Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “temporal computing”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

CSB-RNN: A Faster-Than-Realtime RNN Acceleration Framework with Compressed Structured Blocks

Recurrent Neural Networks (RNN) is widely applied to temporal sequence analysis, where real-time performance is usually in demand. However, RNN suffers a heavy computational workload as the model comes with a large weight matrix. To alleviate the pain, model compression (pruning) schemes have been proposed for RNN that pruning the redundant (near-zero) weight-values. On the one hand, the non-structured pruning methods achieve a considerable pruning rate while bringing the computational irregularity, which is un-friendly to parallel-hardware. On the other hand, the existing structured pruning methods consider the hardware parallelism; However, they suffer a poor pruning rate due to the restrict constraints on pruning structure. This paper presents CSB-RNN, an optimized full-stack RNN framework with the novel compressed structured block (CSB) technique. The CSB-pruned RNN model comes with both fine-granularity that benefits the pruning rate and regular structure that facilitates the hardware-parallelism. Further, we propose a novel hardware architecture for inferencing the CSB-pruned model. Different from conventional parallel hardware, this architecture solves the block-workload imbalance issue and achieves an over 95% hardware utilization. With the experiments on 10 RNN models in 5 application domains, the CSB-RNN realizes 7×-20× lossless compression and up to 50× acceptable lossy-compression, which is 2×-7× to the prior art. With the addition of the novel hardware, the compressed-RNN inference reaches a super real-time latency of 10-400µs with FPGA implementation.

Shi, Runbin↗
DOE OSTI2023

TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers

Dynamic graph embedding has emerged as a very effective technique for addressing diverse temporal graph analytic tasks (i.e., link prediction, node classification, recommender systems, anomaly detection, and graph generation) in various applications. Such temporal graphs exhibit heterogeneous transient dynamics, varying time intervals, and highly evolving node features throughout their evolution. Hence, incorporating long-range dependencies from the historical graph context plays a crucial role in accurately learning their temporal dynamics. In this paper, we develop a graph embedding model with uncertainty quantification, TransformerG2G, by exploiting the advanced transformer encoder to first learn intermediate node representations from its current state (t) and previous context (over timestamps [t–1,t–l], l is the length of context). Moreover, we employ two projection layers to generate lower-dimensional multivariate Gaussian distributions as each node's latent embedding at timestamp t. We consider diverse benchmarks with varying levels of "novelty" as measured by the TEA (Temporal Edge Appearance) plots. Here, our experiments demonstrate that the proposed TransformerG2G model outperforms conventional multi-step methods and our prior work (DynG2G) in terms of both link prediction accuracy and computational efficiency, especially for high degree of novelty. Furthermore, the learned time-dependent attention weights across multiple graph snapshots reveal the development of an automatic adaptive time stepping enabled by the transformer. Importantly, by examining the attention weights, we can uncover temporal dependencies, identify influential elements, and gain insights into the complex interactions within the graph structure. For example, we identified a strong correlation between attention weights and node degree at the various stages of the graph topology evolution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Advanced modeling and simulation of research reactors using dynamic mode decomposition

Full text of publication follows. Due to the ever-increasing safety requirements, the current trend of nuclear reactor analysis is shifting towards high-fidelity multi-physics models, which have a very high computational cost and modelling complexity. As the cost of even a single model run makes it impossible to analyse the behaviour and performance of these models on large-scale commercial plants, it has become even more significant to provide suitable benchmarks to validate and test them extensively. In this sense, research reactors offer a promising solution for the initial validation of high-fidelity models, as they are significantly smaller than commercial reactors and their characteristics are well known. In particular, the reactors of the TRIGA family have been used to assess and validate models and methods for Generation-IV designs, as they have some similar features (such as the dominance of natural convection as cooling mechanism and the difficulties in performing sub-channel analysis using standard codes). Still, the computational requirements of high-fidelity models make them unsuitable for real-time analysis, even following their assessment on research reactors. In this sense, Model Order Reduction (MOR) techniques give an additional strategy to reduce the computational cost of high-fidelity models (whilst preserving sufficient accuracy). In particular, this work focuses on Dynamic Mode Decomposition (DMD), a non-intrusive MOR technique that aims at representing models with explicit temporal dynamics by extracting the time-varying characteristics and the governing structures based only on a set of available data, thus without needing any underlying knowledge of the governing equations. In addition, DMD also computes a low-dimensional surrogate of the dynamic matrix of the system, making it suited for stability analysis and real-time evaluations. This work focuses on the application and validation of the DMD method on the Computational Fluid-Dynamics (CFD) model TRIGA Mark II reactor, also discussing in detail the potentiality of this algorithm as an advanced modelling tool for nuclear reactor analysis. (author)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2019

Real time time-dependent density functional theory using higher order finite-element methods

We present a computationally efficient approach to solve the time-dependent Kohn-Sham equations in real time using higher order finite-element spatial discretization, applicable to both pseudopotential and all-electron calculations. To this end, we develop an a priori mesh adaption technique, based on the semidiscrete (discrete in space but continuous in time) error estimate on the time-dependent Kohn-Sham orbitals, to construct an efficient finite-element discretization. Subsequently, we obtain the full-discrete error estimate to guide our choice of the time step. We employ spectral finite elements along with special reduced order quadrature to render the overlap matrix diagonal, thereby simplifying the inversion of the overlap matrix that features in the evaluation of the discrete time-evolution operator. We use the second-order Magnus operator as the time-evolution operator, wherein the action of the discrete Magnus operator, expressed as exponential of a matrix, on the Kohn-Sham orbitals is obtained efficiently through an adaptive Lanczos iteration. We observe close to optimal rates of convergence of the dipole moment with respect to spatial and temporal discretization, for both pseudopotential and all-electron calculations. We demonstrate a staggering 100-fold reduction in the computational time afforded by higher order finite elements over linear finite elements, for both pseudopotential and all-electron calculations. Further, for similar level of accuracy, we obtain significant computational savings by our approach as compared to state-of-the-art finite-difference methods. Here, we also demonstrate the competence of higher order finite elements for all-electron benchmark systems. Lastly, we observe good parallel scalability of the proposed method on many hundreds of processors.

36 MATERIALS SCIENCE↗
DOE OSTI2017

Physics Verification Overview

The purpose of the verification project is to establish, through rigorous convergence analysis, that each ASC computational physics code correctly implements a set of physics models and algorithms (code verification); Evaluate and analyze the uncertainties of code outputs associated with the choice of temporal and spatial discretization (solution or calculation verification); and Develop and maintain the capability to expand and update these analyses on demand. This presentation describes project milestones.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

The Acoustic Emission signal acquired by the microphones placed in the CABRI test device along the fourteen last R.I.A. experiments: an example of reproducible research in nuclear science

The CABRI facility is an experimental nuclear reactor of the French Atomic Energy Commission. It is located at the Cadarache Research Centre in southern France and it is designed to act as a support to the French nuclear infrastructure. The purpose of the new testing programme termed, 'CABRI International Programme' (CIP) is to study the behaviour of PWR-type fuel rods at high burnup, equipped with an 'advanced' cladding, under Reactivity Initiated Accident (RIA) conditions (such as the scenario of a control rod ejection). Within the framework of this programme, piloted and funded by the French Institute of Nuclear Radioprotection and Safety (IRSN), ten tests are to be conducted with a frequency of two tests per year. The LPRE laboratory of the CEA which is in charge of the Preparation, realisation and breakdown of the test results studies the possibility to set up a new test analysis based on the processing of signals coming from sensors placed within the test equipment. During the experimental phase, the behaviour of the fuel element generates acoustic waves which can be detected by two microphones placed upstream and downstream of the test device. Studies showed the interest to realize temporal and spectral analyses on these signals by showing the existence of signatures which can be correlated with physical phenomena as the rod failure or the test shutdown (i.e. scram). The work presented in this article results from the will to consolidate these studies. Since the main phenomenon to be tracked is the fuel rod failure, the aim would be to highlight specific events which would have been precursors of the rod failure in order to use in the future these signals for further interpretation. Such an antecedent works resumption leads to a better understanding of the experimental needs and constitutes a good initial state to prepare the new very fast digital data acquisition systems. Although all the raw data are accessible in the form of text files, analyses and graphics representations were not straightforward to reproduce from the ancient studies since that, on one hand, people who were in charge of the original work left the laboratory and on the other hand because it is not easy when the time passes, even with our own work, to be able to remember the steps of data manipulations and the exact setup: - During the ancient experiments the use of analog data acquisition systems required to digitize tapes to be able to realize computer treatments. That had had for consequence to lose the initial dating. This one must be correctly edited to do temporal comparisons. - Analyses require functions for calculations whose parameters has to be well-known to reach the same results. We thus wished to manage our workflow in the idea that it can be easily reproducible on all the experiments. The object of the work presented in this article was to put in practice this strong bind between the data, treatments and generation of the document in order not to hesitate to do the iteration principle in action. We do not have to be afraid by the data driven analyses. According to the philosophy of the literate programming, the text of the technical document is woven with the computer code that produces all the printed output as tables, graphs for the study eliminating hence the unrealistic cut and paste. This difficulty is not specific to the nuclear domain. For many years, researchers have been worked out solutions to this mundane issue. And, presently, new technologies and high-level programming languages offer us actual answers. We will firstly present the tools applied in our laboratory to implement this workflow, then we will describe the global perception carried out to continue the study of the Acoustic Emission signals recorded by the two microphones during the fourteen last CABRI R.I.A. test.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2024

Nonsteady Load Responses of Wind Turbines to Atmospheric and Mountain-Generated Turbulence Eddies, With Impacts on the Main Bearing: A Validation Study

Previous computational and field experiments identify three characteristic time scales in the aerodynamic responses of utility-scale wind turbine loads to atmospheric boundary layer (ABL) turbulence: a 30-90 second time scale for the passage of high/low speed "streaks" through the rotor plane, the blade and rotor rotation time scales (approximately 1 to 5 seconds), and a sub-second time scale created by blade rotation through gradients within eddy coherent structure. In the current study we compare aerodynamic load responses from daytime ABL turbulence quantified with large-eddy simulation and a actuator line model of the NREL 5 MW wind turbine with analysis of field data from the NREL/GE 1.5 MW wind turbine 5 kilometers east of the Rocky Mountain Front Range in Colorado. In addition, we contrast the responses to the passage of the mountain-generated eddies embedded within the westerly winds with the ABL eddies embedded within northerly/southerly winds. These analyses are in context with the nonsteady forcing of the main bearing by the aerodynamic generation of nontorque bending moments on the main shaft. Potentially relevant to main bearing failure mechanisms, both computational and field data show that the magnitudes of turbulence-generated nontorque bending moments, that we show generate nonsteady force on the main bearing, are of order, and often larger than, torque (which underlies power). However, the temporal variations in these two responses are uncorrelated, implying that the aerodynamic mechanisms that drive power and main bearing response are fundamentally different. We find this to be the case in the field with both mountain-generated eddies (westerly winds) and ABL-generated eddies (northerly/southerly winds). Whereas the time and length scales are comparable, the mountain eddies were somewhat more energetic than the northerly/southerly ABL eddies. Interestingly, however, the fluctuations in nontorque bending moment that force the main bearing were found to be stronger when forced by the ABL eddies than the mountain eddies. The field studies validate the key results from the computational study and show even stronger response in the nontorque bending moment than in the computer simulations. In all cases, the torque and nontorque bending moments are temporally uncorrelated, torque and power are driven by time variations in rotor-averaged horizontal wind velocity and nontorque bending moments are driven by time changes in the degree of nonuniformity in the distribution of velocity over the rotor plane. Thus the results generalize the mechanisms underlying nonsteady aerodynamic forcing to classes of turbulence eddy types with strength of order or stronger than ABL eddies with transverse scale of order the wind turbine rotor. These include atmospheric turbulence eddies, topography-generated turbulence eddies and, by extension, impacts of turbine-wake-scale turbulence eddies on downstream wind turbine rotors.

17 WIND ENERGY↗
DOE OSTI2015

Progress in fast, accurate multi-scale climate simulations

We present a survey of physical and computational techniques that have the potential to contribute to the next generation of high-fidelity, multi-scale climate simulations. Examples of the climate science problems that can be investigated with more depth with these computational improvements include the capture of remote forcings of localized hydrological extreme events, an accurate representation of cloud features over a range of spatial and temporal scales, and parallel, large ensembles of simulations to more effectively explore model sensitivities and uncertainties. Numerical techniques, such as adaptive mesh refinement, implicit time integration, and separate treatment of fast physical time scales are enabling improved accuracy and fidelity in simulation of dynamics and allowing more complete representations of climate features at the global scale. At the same time, partnerships with computer science teams have focused on taking advantage of evolving computer architectures such as many-core processors and GPUs. As a result, approaches which were previously considered prohibitively costly have become both more efficient and scalable. In combination, progress in these three critical areas is poised to transform climate modeling in the coming decades.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Hybrid learning techniques for scientific data reduction with performance guarantees

The research initiatives supported by the U.S. Department of Energy (DOE) Grant DE-SC0022265 are fundamentally aimed at pioneering advanced machine learning (ML) techniques for scientific data compression within high-performance computing (HPC) environments. This comprehensive body of work addresses the critical challenge posed by the exponential growth of data generated by scientific simulations in domains such as fusion energy, climate modeling, and computational fluid dynamics (CFD). A core objective is to develop compression algorithms that achieve substantial data reduction—often by orders of magnitude—while rigorously ensuring the fidelity of both the primary data (PD) and scientifically crucial derived quantities of interest (QoI). The methodologies deployed under this grant integrate sophisticated deep learning architectures, prominently featuring autoencoders, advanced generative models like conditional diffusion, and hybrid learning techniques. Key innovations include the development of Guaranteed Autoencoders (GAE) and the Guaranteed Conditional Diffusion with Tensor Correction (GCDTC) framework, which provide explicit, instance-level error bounds on reconstructed data. Furthermore, specialized strategies such as nonlinear constraint satisfaction are employed to preserve the integrity of QoI, a vital requirement for the trustworthiness of downstream scientific analyses. This research also focuses on the design and implementation of scalable, GPU-accelerated software pipelines that seamlessly integrate into existing HPC workflows, ensuring both computational efficiency and practical applicability. The CAESAR framework, for example, unifies foundation and generative models to create an adaptive and efficient compression solution for spatio-temporal scientific data. Collectively, these efforts represent a significant advancement in mitigating the scientific data deluge, enabling more effective data management, accelerated scientific discovery, and optimized utilization of HPC resources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Building blocks for a digital twin of additive manufacturing

Properties and serviceability of additively manufactured components are affected by their geometry, microstructure and defects. These important attributes are now optimized by trial and error because the essential process variables cannot currently be selected from scientific principles. A recourse is to build and rigorously validate a digital twin of the additive manufacturing process that can provide accurate predictions of the spatial and temporal variations of metallurgical parameters that affect the structure and properties of components. Key building blocks of a computationally efficient first-generation digital twin of laser-based directed energy deposition additive manufacturing utilize a transient, three-dimensional model that calculates temperature and velocity fields, cooling rates, solidification parameters and deposit geometry. The measured profiles of stainless steel 316L and Alloy 800H deposits as well as the secondary dendrite arm spacing (SDAS) and Vickers hardness measurements are used to validate the proposed digital twin. The predicted cooling rates, temperature gradients, solidification rates, SDAS and micro-hardness values are shown to be more accurate than those obtained from a commonly used heat conduction calculation. Finally, these metallurgical building blocks serve as a phenomenological framework for the development of a digital twin that will make the expanding knowledge base of additive manufacturing usable in a practical way for all scientists and engineers.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Enriching OpenStreetMap network data for transportation applications: Insights into the impact of urban congestion on accessibility

OpenStreetMap (OSM) data is a valuable open-source resource for various transportation, traffic, and planning applications. However, OSM network data lack operating traffic speed information, which is critical for transport planning and operations. Addressing this shortcoming, this study leverages commercial vendor data (to serve as ground truth) with exogenous, open-source variables characterizing local transport infrastructure, land use, and demographic information to predict average congested traffic speeds on OSM networks. Three machine-learning models were tested and estimated for OSM links with and without speed limit information in the Denver metropolitan region. Among these, XGBoost performed best, with mean absolute errors of 3.27 and 3.62 mph for links with and without speed limits, respectively. The developed models accurately predicted traffic speeds for different hours and days of the week compared to ground truth data. Using these predicted speeds, drive accessibility scores were computed for the Denver region for different time periods using the Mobility Energy Productivity (MEP) metric to understand the impact of congestion on energy-efficient accessibility. Results show that congestion-adjusted drive accessibility can be significantly lower compared to accessibility calculated using free flow speeds. Specifically, weekday evening hours saw a 42 % drop in accessibility due to reduced speeds, particularly around downtown Denver. Across the Denver metro region, approximately half as many opportunities and jobs are accessible in under 20 min by car during the evening peak period relative to free flow conditions. These findings underscore the importance of using congestion-adjusted operating speeds rather than speed limits in accessibility calculations, as reliance on speed limits can substantially overestimate energy-efficient drive accessibility in large, car-centric cities susceptible to significant congestion. In conclusion, the methodology presented here could further enrich OSM network data, making them useful for an even broader range of transportation applications.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2025

FLAMES─Fast, Low-Storage, Accurate, and Memory-Efficient Adaptive Sampling─Approach to Resolve Spatially Dependent Dynamics of Molecular Liquids

Many critical phenomena in soft matter occur at large length scales, necessitating the resolution of their structure and dynamics at low wavenumbers. However, resolving wavenumber-dependent dynamics computationally via molecular dynamics simulations presents significant challenges, as these phenomena span several orders of magnitude in both time and length scales, resulting in high computational costs and memory demands. Here, this work highlights the computational and memory challenges associated with analyzing molecular trajectories in reciprocal space and demonstrates a method to address them. We introduce FLAMESFast, Low-storage, Accurate, and Memory-Efficient adaptive Sampling, which is a direct method for calculation of structure factors, allowing us to select only the required number of wavevectors for binning. We also use wavenumber-dependent time steps to extract dynamics. Our FLAMES approach effectively mitigates computational and memory/storage bottlenecks. We demonstrate the method using simulations of a model system, liquid octane, at various temperatures. Comparisons with experimental data and real space computation show that the FLAMES technique achieves high accuracy in resolving temperature- and spatially dependent dynamics while being significantly more computationally efficient and requiring less memory and storage than methods based on a uniform wavevector grid and fixed temporal spacing.

Chen, Guang [Argonne National Laboratory (ANL), Ar↗
DOE OSTI2023

pnnl/PHANTOM

A topology-based anomaly detection tool for temporal varying data. The input is json or CSV formatted data with a timestamp field identified. The algorithm computes vectorizations (using a vectorization config file) of time windows of data and computes a topological measure of anomalousness. The output is a sequence of anomaly scores for each time window

Seppala, Garret↗
DOE OSTI2024

Spatiotemporally Registered In-Situ and Ex-Situ Datasets for Laser-based Blown Powder Directed Energy Deposition

This dataset is comprised of in situ sensing data collected during laser-based, blown powder directed energy deposition (DED) of Inconel 718 representing eight different printing conditions: (1) nominal, (2) +15% scan speed, (3) +12% laser power, (4) +42% powder feed rate, (5) +100% jerk limit, (6) +10% layer height, (7) +20% hatch spacing, (8) +20% carrier gas flow. All eight DED builds constructed an identical test coupon geometry consisting of geometric features representative of industrial print requirements (e.g., bulk deposition, thin walls, overhangs). In situ data consists of xyz-coordinates (100 Hz) and on-axis melt pool camera video (60 Hz), both of which have been temporally synchronized to spatially map the melt pool camera data. In addition, post-build X-ray computed tomography (XCT) data for each of the eight test geometries have been spatially registered to the recorded xyz-coordinates, allowing for comparisons between melt pool camera data and flaws identified in the XCT data.

additive manufacturing↗
DOE OSTI2018

Emergence and selection of isoniazid and rifampin resistance in tuberculosis granulomas

Drug resistant tuberculosis is increasing world-wide. Resistance against isoniazid (INH), rifampicin (RIF), or both (multi-drug resistant TB, MDR-TB) is of particular concern, since INH and RIF form part of the standard regimen for TB disease. While it is known that suboptimal treatment can lead to resistance, it remains unclear how host immune responses and antibiotic dynamics within granulomas (sites of infection) affect emergence and selection of drug-resistant bacteria. We take a systems pharmacology approach to explore resistance dynamics within granulomas. We integrate spatio-temporal host immunity, INH and RIF dynamics, and bacterial dynamics (including fitness costs and compensatory mutations) in a computational framework. We simulate resistance emergence in the absence of treatment, as well as resistance selection during INH and/or RIF treatment. There are four main findings. First, in the absence of treatment, the percentage of granulomas containing resistant bacteria mirrors the non-monotonic bacterial dynamics within granulomas. Second, drug-resistant bacteria are less frequently found in non-replicating states in caseum, compared to drug-sensitive bacteria. Third, due to a steeper dose response curve and faster plasma clearance of INH compared to RIF, INH-resistant bacteria have a stronger influence on treatment outcomes than RIF-resistant bacteria. Finally, under combination therapy with INH and RIF, few MDR bacteria are able to significantly affect treatment outcomes. Overall, our approach allows drug-specific prediction of drug resistance emergence and selection in the complex granuloma context. Since our predictions are based on pre-clinical data, our approach can be implemented relatively early in the treatment development process, thereby enabling pro-active rather than reactive responses to emerging drug resistance for new drugs. Furthermore, this quantitative and drug-specific approach can help identify drug-specific properties that influence resistance and use this information to design treatment regimens that minimize resistance selection and expand the useful life-span of new antibiotics.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2014

SciDAC Institute for Ultra-Scale Visualization: Activity Recognition for Ultra-Scale Visualization

Understanding the science behind ultra-scale simulations requires extracting meaning from data sets of hundreds of terabytes or more. Developing scalable parallel visualization algorithms is a key step enabling scientists to interact and visualize their data at this scale. However, at extreme scales, the datasets are so huge, there is not even enough time to view the data, let alone explore it with basic visualization methods. Automated tools are necessary for knowledge discovery -- to help sift through the information and isolate characteristic patterns, thereby enabling the scientist to study local interactions, the origin of features and their evolution in large volumes of data. These tools must be able to operate on data of this scale and work with the visualization process. In this project, we developed a framework for activity detection to allow scientists to model and extract spatio-temporal patterns from time-varying data.

97 MATHEMATICS AND COMPUTING↗