Engineering Papers⌕ Search

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.

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

At least 1,603 records · Page 89
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

GenAI4UQ: A software for forward and inverse uncertainty quantification using conditional generative AI

We introduce GenAI4UQ, a software package for forward and inverse uncertainty quantification in model calibration, parameter estimation, and ensemble forecasting. GenAI4UQ leverages a generative AI-based conditional modeling framework to address limitations of traditional inverse modeling techniques, such as Markov Chain Monte Carlo (MCMC) methods. By replacing computationally intensive iterative processes with a direct, learned mapping, GenAI4UQ enables efficient calibration of input parameters and generation of predictions directly from observations. The software supports rapid ensemble forecasting with robust uncertainty quantification while maintaining computational and storage efficiency. Built-in auto-tuning of hyperparameters simplifies model training, ensuring accessibility for users with varying expertise. Its versatile conditional generative framework is applicable across diverse scientific domains. While GenAI4UQ offers significant advantages in flexibility and efficiency, users should interpret its uncertainty estimates with caution in data-sparse scenarios, as the model may overestimate uncertainty—an effect common to all surrogate-based approaches including MCMC with surrogate models. Despite this, GenAI4UQ transforms inverse modeling by providing a fast, reliable, and user-friendly solution. It empowers researchers and practitioners to quickly estimate parameter distributions and generate model predictions for new observations, facilitating efficient decision-making and advancing the state of uncertainty quantification in computational modeling.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Efficient Parallelization of Irregular Applications on GPU Architectures

With the enlarging computation capacity of general Graphics Processing Units (GPUs), leveraging GPUs to accelerate parallel applications has become a critical topic in academia and industry. However, a wide range of irregular applications with the computation-/memory-intensive nature cannot easily achieve high GPU utilization. The challenges mainly involve the following aspects: first, data dependence leads to coarse-grained kernel and inefficient parallelism; second, heavy GPU memory usage may cause frequent memory evictions and extra overhead of I/O; third, specific computation patterns produce memory redundancies; last, workload balance and data reusability conjunctly benefit the overall performance, but there may exist a dynamic trade-off between them. Targeting these challenges, this dissertation proposes multiple optimizations to accelerate two real-world applications: many-body correlation functions to simulate nuclear physics in a large-scale scientific system; the other is the eALS-based matrix factorization recommendation system. To accelerate the calculations of many-body correlation functions, this dissertation presents three frameworks in GPU memory management and multi-GPU scheduling. Firstly, an optimized systematic GPU memory management framework, MemHC, utilizes a series of new memory reduction designs in GPU memory allocation, CPU/GPU communications, and GPU memory oversubscription. Secondly, an enhanced multi-GPU scheduling framework, MICCO, particularly by taking both data dimension (e.g., data reuse and data eviction) and computation dimension into account. MICCO designs a heuristic scheduling algorithm and a machine learning-based regression model to generate the optimal settings of a proposed new concept to manage the trade-off. Thirdly, a locality-aware multi-GPU scheduling framework. This scheduler leverages pipeline batch generation with a looking-ahead strategy by building local dependency graphs for memory transfer reduction and better data reuse, achieving up to 79.92% memory cost reduction and 1.67x speedup. To parallelize the eALS-based recommendation system, this dissertation proposes an efficient CPU/GPU heterogeneous recommendation system, HEALS. HEALS employs newly designed architecture-adaptive data formats to achieve load balance and good data locality on CPU and GPU. To mitigate the data dependence, HEALS presents a CPU/GPU collaboration model for both task parallelism and data parallelism with multiple kernel computation optimizations. In summary, this dissertation efficiently accelerates two typical irregular applications on GPUs by building four frameworks, including CPU/GPU collaboration, GPU memory management, and multi-GPU scheduling.

Wang, Qihan↗
NASA NTRSDate not supplied

A Flexible Multibody Approach to Space Launch System Liftoff Pad Separation with Umbilical Disconnect

A flexible multibody dynamic framework is applied to the Space Launch System(SLS)liftoff Coupled Loads Analysis(CLA), enabling computational efficiencies and systematic inclusion of component nonlinearities. This work simulates the SLS liftoff transient pad separation event inclusive of umbilical disconnects and preload strain energy release (twang). For this system level nonlinear dynamic simulation, the flexible multibody framework provides a systematic approach for the addition of component specific algorithms to enforce the subject nonlinearities. As such, the complexities associated with the nonlinear CLA are greatly reduced, facilitating simplified bookkeeping as well as accelerating the execution of the nonlinear time-domain simulations.

Joel W Sills↗
DOE OSTI2021

Virtual Framework for Development and Testing of Federation Software Stack

Softwarization of networked infrastructures combined with containerization of codes promises unprecedented computing capabilities distributed across the federations of computing systems and physical instruments. The development and testing of a software stack that implements these capabilities over an expensive physical production infrastructure is not cost-effective, and in the early stages, may potentially cause service disruptions. To address these aspects, we develop the Virtual Federated Science Instrument Environment (VFSIE), a digital twin of the physical infrastructure that emulates a multi-site federation. Each federated site is emulated using containers and virtual hosts that are connected over local-area networks, and the sites, in turn, are connected over an emulated wide-area network. We describe the framework design and implementation details. We also illustrate its application by emulating a federation of four laboratories that use Jupyter Notebook for computations and the EPICS software system for instrument control.

Al Najjar, Anees↗
DOE OSTI2023

Application of Quantum Machine Learning to High Energy Physics Analysis at LHC using IBM Quantum Computer Simulators and IBM Quantum Computer Hardware

Our group pioneers the use of Quantum Machine Learning (QML) on High Energy Physics analysis at LHC. We have successfully employed several QML classification algorithms in the ttH (Higgs production in association with a top quark pair) and Higgs to two muons (Higgs coupling to second generation fermions), two recent LHC flagship physics analysis, on gate-model quantum computer simulators and hardware. The simulation studies have been performed with the IBM Quantum Framework, Google Tensorflow Quantum Framework, and Amazon Braket Framework, and we have achieved good classification performance that is similar to the performances of the classical machine learning methods currently used in LHC physics analyses, classical SVM, classical BDT, and classical deep neural network for example. We have also performed our studies using IBM superconducting quantum computer hardware and the performance is promising and is approaching the performance from IBM quantum simulators. Moreover, we extend our studies to other QML areas such as quantum anomaly detection and quantum generative adversarial, and some preliminary results have been obtained. Also, we have overcome the challenges of intensive computing resources in the cases of large qubits (25 qubits or more) and large numbers of events using NVIDIA cuQuantum with NERSC Perlmutter HPC. Our studies give an example that Quantum Machine Learning performs as well as its classical counterpart for realistic High Energy Physics analysis datasets. Furthermore, our result on noisy quantum hardware provides important validation for the result on noiseless quantum simulators.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Opportunities for enhancing MLCommons efforts while leveraging insights from educational MLCommons earthquake benchmarks efforts

MLCommons is an effort to develop and improve the artificial intelligence (AI) ecosystem through benchmarks, public data sets, and research. It consists of members from start-ups, leading companies, academics, and non-profits from around the world. The goal is to make machine learning better for everyone. In order to increase participation by others, educational institutions provide valuable opportunities for engagement. In this article, we identify numerous insights obtained from different viewpoints as part of efforts to utilize high-performance computing (HPC) big data systems in existing education while developing and conducting science benchmarks for earthquake prediction. As this activity was conducted across multiple educational efforts, we project if and how it is possible to make such efforts available on a wider scale. This includes the integration of sophisticated benchmarks into courses and research activities at universities, exposing the students and researchers to topics that are otherwise typically not sufficiently covered in current course curricula as we witnessed from our practical experience across multiple organizations. As such, we have outlined the many lessons we learned throughout these efforts, culminating in the need for benchmark carpentry for scientists using advanced computational resources. The article also presents the analysis of an earthquake prediction code benchmark while focusing on the accuracy of the results and not only on the runtime; notedly, this benchmark was created as a result of our lessons learned. Energy traces were produced throughout these benchmarks, which are vital to analyzing the power expenditure within HPC environments. Additionally, one of the insights is that in the short time of the project with limited student availability, the activity was only possible by utilizing a benchmark runtime pipeline while developing and using software to generate jobs from the permutation of hyperparameters automatically. It integrates a templated job management framework for executing tasks and experiments based on hyperparameters while leveraging hybrid compute resources available at different institutions. The software is part of a collection called cloudmesh with its newly developed components, cloudmesh-ee (experiment executor) and cloudmesh-cc (compute coordinator).

58 GEOSCIENCES↗
DOE OSTI2021

Search for efficient formulations for Hamiltonian simulation of non-Abelian lattice gauge theories

Hamiltonian formulation of lattice gauge theories (LGTs) is the most natural framework for the purpose of quantum simulation, an area of research that is growing with advances in quantum-computing algorithms and hardware. It, therefore, remains an important task to identify the most accurate, while computationally economic, Hamiltonian formulation(s) in such theories, considering the necessary truncation imposed on the Hilbert space of gauge bosons with any finite computing resources. This paper is a first step toward addressing this question in the case of non-Abelian LGTs, which further require the imposition of non-Abelian Gauss’s laws on the Hilbert space, introducing additional computational complexity. Focusing on the case of SU(2) LGT in 1+1 dimensions coupled to one flavor of fermionic matter, a number of different formulations of the original Kogut-Susskind framework are analyzed with regard to the dependence of the dimension of the physical Hilbert space on boundary conditions, system’s size, and the cutoff on the excitations of gauge bosons. The impact of such dependencies on the accuracy of the spectrum and dynamics obtained from a Hamiltonian computation is examined, and the (classical) computational-resource requirements given these considerations are studied. Besides the well-known angular-momentum formulation of the theory, the cases of purely fermionic and purely bosonic formulations (with open boundary conditions), and the Loop-String-Hadron formulation are analyzed, along with a brief discussion of a Quantum-Link-Model formulation of the same theory. Clear advantages are found in working with the Loop-String-Hadron framework which implements non-Abelian Gauss’s laws a priori using a complete set of gauge-invariant operators. Although small lattices are studied in the numerical analysis of this work, and only the simplest algorithms are considered, a range of conclusions will be applicable to larger systems and potentially to higher dimensions. Future studies will extend this investigation to the analysis of resource requirements for quantum simulations of non-Abelian LGT, with the goal of shedding light on the most efficient Hamiltonian formulation of gauge theories of relevance in nature

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems

This work proposes an extension of neural ordinary differential equations (NODEs) by introducing an additional set of ODE input parameters to NODEs. This extension allows NODEs to learn multiple dynamics specified by the input parameter instances. Our extension is inspired by the concept of parameterized ordinary differential equations, which are widely investigated in computational science and engineering contexts, where characteristics of the governing equations vary over the input parameters. We apply the proposed parameterized NODEs (PNODEs) for learning latent dynamics of complex dynamical processes that arise in computational physics, which is an essential component for enabling rapid numerical simulations for time-critical physics applications. For this, we propose an encoder-decoder-type framework, which models latent dynamics as PNODEs. We demonstrate the effectiveness of PNODEs with important benchmark problems from computational physics.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

COUPLING SMOOTHED PARTICLE HYDRODYNAMICS WITH FINITE ELEMENT METHOD TO SIMULATE RESIDUAL STRESSES FROM FRICTION STIR PROCESSING

Friction stir processing (FSP) is a solid-state material processing technique that locally modifies the microstructure but also induces undesirable residual stresses. A robust numerical model for the FSP can help in mitigating these residual stresses. Heat source models within a finite element method (FEM) framework suffer from inaccuracies. In contrast, smoothed particle hydrodynamics (SPH) model that explicitly captures the material flow near the tool and the associated heat generation are accurate. However, the computational expense of SPH simulations can be prohibitive. In this work, we propose a coupled SPH-FEM framework. SPH is used to model the heat generation accurately near the tool and which is then inserted into to the FEM model as a heat source. To verify this proposed coupling approach, a test case is set up with typical FSP conditions and it is modeled in both SPH and SPH-FEM. The temperatures profiles were compared after the simulations have reached steady-state temperatures. The similarity of the temperature profiles from SPH-FEA and SPH validated the proposed coupling approach. This proposed approach achieves the accuracy of the SPH method while potentially retaining the low computational expense of FEM.

smoothed particle hydrodynamics, Finite Element Me↗
DOE OSTI2024

Active interlocking metasurfaces enabled by shape memory alloys

Interlocking metasurfaces (ILMs) are a newly developed joining technology that relies on arrays of interlocking features that transmit force and constrain motion between adjoining bodies in one or more directions. This study explores harnessing the shape memory effect (SME) in Nickel-Titanium shape memory alloys (NiTi SMAs) in structures fabricated using additive manufacturing (AM) to advance the development of active ILMs by creating unit cells that open or close at specific temperatures. The study encompasses designing and fabricating two distinct interlocking array configurations using near-equiatomic NiTi powder and the laser powder bed fusion (L-PBF) AM technique, following a previously developed AM process optimization framework to manufacture defect-free parts. To guide the design process, finite element analysis (FEA) was employed to predict strain values during engage-disengage cycles. The martensitic transformation characteristics of the ILMs were characterized. Thermomechanical testing revealed that the ILMs demonstrate high locking force once engaged, coupled with complete shape recovery and good cyclic stability. Digital image correlation (DIC) was also employed to validate the FEA predictions during the engage-disengage cycles. The results indicate that NiTi SMA-based ILMs can be designed and fabricated into complex shapes using L-PBF. By leveraging the SME, the functionality of an ILM can be improved upon. The combination of computational modeling, additive manufacturing, and thermomechanical and physical property characterization provides a framework for designing future ILMs out of active materials.

Additive manufacturing↗
DOE OSTI2022

An Improved Method for Coupling Hydrodynamics with Astrophysical Reaction Networks

Reacting astrophysical flows can be challenging to model, because of the difficulty in accurately coupling hydrodynamics and reactions. This can be particularly acute during explosive burning or at high temperatures where nuclear statistical equilibrium is established. We develop a new approach, based on the ideas of spectral deferred corrections (SDC) coupling of explicit hydrodynamics and stiff reaction sources as an alternative to operator splitting, that is simpler than the more comprehensive SDC approach we demonstrated previously. We apply the new method to a double-detonation problem with a moderately sized astrophysical nuclear reaction network and explore the time step size and reaction network tolerances, to show that the simplified-SDC approach provides improved coupling with decreased computational expense compared to traditional Strang operator splitting. This is all done in the framework of the Castro hydrodynamics code, and all algorithm implementations are freely available.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators

Software simulators play a critical role in the development of new algorithms and system architectures in any field of engineering. Neuromorphic computing, which has shown potential in building brain-inspired energy-efficient hardware, suffers a slow-down in the development cycle due to a lack of flexible and easy-to-use simulators of either neuromorphic hardware itself or of spiking neural networks (SNNs), the type of neural network computation executed on most neuromorphic systems. While there are several openly available neuromorphic or SNN simulation packages developed by a variety of research groups, they have mostly targeted computational neuroscience simulations, and only a few have targeted small-scale machine learning tasks with SNNs. Evaluations or comparisons of these simulators have often targeted computational neuroscience-style workloads. In this work, we seek to evaluate the performance of several publicly available SNN simulators with respect to non-computational neuroscience workloads, in terms of speed, flexibility, and scalability. We evaluate the performance of the NEST, Brian2, Brian2GeNN, BindsNET and Nengo packages under a common front-end neuromorphic framework. Our evaluation tasks include a variety of different network architectures and workload types to mimic the computation common in different algorithms, including feed-forward network inference, genetic algorithms, and reservoir computing. We also study the scalability of each of these simulators when running on different computing hardware, from single core CPU workstations to multi-node supercomputers. Our results show that the BindsNET simulator has the best speed and scalability for most of the SNN workloads (sparse, dense, and layered SNN architectures) on a single core CPU. However, when comparing the simulators leveraging the GPU capabilities, Brian2GeNN outperforms the others for these workloads in terms of scalability. NEST performs the best for small sparse networks and is also the most flexible simulator in terms of reconfiguration capability NEST shows a speedup of at least 2x compared to the other packages when running evolutionary algorithms for SNNs. The multi-node and multi-thread capabilities of NEST show at least 2x speedup compared to the rest of the simulators (single core CPU or GPU based simulators) for large and sparse networks. We conclude our work by providing a set of recommendations on the suitability of employing these simulators for different tasks and scales of operations. We also present the characteristics for a future generic ideal SNN simulator for different neuromorphic computing workloads.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

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

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

Renganathan, S. Ashwin↗
DOE OSTI2022

Computational Fluid Dynamics Simulations to Predict Oxidation in Heat Recovery Steam Generator Tubes

Heat Recovery Steam Generators (HRSGs) are widely used across United States in combined cycle power plants to recover waste heat from the gas turbine (GT). HRSGs are used either to generate electricity or to produce process steam for industrial applications. The primary components of HRSG consists of a duct and a heat exchanger (HX). It is known across the power industry that the high temperature oxidation and ensuing exfoliation problem is a major cause for the damage of HX materials of HRSG. Alloys and/or coatings that can prevent or mitigate oxidation are very expensive, therefore they must be used or applied on the select regions of the HX tubes where the tendency of oxide formation is the highest. The main goal of this project is to identify such regions through Computational Fluid Dynamics (CFD) simulations. Therefore, in this work, we developed a CFD framework using commercial code StarCCM+ for the prediction of the fluid flow and heat transfer in a HRSG and associated oxidation inside the tubes of the HX. The developed CFD framework was verified and validated with experimental data before deployment. We also developed an innovative method to model the effect of the fins on the heat transfer and the pressure drop using a porous media model (PMM) approach to keep the mesh size within reasonable limits. After validation, we performed high-fidelity CFD simulations of a real-scale HRSG using the PMM, with High Performance Computing (HPC) resources of ORNL. From the simulation results, we acquired oxide thickness maps for all the tubes of the select HX sections of HRSG prone to oxidation. These oxide maps can inform regions of the HX tubes that requires oxide-resistant coatings, thereby guiding engineers for cost-efficient manufacturing of the HX that can combat oxidation in HRSGs.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Functional characterization of glycosyltransferases in duckweed to enable predictive biology

Glycosyltransferases (GTs) catalyze the formation of glycosidic linkages to produce almost all complex carbohydrates. This project used a multi-disciplinary, high-throughput (HTP) biochemical and computational biology approach focused on duckweed as a model energy crop, to study carbohydrate metabolic processes. To achieve this, developed and carried out out high-throughput (HTP) functional characterization of plant glycosyltransferases (GTs) role of enzymatic microenvironments be assessed through a combined proteomic and computational biology approach, and the combined data was used to populate deep-learning frameworks to predict plant GT function. Functional validation achieved through this research is being used to assign gene function and study plant processes at the systems level to efficiently link the genome sequence with gene function. Together, the combined approaches used within this study provide a foundation for how computational prediction, in combination with high-throughput functional validation, can be used to study plant processes at the systems level and translate knowledge gained to efficiently link genome sequence with gene function in a species agnostic manner.

09 BIOMASS FUELS↗
NASA NTRS1990

Computation of instability and transition

The state of transition calculations in 1989 and desirable future trends are analyzed within the framework of aeronautical applications with emphasis on wall-bounded flows. A shift to studies of the early stages of transition, particularly to receptivity, from studies of the late stages in excessively confined periodic domains is proposed. It is pointed out that early-stage studies require a larger computational domain and more difficult boundary conditions but not a very fine grid. Intermediate strategies, more involved than the classical Orr-Sommerfeld equation but much more economical than full Navier-Stokes equations, are emphasized, along with the need for compressible calculations.

Spalart, P. R.↗
DOE OSTI2022

Inverse Modeling of Hydrologic Parameters in CLM4 via Generalized Polynomial Chaos in the Bayesian Framework

In this work, generalized polynomial chaos (gPC) expansion for land surface model parameter estimation is evaluated. We perform inverse modeling and compute the posterior distribution of the critical hydrological parameters that are subject to great uncertainty in the Community Land Model (CLM) for a given value of the output LH. The unknown parameters include those that have been identified as the most influential factors on the simulations of surface and subsurface runoff, latent and sensible heat fluxes, and soil moisture in CLM4.0. We set up the inversion problem in the Bayesian framework in two steps: (i) building a surrogate model expressing the input–output mapping, and (ii) performing inverse modeling and computing the posterior distributions of the input parameters using observation data for a given value of the output LH. The development of the surrogate model is carried out with a Bayesian procedure based on the variable selection methods that use gPC expansions. Our approach accounts for bases selection uncertainty and quantifies the importance of the gPC terms, and, hence, all of the input parameters, via the associated posterior probabilities.

97 MATHEMATICS AND COMPUTING↗