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 703 records · Page 39

Siting considerations for a deep borehole disposal facility - 15403

This paper describes considerations for siting and designing a facility for deep borehole disposal of spent nuclear fuel (SNF) and/or high-level radioactive waste (HLW). Technical considerations include geological, hydrogeochemical, and geophysical characteristics that are related to the suitability of the site for deep drilling and borehole construction, waste emplacement activities, waste isolation (seals and surrounding geology), and long-term safety of the deep borehole disposal system. Logistical factors to be considered include: local or regional availability of drilling contractors (equipment, services, and materials) capable of drilling a large-diameter hole to approximately 5,000 m depth; construction of surface facilities and waste handling and emplacement equipment; legal and regulatory requirements associated with drilling, operation, and post-closure; and access to transportation systems. Social and political considerations include the distance from population centers and the support or opposition of local and state entities and other stakeholders to the facility and its operations. These technical, logistical, and socio-political factors are examined in the context of a consent-based siting process for a deep disposal borehole, which would be the first phase in developing an operating facility. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Panel Session 62: Progress on Deep Repository Programs Around the World

This panel session focused on the progress of deep repository programs, worldwide. While efforts on a deep geological repository for SNF/UNF and HLW in the USA were terminated in 2010, several other repository programs continue to make considerable progress and deserve to be recognized. Panelists were invited from national, multi-national, and international repository programs and organizations to report upon the status and future as well as the perceived reasons underlying the success and the failure of components of their respective repository program. This panel provided a forum for interested parties to present, exchange, and take advantage of, as appropriate, repository progress, challenges, concepts/designs and other lessons learned around the world, including site characterization, site selection, research and development, licensing, construction, operation, and public acceptance and participation. Presentations proposed include: 1 - Cigeo (French Deep Geological Repository Project) update 2018 (Daniel Delort, Andra (France)); 2 - Progress on Deep Geological Repository Programs Around the World (Bruce McKirdy, Radioactive Waste Management (United Kingdom)); 3 - Geological disposal facility in Belgium (Didier Leonard, ONDRAF/NIRAS (Belgium))

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Application of a Deep Learning Network to 3D Modeling of Nuclear Facilities - 19614

The ultimate goal of this study is to minimize (or eliminate) human intervention in the scanning and 3D CAD modeling process in the generation of 3D as-built model of nuclear facilities. This paper describes the application of the state-of-the-art deep learning technology in 3D point cloud data segmentation which is a part of the 3D modeling process. The baseline deep learning network chosen in this study is PointNet. We compare the deep learning approach with a conventional filtering approach, and show the feasibility and potential of deep learning technology. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Applications of data mining technology to enhance O and M: automatic planning of electrical isolation with deep learning - 255

Data mining technology is now readily available, thanks to high powered, low cost computing resource and useful coding tools. We study several applications of data mining to enhance operation and maintenance (O and M), such as abnormality prediction, efficiency diagnosis, document traceability, image recognition, etc. In field support, we try automatic planning of electrical isolation with deep learning. Currently, a skilled engineer plans electrical isolation procedure with hundreds of the circuit diagrams and the related documents, taking man-hours. If this task becomes automatic, it is very efficient. The automatic planning has two issues. One is much calculation time of electrical circuit simulator, searching billions of electrical conducting paths. The other is interpretation of human fuzzy information, such as ease of work. Deep learning is helpful to resolve them. We performed a model case study of the electrical isolation. We applied a deep neural network (DNN) for dropping in the calculation time. We trained the circuit diagrams and the responses of the circuit simulator to the DNN, constructing an efficient path search algorithm in the DNN. The calculation time of the DNN was shorter by a factor of 32 for the model case, compared with that of the electrical circuit simulator. We applied a deep Q-network (DQN) for the interpretation of fuzzy information. The DQN optimized isolation procedure from the viewpoint of the work load with the equipment layout, related doses, and values of wet bulb globe temperature (WBGT) to prevent heatstroke. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Preface to "Insights into the Earth's Deep Lithosphere"

Dear Readers: I am pleased to present a special issue of Tectonophysics entitled 'Insights into the Earth's Deep Lithosphere.' This compilation sought to capture the flavor of the increasing number of studies that are emerging to investigate the complex lithospheric structure of the earth. This issue evolved out of a Fall 2007 AGU special session entitled 'Understanding the Earth's Deep Lithosphere' that I organized with Irina Artemieva from the University of Copenhagen. For that session, we solicited talks that discussed the increasing number of methods that have surfaced to study various aspects of the earth's deep lithosphere. These methods include seismic, gravity, thermal, geochemical, and various combinations of these methods. The quality of the presentations (2 oral sessions with 16 talks and 23 associated poster presentations) was such that we felt that the emerging topic deserved a dedicated forum to address these questions in greater detail. The availability of new data sets has also improved the number and quality of lithospheric studies. With many new studies and methodologies, a better understanding of both continental and oceanic lithospheres is starting to emerge. Questions remain about the thickness and evolution of the lithosphere, the presence of lithospheric keels, the density and anisotropy of lithospheric roots, mechanisms of lithospheric thinning, and differences between mechanical, thermal and chemical boundary layers. While we did not get contributions on the full gamut of methods and regions, a lot of ground was covered in this issue's manuscripts. Like any collection of papers on the deep lithosphere, the topics are quite varied in methodology, geographic location, and what aspect of the lithosphere being studied. Still, the results highlight the rewarding aspects of earth structure, history, and evolution that can be gleaned. A brief synopsis of the papers contained in this issue is given.

58 GEOSCIENCES↗

Deep reinforcement learning assisted co-optimization of Volt-VAR grid service in distribution networks

With the increasing penetration of distributed energy resources in distribution networks, Volt-VAR control and optimization (VVC/VVO) have become very important to ensure an acceptable quality of service to all customers. System operators can rely on slow-responding utility devices, including capacitor banks and on-load tap changing transformers, along with fast-responding battery and photovoltaic (PV) inverters for the VVC/VVO implementation. Because of variations in response time of these two classes of devices, and different control actions (discrete versus continuous), coordinated and optimal scheduling and operation have become of utmost importance. Here, this paper develops a look-ahead deep reinforcement learning (DRL)-based multi-objective VVO technique to improve the voltage profile of active distribution networks, decrease network and inverter power loss, and save the operational cost of the grid. It proposes a deep deterministic policy gradient (DDPG)-based approach to schedule the optimal reactive and/or active power set-points of fast-responding inverters, and a deep Q-network (DQN)-based DRL agent to schedule the discrete decisions variables of slow-responding assets. The reactive power output of PV and battery smart inverters are scheduled at 30-minute intervals and the capacitors’ commitment status is scheduled with several hour intervals. The proposed framework is validated on the modified IEEE 34-bus and 123-bus test cases with embedded PV and PV-plus-storage. To validate the efficacy of the proposed VVO, it is compared with several scenarios, including the base case without VVO, localized droop control of DERs, DDPG-only, and twin delayed DDPG (TD3) agent-based DRL techniques. The results justify the superior performance of the proposed method to improve the voltage profile, reduce network power loss, and minimize the look-ahead grid operational cost while minimizing the undesirable power losses in inverters as a result of power factor adjustments.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

47 OTHER INSTRUMENTATION↗

BUTTER-E - Energy Consumption Data for the BUTTER Empirical Deep Learning Dataset

The BUTTER-E - Energy Consumption Data for the BUTTER Empirical Deep Learning Dataset adds node-level energy consumption data from watt-meters to the primary sweep of the BUTTER - Empirical Deep Learning Dataset. This dataset contains energy consumption and performance data from 63,527 individual experimental runs spanning 30,582 distinct configurations: 13 datasets, 20 sizes (number of trainable parameters), 8 network "shapes", and 14 depths on both CPU and GPU hardware collected using node-level watt-meters. This dataset reveals the complex relationship between dataset size, network structure, and energy use, and highlights the impact of cache effects. BUTTER-E is intended to be joined with the BUTTER dataset (see "BUTTER - Empirical Deep Learning Dataset on OEDI" resource below) which characterizes the performance of 483k distinct fully connected neural networks but does not include energy measurements.

Array↗

SPRUCE Deep Peat Heating (DPH) Environmental Data, February 2014 through July 2015

This data set provides a record of the half-hourly automated environmental data collected for 14 SPRUCE plots (4, 5, 6, 7, 8, 10, 11, 13, 14, 16, 17, 19, 20, and 21) during the Deep Peat Heating (DPH) study. In June 2014, deep soil heating was initiated at 5 warming levels (+0, +2.25, +4.5, +6.75 and +9 °C) with 2 replicate plots per level. Measurements were underway before the initiation of heating treatments and continued through July 27 of 2015 at the transition to whole-ecosystem warming manipulations. The DPH study was undertaken to evaluate possible rapid responses of deep peat carbon (C) stocks, microbial communities, and biogeochemical cycling processes to unprecedented temperatures. Warming levels at depth were achieved over a 25 (+ 2.25 °C) to 60-day (+9 °C) period depending on the target treatment temperatures.

54 ENVIRONMENTAL SCIENCES↗

Physics-guided Deep Learning for Power System State Estimation

In the past decade, dramatic progress has been made in the field of machine learning. This paper explores the possibility of applying deep learning in power system state estimation. Traditionally, physics-based models are used including weighted least square (WLS) or weighted least absolute value (WLAV). These models typically consider a single snapshot of the system without capturing temporal correlations of system states. In this paper, a physics-guided deep learning (PGDL) method is proposed. Specifically, inspired by autoencoders, deep neural networks (DNNs) are used to learn the temporal correlations. The estimated system states from DNNs are then checked against physics laws by running through a set of power flow equations. Hence, the proposed PGDL is both data-driven and physics-guided. The accuracy and robustness of the proposed PGDL method are compared with traditional methods in standard IEEE cases. Simulations show promising results and the applicability is further discussed.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Growth Rate of Deep Convective System Cloud Shields: Satellite Observations and Km-Scale Radiative Convective Equilibrium Simulations

Deep convection gives rise to large upper level clouds that strongly interact with radiation and are important to the climate energy budget. From an object-oriented perspective, these individual deep cloud systems are characterized by a well depicted cloud shield life cycle, starting with small cloud extents that grow at varying rates before decaying and vanishing. A simple formulation of the growth rate of the cloud shield has been proposed that links together the growth rate on the convective part of the cloud, the mass flux of both the convective and stratiform parts of the cluster and a simple removal sink term (Elsaesser et al., 2022). In this presentation we first show using a suite of satellite observations (infrared from geostationary satellites, GPM radar, etc.) that the functional form of the proposed equation is well suited to quantify the shield growth rate. We then focus on RCE simulations, with deep cloud system objects post processed, to explore the relative role of each term of the growth rate budget. Three different models are used in the same RCEMIP-like configurations. The results show that the budget equation works very well for each model, although the time constants require model-dependent adjustments. We will further show in Vienna the commonalities and the specificities of each model.

Deep convection↗

Van Allen Probes Measurements of Energetic Particle Deep Penetration Into the Low L Region (L < 4) During the Storm on 8 April 2016

In this paper, using measurements from the Van Allen Probes, a penetration event of tens to hundreds of keV electrons and tens of keV protons into the low L shells (L < 4) is studied. Timing and magnetic local time (MLT) differences of energetic particle deep penetration are unveiled and underlying physical processes are examined. During this event, both proton and electron penetrations are MLT asymmetric. The observed MLT difference of proton penetration is consistent with convection of plasma sheet protons, suggesting enhanced convection during geomagnetic active times to be the cause of energetic proton deep penetration during this event. The observed MLT difference of tens to hundreds of keV electron penetration is completely different from tens of keV protons and cannot be well explained by inward radial diffusion, convection of plasma sheet electrons, or transport of trapped electrons by enhanced convection electric field represented by the Volland-Stern model or a uniform dawn-dusk electric field model based on the electric field measurements. Finally, it suggests that the underlying physical mechanism responsible for energetic electron deep penetration, which is very important for fully understanding energetic electron dynamics in the low L shells, should be MLT localized.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive Review

Deep neural networks (DNNs) are empirically derived systems that have transformed traditional research methods, and are driving scientific discovery. Here, artificial electromagnetic materials (AEMs)—including electromagnetic metamaterials, photonic crystals, and plasmonics—are research fields where DNN results valorize the data driven approach; especially in cases where conventional methods have failed. In view of the great potential of deep learning for the future of artificial electromagnetic materials research, the status of the field with a focus on recent advances, key limitations, and future directions is reviewed. Strategies, guidance, evaluation, and limits of using deep networks for both forward and inverse AEM problems are presented.

14 SOLAR ENERGY↗

Stabilizing the Deep Sodiation Process in Layered Sodium Manganese Cathodes by Anchoring Boron Ions

Advanced high-energy-density sodium-ion batteries (SIBs) are inseparable from cathode materials with high specific capacities. Layered manganese-rich oxides (Na x MnO 2 , 0.6 ≤ x ≤1) are promising cathode materials owing to their ease of intercalation and extraction of a considerable amount of sodium ions. However, lattice interactions, especially electrostatic repulsive forces and anisotropic stresses, are usually caused by deep desodiatin/sodiation process, resulting in intragranular cracks and capacity degradation in SIBs. Here, boron ions are introduced into the layered structure to build up B-O-Mn bonds. Further, the regulated electronic structure in Na 0.637 B 0.038 MnO 2 (B-NMO) materials inhibits the deformation of MnO 6 octahedra, which finally achieves a gentle structural transition during the deep sodiation process. B-NMO electrode exhibits a high capacity (141 mAh g –1 ) at 1 C with a capacity retention of 81% after 100 cycles. Therefore, anchoring boron to manganese-rich materials inhibits the detrimental structural evolution of deep sodiation and can be used to obtain excellent cathode materials for SIBs.

25 ENERGY STORAGE↗

Unlocking plant-microbial interactions in deep Mollisols in the Midwestern US: Linking depth gradients in roots, microbial activity, and soil carbon in agroecosystems

Deep-rooted plants may build soil carbon (C) stocks, but most research has focused on shallow soils, leaving gaps in our understanding of how shifts in the balance between decomposition and C inputs drive soil C accumulation with depth. Thus, our objectives were to: (1) link depth gradients in root biomass with microbial activity and soil C stocks down to 1 m, and (2) examine the potential of simple C inputs to prime soil C across depths. To this end, we dug 5 quantitative soil pits in Argiudolls under mature perennial miscanthus plots in the SoyFACE Farm (Champaign-Urbana, IL). We added 13 C labeled glucose to our soils to determine the fate of simple C inputs with depth. We found that fine root biomass, total soil C, mineral-associated organic C (MAOC), particulate organic C (POC), and microbial activity (as measured by potential enzyme activity) declined with depth. POC declined more rapidly than MAOC, resulting in an increase in the ratio of MAOC-to-POC. Root biomass, enzyme activity (either acid phosphatase or n-acetyl-glucosaminadase) activity, and microbial respiration explained 74% and 38% of the variability in soil total C and MAOC, respectively, while POC was dependent on root biomass and microbial respiration (47%). Although the incorporation of simple 13 C inputs into MAOC was similar across depths, these inputs led to greater net MAOC losses in shallow soils than in deeper soils between 50 and 100 cm. The divergent impact of simple C inputs across depths may suggest that MAOC in shallow soils is more susceptible to priming losses, while C inputs into deep soils may instead be more persistent. Collectively, our results suggest that depth gradients in soil C stocks represents a balance between inputs, decomposition, and microbial necromass production and that increases in root C inputs by deep-rooted plants may have the potential to build stable MAOC.

60 APPLIED LIFE SCIENCES↗

Deep-learning based artificial intelligence tool for melt pools and defect segmentation

Accelerating fabrication of additively manufactured components with precise microstructures is important for quality and qualification of built parts, as well as for a fundamental understanding of process improvement. Accomplishing this requires fast and robust characterization of melt pool geometries and structural defects in images. This paper proposes a pragmatic approach based on implementation of deep learning models and self-consistent workflow that enable systematic segmentation of defects and melt pools in optical images. Deep learning is based on an image-to-image translation–conditional generative adversarial neural network architecture. An artificial intelligence (AI) tool based on this deep learning model enables fast and incrementally more accurate predictions of the prevalent geometric features, including melt pool boundaries and printing-induced structural defects. We present statistical analysis of geometric features that is enabled by the AI tool, showing strong spatial correlation of defects and the melt pool boundaries. The correlations of widths and heights of melt pools with dataset processing parameters show the highest sensitivity to thermal influences resulting from laser passes in adjacent and subsequent layer passes. The presented models and tools are demonstrated on the aluminum alloy and datasets produced with different sets of processing parameters. However, they have universal quality and could easily be adapted to different material compositions. The method can be easily generalized to microstructural characterizations other than optical microscopy.

additive manufacturing↗

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗

Seismic signal augmentation to improve generalization of deep neural networks

Deep learning has emerged as an effective approach for seismic data processing in general, and for earthquake monitoring in particular. The ability of deep learning models to generalize beyond the training and validation data is important for comprehensive earthquake monitoring; this ability furthermore depends on the availability of a sufficiently large and complete training dataset. However, this requirement can prove challenging to meet due to significant effort and time for data collection and labeling. Data augmentation provides an efficient and effective approach for increasing the dimension of training samples and improving generalization to unseen samples. In this paper, we present augmentation methods appropriate for seismic waveforms and demonstrate their ability to reduce bias and increase performance. Furthermore, these augmentation methods can be applied to a wide range of deep learning applications designed for seismic data.

58 GEOSCIENCES↗