SEARCH · Engineering Papers

Results for “Network Models”

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 1,369 records · Page 76

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Foundation AI Models for Science

Foundation Models (FM) are AI models that are designed to replace a task or an application specific model. These FM can be applied to many different downstream applications. These FM are trained using self supervised techniques and can be built on any type of sequence data. The use of self supervised learning removes the hurdle for developing a large labeled dataset for training. Most FM use transformer architecture utilizes the notion of self attention which allows the network to model the influence of distant data points to each other both in space and time. The FM models exhibit emergent properties that are induced from the data. FM can be an important tool for science. The scale of these models results in better performance for different downstream applications and these applications show better accuracy over models built from scratch. FM drastically reduces the cost of entry to build different downstream applications both in time and effort. FM for selected science datasets such as optical satellite data, can accelerate applications ranging from data quality monitoring, feature detection and prediction. FM can make it easier to infuse AI into scientific research by removing the training data bottleneck and increasing the use of science data.

Manil Maskey↗

DOE OSTI2023

Identifying common stored product insects using automated deep learning methods

Monitoring stored product insect pests is a common practice for post-harvest management of stored grain and grain-based commodities, which helps ensure product quality from harvest to final consumer. Current methods of sampling and monitoring can be time-consuming, labor-intensive, expensive and require expertise in insect identification. Therefore, this study aims to develop an image-based automated identification system for common stored product insect species using deep-learning methods. Top-down images of the common stored product adult insect species of Rhyzopertha dominica, Cryptolestes ferrugineus, Tribolium castaneum, Sitophilus oryzae, and Oryzaephilus surinamensis were acquired and analyzed. Deep learning-based, state-of-the-art Convolutional Neural Networks (CNN) models (ResNet-50, MobileNet-v2, DarkNet-53, and EfficientNet-b0) were fine-tuned with a transfer learning approach to classify the insect species. All models were able to correctly identify the insect species with at least 96% accuracy and with few misclassifications. One issue with trained CNNs is that they do not explain the reasoning for the classification and are often called a “black box”. Therefore, visualization methods called Gradient-weighted Class Activation Mapping (Grad-CAM) were implemented to explore the black box network. The Grad-CAM uses heat maps to highlight the major image features that the network focused on to make insect species predictions. The Grad-CAM verifies the network's prediction and also helps improve network performance. This study contributes to the overall goal of developing a camera-based system for monitoring stored grain insects. As a result, the developed system would empower warehouse, flour mills, and other food facilities with a tool to quickly and accurately identify insect species in stored product environments and could be implemented as part of a close to real-time monitoring system.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Deep energy-pressure regression for a thermodynamically consistent EOS model

Abstract In this paper, we aim to explore novel machine learning (ML) techniques to facilitate and accelerate the construction of universal equation-Of-State (EOS) models with a high accuracy while ensuring important thermodynamic consistency. When applying ML to fit a universal EOS model, there are two key requirements: (1) a high prediction accuracy to ensure precise estimation of relevant physics properties and (2) physical interpretability to support important physics-related downstream applications. We first identify a set of fundamental challenges from the accuracy perspective, including an extremely wide range of input/output space and highly sparse training data. We demonstrate that while a neural network (NN) model may fit the EOS data well, the black-box nature makes it difficult to provide physically interpretable results, leading to weak accountability of prediction results outside the training range and lack of guarantee to meet important thermodynamic consistency constraints. To this end, we propose a principled deep regression model that can be trained following a meta-learning style to predict the desired quantities with a high accuracy using scarce training data. We further introduce a uniquely designed kernel-based regularizer for accurate uncertainty quantification. An ensemble technique is leveraged to battle model overfitting with improved prediction stability. Auto-differentiation is conducted to verify that necessary thermodynamic consistency conditions are maintained. Our evaluation results show an excellent fit of the EOS table and the predicted values are ready to use for important physics-related tasks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Application of machine learning to characterize gas hydrate reservoirs in Mackenzie Delta (Canada) and on the Alaska north slope (USA)

Here, artificial neural network-trained models were used to predict gas hydrate saturation distributions in permafrost-associated deposits in the Eileen Gas Hydrate Trend on the Alaska North Slope (ANS), USA and at the Mallik research site in the Beaufort-Mackenzie Basin, Northwest Territories, Canada. The database of Logging-While-Drilling (LWD) and wireline logs collected at five wells (Mount Elbert, Ignik Sikumi, and Kuparuk 7–11–12 wells at ANS, plus 2L-38 and 5L-38 wells at the Mallik research site) includes more than 10,000 depth points, which were used for training, validation, and testing the machine learning (ML) models. Data used in training the ML models include the well logs of density, porosity, electrical resistivity, gamma radiation, and acoustic wave velocity measurements. Combinations of two or three out of these five well logs were found to reliably predict the gas hydrate saturation with accuracy varying between 80 and 90% when compared to the gas hydrate saturations derived from Nuclear Magnetic Resonance (NMR)-based technique. The ML models trained on data from three ANS wells achieved high fidelity predictions of gas hydrate saturation at the Mallik site. The results obtained in this study indicate that ML models trained on data from one geological basin can successfully predict key reservoir parameters for permafrost-associated gas hydrate accumulations within another basin. A generalized approach for selecting a well log combination that can improve model accuracy is discussed. Overall, the study outcome supports earlier work demonstrating that ML models trained on non-NMR well logs are a viable alternative to physics-driven methods for predicting gas hydrate saturations.

58 GEOSCIENCES↗

DOE OSTI2020

Comparison of machine learning techniques to optimize the analysis of plutonium surrogate material via a portable LIBS device

The utilization of machine learning techniques has become commonplace in the analysis of optical emission spectra. These methods are often limited to variants of principal components analysis (PCA), partial-least squares (PLS), and artificial neural networks (ANNs). A plethora of other techniques exist and are well established in the world of data science, yet are seldom investigated for their use in spectroscopic problems. In this study, machine learning techniques were used to analyze optical emission spectra of laser-induced plasma from ceria pellets doped with silicon in order to predict silicon content. Additionally, a boosted regression ensemble model was created, and its predictive accuracy was compared to that of traditional PCA, PLS, and ANN regression models. Boosted regression tree ensembles yielded fits with R-squared (R2) values as high as 0.964 and mean-squared errors of prediction (MSEPs) as low as 0.074, providing the most accurate predictive model. Neural networks performed with slightly lower R2 values and higher MSEPs compared to the ensemble methods, thus indicating susceptibility to overfitting.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

SWARM: Reimagining scientific workflow management systems in a distributed world

Modern scientific workflows process massive amounts of data from diverse instruments and sensors, leveraging geographically distributed, heterogeneous compute and storage resources—from leadership-class systems to edge devices—connected by high-performance networks. The diversity of resources introduces challenges in harnessing their full potential, with resilience issues arising across applications, system software, networks, storage, and hardware. Today, workflow management systems (WMS) coordinate the execution of computation and data management tasks across target resources. However, WMS’s centralized nature makes them vulnerable to faults and scalability issues that may result in failures of entire computational campaigns. In conclusion, this paper introduces a novel agentic framework for workflow management, fully distributing and decentralizing the WMS functions and modeling them as swarm intelligence agents infused with advanced artificial intelligence solutions and traditional distributed computing algorithms that can make coordinated decisions in the presence of failures of the underlying cyberinfrastructure.

Swarm intelligence↗

DOE OSTI2021

Deep Learning-Based Hardness Prediction of Novel Refractory High-Entropy Alloys with Experimental Validation

Hardness is an essential property in the design of refractory high entropy alloys (RHEAs). This study shows how a neural network (NN) model can be used to predict the hardness of a RHEA, for the first time. We predicted the hardness of several alloys, including the novel C0.1Cr3Mo11.9Nb20Re15Ta30W20 using the NN model. The hardness predicted from the NN model was consistent with the available experimental results. The NN model prediction of C0.1Cr3Mo11.9Nb20Re15Ta30W20 was verified by experimentally synthesizing and investigating its microstructure properties and hardness. This model provides an alternative route to determine the Vickers hardness of RHEAs.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations

This paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process from multivariate time-series data and the effects of exogenous variables, such as control adjustment and ambient temperature. In the LSDNN model, an encoder–decoder architecture was designed to capture cross-correlation among different measured variables. In addition, a latent space dynamic structure was proposed to propagate the dynamics in the latent space to enable prediction. The prediction power of the LSDNN was utilized for monitoring a geothermal power plant and detecting abnormal events. The model was integrated with principal component analysis (PCA)-based process monitoring techniques to develop a fault-detection procedure. The performance of the proposed LSDNN model and fault detection approach was demonstrated using field data collected from a geothermal power plant.

15 GEOTHERMAL ENERGY↗

NASA NTRS1990

Modeling of the Space Station Freedom data management system

The data management system (DMS) is the information and communications system onboard Space Station Freedom. Extensive modeling of the DMS is being conducted throughout NASA to aid in the design and development of this vital system. Activities to model the DMS network infrastructure are described, focusing on modeling of the fiber distributed data interface (FDDI) token-ring protocol and experimental testbedding of networking aspects of the DMS.

Johnson, Marjory J.↗

DOE OSTI2022

ASPIRES: Airport Shuttle Planning and Improved Routing Event-driven Simulation

Most of the existing traffic simulation packages require significant calibration work to be able to reflect reality. To evaluate special operations including emerging technologies, a microscopic simulation that tracks detailed interactions of all the elements of the traffic systems is usually needed. This type of simulation is usually computationally demanding. This work developed an Airport Shuttle Planning and Improved Routing Event-driven Simulation (ASPIRES) package to simulate and evaluate current, potential, and future airport shuttle operations. Here, the simulation was driven by data and thus did not require much calibration effort. The discrete-event simulation nature of ASPIRES makes the simulation computationally efficient. Simulating 1 day of shuttle operations takes less than 2s. The study site of this work is the Dallas/Fort Worth International Airport in the U.S. The shuttle service that connects the five terminals of the airport and the rental car center was studied. Travel times, dwell times, and passenger arrivals were simulated using empirical distributions derived mainly from real data to capture the stochastic nature of the rental car center shuttle bus operations. Data on bus miles traveled, bus energy consumption, passenger wait times, and passengers left behind at stops were collected to study the trade-off between energy use and passenger experience. Electric bus and on-demand bus operations were also included. The simulation outputs can show passengers statistics at terminals, shuttles statistics, and charging station statistics. ASPIRES cannot be used to model a generic traffic system but is well-suited for fleet systems.

33 ADVANCED PROPULSION SYSTEMS↗

NASA NTRS1992

Functional expansion representations of artificial neural networks

In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.

Gray, W. Steven↗

DOE OSTI2022

Analytic model of dislocation density evolution in fcc polycrystals accounting for dislocation generation, storage, and dynamic recovery mechanisms

Here, an analytic model of the evolution of dislocation density in fcc polycrystals is described. The evolution equations approximately account for most known dislocation storage, dynamic recovery, and dislocation generation mechanisms in fcc polycrystals. Specifically, the model incorporates network (forest) and grain boundary storage, mobile-network and mobile–mobile annihilation, screw–screw annihilation via athermal and thermal single cross-slip, generation by double cross-slip (Koehler mechanism, including dipole formation), Frank-Read sources, grain boundary nucleation, and mobile–immobile dislocation nucleation due to shock loading. Single cross-slip is assumed to proceed through the Friedel–Escaig (FE) mechanism; the corresponding activation energy is calculated using a modified FE model. The activation energy for double cross-slip is calculated for the first time by extending the FE model. The exact evolution equations are integro-differential equations, and as such are difficult to implement in a code; hence, the evolution equations are simplified by making several approximations. Preliminary results on copper are presented, including comparisons to experimental data.

36 MATERIALS SCIENCE↗

NASA NTRS2012

Aircraft system modeling error and control error

A method for modeling error-driven adaptive control of an aircraft. Normal aircraft plant dynamics is modeled, using an original plant description in which a controller responds to a tracking error e(k) to drive the component to a normal reference value according to an asymptote curve. Where the system senses that (1) at least one aircraft plant component is experiencing an excursion and (2) the return of this component value toward its reference value is not proceeding according to the expected controller characteristics, neural network (NN) modeling of aircraft plant operation may be changed. However, if (1) is satisfied but the error component is returning toward its reference value according to expected controller characteristics, the NN will continue to model operation of the aircraft plant according to an original description.

Kulkarni, Nilesh V.↗

DOE OSTI2021

Modeling laser-driven ion acceleration with deep learning

Developments in machine learning promise to ameliorate some of the challenges of modeling complex physical systems through neural-network-based surrogate models. High-intensity, short-pulse lasers can be used to accelerate ions to mega-electronvolt energies, but to model such interactions requires computationally expensive techniques such as particle-in-cell simulations. Multilayer neural networks allow one to take a relatively sparse ensemble of simulations and generate a surrogate model that can be used to rapidly search the parameter space of interest. In this study, we created an ensemble of over 1,000 simulations modeling laser-driven ion acceleration and developed a surrogate to study the resulting parameter space. A neural-network-based approach allows for rapid feature discovery not possible for traditional parameter scans given the computational cost. A notable observation made during this study was the dependence of ion energy on the pre-plasma gradient length scale. While this methodology harbors great promise for ion acceleration, it has ready application to all topics in which large-scale parameter scans are restricted by significant computational cost or relatively large, but sparse, domains.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

SOC Microstructural Property Estimator

This pre-trained ML model is a tool that uses basic compositional parameters for porous solid oxide cell (SOC) electrodes - the phase fractions and mean particle/pore diameters – as inputs and uses them to estimate additional electrochemical performance parameters: active (i.e., connected) TPB density, all tortuosity factors, and phase pair specific interfacial areas. The electrode is assumed to be composed of two solid phases and a pore phase. The property calculations are performed using neural network regression models trained on a large bank of synthetic electrode microstructural data that NETL has generated using the program DREAM3D (that bank is also hosted on EDX: https://edx.netl.doe.gov/dataset/soc-synthetic-microstructure-bank). This means the generated parameters are based on training from actual measured properties from 3D microstructures, not estimated from geometric simplifications. This tool was developed and is intended to replace percolation theory calculations in models that use hypothetical electrode properties. An example use case would be running SOC performance simulations across a parametric sweep of electrode designs (e.g., varying phase fractions and particle sizes) and assessing how it impacts the electrochemical performance of the SOC. Within the parameter space of the training data (statistics of that parameter space is provided in the readme file), this model achieves sub-5% mean absolute percent errors, an order of magnitude less error than percolation theory across the same parameter space. However, be aware that this tool was developed with parametric simulations in mind, and users are encouraged to assess accuracy for their own specific use case rather than taking accuracy metrics at face value. More info, including a usage guide, is in the included readme file. This tool should be cited with the DOI number provided.

Electrode Microstructure↗

DOE OSTI2025

Machine learning-enabled multiscale modeling of mechanical deformation of aluminum and Al-SiC nanocomposites

A machine learning-enabled multiscale framework is developed for modeling the mechanical response of both pure metal and nanoparticle-reinforced metal matrix nanocomposites (MMNCs). Using aluminum–silicon carbide (Al-SiC) as an example MMNC, atomistic simulations reveal three distinct deformation mechanisms (i.e., defect-free, dislocation-based, and interface separation) governed by the interfaces between the Al matrix and SiC nanoparticles. As compared with single crystal Al, the lattice undergoes a more abrupt failure once the dislocation network becomes extensive and void nucleation initiates, whereas in Al-SiC, nanoparticle interfaces enable a more gradual progression of damage. These mechanisms are captured through a combined classification-regression neural network surrogate model that bridges atomic-scale insights with continuum-scale finite element analysis. Machine learning-enabled multiscale modeling of pure Al accurately predicted strain localization and confirmed by in-situ scanning electron microscopic tensile testing on perforated Al specimens. This study underscores the promise of integrating physics-informed machine learning with hierarchical modeling to capture the interface dominated phenomena and guide the design of advanced MMNCs.

Al-SiC↗

DOE OSTI2021

Study of microgrid resilience through co-simulation of power system dynamics and communication systems

The interdependence of power and communication systems in smart grid technologies is acknowledged, but difficult to quantify. Communication systems can be essential to maintaining stability in microgrids that are islanded due to extreme events. Though many power system studies assume the presence of communication networks, detailed modeling of power and communication systems for dynamic studies of microgrids is rare. The work presented in this paper develops a framework for power and communication system co-simulation to study the impact of communications system on microgrid stability. An operational use case is examined where a battery energy storage system operates to offset the loss of generation in an islanded microgrid. The framework is evaluated for different communication technologies, network structures, and communication media.

Thekkumparambath Mana, Priya↗

NASA NTRS1983

Satellite provided customer premise services: A forecast of potential domestic demand through the year 2000. Volume 2: Technical report

The potential United States domestic telecommunications demand for satellite provided customer premises voice, data and video services through the year 2000 were forecast, so that this information on service demand would be available to aid in NASA program planning. To accomplish this overall purpose the following objectives were achieved: development of a forecast of the total domestic telecommunications demand, identification of that portion of the telecommunications demand suitable for transmission by satellite systems, identification of that portion of the satellite market addressable by Computer premises services systems, identification of that portion of the satellite market addressabble by Ka-band CPS system, and postulation of a Ka-band CPS network on a nationwide and local level. The approach employed included the use of a variety of forecasting models, a market distribution model and a network optimization model. Forecasts were developed for; 1980, 1990, and 2000; voice, data and video services; terrestrial and satellite delivery modes; and C, Ku and Ka-bands.

Kratochvil, D.↗