and areas historically managed for agricultural, while the non-contiguous US and interior West were underrepresented. The soil had been studied deeper than the estimated soil depth in 455 out of 56,889 observation points concentrated in Alaska, California, Texas, Florida, Puerto Rico, and the US Virgin Islands. To understand the diversity and any taxonomic bias of the global soil data available, soil order was compared to US-based National Resource Conservation Service percentages and it was found that Oxisols, Alfisols, Ultisols, Andisols, and Histosols were overrepresented while Gelisols, Aridisols, Vertisols, Entisols, and Spodosols are underrepresented. Soil depth is important in exploring the complexity of biogeochemical processes that take place in soil.

Bedrock↗

Reconstructing the kinematics of deep inelastic scattering with deep learning

We introduce a method to reconstruct the kinematics of neutral-current deep inelastic scattering (DIS) using a deep neural network (DNN). Unlike traditional methods, it exploits the full kinematic information of both the scattered electron and the hadronic-final state, and it accounts for QED radiation by identifying events with radiated photons and event-level momentum imbalance. The method is studied with simulated events at HERA and the future Electron–Ion Collider (EIC). We show that the DNN method outperforms all the traditional methods over the full phase space, improving resolution and reducing bias. Our method has the potential to extend the kinematic reach of future experiments at the EIC, and thus their discovery potential in polarized and nuclear DIS.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

e-vector-{sup 2}H Parity Violating Deep Inelastic Scattering at Jefferson Laboratory at 6 GeV

The upcoming parity violating deep inelastic scattering (PVDIS) experiment E08-011 in Hall A at Thomas Jefferson National Accelerator Facility (Jefferson Lab) aims to measure a combination of the axial hadronic couplings of the electron with a factor of six improvement in precision over world data. Precise data for the couplings are essential to search for physics beyond the Standard Model. The experiment will measure a 10{sup -4} asymmetry using polarized electron scattering from deuterium with a beam energy of 6 GeV. Recent progress on the preparation for this experiment, with an emphasis on the tests of the data acquisition system and the capability of measuring a small asymmetry, deadtime, and pileup effects are presented.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Study of semi-inclusive deep inelastic (e,e'{pi}{sup {+-}}) production with a polarized {sup 3}He target

The 12 GeV upgrade at Jefferson Lab will open a new era of precision measurement of the Transverse Momentum Dependent parton distribution functions (TMDs) through the Semi-Inclusive Deep-Inelastic Scattering (SIDIS). In this talk, we discussed the projected results on measurements of TMDs using a newly proposed large acceptance solenoid detector together with the standard Hall A polarized {sup 3}He target. The high luminosity and the large acceptance detector will allow for a precise 3-D (x, z and P{sub T}) mapping of azimuthal asymmetries. Furthermore, the full 2{pi} azimuthal angular coverage for the solenoid detector is essential to control the relevant systematic uncertainties in extracting the azimuthal asymmetries. With a 40 cm long transversely polarized {sup 3}He target, a total of 60 days of beam time at a beam current of 15 {mu}A, we can determine tensor charge of d quark to 10% in a model independent way. The extracted Sivers asymmetry will provide important information to understand the correlation between the quark orbital angular momentum and the nucleon spin.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Beam spin asymmetries from semi-inclusive pion electroproduction in deep inelastic scattering

Measurements of beam-spin asymmetries from semi-inclusive pion electro-production in deep inelastic scattering (DIS) have been performed. Data were taken with the CEBAF Large Acceptance Spectrometer (CLAS) at Jefferson Lab using a 5.7 GeV longitudinally polarized electron beam and an unpolarized liquid hydrogen target. All three pion channels ({pi}{sup +}, {pi}{sup 0} and {pi}{sup -}) were measured simultaneously over a large range of kinematics at the intermediate Q{sup 2} range (Q{sup 2}{approx_equal}1-3 GeV{sup 2}). We present our preliminary studies of single-spin azimuthal asymmetries of the two charged pion channels as functions of z and P{sub T}. This new high statistical data will provide important means of studying physics underlying the spin structure of the nucleon.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Laplace-Transform Deep-Level Spectroscopy Characterization of the Intrinsic and Deep-Level States in Self-Assembled InAs Quantum-Dot Structures

The electron emission from the intrinsic and deep-level states in self-assembled InAs/GaAs quantum-dot structures is probed using the Laplace-transform deep-level transient spectroscopy. The technique shows sufficient resolution to resolve electron emission from the singly and doubly occupied QD s states. By applying an appropriate set of voltage pulses across the Schottky-diode structure, we identify the electron distribution profile in the quantum-dot intrinsic states.

36 MATERIALS SCIENCE↗

6 GeV Parity Violating Deep Inelastic Scattering at Jefferson Laboratory

The 6 GeV Parity Violating Deep Inelastic Scattering (PVDIS) experiment has measured a 10{sup -4} level asymmetry through polarized electron scattering off a liquid deuterium target with a beam energy of 6 GeV. This experiment has a goal of measuring a combination of the product of the weak neutral couplings of the electron and the quark with a factor of six improvement in precision over world data. Precise data for the couplings are essential to search for physics beyond the Standard Model. The experiment took place in Hall A at Thomas Jefferson National Accelerator Facility (Jefferson Laboratory) and data collection was completed in the end of 2009. A highly specialized counting data acquisition system with an inherent particle identification was developed and utilized. We have taken data at two Q{sup 2} points in order to possibly address the hadronic correction due to higher twist effects. An overview of the experiment will be presented.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Measurement of Charged-Pion Production in Deep-Inelastic Scattering off Nuclei with the CLAS Detector

Background: Energetic quarks in nuclear deep-inelastic scattering propagate through the nuclear medium. Processes that are believed to occur inside nuclei include quark energy loss through medium-stimulated gluon bremsstrahlung and intranuclear interactions of forming hadrons. More data are required to gain a more complete understanding of these effects. Purpose: To test the theoretical models of parton transport and hadron formation, we compared their predictions for the nuclear and kinematic dependence of pion production in nuclei. Methods: We have measured charged-pion production in semi-inclusive deep-inelastic scattering off D, C, Fe, and Pb using the CLAS detector and the CEBAF 5.014-GeV electron beam. We report results on the nuclear-to-deuterium multiplicity ratio for π + and π - as a function of energy transfer, four-momentum transfer, and pion energy fraction or transverse momentum—the first three-dimensional study of its kind. Results: The π + multiplicity ratio is found to depend strongly on the pion fractional energy z and reaches minimum values of 0.67 ± 0.03, 0.43 ± 0.02, and 0.27 ± 0.01 for the C, Fe, and Pb targets, respectively. The z dependencies of the multiplicity ratios for π + and π - are equal within uncertainties for C and Fe targets but show differences at the level of 10% for the Pb-target data. The results are qualitatively described by the GIBUU transport model, as well as with a model based on hadron absorption, but are in tension with calculations based on nuclear fragmentation functions. Conclusions: These precise results will strongly constrain the kinematic and flavor dependence of nuclear effects in hadron production, probing an unexplored kinematic region. They will help to reveal how the nucleus reacts to a fast quark, thereby shedding light on its color structure and transport properties and on the mechanisms of the hadronization process.

Moran, S.↗

Structure of {sup 65,67}Co studied through the {beta} decay of {sup 65,67}Fe and a deep-inelastic reaction

The neutron-rich isotopes {sup 65,67}Fe and {sup 65}Co have been produced at the LISOL facility, Louvain-La-Neuve, in the proton-induced fission of {sup 238}U. Beams of these isotopes have been extracted with high selectivity by means of resonant laser ionization combined with mass separation. Yrast and near-yrast levels of {sup 65}Co have also been populated in the {sup 64}Ni+{sup 238}U reaction at Argonne National Laboratory. The level structure of {sup 65}Co could be investigated by combining all the information from both the {sup 65}Fe and {sup 65}Co{beta} decay and the deep-inelastic reaction. The {sup 65}Fe, {sup 65}Co, and {sup 67}Fe decay schemes and the {sup 65}Co yrast structure are fully established. The {sup 65,67}Co level structures can be interpreted as resulting from the coexistence of core-coupled states with levels based on a low-energy proton-intruder configuration.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Cross-Market Price Difference Forecast Using Deep Learning for Electricity Markets

Price forecasting is in the center of decision making in electricity markets. Many researches have been done in forecasting energy prices while little research has been reported on forecasting price difference between day-ahead and realtime markets due to its high volatility, which however plays a critical role in virtual trading. To this end, this paper takes the first attempt to employ novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units to forecast the price difference between day-ahead and real-time markets for the same node. The raw data is collected from PJM market, processed and fed into the proposed network. The Root Mean Squared Error (RMSE) and customized performance metric are used to evaluate the performance of the proposed method. Case studies show that it outperforms the traditional statistical models like ARIMA, and machine learning models like XGBoost and SVR methods in both RMSE and the capability of forecasting the sign of price difference. Additionally, to cross-market price difference forecast, the proposed approach has the potential to be applied to solve other forecasting problems such as price spread forecast in DA market for Financial Transmission Right (FTR) trading purpose.

DA/RT price difference↗

A Fast and Accurate Transient Stability Assessment Method Based on Deep Learning: WECC Case Study

Transient stability is one of the critical aspects of power system stability assessment. The increasing integration of inverter-based resources and the retirement of conventional synchronous generators result in the decreasing system inertia and growing complexity of system operating conditions. Using a few selected typical operating conditions cannot guarantee system transient stability in all operating conditions, and the time-domain simulation of all operating conditions requires tremendous time and is often infeasible. This paper proposes a more efficient transient stability assessment method based on deep learning. The binary search method is used to determine the critical clearing time (CCT) in creating training databased by time-domain simulation. This method is fast and accurate with 1 ms resolution. The buses whose CCTs are lower than 200 ms are considered critical buses. Buses close to each other are grouped based on their mutual admittance matrix to reduce the search space of the critical buses. This paper also proposes the generator feature normalization based on the physical model. Case study on the reduced 240-bus WECC system model demonstrates that the proposed method can predict CCT accurately and efficiently.

critical clearing time↗

Deep Reinforcement Learning Based HVAC Control for Reducing Carbon Footprint of Buildings

In this paper, we present our work on deep reinforcement learning (DRL) based intelligent control of Heating, Ventilation, and Air Conditioning (HVAC) with the goal of reducing carbon emission. We performed this task using 1) Marginal Operating Emission Rates (MOER), where the objective was to shift the demand to the low emission period of the day and 2) Time-Of-Use (TOU) demand-response price where the objective was to shift the demand to low price period of the day. This was achieved by learning an optimal pre-cooing strategy. We found the carbon emission reduction in the range of 6%-16% depending on the opportunity presented by the MOER signal. Similarly, we observed the carbon emission reduction in the range of 23%-29% during the peak price period when TOU price was used. The results clearly demonstrated the applicability of our approach in reducing the carbon footprint of the building.

carbon emission↗

Transverse spin structure of the nucleon through target single-spin asymmetry in semi-inclusive deep-inelastic (e, e’ $ \pi^{\pm}_{}$ ) reaction at Jefferson Lab

Jefferson Lab (JLab) 12 GeV energy upgrade provides a golden opportunity to perform precision studies of the transverse spin and transverse-momentum-dependent structure in the valence quark region for both the proton and the neutron. In this paper, we focus our discussion on a recently approved experiment on the neutron as an example of the precision studies planned at JLab. The new experiment will perform precision measurements of target Single Spin Asymmetries (SSA) from semi-inclusive electro-production of charged pions from a 40-cm long transversely polarized 3 He target in Deep-Inelastic-Scattering kinematics using 11 and 8.8 GeV electron beams. This new coincidence experiment in Hall A will employ a newly proposed solenoid spectrometer (SoLID). The large acceptance spectrometer and the high polarized luminosity will provide precise 4-D (x, z, P T ​ and Q 2 ) data on the Collins, Sivers, and pretzelocity asymmetries for the neutron through the azimuthal angular dependence. The full 2ππ azimuthal angular coverage in the lab is essential in controlling the systematic uncertainties. The results from this experiment, when combined with the proton Collins asymmetry measurement and the Collins fragmentation function determined from the e + e − collision data, will allow for a quark flavor separation in order to achieve a determination of the tensor charge of the d quark to a 10% accuracy. As a result, the extracted Sivers and pretzelocity asymmetries will provide important information to understand the correlations between the quark orbital angular momentum and the nucleon spin and between the quark spin and nucleon spin.

Parton Distribution Function↗

Enhanced Data Efficiency Using Deep Neural Networks and Gaussian Processes for Aerodynamic Design Optimization

Adjoint-based optimization methods are attractive for aerodynamic shape design primarily due to their computational costs being independent of the dimensionality of the input space and their ability to generate high-fidelity gradients that can then be used in a gradient-based optimizer. This makes them very well suited for high-fidelity simulation based aerodynamic shape optimization of highly parametrized geometries such as aircraft wings. However, the development of adjoint-based solvers involve careful mathematical treatment and their implementation require detailed software development. Furthermore, they can become prohibitively expensive when multiple optimization problems are being solved, each requiring multiple restarts to circumvent local optima. In this work, we propose a machine learning enabled, surrogate-based framework that replaces the expensive adjoint solver, without compromising on predicting predictive accuracy. Specifically, we first train a deep neural network (DNN) from training data generated from evaluating the high-fidelity simulation model on a model-agnostic design of experiments on the geometry shape parameters. The optimum shape may then be computed by using a gradient-based optimizer coupled with the trained DNN. Subsequently, we also perform a gradient-free Bayesian optimization, where the trained DNN is used as the prior mean. We observe that the latter framework (DNN-BO) improves upon the DNN-only based optimization strategy for the same computational cost. Overall, this framework predicts the true optimum with very high accuracy, while requiring far fewer high-fidelity function calls compared to the adjoint-based method. Furthermore, we show that multiple optimization problems can be solved with the same machine learning model with high accuracy, to amortize the offline costs associated with constructing our models. Our methodology finds applications in the early stages of aerospace design. (C) 2021 Published by Elsevier Masson SAS.

Renganathan, S. Ashwin↗