Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Architecture patterns”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Surface Stress Characterization and Trends in Thermally Strengthened Photovoltaic Module Glass

Simultaneous changes in photovoltaic (PV) module architecture-such as increased area, replacing the polymeric backsheet with a glass backsheet, and reducing glass thickness from 3.2 to 2.0 mm-have resulted in a novel failure called spontaneous glass breakage. Spontaneous glass breakage results in front and/or rear glass failure without any obvious cause. The resulting low-energy fracture patterns have raised concerns about the thermal strengthening in 2.0-mm glass. We present validation of a nondestructive method for measuring the glass surface stress in PV modules. We use a scattered light polariscope to examine the glass properties of 11 modules from 6 solar fields, with and without spontaneous glass breakage. Based on a Mann-Whitney test p-value of 1.4 x 10-6, we conclude that there is a correlation between lower surface stress and susceptibility to spontaneous breakage. A Kendall's Tau test p-value of 2.0 x 10-4 indicates a correlation between increased module area and lower surface stress. We find that 2.0-mm glass can be, and often is, fully tempered (surface stress ≥69 MPa), but inspecting the fracture pattern is not a reliable way to assess the amount of thermal strengthening. A combination of factors, not just surface stress, influences glass breakage.

14 SOLAR ENERGY↗
DOE OSTI2024

NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements

Multiphysics problems that are characterized by complex interactions among fluid dynamics, heat transfer, structural mechanics, and electromagnetics, are inherently challenging due to their coupled nature. While experimental data on certain state variables may be available, integrating these data with numerical solvers remains a significant challenge. Physics-informed neural networks (PINNs) have shown promising results in various engineering disciplines, particularly in handling noisy data and solving inverse problems in partial differential equations (PDEs). However, their effectiveness in forecasting nonlinear phenomena in multiphysics regimes, particularly involving turbulence, is yet to be fully established. Here, this study introduces NeuroSEM, a hybrid framework integrating PINNs with the highfidelity Spectral Element Method (SEM) solver, Nektar++. NeuroSEM leverages the strengths of both PINNs and SEM, providing robust solutions for multiphysics problems. PINNs are trained to assimilate data and model physical phenomena in specific subdomains, which are then integrated into the Nektar++ solver. We demonstrate the efficiency and accuracy of NeuroSEM for thermal convection in cavity flow and flow past a cylinder. The framework effectively handles data assimilation by addressing those subdomains and state variables where the data is available. We applied NeuroSEM to the Rayleigh-B´enard convection system, including cases with missing thermal boundary conditions and noisy datasets. Finally, we applied the proposed NeuroSEM framework to real particle image velocimetry (PIV) data to capture flow patterns characterized by horseshoe vortical structures. Our results indicate that NeuroSEM accurately models the physical phenomena and assimilates the data within the specified subdomains. The framework’s plug-and-play nature facilitates its extension to other multiphysics or multiscale problems. Furthermore, NeuroSEM is optimized for efficient execution on emerging integrated GPU-CPU architectures. This hybrid approach enhances the accuracy and efficiency of simulations, making it a powerful tool for tackling complex engineering challenges in various scientific domains.

42 ENGINEERING↗
DOE OSTI2022

Developing a Chemical and Structural Understanding of the Surface Oxide in a Niobium Superconducting Qubit

We report superconducting thin films of niobium have been extensively employed in transmon qubit architectures. Although these architectures have demonstrated remarkable improvements in recent years, further improvements in performance through materials engineering will aid in large-scale deployment. Here, we use information retrieved from secondary ion mass spectrometry and electron microscopy to conduct a detailed assessment of the surface oxide that forms in ambient conditions for transmon test qubit devices patterned from a niobium film. We observe that this oxide exhibits a varying stoichiometry with NbO and NbO 2 found closer to the niobium film and Nb 2 O 5 found closer to the surface. In terms of structural analysis, we find that the Nb 2 O 5 region is semicrystalline in nature and exhibits randomly oriented grains on the order of 1-2 nm corresponding to monoclinic N-Nb 2 O 5 that are dispersed throughout an amorphous matrix. Using fluctuation electron microscopy, we are able to map the relative crystallinity in the Nb 2 O 5 region with nanometer spatial resolution. Through this correlative method, we observe that amorphous regions are more likely to contain oxygen vacancies and exhibit weaker bonds between the niobium and oxygen atoms. Based on these findings, we expect that oxygen vacancies likely serve as a decoherence mechanism in quantum systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Pin-pointing Node Failures in HPC Systems

Automated fault prediction and diagnosis in HPC systems needs to be efficient for better system resilience. With increasing scalability required for exascale, accurate fault prediction aiding in quick remedy is hard. With changing supercomputer architectures, distilling fault data from the noisy raw logs requires substantial efforts. Predicting node failures in such voluminous system logs is challenging. To this end, we investigate an interesting way to pin-point node failures in such supercomputing systems. Our study on Cray system data with automated machine learning tools suggests that specific patterns of event messages on node unavailability can be indicator to node failures. This data extraction coupled with system and job data correlation helps in devising a methodology to predict node failures and their location over a specific time frame. This work aims to enable broader applicability for a generic fault prediction framework.

Roman, E↗
DOE OSTI2023

Building the I (Interoperability) of FAIR for performance reproducibility of large-scale composable workflows in RECUP

Abstract-Scientific computing communities increasingly run their experiments using complex data- and compute-intensive workflows that utilize distributed and heterogeneous architectures targeting numerical simulations and machine learning, often executed on the Department of Energy Leadership Computing Facilities (LCFs). We argue that a principled, systematic approach to implementing FAIR principles at scale, including fine-grained metadata extraction and organization, can help with the numerous challenges to performance reproducibility posed by such workflows. We extract workflow patterns, propose a set of tools to manage the entire life cycle of performance metadata, and aggregate them in an HPC-ready framework for reproducibility (RECUP). We describe the challenges in making these tools interoperable, preliminary work, and lessons learned from this experiment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Root lateral interactions drive water uptake patterns under water limitation

The plasticity of root water uptake determines the maintenance of transpiration during periods of water limitation and drought. However, the mechanistic basis of plant water uptake, as well as the implications of water uptake strategies at the individual and ecosystem scale remain elusive. We model three-dimensional root water uptake under variably saturated conditions for a one-hectare temperate forest plot for a growing season with a pronounced mid-season dry period. Variations in root architecture, hydraulic properties, and degree of lateral interaction between root systems produce divergent local responses to water limitation and provide insights on individual and community response to meteorological conditions. Results demonstrate the plasticity of ecosystem-scale responses to surface drying, where interacting roots shift regions of active uptake to deeper soil layers with less abundant root biomass. These shifts, a product of both root system and soil hydraulic properties, illustrate intimate links between root and soil hydraulics in determining plant water sourcing. Furthermore, we demonstrate that root lateral interactions are beneficial at the ecosystem-scale, even when trees compete for water. Specifically, a more spatially extensive root system facilitates access to a larger soil water reservoir, often ameliorating water limitation and reducing sharp water potential gradients. While the reduction of water stress is a benefit, it can be offset by increased root construction and maintenance costs associated with the larger rooting system. A plausible “viability” region of root communal co-existence is therefore implied where competitive pressures and root production costs are balanced by a potential water benefit.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Recurrent neural networks for short-term and long-term prediction of geothermal reservoirs

Accurate prediction of geothermal reservoir responses to alternative energy production scenarios is critical for optimizing the development of the underlying resources. While the conventional physics-based models offer a comprehensive prediction tool, data-driven models provide an efficient alternative to build fit-for-purpose predictive models by extracting and using the statistical patterns in the collected data to make predictions. The recurrent neural network (RNN) is a data-driven model that is commonly applied to predict time series sequences. This paper presents a variant of RNN that also utilizes the efficiency of convolutional neural networks (CNN) for the prediction of energy production from geothermal reservoirs. Specifically, a CNN–RNN architecture is developed that takes historical well controls as input (features) and their corresponding production response data as output (labels) to learn an input-output mapping that can predict the future well production responses/performance for any given future well control inputs. The model is paired with a labeling scheme to handle real field disturbances that create data gaps. In addition to the model structure, we introduce a thorough workflow for applying the model, which includes data pre-processing, feature selection, as well as different training strategies for short-term and long-term prediction. Finally, the performance and accuracy of the model are evaluated by applying it to multiple datasets, including a field reservoir model.

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

Verification of Triso Fuel Burnup Using Machine Learning Algorithms

Pebble Bed Reactors are fueled with fuel pebbles that are circulated multiple times through the reactor vessel before discharge. During the normal operation of a PBR, ejected pebbles are returned to the reactor or discharged depending on the fuel burnup and physical condition of the pebbles. The burnup measurement is usually based on detected radiation signatures of fission products accumulated in the pebble fuel over burnup. Previous research has shown that height of photopeaks of fission products, such as 134 Cs, 137 Cs, 154 Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values. We propose to use machine learning (ML) method to interpret gamma-ray spectra and predict the burnup values of the pebbles. ML has achieved widespread success and adoption across a few domains that require pattern recognition and analysis in varied data types. In this work, we apply three proven ML approaches - multilayer perceptrons, convolutional neural networks, and transformers - to the task of predicting fuel burnup from measured gamma spectra, and compile a dataset of simulated spectra for training and validation of the ML models. In this paper, we will discuss the network architecture of these three ML approaches and compare the performance of the simplest of these (MLP) to a standard linear regression.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

VERIFICATION OF TRISO FUEL BURNUP USING MACHINE LEARNING ALGORITHMS

Pebble Bed Reactors are fueled with fuel pebbles that are circulated multiple times through the reactor vessel before discharge. During the normal operation of a PBR, ejected pebbles are returned to the reactor or discharged depending on the fuel burnup and physical condition of the pebbles. The burnup measurement is usually based on detected radiation signatures of fission products accumulated in the pebble fuel over burnup. Previous research has shown that height of photopeaks of fission products, such as 134Cs, 137Cs, 154Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values. We propose to use machine learning (ML) method to interpret gamma-ray spectra and predict the burnup values of the pebbles. ML has achieved widespread success and adoption across a few domains that require pattern recognition and analysis in varied data types. In this work, we apply three proven ML approaches - multilayer perceptrons, convolutional neural networks, and transformers - to the task of predicting fuel burnup from measured gamma spectra, and compile a dataset of simulated spectra for training and validation of the ML models. In this paper, we will discuss the network architecture of these three ML approaches and compare the performance of the simplest of these (MLP) to a standard linear regression.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2020

AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing

The recent development of deep learning has been mostly focusing on Euclidean data, such as images, videos, audios, etc. However, most real-world information and relation are often expressed as graphs. To efficiently learn from graph data, graph convolutional networks (GCNs) emerge as a promising approach, showing advantages in several practical applications such as social network analysis, knowledge discovery, 3D modeling, motion capturing, etc. Real-world graphs are usually extremely large and imbalanced, posting significant performance demand and design challenges on the hardware dedicated for GCN inference. In this paper, we propose an architecture design called UW-GCN to accelerate graph convolutional network inference. To tackle the major performance bottleneck from workload imbalance, we propose dynamic neighborhood stealing and remote chunk shuffling techniques, relying on hardware flexibility to achieve hardware auto-tuning under negligible area or delay overhead. Specifically, UW-GCN is able to smartly profile the sparse graph pattern while continuously adjusting the workload distribution via routing reconfiguration among parallel processing elements (PEs). The ideal configuration is then reused in the remaining iterations. To the best of our knowledge, this is the first accelerator design particularly for GCN and the first work relying on hardware auto-tuning, which is normally based on software, to achieve near-optimal workload balance in processing sparse structures.

Geng, Tong↗
DOE OSTI2024

Cohesive phase-field chemo-mechanical simulations of inter- and trans- granular fractures in polycrystalline NMC cathodes via image-based 3D reconstruction

The optimal design and durable utilization of lithium-ion batteries necessitates an objective modeling approach to understand fracture and failure mechanisms. This paper presents a comprehensive chemo-mechanical modeling study focused on elucidating fracture-induced damage and degradation phenomena in the polycrystalline Li $\mathcal{x}$ Ni 0.5 Mn 0.3 Co 0.2 O 2 (NMC532) cathode. An innovative approach that utilizes image-based reconstructed 3D geometry as finite element (FE) mesh input is employed to enhance the precision in capturing the convoluted architecture and morphological features. For accurately representing the intricate crack configurations within the polycrystalline system, we adopted the cohesive phase-field fracture (CPF) model. Through the integration of advanced image-based geometry reconstruction technique and the promising CPF modeling approach, lithium (de)intercalation induced crack evolution (e.g., nucleation, propagation, branching and diverse modes including inter-/trans-(intra-) granular patterns) and the resulting chemical degradation can be precisely captured, which is also compared and validated with numerical predictions using a continuum damage model. In particular, this model predicts fracture induced degradation under varying fracture properties of grain boundaries and charging rates; the conclusion that NMC particles comprised of larger grains are predicted to have less degradation than those with smaller grains can also be drawn. This comprehensive analysis provides valuable insights into the fracture and degradation within polycrystalline NMC cathodes.

25 ENERGY STORAGE↗
DOE OSTI2025

Variational AutoEncoders Reveal Intensifying GPP Extremes in Continental United States based on CESM2 Simulations

Climate extremes significantly impact terrestrial carbon cycle dynamics, necessitating robust methods for detecting and analyzing anomalous behavior in plant productivity. This study presents a novel application of variational autoencoders (VAE) for identifying extreme events in gross primary productivity (GPP) from Community Earth System Model version 2 simulations across four AR6 regions in the Continental United States. We compare VAE-based anomaly detection with traditional singular spectral analysis (SSA) methods across three time periods: 1850-80, 1950-80, and 2050-80 under SSP5-8.5 scenario. The VAE architecture employs three dense layers and a latent space with input sequence length of 12 months, training on normalized GPP time series to reconstruct the GPP and identify anomalies based on reconstruction errors. Extreme events are defined using 5th percentile thresholds applied to both VAE and SSA anomalies. Results demonstrate strong regional agreement between VAE and SSA methods in spatial patterns of extreme event frequencies, despite VAE consistently producing higher threshold values (179-756 GgC for VAE vs. 100-784 GgC for SSA across regions and periods). Both methods reveal increasing magnitudes and frequencies of negative carbon cycle extremes toward 2050-80, particularly in Western and Central North America. The VAE approach shows comparable performance to established SSA techniques while offering computational advantages and enhanced capability for capturing non-linear temporal dependencies in carbon cycle variability. This research demonstrates the potential of deep learning approaches for extremes detection and provides a foundation for improved understanding of future carbon cycle risks under future conditions.

Sharma, Bharat [ORNL] (ORCID:0000000266982487)↗
DOE OSTI2022

Mass transport limitations in polymer electrolyte water electrolyzers using spatially-resolved current measurement

Here this work utilizes spatially-resolved current measurements to provide insight into mass transport limitations in electrolyzers that are not observable from traditional polarization measurement. In this study, two types of flow-fields (parallel and triple-serpentine) and two types of diffusion media (patterned porous thin titanium foil LGDLs and Ir-coated titanium felt PTLs) were examined. A non-uniform current distribution dominated by mass transport limitations was observed to be instigated by the restriction of liquid water transport to catalyst sites. Additionally, conditions are revealed which yield similar polarization performance but dissimilar current distributions. In such cases, the transport limitations for different architectures and porous media affect polarization in different regions of the active area. Furthermore, the triple-serpentine flow-field used in this study performs better than the parallel flow-field under mass transport limited operating conditions. This indicates that the parallel flow-field used in this study is more susceptible to starvation than the triple-serpentine flow-field for the electrolyzer studied.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Interpreting Transformers for Jet Tagging

Machine learning (ML) algorithms, particularly attention-based transformer models, have become indispensable for analyzing the vast data generated by particle physics experiments like ATLAS and CMS at the CERN LHC. Particle Transformer (ParT), a state-of-the-art model, leverages particle-level attention to improve jet-tagging tasks, which are critical for identifying particles resulting from proton collisions. This study focuses on interpreting ParT by analyzing attention heat maps and particle-pair correlations on the $\eta$-$\phi$ plane, revealing a binary attention pattern where each particle attends to at most one other particle. At the same time, we observe that ParT shows varying focus on important particles and subjets depending on decay, indicating that the model learns traditional jet substructure observables. These insights enhance our understanding of the model's internal workings and learning process, offering potential avenues for improving the efficiency of transformer architectures in future high-energy physics applications.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records

Objective: Physicians and clinicians rely on data contained in electronic health records (EHRs), as recorded by health information technology (HIT), to make informed decisions about their patients. The reliability of HIT systems in this regard is critical to patient safety. Consequently, better tools are needed to monitor the performance of HIT systems for potential hazards that could compromise the collected EHRs, which in turn could affect patient safety. In this paper, we propose a new framework for detecting anomalies in EHRs using sequence of clinical events. This new framework, EHR-Bidirectional Encoder Representations from Transformers (BERT), is motivated by the gaps in the existing deep-learning related methods, including high false negatives, sub-optimal accuracy, higher computational cost, and the risk of information loss. EHR-BERT is an innovative framework rooted in the BERT architecture, meticulously tailored to navigate the hurdles in the contemporary BERT method; thus, enhancing anomaly detection in EHRs for healthcare applications.Methods: The EHR-BERT framework was designed using the Sequential Masked Token Prediction (SMTP) method. This approach treats EHRs as natural language sentences and iteratively masks input tokens during both training and prediction stages. This method facilitates the learning of EHR sequence patterns in both directions for each event and identifies anomalies based on deviations from the normal execution models trained on EHR sequences.Results: Extensive experiments on large EHR datasets across various medical domains demonstrate that EHR-BERT markedly improves upon existing models. It significantly reduces the number of false positives and enhances the detection rate, thus bolstering the reliability of anomaly detection in electronic health records. This improvement is attributed to the model’s ability to minimize information loss and maximize data utilization effectively.Conclusion: EHR-BERT showcases immense potential in decreasing medical errors related to anomalous clinical events, positioning itself as an indispensable asset for enhancing patient safety and the overall standard of healthcare services. The framework effectively overcomes the drawbacks of earlier models, making it a promising solution for healthcare professionals to ensure the reliability and quality of health data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Root anatomy helps to reconcile observed root trait syndromes in tropical tree species

Premise Studying the organization of functional traits in plant leaves and stems has revealed notable patterns linking function and form; however, evidence of similarly robust organization in root tissues remains controversial. We posit that anatomical traits in roots can provide insight on the overall organization of the root system. We hypothesized that size variation in the tissue outside the stele is related in a nonlinear fashion with functional traits associated with direct resource uptake, including a negative relationship with root architectural traits, and that similar relationships detected in tropical areas also hold true in other biomes. Methods We addressed our hypotheses using empirical data from 24 tropical tree species in French Guiana, including anatomical measurements in first order roots and functional trait description for the entire fine root system. In addition, we compiled a global meta‐analysis of root traits for 500+ forest species across tropical, subtropical, and temperate forests. Results Our results supported the expected nonlinear relationships between cortical size and morphological traits and a negative linear trend with architectural traits. We confirmed a global negative relationship among specific root length (SRL), diameter, and tissue density, suggesting similar anatomical constraints in root systems across woody plants. However, the importance of factors varies across biomes, possibly related to the unequal phylogenetic representation across latitudes. Conclusions Our findings imply that the rhizocentric hypothesis can be a valuable approach to understand fine root trait syndromes and the evolution of absorptive roots in vascular plants.

Valverde‐Barrantes, Oscar J.↗
DOE OSTI2026

Recurrent convolutional neural networks for modeling nonadiabatic dynamics of quantum-classical systems

Recurrent neural networks (RNNs) have recently been extensively applied to model the time evolution in fluid dynamics, weather predictions, and even chaotic systems due to their ability to capture temporal dependencies and sequential patterns in data. Here we present an RNN model based on convolutional neural networks for modeling the nonlinear nonadiabatic dynamics of hybrid quantum-classical systems. The dynamical evolution of the hybrid systems is governed by equations of motion for classical degrees of freedom and von Neumann equation for electrons. The Physics-Aware Recurrent Convolution (PARC) neural network structure incorporates a differentiator-integrator architecture that inductively models the spatiotemporal dynamics of generic physical systems. Here, we apply our RNN approach to learn the space-time evolution of a one-dimensional semiclassical Holstein model after an interaction quench. For shallow quenches (small changes in electron-lattice coupling), the deterministic dynamics can be accurately captured using a single-CNN-based recurrent network. In contrast, deep quenches induce chaotic evolution, making long-term trajectory prediction significantly more challenging. Nonetheless, we demonstrate that the PARC-CNN architecture can effectively learn the statistical climate of the Holstein model under deep-quench conditions.

Holstein model↗
DOE OSTI2021

Bedrock architecture, soil texture, and hyporheic zone characterization combining electrical resistivity and induced polarization imaging

The shallow (<15 m depth) subsurface environment of a short reach along a bedrock stream was investigated with electrical resistivity and induced polarization (IP) to map details of bedrock and soil sediments. The bedrock is mostly comprised of limestone, and is generally resistive compared to the overlying soil. The soil-bedrock interface was determined through a trial and error approach using a sharp boundary feature in the inversion model. The inferred bedrock surface determined from the inversions exhibited undulating patterns with troughs and ridges. A near continuous trough ran alongside the stream within the floodplain, and is suggestive of a paleochannel among other interpretations of this feature. The structure of the electrical resistivity above the bedrock showed small-scale elongated features. The chargeability from the IP method showed larger scale features. High values of chargeability were associated with the sediments in the floodplain, and low values were associated with bedrock, stream, and soil on the elevated banks above the stream. If the chargeability is associated with membrane polarization characteristic of clayey soils, then IP seems to highlight the mere existence of clay, while the resistivity may be more discernable of the relative proportion of clay. Vegetation differences may also explain the chargeability distribution, where parts of the survey with high chargeability had dense pine with no understory making the soils more organically rich.

54 ENVIRONMENTAL SCIENCES↗