Search NASA⌕ Search

SEARCH · Search NASA

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 271 records · Page 15

A Privacy-Aware Federated Learning Framework for Distributed Energy Resource Analytics in Constrained Environments

To be resilient against extreme weather events, the rural communities in Puerto Rico are leveraging distributed energy resources (DER). However, computing frameworks sup-porting the grid in critical decision-making are still largely centralized. Sensitive consumer data are transmitted over the Internet or cellular networks to a secondary or tertiary node. It guarantees better situational awareness at the cost of a wider attack surface, jeopardizing user privacy, as more DER come online. Cloud, Edge, and Fog computing all require data aggregation at some level. This paper introduces a privacy-aware federated learning framework that leverages the Fog model by pushing analytics all the way to the DER and load assets. These local models train on individual asset data and transmit only learned parameters (such as weights) over secure communications to a global decision-maker. By abstracting personally identifiable consumer data without impacting decision optimality, this framework better aligns with distributed power generation paradigm.

Sundararajan, Aditya↗

Quantum embedding theories to simulate condensed systems on quantum computers.

Quantum computers hold promise to improve the efficiency of quantum simulations of materials and to enable the investigation of systems and properties that are more complex than tractable at present on classical architectures. Here, we discuss computational frameworks to carry out electronic structure calculations of solids on noisy intermediate-scale quantum computers using embedding theories, and we give examples for a specific class of materials, that is, solid materials hosting spin defects. These are promising systems to build future quantum technologies, such as quantum computers, quantum sensors and quantum communication devices. Although quantum simulations on quantum architectures are in their infancy, promising results for realistic systems appear to be within reach.

Vorwerk, Christian↗

Microbiological-enhanced mixing across scales during in-situ bioreduction of metals and radionuclides at Department of Energy Sites

Bioreduction is being actively investigated as an effective strategy for subsurface remediation and long-term management of DOE sites contaminated by metals and radionuclides (i.e. U(VI)). These strategies require manipulation of the subsurface, usually through injection of chemicals (e.g., electron donor) which mix at varying scales with the contaminant to stimulate metal reducing bacteria. There is evidence from DOE field experiments suggesting that mixing limitations of substrates at all scales may affect biological growth and activity for U(VI) reduction. Although current conceptual models hold that biomass growth and reduction activity is limited by physical mixing processes, a growing body of literature suggests that reaction could be enhanced by cell-to-cell interaction occurring over length scales extending tens to thousands of microns. Our project investigated two potential mechanisms of enhanced electron transfer. The first is the formation of single- or multiple-species biofilms that transport electrons via direct electrical connection such as conductive pili (i.e. ‘nanowires’) through biofilms to where the electron acceptor is available. The second is through diffusion of electron carriers from syntrophic bacteria to dissimilatory metal reducing bacteria (DMRB). The specific objectives of this work are (i) to quantify the extent and rate that electrons are transported between microorganisms in physical mixing zones between an electron donor and electron acceptor (e.g. U(IV)), (ii) to quantify the extent that biomass growth and reaction are enhanced by interspecies electron transport, and (iii) to integrate mixing across scales (e.g., microscopic scale of electron transfer and macroscopic scale of diffusion) in an integrated numerical model to quantify these mechanisms on overall U(VI) reduction rates. We tested these hypotheses with five tasks that integrate microbiological experiments, unique micro-fluidics experiments, flow cell experiments, and multi-scale numerical models. Continuous fed-batch reactors were used to derive kinetic parameters for DMRB, and to develop an enrichment culture for elucidation of syntrophic relationships in a complex microbial community. Pore and continuum scale experiments using microfluidic and bench top flow cells were used to evaluate the impact of cell-to-cell and microbial interactions on reaction enhancement in mixing-limited bioactive zones, and the mechanisms of this interaction. Some of the microfluidic experiments were used to develop and test models that considers direct cell-to-cell interactions during metal reduction. Pore scale models were incorporated into a multi-scale hybrid modeling framework that combines pore scale modeling at the reaction interface with continuum scale modeling. New computational frameworks for combining continuum and pore-scale models were also developed

54 ENVIRONMENTAL SCIENCES↗

AdditiveFOAM: A Continuum Multiphysics Code for Additive Manufacturing

AdditiveFOAM is a computational framework that simulates transport phenomena in Additive Manufacturing (AM) processes. It is built on OpenFOAM (Weller et al., 1998), the leading free, open-source software package for computational fluid dynamics (CFD). OpenFOAM offers an extensible platform for solving complex multiphysics problems using state-of-the-art finite volume methods. AdditiveFOAM leverages these capabilities to develop specialized tools aimed at addressing challenges in AM processing. Metal additive manufacturing, also known as metal 3D printing, is an advanced manufacturing technique that creates physical parts from a three-dimensional (3D) digital model by melting metal powder or wire feedstock. A significant area of research in metal AM focuses on process planning to mitigate anomalous features during printing that are deleterious to part performance (e.g., porosity and cracking), as well as controlling localized microstructure and material properties. Given the high costs and substantial time requirements associated with experimental methods for qualifying new materials and processes, there is a compelling incentive for researchers to utilize advanced computational simulations. In this context, AdditiveFOAM offers a simulation framework to better understand undesirable features in printing, thereby enhancing process planning and reducing the reliance on labor-intensive experimental campaigns.

Coleman, John [Oak Ridge National Laboratory (ORNL↗

PyFly: A fast, portable aerodynamics simulator

Here, we present a fast, user-friendly implementation of a potential flow solver based on the unsteady vortex lattice method (UVLM), namely PyFly. UVLM computes the aerodynamic loads applied on lifting surfaces while capturing the unsteady effects such as the added mass forces, the growth of bound circulation, and the wake while assuming that the flow separation location is known a priori. This method is based on discretizing the body surface into a lattice of vortex rings and relies on the Biot–Savart law to construct the velocity field at every point in the simulated domain. We introduce the pointwise approximation approach to simulate the interactions of the far-field vortices to overcome the computational burden associated with the classical implementation of UVLM. The computational framework uses the Python programming language to provide an easy to handle user interface while the computational kernels are written in Fortran. The mixed language approach enables high performance regarding solution time and great flexibility concerning easiness of code adaptation to different system configurations and applications. The computational tool predicts the unsteady aerodynamic behavior of multiple moving bodies (e.g., flapping wings, rotating blades, suspension bridges) subject to incoming air. The aerodynamic simulator can also deal with enclosure effects, multi-body interactions, and B-spline representation of body shapes. Finally, we simulate different aerodynamic problems to illustrate the usefulness and effectiveness of PyFly.

97 MATHEMATICS AND COMPUTING↗

Enhanced read resolution in reconfigurable memristive synapses for Spiking Neural Networks

Abstract The synapse is a key element circuit in any memristor-based neuromorphic computing system. A memristor is a two-terminal analog memory device. Memristive synapses suffer from various challenges including high voltage, SET or RESET failure, and READ margin issues that can degrade the distinguishability of stored weights. Enhancing READ resolution is very important to improving the reliability of memristive synapses. Usually, the READ resolution is very small for a memristive synapse with a 4-bit data precision. This work considers a step-by-step analysis to enhance the READ current resolution or the read current difference between two resistance levels for a current-controlled memristor-based synapse. An empirical model is used to characterize the $${\hbox {HfO}}_{2}$$ HfO 2 based memristive device. $$1\textrm{st}$$ 1 st and $$2\textrm{nd}$$ 2 nd stage device of our proposed synapse design can be scaled to enhance the READ current margin up to $$\sim$$ ∼ 4.3 $$\times$$ × and $$\sim$$ ∼ 21%, respectively. Moreover, READ current resolution can be enhanced with run-time adaptation techniques such as READ voltage scaling and body biasing. The READ voltage scaling and body biasing can improve the READ current resolution by about 46% and 15%, respectively. TENNLab’s neuromorphic computing framework is leveraged to evaluate the effect of READ current resolution on classification, control, and reservoir computing applications. Higher READ current resolution shows better accuracy than lower resolution even when facing different levels of read noise.

97 MATHEMATICS AND COMPUTING↗

Gas-Granular Simulation Framework for Spacecraft Landing Plume-Surface Interaction and Debris Transport Analysis

The Gas-Granular Flow Solver (GGFS) multi-phase flow computational framework has been developed to enable simulations of particle flows complex extra-terrestrial regolith materials. Particle flows of interest include the damage of unprepared landing sites from rocket plume impingement on Moon, Mars, and asteroids. The flow solver implements an Eulerian-Eulerian two-fluid model with fluid representation of the gas phase and granular phase to avoid the need to model billions of particle interactions. The granular phase is modeled as an Eulerian fluid with constituent physics closure models derived from first-principle Discrete Element Model (DEM) particle interaction simulations that capture the complex, non-linear granular particle interaction effects. Granular phase constituent models have been developed and integrated that address the complex, non-linear granular material mechanics complexities resulting from both: the irregular, jagged particle shapes and poly-disperse mixture effects encountered in extra-terrestrial regolith, with lunar regolith as the extreme. The GGFS capabilities are being integrated into a proven NASA plume-surface interaction and debris transport simulation framework featuring the Loci/CHEM CFD program and Debris Transport Analysis (DTA) post-processing tools for applications in robotic and human Moon and Mars lander development. Integration of the three simulation tool components. Loci/CHEM, GGFS, and DTA, into a coordinated simulation framework will enable time-accurate spacecraft landing simulations that account for the alteration of the landing surface through plume-induced cratering and the resulting redirection of plume impingement flow and debris transport. Initial implementation of this simulation framework and application examples will be presented.

Liever, Peter A.↗

Engineering Overview of a Multidisciplinary HSCT Design Framework Using Medium-Fidelity Analysis Codes

An objective of the HPCC Program at NASA Langley has been to promote the use of advanced computing techniques to more rapidly solve the problem of multidisciplinary optimization of a supersonic transport configuration. As a result, a software system has been designed and is being implemented to integrate a set of existing discipline analysis codes, some of them CPU-intensive, into a distributed computational framework for the design of a High Speed Civil Transport (HSCT) configuration. The proposed paper will describe the engineering aspects of integrating these analysis codes and additional interface codes into an automated design system. The objective of the design problem is to optimize the aircraft weight for given mission conditions, range, and payload requirements, subject to aerodynamic, structural, and performance constraints. The design variables include both thicknesses of structural elements and geometric parameters that define the external aircraft shape. An optimization model has been adopted that uses the multidisciplinary analysis results and the derivatives of the solution with respect to the design variables to formulate a linearized model that provides input to the CONMIN optimization code, which outputs new values for the design variables. The analysis process begins by deriving the updated geometries and grids from the baseline geometries and grids using the new values for the design variables. This free-form deformation approach provides internal FEM (finite element method) grids that are consistent with aerodynamic surface grids. The next step involves using the derived FEM and section properties in a weights process to calculate detailed weights and the center of gravity location for specified flight conditions. The weights process computes the as-built weight, weight distribution, and weight sensitivities for given aircraft configurations at various mass cases. Currently, two mass cases are considered: cruise and gross take-off weight (GTOW). Weights information is obtained from correlations of data from three sources: 1) as-built initial structural and non-structural weights from an existing database, 2) theoretical FEM structural weights and sensitivities from Genesis, and 3) empirical as-built weight increments, non-structural weights, and weight sensitivities from FLOPS. For the aeroelastic analysis, a variable-fidelity aerodynamic analysis has been adopted. This approach uses infrequent CPU-intensive non-linear CFD to calculate a non-linear correction relative to a linear aero calculation for the same aerodynamic surface at an angle of attack that results in the same configuration lift. For efficiency, this nonlinear correction is applied after each subsequent linear aero solution during the iterations between the aerodynamic and structural analyses. Convergence is achieved when the vehicle shape being used for the aerodynamic calculations is consistent with the structural deformations caused by the aerodynamic loads. To make the structural analyses more efficient, a linearized structural deformation model has been adopted, in which a single stiffness matrix can be used to solve for the deformations under all the load conditions. Using the converged aerodynamic loads, a final set of structural analyses are performed to determine the stress distributions and the buckling conditions for constraint calculation. Performance constraints are obtained by running FLOPS using drag polars that are computed using results from non-linear corrections to the linear aero code plus several codes to provide drag increments due to skin friction, wave drag, and other miscellaneous drag contributions. The status of the integration effort will be presented in the proposed paper, and results will be provided that illustrate the degree of accuracy in the linearizations that have been employed.

Weston, R. P.↗

Autonomous nondestructive evaluation of resistance spot welded joints

The application of non-destructive evaluation approaches has attracted strong interests in modern automotive industries. Here, we present an autonomous deep-computing framework to analyze raw videos from infrared systems and to predict weld nugget shape and size with unprecedented accuracy and speed. In a comprehensive training and testing experiment with 90 videos (seven sets of welding material stack-ups), a new method was developed to assemble sufficient datasets for neural network training. Our framework successfully predicts all the nugget shapes with F1 scores that range from 0.84 to 0.92. The total training time on Nvidia DGX station takes less than 10 min for each set of welding material stack-up. The real inference time of an individual dataset (with 30 video frames) takes about 0.005 s. The procedure and methods developed in the study can be applied to other image-based weld property prediction, as well as other manufacturing processes. Furthermore, our well-trained neural networks take limited memory resources (2.3 MB) and are suitable for embedded microprocessors for in-situ welding quality control as edge computing within an intelligent welding framework.

42 ENGINEERING↗

Nanoindentation mapping defects filtration for heterogeneous materials using generative adversarial networks

Advanced composite materials with multiple phases and heterogeneous microstructure necessitate spatial mapping characterization of elastic modulus to develop constitutive relations and overall mechanical response. Such modulus mapping can be obtained using the nanoindentation technique, where the indenter tip raster over the selected microstructure region. Typically, a surface preparation procedure is done in the specimens to ensure proper contact between the indenter tip and sample surface. However, a near-perfect surface finish is unachievable in heterogeneous materials, primarily with ceramic reinforcements, due to the differential material removal rate during polishing. Thus, the nanoindenter records localized erroneous measurements due to differences in surface roughness and corresponding force response. This study establishes a novel deep learning-based strategy to rectify incorrect experimental spatial measurements acquire during nanoindentation modulus mapping. Here, the integrated bicubic interpolation and generative adversarial networks (GANs) model was trained using 14 ceramic and 18 metallic data sets, each comprising 65,536 measurements. The developed algorithm was validated against experimental measurements on four unknown specimens. The standard deviation in measured elastic modulus reduces by ~50% in ceramics and ~72% in metallic samples. This computational framework proposes a novel approach to reducing uncertainty in materials’ properties using state-of-the-art computer vision techniques.

36 MATERIALS SCIENCE↗

The LHC Compact Muon Solenoid experiment detector control system

The Compact Muon Solenoid (CMS) experiment at CERN is a multi-purpose experiment designed to exploit the physics of proton-proton collisions at the Large Hadron Collider collision energy (14TeV at centre of mass) over the full range of expected luminosities (up to 10(34)cm(-')(2)s(-')(1)). The CMS detector control system (DCS) ensures a safe, correct and efficient operation of the detector so that high quality physics data can be recorded. The system is also required to operate the detector with a small crew of experts who can take care of the maintenance of its software and hardware infrastructure. The subsystems size sum up to more than a million parameters that need to be supervised by the DCS. A cluster of roughly 100 servers is used to provide the required processing resources. A scalable approach has been chosen factorizing the DCS system as much as possible. CMS DCS has made clear a division between its computing resources and functionality by creating a computing framework allowing plugging in of functional components. DCS components are developed by the subsystems expert groups while the computing infrastructure is developed centrally. To ensure the correct operation of the detector, DCS organizes the communication between the accelerator and the experiment systems making sure that the detector is in a safe state during hazardous situations and is fully operational when stable conditions are present. This paper describes the current status of the CMS DCS focusing on operational aspects and the role of DCS in this communication.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Kodiak: An Implementation Framework for Branch and Bound Algorithms

Recursive branch and bound algorithms are often used to refine and isolate solutions to several classes of global optimization problems. A rigorous computation framework for the solution of systems of equations and inequalities involving nonlinear real arithmetic over hyper-rectangular variable and parameter domains is presented. It is derived from a generic branch and bound algorithm that has been formally verified, and utilizes self-validating enclosure methods, namely interval arithmetic and, for polynomials and rational functions, Bernstein expansion. Since bounds computed by these enclosure methods are sound, this approach may be used reliably in software verification tools. Advantage is taken of the partial derivatives of the constraint functions involved in the system, firstly to reduce the branching factor by the use of bisection heuristics and secondly to permit the computation of bifurcation sets for systems of ordinary differential equations. The associated software development, Kodiak, is presented, along with examples of three different branch and bound problem types it implements.

Smith, Andrew P.↗

A Framework for Neural Network Inference on FPGA-Centric SmartNICs

FPGA-based SmartNICs offer great potential to significantly improve the performance of high-performance computing and warehouse data processing by tightly coupling support for reconfigurable data-intensive computation with cross-node communication, thereby mitigating the von Neumann bottleneck. Existing work, however, has been generally been limited in that it assumes an accelerator model where kernels are offloaded to SmartNICs, but most control tasks are left to the CPUs. This leads to frequent waiting, inferior performance, and scaling challenges. In this work, we propose a new distributive data-centric computing framework, named FCsN, for reconfigurable SmartNIC-based systems. Through a lightweight task circulation execution model and its implementation architecture, FCsN allows the complete detaching of kernel execution, control logic, system scheduling, and network communication to the SmarNICs. This boosts performance by: (i) avoiding the control dependency with CPUs and (ii) supporting streaming kernel execution and network communication at line rate and in a very fine-grained manner. We demonstrate the efficiency and flexibility of FCsN using various types of neural network applications including graph neural networks; as these last are both irregular and data intensive they offer an especially robust demonstration. Evaluations using commonly-used neural network models and graph datasets show that a system with the support of FCsN can achieve, on average, 144 speedups over the MPI-based standard CPU baselines.

Guo, Anqi↗

A Machine Learning Framework for Modeling Ensemble Properties of Atomically Disordered Materials

Atomic disorder can strongly influence material properties such as charge transport, optical response, and catalytic activity. However, efficiently modeling these disorder effects remains challenging for first-principles methods due to the cost of sampling large configurational spaces and computing complex physical quantities. Recent advances of machine learning techniques, particularly graph neural networks (GNNs), has enabled the efficient and accurate predictions of complex material properties, offering promising tools for studying disordered systems. In this work, we present a general machine-learning-assisted computational framework that integrates equivariant GNNs with Monte Carlo simulations to compute the thermodynamic and ensemble-averaged functional properties of disordered materials. Using the surface-termination-disordered MXene monolayer Ti 3 C 2 T 2–x as a representative system, we find that electrical conductivity exhibits an emergent peak near the order–disorder phase transition temperature due to the interplay between electron scattering and doping. In contrast, optical conductivity remains largely insensitive to local atomic disorder and reflects the global surface chemical composition. These results highlight the role of atomic disorder in affecting material properties and demonstrate the potential of our approach for statistically modeling disorder effects in a wide range of materials such as high-entropy alloys and spin liquids.

MXene↗

Atomistic non-adiabatic dynamics of the LH2 complex with a GPU-accelerated ab initio exciton model

We recently outlined an efficient multi-tiered parallel ab initio excitonic framework that utilizes time dependent density functional theory (TDDFT) to calculate ground and excited state energies and gradients of large supramolecular complexes in atomistic detail – enabling us to undertake non-adiabatic simulations which explicitly account for the coupled anharmonic vibrational motion of all the constituent atoms in a supramolecular system. Here we apply that framework to the 27 coupled bacterio-chlorophyll-a chromophores which make up the LH2 complex, using it to compute an on-the-fly nonadiabatic surface-hopping (SH) trajectory of electronically excited LH2. Part one of this article is focussed on calibrating our ab initio exciton Hamiltonian using two key parameters: a shift δ, which corrects for the error in TDDFT vertical excitation energies; and an effective dielectric constant ε, which describes the average screening of the transition-dipole coupling between chromophores. Using snapshots obtained from equilibrium molecular dynamics simulations (MD) of LH2, we tune the values of both δ and ε through fitting to the thermally broadened experimental absorption spectrum, giving a linear absorption spectrum that agrees reasonably well with experiment. In part two of this article, we construct a time-resolved picture of the coupled vibrational and excitation energy transfer (EET) dynamics in the sub-picosecond regime following photo-excitation. Assuming Franck–Condon excitation of a narrow eigenstate band centred at 800 nm, we use surface hopping to follow a single nonadiabatic dynamics trajectory within the full eigenstate manifold. Consistent with experimental data, this trajectory gives timescales for B800→B850 population transfer (τ B800→B850 ) between 650–1050 fs, and B800 population decay (τ 800→ ) between 10–50 fs. The dynamical picture that emerges is one of rapidly fluctuating LH2 eigenstates that are delocalized over multiple chromophores and undergo frequent crossing on a femtosecond timescale as a result of the atomic vibrations of the constituent chromophores. The eigenstate fluctuations arise from disorder that is driven by vibrational dynamics with multiple characteristic timescales. The scalability of our ab initio excitonic computational framework across massively parallel architectures opens up the possibility of addressing a wide range of questions, including how specific dynamical motions impact both the pathways and efficiency of electronic energy-transfer within large supramolecular systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Unit commitment with wind power generation: integrating wind forecast uncertainty and stochastic programming.

We present a computational framework for integrating the state-of-the-art Weather Research and Forecasting (WRF) model in stochastic unit commitment/energy dispatch formulations that account for wind power uncertainty. We first enhance the WRF model with adjoint sensitivity analysis capabilities and a sampling technique implemented in a distributed-memory parallel computing architecture. We use these capabilities through an ensemble approach to model the uncertainty of the forecast errors. The wind power realizations are exploited through a closed-loop stochastic unit commitment/energy dispatch formulation. We discuss computational issues arising in the implementation of the framework. In addition, we validate the framework using real wind speed data obtained from a set of meteorological stations. We also build a simulated power system to demonstrate the developments.

17 WIND ENERGY↗