Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “NETWORKING”

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

Propagating uncertainties in large-scale hemodynamics models via network uncertainty quantification and reduced-order modeling

Numerical simulations of the cardiovascular system are affected by uncertainties arising from a substantial lack of data related to the boundary conditions and the physical parameters of the mathematical models. Quantifying the impact of this uncertainty on the numerical results along the circulatory network is challenged by the complexity of both the morphology of the domain and the local dynamics. Here, we propose to integrate (i) the Transverse Enriched Pipe Element Methods (TEPEM) as a reduced-order model for effectively computing the 3D local hemodynamics; and (ii) a combination of uncertainty quantification via Polynomial Chaos Expansion and classical relaxation methods – called network uncertainty quantification (NetUQ) – for effectively propagating random variables that encode uncertainties throughout the networks. The findings demonstrate the computational effectiveness of computing the propagation of uncertainties in networks with nontrivial topology, including portions of the cerebral and the coronary systems.

97 MATHEMATICS AND COMPUTING↗

SO(3)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials

This work examines the frame-invariance (and the lack thereof) exhibited in simulated anisotropic elasto-plastic responses generated from supervised machine learning of classical multi-layer and informed-graph-based neural networks, and proposes different remedies to fix this drawback. The inherent hierarchical relations among physical quantities and state variables in an elasto-plasticity model are first represented as informed, directed graphs, where three variations of the graph are tested. While feed-forward neural networks are used to train path-independent constitutive relations (e.g., elasticity), recurrent neural networks are used to replicate responses that depends on the deformation history, i.e. or path dependent. In dealing with the objectivity deficiency, we use the spectral form to represent tensors and, subsequently, three metrics, the Euclidean distance between the Euler Angles, the distance from the identity matrix, and geodesic on the unit sphere in Lie algebra, can be employed to constitute objective functions for the supervised machine learning. In this, the aim is to minimize the measured distance between the true and the predicted 3D rotation entities. Following this, we conduct numerical experiments on how these metrics, which are theoretically equivalent, may lead to differences in the efficiency of the supervised machine learning as well as the accuracy and robustness of the resultant models. Neural network models trained with tensors represented in component form for a given Cartesian coordinate system are used as a benchmark. Our numerical tests show that, even given the same amount of information and data, the quality of the anisotropic elasto-plasticity model is highly sensitive to the way tensors are represented and measured. The results reveal that using a loss function based on geodesic on the unit sphere in Lie algebra together with an informed, directed graph yield significantly more accurate rotation prediction than the other tested approaches.

42 ENGINEERING↗

PPINN: Parareal physics-informed neural network for time-dependent PDEs

Physics-informed neural networks (PINNs) encode physical conservation laws and prior physical knowledge into the neural networks, ensuring the correct physics is represented accurately while alleviating the need for supervised learning to a great degree. While effective for relatively short-term time integration, when long time integration of the time-dependent PDEs is sought, the time–space domain may become arbitrarily large and hence training of the neural network may become prohibitively expensive. To this end, we develop a parareal physics-informed neural network (PPINN), hence decomposing a long-time problem into many independent short-time problems supervised by an inexpensive/fast coarse-grained (CG) solver. In particular, the serial CG solver is designed to provide approximate predictions of the solution at discrete times, while initiate many fine PINNs simultaneously to correct the solution iteratively. There is a two-fold benefit from training PINNs with small-data sets rather than working on a large-data set directly, i.e., training of individual PINNs with small-data is much faster, while training the fine PINNs can be readily parallelized. Consequently, compared to the original PINN approach, the proposed PPINN approach may achieve a significant speed-up for long-time integration of PDEs, assuming that the CG solver is fast and can provide reasonable predictions of the solution, hence aiding the PPINN solution to converge in just a few iterations. To investigate the PPINN performance on solving time-dependent PDEs, we first apply the PPINN to solve the Burgers equation, and subsequently we apply the PPINN to solve a two-dimensional nonlinear diffusion–reaction equation. Furthermore, our results demonstrate that PPINNs converge in a few iterations with significant speed-ups proportional to the number of time-subdomains employed.

42 ENGINEERING↗

hp -VPINNs: Variational physics-informed neural networks with domain decomposition

We formulate a general framework for hp-variational physics-informed neural networks (hp-VPINNs) based on the nonlinear approximation of shallow and deep neural networks and hp-refinement via domain decomposition and projection onto the space of high-order polynomials. The trial space is the space of neural network, which is defined globally over the entire computational domain, while the test space contains piecewise polynomials. Specifically in this study, the hp-refinement corresponds to a global approximation with a local learning algorithm that can efficiently localize the network parameter optimization. Here, we demonstrate the advantages of hp-VPINNs in both accuracy and training cost for several numerical examples of function approximation and in solving differential equations.

42 ENGINEERING↗

Learning viscoelasticity models from indirect data using deep neural networks

In this study, we propose a novel approach to model viscoelasticity materials, where rate-dependent and non-linear constitutive relationships are approximated with deep neural networks. We assume that inputs and outputs of the neural networks are not directly observable, and therefore common training techniques with input–output pairs for the neural networks are inapplicable. To that end, we develop a novel computational approach to both calibrate parametric and learn neural-network-based constitutive relations of viscoelasticity materials from indirect displacement data in the context of multiple-physics systems. We show that limited displacement data holds sufficient information to quantify the viscoelasticity behavior. We formulate the inverse computation – modeling viscoelasticity properties from observed displacement data – as a PDE-constrained optimization problem and minimize the error functional using a gradient-based optimization method. The gradients are computed by a combination of automatic differentiation and implicit function differentiation rules. The effectiveness of our method is demonstrated through numerous benchmark problems in geomechanics and porous media transport.

97 MATHEMATICS AND COMPUTING↗

Effects of input gradient regularization on neural networks time-series forecasting of thermal power systems

This study proposes using neural networks, specifically gated recurrent unit (GRU), long-short-term memory (LSTM), and transformer networks, to improve control strategies in a 450 MW coal-fired power plant. However, neural networks face issues of becoming overly dependent on just a few variables to make predictions, which negatively impacts control decisions that rely on the model to determine the value of all manipulated variables. The paper introduces regularization techniques, including noise injection and input gradient regularization, during the training phase. Here, the work presents novel contributions in adapting neural networks to control industrial systems and applying regularization techniques from computer vision to industrial process control. Results demonstrate the effectiveness of input gradient regularization in reducing model dependence on subsets of variables, emphasizing the balance between fidelity and controllability. Further exploration is recommended, including the development of recurrent transformers, closed-loop control testing, and a sensitivity analysis on computer models to provide further insight.

20 FOSSIL-FUELED POWER PLANTS↗

Keras2c: A library for converting Keras neural networks to real-time compatible C

With the growth of machine learning models and neural networks in measurement and control systems comes the need to deploy these models in a way that is compatible with existing systems. Existing options for deploying neural networks either introduce very high latency, require expensive and time consuming work to integrate into existing code bases, or only support a very limited subset of model types. We have therefore developed a new method called Keras2c, which is a simple library for converting Keras/TensorFlow neural network models into real-time compatible C code. It supports a wide range of Keras layers and model types including multidimensional convolutions, recurrent layers, multi-input/output models, and shared layers. Keras2c re-implements the core components of Keras/TensorFlow required for predictive forward passes through neural networks in pure C, relying only on standard library functions considered safe for real-time use. The core functionality consists of ~ 1500 lines of code, making it lightweight and easy to integrate into existing codebases. Keras2c has been successfully tested in experiments and is currently in use on the plasma control system at the DIII-D National Fusion Facility at General Atomics in San Diego.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Physics-informed heterogeneous graph neural networks for DC blocker placement

The threat of geomagnetic disturbances (GMDs) to the reliable operation of the bulk energy system has spurred the development of effective strategies for mitigating their impacts. One such approach involves placing transformer neutral blocking devices, which interrupt the path of geomagnetically induced currents (GICs) to limit their impact. The high cost of these devices and the sparsity of transformers that experience high GICs during GMD events, however, calls for a sparse placement strategy that involves high computational cost. To address this challenge, we developed a physics-informed heterogeneous graph neural network (PIHGNN) for solving the graph-based dc-blocker placement problem. Our approach combines a heterogeneous graph neural network (HGNN) with a physics-informed neural network (PINN) to capture the diverse types of nodes and edges in ac/dc networks and incorporates the physical laws of the power grid. We train the PIHGNN model using a surrogate power flow model and validate it using case studies. Results demonstrate that PIHGNN can effectively and efficiently support the deployment of GIC dc-current blockers, ensuring the continued supply of electricity to meet societal demands. Furthermore, our approach has the potential to contribute to the development of more reliable and resilient power grids capable of withstanding the growing threat that GMDs pose.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Moving small files in a networked environment

Globally distributed computing infrastructures, such as clouds and supercomputers, are currently used to manage data that is generated with an unprecedented speed from a variety of resources. Coping with this trend, the volume of data exchanged across distant sites increases substantially. To accelerate data transfer, high-speed networks are provided to connect remote sites. Most existing data movement solutions are optimized for moving large files. However, it is still challenging to transfer a large number of small files across networks. This disadvantage not only lowers data transfer performance, but also decreases overall system utilization. Here, we identify that moving small files is mainly constrained by degraded file system throughput, not just network performance as might be suspected. We have built a data transfer pipeline model to analyze the impact of small network I/O and storage I/O on data movement. Extending one of the widely used open source data movement solutions, GridFTP, we demonstrate several appropriate engineering approaches that mitigate the bottleneck and increase data transfer efficiency. We show optimizations that improve data transfer performance more than 5 times. In comparison to existing solutions, our approaches can save a significant amount of system resources for moving lots of small files.

97 MATHEMATICS AND COMPUTING↗

Brain in situ hybridization maps as a source for reverse-engineering transcriptional regulatory networks: Alzheimer's disease insights

Microarray data have been a valuable resource for identifying transcriptional regulatory relationships among genes. As an example, brain region-specific transcriptional regulatory events have the potential of providing etiological insights into Alzheimer Disease (AD). However, there is often a paucity of suitable brain-region specific expression data obtained via microarrays or other high throughput means. The Allen Brain Atlas in situ hybridization (ISH) data sets (Jones et al., 2009) represent a potentially valuable alternative source of high-throughput brain region-specific gene expression data for such purposes. In this study, Allen BrainAtlasmouse ISH data in the hippocampal fields were extracted, focusing on 508 genes relevant to neurodegeneration. Transcriptional regulatory networkswere learned using three high-performing network inference algorithms. Only 17% of regulatory edges from a network reverse-engineered based on brain region-specific ISH data were also found in a network constructed upon gene expression correlations inmousewhole brain microarrays, thus showing the specificity of gene expression within brain sub-regions. Furthermore, the ISH data-based networks were used to identify instructive transcriptional regulatory relationships. Ncor2, Sp3 and Usf2 form a unique three-party regulatory motif, potentially affecting memory formation pathways. Nfe2l1, Egr1 and Usf2 emerge among regulators of genes involved in AD (e.g. Dhcr24, Aplp2, Tia1, Pdrx1, Vdac1, andSyn2). Further, Nfe2l1, Egr1 and Usf2 are sensitive to dietary factors and could be among links between dietary influences and genes in the AD etiology. Thus, this approach of harnessing brain region-specific ISH data represents a rare opportunity for gleaning unique etiological insights for diseases such as AD.

59 BASIC BIOLOGICAL SCIENCES↗

Carbon dioxide pipeline network transportation cost model: evaluating economic and geographic factors for efficient carbon capture, storage, and utilization

This study presents a comprehensive pipeline network modeling framework to estimate the CO 2 delivery cost for CO 2 utilization and geologic CO 2 storage across the United States. We developed a Python-based CO 2 pipeline transportation cost model leveraging Argonne National Laboratory’s pipeline engineering expertise and detailed natural gas transmission pipeline cost data across U.S. regions. Using existing road corridors as practical routing guides, the model designs pipeline networks that aggregate CO 2 from one or multiple sources and deliver it to selected destinations. It then minimizes the total transportation cost by optimizing pipeline diameters and incorporating booster pumps. A key contribution is the incorporation of up-to-date, region-specific cost factors with itemized components for materials, labor, miscellaneous construction expenses, and right-of-way acquisition. Results emphasize that regional variation and economies of scale associated with CO 2 pipeline costs are significant and should be explicitly accounted for in screening and planning studies. By combining realistic routing constraints with regionalized cost inputs, the model provides transparent design methodology and location-specific insights into source–destination delivery costs, including the effects of routing complexity along existing road networks. We demonstrate the model with two illustrative case studies – one for CO 2 storage and one for CO 2 utilization – in which the model designs pipeline networks spanning hundreds of miles across the states, collecting CO 2 from multiple sources and delivering it to designated endpoints while minimizing levelized cost of delivery via diameter and compression optimization. The model offers a practical, scalable approach for alternative design option screening and early-stage CO 2 transportation planning.

CCS↗

Cost of a potential hydrogen-refueling network for heavy-duty vehicles with long-haul application in Germany 2050

Long-distance road-freight transport emits a large share of Germany's greenhouse gas (GHG) emissions. A potential solution for reducing GHG emissions in this sector is to use green hydrogen in fuel cell electric vehicles (FC-HDV) and establish an accompanying hydrogen refueling station (HRS) network. In this paper, we apply an existing refueling network design model to a HDV-HRS network for Germany until 2050 based on German traffic data for heavy-duty trucks and estimate its costs. Comparing different fuel supply scenarios (pipeline vs. on-site), the on-site scenario results show a network consisting of 137 stations at a cost of 8.38 billion € per year in 2050 (0.40 € per vehicle km), while the centralized scenario with the same amount of stations shows a cheaper cost with 7.25 billion euros per year (0.35 € per vehicle km). Finally, the hydrogen cost (LCOH) varies from 5.59 €/kg (pipeline) to 6.47 €/kg (on-site) in 2050.

08 HYDROGEN↗

Algebraic Stabilization of Explicit Numerical Integration for Extremely Stiff Reaction Networks

In contrast to the prevailing view in the literature, it is shown that even extremely stiff sets of ordinary differential equations may be solved efficiently by explicit methods if limiting algebraic solutions are used to stabilize the numerical integration. The stabilizing algebra differs essentially for systems well removed from equilibrium and those near equilibrium. Explicit asymptotic and quasi-steady-state methods that are appropriate when the system is only weakly equilibrated are examined first. These methods are then extended to the case of close approach to equilibrium through a new implementation of partial equilibrium approximations. Using stringent tests with astrophysical thermonuclear networks, evidence is provided that these methods can deal with the stiffest networks, even in the approach to equilibrium, with accuracy and integration timestepping comparable to that of implicit methods. Because explicit methods can execute a timestep faster and scale more favorably with network size than implicit algorithms, our results suggest that algebraically stabilized explicit methods might enable integration of larger reaction networks coupled to fluid dynamics than has been feasible previously for a variety of disciplines.

differential equations↗

A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems

Presently the training of neural networks relies on data of comparable accuracy but in real applications only a very small set of high-fidelity data is available while inexpensive lower fidelity data may be plentiful. We propose a new composite neural network (NN) that can be trained based on multi-fidelity data. It is comprised of three NNs, with the first NN trained using the low-fidelity data and coupled to two high-fidelity NNs, one with activation functions and another one without, in order to discover and exploit nonlinear and linear correlations, respectively, between the low-fidelity and the high-fidelity data. We first demonstrate the accuracy of the new multi-fidelity NN for approximating some standard benchmark functions but also a 20-dimensional function that is not easy to approximate with other methods, e.g. Gaussian process regression. Subsequently, we extend the recently developed physics-informed neural networks (PINNs) to be trained with multi-fidelity data sets (MPINNs). MPINNs contain four fully-connected neural networks, where the first one approximates the low-fidelity data, while the second and third construct the correlation between the low- and high-fidelity data and produce the multi-fidelity approximation, which is then used in the last NN that encodes the partial differential equations (PDEs). Specifically, by decomposing the correlation into a linear and nonlinear part, the present model is capable of learning both the linear and complex nonlinear correlations between the low- and high-fidelity data adaptively. By training the MPINNs, we can: (1) obtain the correlation between the low- and high-fidelity data, (2) infer the quantities of interest based on a few scattered data, and (3) identify the unknown parameters in the PDEs. In particular, we employ the MPINNs to learn the hydraulic conductivity field for unsaturated flows as well as the reactive models for reactive transport. The results demonstrate that MPINNs can achieve relatively high accuracy based on a very small set of high-fidelity data. Despite the relatively low dimension and limited number of fidelities (two-fidelity levels) for the benchmark problems in the present study, the proposed model can be readily extended to very high-dimensional regression and classification problems involving multi-fidelity data.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Explicitly integrating parameter, input, and structure uncertainties into Bayesian Neural Networks for probabilistic hydrologic forecasting

Estimating uncertainty of hydrologic forecasting is valuable to water resources and other relevant decision making processes. Recently, Bayesian Neural Networks (BNNs) have been proved powerful tools for quantifying uncertainty of streamflow forecasting. In this study, we propose a Markov Chain Monte Carlo (MCMC) framework to incorporate the uncertainties associated with input, model structure, and parameter into BNNs. This framework allows the structure of the neural networks to change by removing or adding connections between neurons and enables scaling of input data by using rainfall multipliers. The results show that the new BNNs outperform the BNNs that only consider uncertainties associated with parameter and model structure. Critical evaluation of posterior distribution of neural network weights, number of effective connections, rainfall multipliers, and hyper-parameters show that the assumptions held in our BNNs are not well supported. Further understanding of characteristics of different uncertainty sources and including output error into the MCMC framework are expected to enhance the application of neural networks for uncertainty analysis of hydrologic forecasting.

58 GEOSCIENCES↗

Dynamics of virtual water networks: Role of national socio-economic indicators across the world

Intensified water usage due to rapid industrialization is often dictated by economic policies based on monetary growth rather than sustainable use of environmental resources. In addition, interdependence within economic sectors further interweaves water usage through product transactions, which further makes it difficult to quantify the dynamics of hydro-economic systems at regional, national and global scale. In this study, we investigated the dynamics of domestic virtual water networks (VWN) of 189 countries based on concept of information theory by quantifying network metrics that describes VWN flow capacity, robustness, efficiency and flexibility. These networks represent virtual water interconnected through economic sectors within a specified country built based on environmentally extended multi region input output (EE-MRIO) approach. We further estimated trends associated with network metrics, as well as coupling intensity between metrics with respect to socio-economic indicators, such as, population, Gross Domestic Product (GDP) and Gross National Income (GNI). It was observed that capacity and flexibility of VWNs are strongly and positively correlated indicating that a high capacity VWN can be more flexible. Our results also indicate that, in general a higher percentage of developing countries (i.e. both least developing and developing nations) have exhibited increasing trends in capacity, robustness, efficiency and flexibility of VWN compared to developed nations. It was revealed that the dynamics of VWNs are positively coupled with socio-economic growth for few countries, which indicates the sustainable behavior of VWN with socio-economic growth. Our results argue that the information theory-based metrics by embedding water footprints can holistically capture sustainability aspect of the VWN dynamics.

54 ENVIRONMENTAL SCIENCES↗

Generating synthetic signaling networks for in silico modeling studies

Predictive models of signaling pathways have proven to be difficult to develop. Reasons include the uncertainty in the number of species, the complexity in species’ interactions, and the sparseness and uncertainty in experimental data. Traditional approaches to developing mechanistic models rely on collecting experimental data and fitting a single model to that data. This approach works for simple systems but has proven unreliable for complex systems such as biological signaling networks. For example, uncertainty and sparseness of the data often result in overfitted models that have little predictive value beyond recapitulating the experimental data itself. Thus, there is a need to develop new approaches to create predictive mechanistic models of complex systems. However, to determine the effectiveness of any new algorithm, a baseline model is needed to test its performance. To meet this need, we developed a method for generating artificial synthetic networks that are reasonably realistic and thus can be treated as ground truth models. These synthetic models can then be used to generate synthetic data for developing and testing algorithms designed to recover the underlying network topology and associated parameters. Here, we describe a simple approach for generating synthetic signaling networks that can be used for this purpose.

42 ENGINEERING↗

SympGNNs: Symplectic Graph Neural Networks for identifying high-dimensional Hamiltonian systems and node classification

Existing neural network models to learn Hamiltonian systems, such as SympNets, although accurate in low-dimensions, struggle to learn the correct dynamics for high-dimensional many-body systems. Herein, we introduce Symplectic Graph Neural Networks (SympGNNs) that can effectively handle system identification in high-dimensional Hamiltonian systems, as well as node classification. SympGNNs combine symplectic maps with permutation equivariance, a property of graph neural networks. Specifically, we propose two variants of SympGNNs: (i) G-SympGNN and (ii) LA-SympGNN, arising from different parameterizations of the kinetic and potential energy. We demonstrate the capabilities of SympGNN on two physical examples: a 40-particle coupled Harmonic oscillator, and a 2000-particle molecular dynamics simulation in a two-dimensional Lennard-Jones potential. Furthermore, we demonstrate the performance of SympGNN in the node classification task, achieving accuracy comparable to the state-of-the-art. Finally, we also empirically show that SympGNN can overcome the oversmoothing and heterophily problems, two key challenges in the field of graph neural networks.

Deep learning↗