SEARCH · Engineering Papers

Results for “computational framework”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 775 records · Page 43

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations

Accurate frequency modelling of inverter‐based resource (IBR)‐dominated power systems is crucial for ensuring stable, reliable and resilient operations, particularly given their inherent low‐inertia characteristics and fast dynamics that traditional swing equation‐based models inadequately capture. This paper explores neural ordinary differential equations (Neural ODEs) as a computationally efficient, data‐driven framework for modelling power system frequency dynamics, specifically within microgrids integrating high penetrations of distributed energy resources (DERs). The developed neural ODEs framework incorporates a neural network architecture designed to capture input dynamics. By actively perturbing the system with a known signal, the Python‐based neural ODEs framework was trained using measured system states and inputs, without the need for detailed system information. The framework, tested on a model of the Cordova, AK, microgrid, achieved a goodness of fit ranging from 60% to 99% across different state variables and maintained a mean square error in the 10 -6 p.u. range under square and step excitation signals. The proposed approach demonstrated robustness to measurement noise and initial condition variations while maintaining low computational complexity suitable for real‐time power system control applications. Furthermore, transfer learning enabled the neural ODEs model to adapt to the following changes in system topology or generator dispatch, highlighting its effectiveness for dynamic microgrids with frequently evolving configurations and diverse DERs.

Aryal, Tara [South Dakota State Univ., Brookings, ↗

DOE OSTI2024

Accelerated Constrained Sparse Tensor Factorization on Massively Parallel Architectures

This study presents the first constrained sparse tensor factorization (cSTF) framework that optimizes and fully offloads computation to massively parallel GPU architectures, and the first performance characterization of cSTF on GPU architectures. In contrast to prior work on tensor factorization, where the matricized tensor times Khatri-Rao product (MTTKRP) is the primary performance bottleneck, our systematic analysis of the cSTF algorithm on GPUs reveals that adding constraints creates an additional bottleneck in the update operation for many real-world sparse tensors. While executing the update operation on the GPU brings significant speedup over its CPU counterpart, it remains a significant bottleneck. To further accelerate the update operation, we propose cuADMM, a new update algorithm that leverages algorithmic and code optimization strategies to minimize both computation and data movement on GPUs. As a result, our framework delivers significantly improved performance compared to prior state-of-the-art. On 10 real-world sparse tensors, our framework achieves geometric mean speedup of 5.1 × (max 41.59 ×) and 7.01 × (max 58.05 ×) on the NIVIDA A100 and H100 GPUs, respectively, over the state-of-the-art SPLATT library running on a 26-core Intel Ice Lake Xeon CPU.

Soh, Yongseok↗

NASA NTRS1995

Three-dimensional user interfaces for scientific visualization

The main goal of this project is to develop novel and productive user interface techniques for creating and managing visualizations of computational fluid dynamics (CFD) datasets. We have implemented an application framework in which we can visualize computational fluid dynamics user interfaces. This UI technology allows users to interactively place visualization probes in a dataset and modify some of their parameters. We have also implemented a time-critical scheduling system which strives to maintain a constant frame-rate regardless of the number of visualization techniques. In the past year, we have published parts of this research at two conferences, the research annotation system at Visualization 1994, and the 3D user interface at UIST 1994. The real-time scheduling system has been submitted to SIGGRAPH 1995 conference. Copies of these documents are included with this report.

Vandam, Andries↗

DOE OSTI2026

Computational capacity in hydrodynamic real-time hybrid simulation applied to simulate the dynamic response of floating offshore wind turbines

Real-time hybrid simulation (RTHS) mitigates similitude distortions in model-scale tests of floating offshore wind turbines (FOWTs) by coupling physical experiments with numerical models in real time. The coupling requires faster-than-real-time numerical computations to satisfy temporal similitude with the physical experiment, presenting a bottleneck for using more complex numerical models in RTHS. This paper presents a hydrodynamic-RTHS (hydro-RTHS) framework for FOWTs that simulates the hydrodynamics physically and the aerodynamics numerically with sensor feedback from the physical testing. The framework adapts the three-loop hardware architecture to leverage greater computational resources and mitigate strict temporal requirements, enabling more computationally demanding numerical analyses in hydro-RTHS. The three-loop hardware architecture integrates multiple machines, each dedicated to either numerical analysis or RTHS controls, with a rate-transition algorithm to synchronize the tasks executed across the different machine processors. Virtual and physical tests verified and validated the hydro-RTHS framework, respectively. The ”virtual” tests, which approximates the physical domain numerically, verified the RTHS framework with respect to a numerical full-scale complete FOWT model simulated in the open-source software, OpenFAST. The virtual tests were able to maintain comparable control signals while enabling greater computational resources for the numerical calculations. Real-world physical tests demonstrated that the hydro-RTHS framework computes aerodynamic forces similar to the complete OpenFAST model, validating the hydro-RTHS framework using the three-loop hardware architecture. Findings show that the hydro-RTHS framework with the three-loop hardware architecture is computationally efficient, with reserve capacity to simulate more complex problems due to the customized software, hardware, and rate-transition algorithm.

17 WIND ENERGY↗

DOE OSTI2025

Atomate2: modular workflows for materials science

High-throughput density functional theory (DFT) calculations have become a vital element of computational materials science, enabling materials screening, property database generation, and training of “universal” machine learning models. While several software frameworks have emerged to support these computational efforts, new developments such as machine learned force fields have increased demands for more flexible and programmable workflow solutions. This manuscript introduces atomate2, a comprehensive evolution of our original atomate framework, designed to address existing limitations in computational materials research infrastructure. Key features include the support for multiple electronic structure packages and interoperability between them, along with generalizable workflows that can be written in an abstract form irrespective of the DFT package or machine learning force field used within them. Our hope is that atomate2's improved usability and extensibility can reduce technical barriers for high-throughput research workflows and facilitate the rapid adoption of emerging methods in computational material science.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

An Ab Initio Multiple Cloning Method for Non-Adiabatic Excited-State Molecular Dynamics in NWChem

The recently developed ab-initio multiple cloning (AIMC) approach based on the multicongurational Ehrenfest (MCE) method provides a powerful and accurate way of describing the excited-state dynamics of molecular systems. The AIMC method is a controlled approximation to non-adiabatic dynamics with a particular strength in the proper description of decoherence effects due to branching of vibrational wavepackets at a level crossing. In this work, we report a new implementation of the AIMC algorithm in the open source NWChem computational chemistry program. The framework combines linear-response time-dependent density functional theory with Ehrenfest mean-eld theory to determine the equations of motion for classical trajectories. The multi-dimensional wave function is decomposed into a superposition of Gaussian coherent states guided by Ehrenfest trajectories (i.e., MCE approach), which can clone with fully quantum mechanical amplitudes and phases. By using an efficient time-derivative based non-adiabatic coupling approach within the AIMC method, all observable are calculated on-the-y in the non-adiabatic molecular dynamics process. As a representative example, we apply our implementation to study the ultrafast photoinduced electronic and vibrational energy transfer in a pyridine molecule. The effects of the cloning procedure on electronic and vibrational coherence, relaxation and unidirectional energy transfer are discussed. This new AIMC implementation provides a high-level non-adiabatic molecular dynamics framework for simulating photoexcited dynamics in complex molecular systems and experimentally relevant ultrafast spectroscopic probes, such as nonlinear coherent optical and X-ray signals.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

NASA NTRS2012

Uncertainty Quantification for Polynomial Systems via Bernstein Expansions

This paper presents a unifying framework to uncertainty quantification for systems having polynomial response metrics that depend on both aleatory and epistemic uncertainties. The approach proposed, which is based on the Bernstein expansions of polynomials, enables bounding the range of moments and failure probabilities of response metrics as well as finding supersets of the extreme epistemic realizations where the limits of such ranges occur. These bounds and supersets, whose analytical structure renders them free of approximation error, can be made arbitrarily tight with additional computational effort. Furthermore, this framework enables determining the importance of particular uncertain parameters according to the extent to which they affect the first two moments of response metrics and failure probabilities. This analysis enables determining the parameters that should be considered uncertain as well as those that can be assumed to be constants without incurring significant error. The analytical nature of the approach eliminates the numerical error that characterizes the sampling-based techniques commonly used to propagate aleatory uncertainties as well as the possibility of under predicting the range of the statistic of interest that may result from searching for the best- and worstcase epistemic values via nonlinear optimization or sampling.

Crespo, Luis G.↗

DOE OSTI2024

Multicycle large-eddy simulations of a direct-injection hydrogen-fueled optical engine

Hydrogen (H 2 ) is a carbon-free chemical energy carrier and one promising solution for achieving effective decarbonization of the transportation sector, particularly for internal combustion engines (ICEs). With a focus on ICEs, and compared to port-fuel injection, direct injection (DI) of gaseous H 2 during the compression stroke offers potential advantages, which include backfire avoidance and reduction of preignition occurrence. In these last two decades, much research, experimental and numerical, has been devoted to understanding H 2 's mixing and combustion processes in ICEs. Computational fluid dynamics modeling efforts commonly rely on unsteady Reynolds-averaged Navier Stokes (URANS) turbulence frameworks, mostly due to their computational affordability. However, many authors have pointed out the opportunity to perform large-eddy simulations (LESs) to investigate the cyclic variability of H 2 engines and assess potential advantages of using LES in place of URANS, especially for lean operation. This study addresses this knowledge gap and presents a computational fluid dynamics (CFD) study of the H 2 DI process in an optical engine operating at relatively low tumble conditions, using multicycle LESs. In conclusion, the manuscript presents a thorough validation of the results against experimental data available from the literature as well as direct comparison with URANS, demonstrating the feasibility of multicycle LESs for CFD modeling of DI H 2 -fueled ICEs.

Direct injection↗

NASA NTRSDate not supplied

Dust Particle Aeroheating Calculations for Mars Entry Hypersonic Flows

The purpose of the current research effort is to predict particle trajectories in a hypersonic flowfield while accounting for all relevant particle-fluid and particle-particle interactions. The resulting particle solver is titled DUst Simulation & Tracking (DUST) and works in conjunction with the US3D CFD flow solver. The key elements underpinning the current work are an efficient mesh-localiztion algorithm, time-driven hard-sphere model, point-to-point MPI framework, coarse-graining using computational parcels, and high-order Adams-Bashforth time stepping. The coupled US3D-DUST framework will be applied to conduct a multi-physics examination of dust-laden flows around the the Schiarparelli capsule.

Dusty Flows↗

NASA NTRSDate not supplied

Dust Particle Aeroheating Calculations for Mars Entry Hypersonic Flows

Dusty Flows↗

DOE OSTI2025

Real time computations of cryogenic He properties

The Fermilab PIP-II (proton improvement plan - II) project is being constructed at Fermilab to deliver $800\,MeV$ protons of $>1\,MW$ beam power to replace the present LINAC and provide protons to the remainder of the existing accelerator complex. The new LINAC consists of a warm front end, 23 superconducting RF cryomodules, and a beam transfer line to the existing complex. The cryomodules (CMs) are to be tested at Fermilab's CryoModule Test Facility (CMTF).An important measurement in cryogenic testing is the heat load of each CM. Traditionally, at Fermilab, these measurements were made collecting archived data offline and analyzing it. The new control system for PIP-II is being developed with the EPICS (Experimental Physics and Industrial Control System) framework, which allows us to compute the heat load in real time using the HePak library.We are exploring other $He$ properties, such as flow, where flow meters are not available, which can also be calculated in real time and fed back to the cryogenics engineers.This paper details the real time heat load calculation and $He$ flow software developed for CM testing at CMTF, as well as the first results from the prototype HB650 CM. Future plans for 2-phase $LHe$ flow will also be outlined.

Hanlet, Pierrick [Fermilab]↗

DOE OSTI2023

SHAPER: can you hear the shape of a jet?

The identification of interesting substructures within jets is an important tool for searching for new physics and probing the Standard Model at colliders. Many of these substructure tools have previously been shown to take the form of optimal transport problems, in particular the Energy Mover’s Distance (EMD). In this work, we show that the EMD is in fact the natural structure for comparing collider events, which accounts for its recent success in understanding event and jet substructure. We then present a Shape Hunting Algorithm using Parameterized Energy Reconstruction (SHAPER), which is a general framework for defining and computing shape-based observables. SHAPER generalizes N-jettiness from point clusters to any extended, parametrizable shape. This is accomplished by efficiently minimizing the EMD between events and parameterized manifolds of energy flows representing idealized shapes, implemented using the dual-potential Sinkhorn approximation of the Wasserstein metric. We show how the geometric language of observables as manifolds can be used to define novel observables with built-in infrared-and-collinear safety. We demonstrate the efficacy of the SHAPER framework by performing empirical jet substructure studies using several examples of new shape-based observables.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

NASA NTRS1999

Parallel Tetrahedral Mesh Adaptation with Dynamic Load Balancing

The ability to dynamically adapt an unstructured grid is a powerful tool for efficiently solving computational problems with evolving physical features. In this paper, we report on our experience parallelizing an edge-based adaptation scheme, called 3D_TAG. using message passing. Results show excellent speedup when a realistic helicopter rotor mesh is randomly refined. However. performance deteriorates when the mesh is refined using a solution-based error indicator since mesh adaptation for practical problems occurs in a localized region., creating a severe load imbalance. To address this problem, we have developed PLUM, a global dynamic load balancing framework for adaptive numerical computations. Even though PLUM primarily balances processor workloads for the solution phase, it reduces the load imbalance problem within mesh adaptation by repartitioning the mesh after targeting edges for refinement but before the actual subdivision. This dramatically improves the performance of parallel 3D_TAG since refinement occurs in a more load balanced fashion. We also present optimal and heuristic algorithms that, when applied to the default mapping of a parallel repartitioner, significantly reduce the data redistribution overhead. Finally, portability is examined by comparing performance on three state-of-the-art parallel machines.

Oliker, Leonid↗

DOE OSTI2022

Physics constrained learning for data-driven inverse modeling from sparse observations

Deep neural networks (DNN) have been used to model nonlinear relations between physical quantities. Those DNNs are embedded in physical systems described by partial differential equations (PDE) and trained by minimizing a loss function that measures the discrepancy between predictions and observations in some chosen norm. This loss function often includes the PDE constraints as a penalty term when only sparse observations are available. As a result, the PDE is only satisfied approximately by the solution. However, the penalty term typically slows down the convergence of the optimizer for stiff problems. We present a new approach that trains the embedded DNNs while numerically satisfying the PDE constraints. We develop an algorithm that enables differentiating both explicit and implicit numerical solvers in reverse-mode automatic differentiation. This allows the gradients of the DNNs and the PDE solvers to be computed in a unified framework. We demonstrate that our approach enjoys faster convergence and better stability in relatively stiff problems compared to the penalty method. Furthermore, our approach allows for the potential to solve and accelerate a wide range of data-driven inverse modeling, where the physical constraints are described by PDEs and need to be satisfied accurately.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1992

Optimal matrix approximants in structural identification

Problems of model correlation and system identification are central in the design, analysis, and control of large space structures. Of the numerous methods that have been proposed, many are based on finding minimal adjustments to a model matrix sufficient to introduce some desirable quality into that matrix. In this work, several of these methods are reviewed, placed in a modern framework, and linked to other previously known ideas in computational linear algebra and optimization. This new framework provides a point of departure for a number of new methods which are introduced here. Significant among these is a method for stiffness matrix adjustment which preserves the sparsity pattern of an original matrix, requires comparatively modest computational resources, and allows robust handling of noisy modal data. Numerical examples are included to illustrate the methods presented herein.

Beattie, C. A.↗

DOE OSTI2021

iSPECTRON: a simulation interface for linear and nonlinear spectra with ab-initio quantum chemistry software

We introduce iSPECTRON, an open source (under the Educational Community License version 2.0) program that parses data from common quantum chemistry software (NWChem, OpenMolcas, Gaussian, Cobramm, etc.), produces the input files for the simulation of linear and nonlinear spectroscopy of molecules with the Spectron code, and analyzes the spectra with a broad range of tools. Vibronic spectra are expressed in term of the electronic eigenstates, obtained through quantum chemistry computations, and vibrational/bath effects are incorporated in the framework of the displaced harmonic oscillator model, where all required quantities are computed at the Franck-Condon point. The code capabilities are illustrated by simulating linear absorption, transient absorption and two dimensional electronic spectra of the pyrene molecule. Two levels of electronic structure theory, TDDFT (with NWChem) and RASSCF/RASPT2 (with OpenMolcas), are compared where possible. Acknowledgements: F.S., A.N., D.R.N., N.G., S.M, M.G. acknowledge support from the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Chemical Sciences, Geosciences, and Biosciences Division under Award Nos. DE-SC0019484, KC-030103172684. The Spectron code was developed with support from the National Science Foundation (Grant CHE- 1953045). This research benefited from computational resources provided by EMSL, a DOE Office of Science User Facility sponsored by the Office of Biological and Environmental Research and located at PNNL. PNNL is operated by Battelle Memorial Institute for the United States Department of Energy under DOE Contract No. DE-AC05-76RL1830.

Segatta, Francesco↗

DOE OSTI2024

Scheduling and Performance of Asynchronous Tasks in Fortran 2018 with FEATS

Most parallel scientific programs contain compiler directives (pragmas) such as those from OpenMP (Hermanns in Parallel programming in Fortran 95 using openMP, 2002. School of Aeronautical Engineering, Universidad Politécnica de Madrid, España, 2011), explicit calls to runtime library procedures such as those implementing the Message Passing Interface (MPI) (in A message-passing interface standard version 4.0, 2021. https://www.mpi-forum.org/docs/mpi-4.0/mpi40-report.pdf), or compiler-specific language extensions such as those provided by CUDA (Ruetsch and Fatica in CUDA Fortran for scientists and engineers: best practices for efficient CUDA Fortran programming, Elsevier, 2013). By contrast, the recent Fortran standards empower developers to express parallel algorithms without directly referencing lower-level parallel programming models (Numrich in Parallel programming with co-arrays, CRC Press, 2018, and Curcic in Modern Fortran: building efficient parallel applications, Manning Publications, 2020). Fortran’s parallel features place the language within the Partitioned Global Address Space (PGAS) class of programming models. When writing programs that exploit data parallelism, application developers often find it straightforward to develop custom parallel algorithms. Problems involving complex, heterogeneous, staged calculations, however, pose much greater challenges. Such applications require careful coordination of tasks in a manner that respects dependencies prescribed by a directed acyclic graph. When rolling one’s own solution proves difficult, extending a customizable framework becomes attractive. Further, the paper presents the design, implementation, and use of the Framework for Extensible Asynchronous Task Scheduling (FEATS), which we believe to be the first task scheduling tool written in modern Fortran. We describe the benefits and compromises associated with choosing Fortran as the implementation language, and we propose ways in which future Fortran standards can best support the use case in this paper.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

SimELIT: A Novel GUI-Based Comprehensive Ion Trajectory Simulation Software for Mass Spectrometry

Ion trajectory simulation in mass spectrometry systems from injection to detection is technically challenging but very important for better understanding the ion dynamics in instrument development. Here, in this work, we present SimELIT (Simulator of Eulerian and Lagrangian Ion Trajectories), a novel ion trajectory simulation platform. SimELIT is built upon a suite of multiphysics solvers compiled into OpenFOAM (an open-source numerical solver library particularly used for computational mechanics), with a simple web-based graphical user interface (GUI) allowing users to define the details of OpenFOAM cases and run simulations. SimELIT is a modular program and can provide extensions of physics (e.g., gas flows, electrodynamic fields) and thus enable ion trajectory simulations from the ion source to detector. The current version (SimELIT) provides two numerical solvers for ion trajectory simulations–(1) a Lagrangian particle tracker in vacuum and (2) a Eulerian ion density solver in background gas in the presence of electric fields. Here, we describe the architecture of SimELIT, including its use of Docker and the React Framework, and demonstrate the computation of ion trajectories of multiple m/z values in a static/linear voltage drop in vacuum (across a 1 m long flight tube). Further, the drift motion of ions under 1 Torr pressure conditions in a static background (N 2 ) gas through a 20 V/cm static electric field is shown. The results produced from SimELIT were compared with SIMION and theoretical estimates. In addition, we report the computation of ion trajectories in electrodynamic fields within a planar FAIMS device operating at atmospheric pressure.

97 MATHEMATICS AND COMPUTING↗