SEARCH · Search NASA

Results for “network optimization”

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 1,603 records · Page 89

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2023

Insights into Constraining Rate Coefficients in Fuel Oxidation Mechanisms Using Genetic Algorithm Optimization

Accurate fuel oxidation mechanisms can enable predictive capabilities that aid in advancing combustion technologies. High-level computational kinetics can yield reasonable rate coefficients with uncertainties, in some cases, below a factor of 2. Computed rate coefficients can be constrained further by optimizing against experimental data. Here, we explore the application of genetic algorithm (GA) optimization to constrain computed rate coefficients in complex fuel oxidation mechanisms in conjunction with temperature-dependent species mole fractions from jet-stirred reactor (JSR) measurements. Cyclohexane is a model candidate for understanding the reactivity of cyclic fuels. In this work, we optimize the rate coefficients of the most recent literature cyclohexane mechanism, which incorporates theoretically computed rate coefficients for the reaction networks stemming from the first and second O 2 addition pathways, against the experimental results of two separate literature JSR studies. Optimization consistency is evaluated by carrying out three GA optimizations: fitting to the temperature-dependent species mole fractions in each JSR experiment separately and simultaneously fitting the species mole fractions in both experiments. Local sensitivity analyses are used to identify five influential low-temperature oxidation reactions for optimization. Although the three optimizations do not yield identical rate coefficients, the direction of change in all five rate coefficients is consistent among the three optimizations. Performance of the models from the three optimizations is assessed against literature ignition delay times with differences in the level of agreement observed among the different optimizations. In conclusion, comparisons are made with our recent optimization work of a cyclopentane oxidation master-equation model against time-resolved species concentrations, and insights and improvements of the strategy for constraining rate coefficients using GA optimization are discussed.

33 ADVANCED PROPULSION SYSTEMS↗

NASA NTRS2005

LEO Download Capacity Analysis for a Network of Adaptive Array Ground Stations

To lower costs and reduce latency, a network of adaptive array ground stations, distributed across the United States, is considered for the downlink of a polar-orbiting low earth orbiting (LEO) satellite. Assuming the X-band 105 Mbps transmitter of NASA s Earth Observing 1 (EO-1) satellite with a simple line-of-sight propagation model, the average daily download capacity in bits for a network of adaptive array ground stations is compared to that of a single 11 m dish in Poker Flats, Alaska. Each adaptive array ground station is assumed to have multiple steerable antennas, either mechanically steered dishes or phased arrays that are mechanically steered in azimuth and electronically steered in elevation. Phased array technologies that are being developed for this application are the space-fed lens (SFL) and the reflectarray. Optimization of the different boresight directions of the phased arrays within a ground station is shown to significantly increase capacity; for example, this optimization quadruples the capacity for a ground station with eight SFLs. Several networks comprising only two to three ground stations are shown to meet or exceed the capacity of the big dish, Cutting the data rate by half, which saves modem costs and increases the coverage area of each ground station, is shown to increase the average daily capacity of the network for some configurations.

Ingram, Mary Ann↗

DOE OSTI2026

Data for High Yield Production of 3-Hydroxypropionic Acid Using Issatchenkia orientalis

Biomanufacturing provides a more sustainable alternative to fossil-based chemical manufacturing. 3-Hydroxypropionic acid (3HP) is a top Department of Energy value-added chemical and precursor to bioplastics, yet cost-effective microbial production remains elusive. Here, we establish the acid-tolerant yeast Issatchenkia orientalis as a robust host for low-pH 3HP biosynthesis. Genome-scale modeling identifies the β-alanine pathway as optimal, offering the highest theoretical yield and lowest oxygen requirement. Thermodynamic analysis confirms its favorability under acidic conditions. Using sequence similarity network analysis, we discover highly active aspartate 1-decarboxylase (PAND), β-alanine-pyruvate aminotransferase (BAPAT), and 3HP dehydrogenase (YDFG), which significantly improve the pathway efficiency. Next, to further elevate the production, pathway optimization through multi-copy PAND integration, byproduct elimination (knockouts of pyruvate decarboxylase and glycerol-3-phosphate dehydrogenase), and reinforcement of aspartate flux by overexpression of pyruvate carboxylase and aspartate amino transferase improves the titer to 29 g/L in shake flasks. Fed-batch fermentation at pH 4 with low-cost corn steep liquor medium further increases the production to 92 g/L with 0.7 g/g yield and 0.55 g/L/h productivity. Techno-economic analysis indicates that such performance could potentially enable a financially viable process for sustainable acrylic acid production. This work establishes I. orientalis as a next-generation platform for cost-effective 3HP production and paves the way toward industrial commercialization.

Bioproducts↗

DOE OSTI2018

Microstructural Materials Design Via Deep Adversarial Learning Methodology

Identifying the key microstructure representations is crucial for computational materials design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for microstructural materials design. Some MCR approaches are not applicable for microstructural materials design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for microstructural materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural materials design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

Engineering↗

DOE OSTI2023

Journey Over Destination: Differentiable Sensor Placement Enhances Generalization [Poster]

The challenge of reconstructing spatial fields that change over time from limited sensor data has been a focal point for many research studies. Various machine learning methods have been used in attempts to address this complex issue, including convolutional neural networks. All of the proposed methods share a common requirement that the user needs to manually determine the sensor positions. This requirement remains a limiting factor in the ongoing quest for efficient learning and accurate field reconstruction. This study aims to present a method that enables a model to optimize sensor positions via backpropagation, thereby facilitating the model’s exploration of the spatial domain and enhancing sensor positioning effectively. Indexing naturally incorporates discrete decisions. This operation is nondifferentiable which is a requirement for the application of gradient-based optimization methods. We showcased its effectiveness by training an attention-based neural network, which achieved top-tier performance on two separate datasets. To our knowledge, this represents the first fully end-to-end differentiable workflow for enhancing sensor placement within a neural network model.

58 GEOSCIENCES↗

DOE OSTI2022

Sparse Deep Neural Network Inference using different Programming Models

Sparse deep neural networks have gained increasing attention recently in achieving speedups on inference with reduced memory footprints. However, the real-world applications are little shown with specialized optimizations, yet a wide variety of DNN tasks remain dense without exploiting the advantages of sparsity in networks. Recent work presented by MIT/IEEE/Amazon GraphChallenge has demonstrated significant speedups and various techniques. Still, we find that there is limited investigation of the impact of various Python and C\slash C++ based programming models to explore new opportunities in general cases. In this work, we provide performance evaluation through different programming models using CuPy, cuSPARSE, and OpenMP to discuss the advantages and disadvantages of our sparse implementations on single-GPU and multiple GPUs of NVIDIA DGX-A100 40GB/80GB platforms.

machine learning, HPC↗

NASA NTRS1991

Lightning location system supervising Swedish power transmission network

For electric utilities, the ability to prevent or minimize lightning damage on personnel and power systems is of great importance. Therefore, the Swedish State Power Board, has been using data since 1983 from a nationwide lightning location system (LLS) for accurately locating lightning ground strikes. Lightning data is distributed and presented on color graphic displays at regional power network control centers as well as at the national power system control center for optimal data use. The main objectives for use of LLS data are: supervising the power system for optimal and safe use of the transmission and generating capacity during periods of thunderstorms; warning service to maintenance and service crews at power line and substations to end operations hazardous when lightning; rapid positioning of emergency crews to locate network damage at areas of detected lightning; and post analysis of power outages and transmission faults in relation to lightning, using archived lightning data for determination of appropriate design and insulation levels of equipment. Staff have found LLS data useful and economically justified since the availability of power system has increased as well as level of personnel safety.

Melin, Stefan A.↗

DOE OSTI2026

Deciphering the Conflict Between Ion and Electron Percolating Networks in Solid-State Battery Cathodes

High-energy- and power-density solid state batteries require an optimal cathode composition and microstructural arrangement of cathode active material, solid-state electrolyte, conductive carbon, and binder to simultaneously support lithium-ion transport, electron conduction, and storage capacity. The ion and electron conducting phases in solid-state cathodes counteract each other's percolating networks as their mass ratios increase or decrease relative to each other. Here, we investigate targeted mass ratio variations of argyrodite solid electrolyte and two different types of conductive carbon (particles and fibers) in composite LiNi0.8Mn0.1Co0.1O2 (NMC811) solid-state cathodes to ascertain the ionic-electronic tradeoffs in cathode performance. Through ionic and electronic conductivity measurements on composite cathodes, as well as rate-testing and cycling performance in full cells, it is shown that the conductive carbon fibers form a percolative electronic network within the composite at a lower mass ratio (3-5 wt%) than particulate carbon (>5 wt%). The threshold to achieve electronic percolation coincides with higher accessible capacity in the cathode as the active material particles become electronically connected. However, carbon loadings beyond this percolation threshold lead to increased ion transport resistance, arising from disruptions to ionic conduction pathways and degraded contact at the interface between the electrolyte and active materials. Imaging, spectroscopy, and physics-based models quantitatively describe the relationship between carbon and electrolyte compositions and the cell's capacity and rate performance through percolation theory. This work demonstrates the importance of quantitatively understanding percolating networks in solid-state cells and that strategic engineering of conductive carbon morphologies can further increase the energy- and power-density of solid-state cells.

25 ENERGY STORAGE↗

DOE OSTI2019

Assessment of Existing Capabilities and Future Needs for Designing Networked Microgrids

This is a review of existing microgrid design tool capabilities, such as the Microgrid Design Tool (MDT), LANL PNNL NRECA Optimal Resilience Model (LPNORM), Distributed Energy Resource-Customer Adoption Model (DER-CAM), Renewable Energy Optimization (REopt), and the Hybrid Optimization Model for Multiple Energy Resources (HOMER). Additionally, other simulation and analysis tools which may provide fundamental support will be examined. These will include GridLAB-DTM, OpenDSS, and the hierarchical Engine for Large-scale Infrastructure Co-Simulation (HELICS). Their applicability to networked microgrid operations will be evaluated, and strengths and gaps of existing tools will be identified. This review will help to determine which elements of the proposed optimal design and operations (OD&D) tool should be formulated from first principles, and which elements should be integrated from past DOE investments.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains difficult. In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale. Despite the empirical success of deep Q-learning, the non-asymptotic convergence rate of Neural-Q-Whittle, which couples neural networks with two-timescale Q-learning largely remains unclear. This paper provides a finite-time analysis of Neural-Q-Whittle, where data are generated from a Markov chain, and Q-function is approximated by a ReLU neural network. Our analysis leverages a Lyapunov drift approach to capture the evolution of two coupled parameters, and the nonlinearity in value function approximation further requires us to characterize the approximation error. Combing these provide Neural-Q-Whittle with convergence rate, where is the number of iterations.

reinforcement learning, structured learning, conve↗

NASA NTRS1992

A conjugate gradients/trust regions algorithms for training multilayer perceptrons for nonlinear mapping

This paper addresses the issue of applying a globally convergent optimization algorithm to the training of multilayer perceptrons, a class of Artificial Neural Networks. The multilayer perceptrons are trained towards the solution of two highly nonlinear problems: (1) signal detection in a multi-user communication network, and (2) solving the inverse kinematics for a robotic manipulator. The research is motivated by the fact that a multilayer perceptron is theoretically capable of approximating any nonlinear function to within a specified accuracy. The algorithm that has been employed in this study combines the merits of two well known optimization algorithms, the Conjugate Gradients and the Trust Regions Algorithms. The performance is compared to a widely used algorithm, the Backpropagation Algorithm, that is basically a gradient-based algorithm, and hence, slow in converging. The performances of the two algorithms are compared with the convergence rate. Furthermore, in the case of the signal detection problem, performances are also benchmarked by the decision boundaries drawn as well as the probability of error obtained in either case.

Madyastha, Raghavendra K.↗

DOE OSTI2024

Modern deep neural networks for Direct Normal Irradiance forecasting: A classification approach

The escalating energy demand and the adverse environmental impacts of fossil-fuel use necessitate a shift towards cleaner and renewable alternatives. Concentrated Solar Power (CSP) technology emerges as a promising solution, offering a carbon-free alternative for power generation. The efficiency and profitability of CSP depend on the Direct Normal Irradiance (DNI) component of solar radiation; hence, accurate DNI forecasting can help optimize CSP plants’ operations and performance. The unpredictable nature of weather phenomena, particularly cloud cover, introduces uncertainty into DNI projections. Existing DNI forecasting models use meteorological factors, which are both challenging to estimate numerically over short prediction windows and expensive to model through data at a sufficiently high spatial and temporal resolution. This research addresses the challenge by presenting a novel approach that formulates DNI prediction as a multi-class classification problem, departing from conventional regression-based methods. The primary objective of this classification framework is to identify optimal periods aligning with specific operational thresholds for CSP plants, contributing to enhanced dispatch optimization strategies. We model the DNI classification problem using four advanced deep neural networks – rectified linear unit (ReLU) networks, 1D residual networks (ResNets), bidirectional long short-term memory (BiLSTM) networks, and transformers – achieving accuracies up to 93.5% without requiring meteorological parameters.

14 SOLAR ENERGY↗

DOE OSTI2018

Programmable design of orthogonal protein heterodimers

Specificity of interactions between two DNA strands, or between protein and DNA, is often achieved by varying bases or side chains coming off the DNA or protein backbone—for example, the bases participating in Watson–Crick pairing in the double helix, or the side chains contacting DNA in TALEN–DNA complexes. By contrast, specificity of protein–protein interactions usually involves backbone shape complementarity1, which is less modular and hence harder to generalize. Coiled-coil heterodimers are an exception, but the restricted geometry of interactions across the heterodimer interface (primarily at the heptad a and d positions2) limits the number of orthogonal pairs that can be created simply by varying side-chain interactions3,4. Here we show that protein–protein interaction specificity can be achieved using extensive and modular side-chain hydrogen-bond networks. We used the Crick generating equations5 to produce millions of four-helix backbones with varying degrees of supercoiling around a central axis, identified those accommodating extensive hydrogen-bond networks, and used Rosetta to connect pairs of helices with short loops and to optimize the remainder of the sequence. Of 97 such designs expressed in Escherichia coli, 65 formed constitutive heterodimers, and the crystal structures of four designs were in close agreement with the computational models and confirmed the designed hydrogen-bond networks. In cells, six heterodimers were fully orthogonal, and in vitro—following mixing of 32 chains from 16 heterodimer designs, denaturation in 5 M guanidine hydrochloride and reannealing—almost all of the interactions observed by native mass spectrometry were between the designed cognate pairs. The ability to design orthogonal protein heterodimers should enable sophisticated protein-based control logic for synthetic biology, and illustrates that nature has not fully explored the possibilities for programmable biomolecular interaction modalities.

Chen, Zibo↗

DOE OSTI2025

Digital twin framework for PIP-II linac: AI-driven multi-scale modeling from ion source to 800 MeV

The PIP-II superconducting linac at Fermilab is designed to deliver multi-megawatt proton beams for neutrino physics and other high-intensity applications. To expedite commissioning and enhance operational reliability, we have developed an EPICS-based data flow framework that seamlessly integrates digital twins (DT) with physical twins (PT). These digital twins comprise high-fidelity beam dynamics models or data-driven surrogate models connected to their physical counterparts through real-time diagnostics and advanced machine-learning algorithms.Central to this framework is Linac_Gen, an accelerated simulation tool that incorporates convolutional neural networks, random forests, and genetic algorithms to provide up to a tenfold speedup in optimizing the accelerator geometry model. An EPICS translator layer ensures interoperability by efficiently mapping lattice parameters across diverse simulation platforms.Our EPICS-based framework supports multiple operational modes—monitoring, passive learning, closed-loop control, and online learning—covering the entire machine lifecycle. By leveraging HPC resources and multi-objective optimization techniques, the digital twin enables adaptive trajectory correction, real-time fault detection, and predictive modeling of beam stability. This comprehensive approach paves the way for robust, high-intensity operation and data-driven accelerator R&D at Fermilab.

Pathak, Abhishek [Fermilab]↗

NASA NTRS1991

A cost-effective intelligent robotic system with dual-arm dexterous coordination and real-time vision

Dexterous coordination of manipulators based on the use of redundant degrees of freedom, multiple sensors, and built-in robot intelligence represents a critical breakthrough in development of advanced manufacturing technology. A cost-effective approach for achieving this new generation of robotics has been made possible by the unprecedented growth of the latest microcomputer and network systems. The resulting flexible automation offers the opportunity to improve the product quality, increase the reliability of the manufacturing process, and augment the production procedures for optimizing the utilization of the robotic system. Moreover, the Advanced Robotic System (ARS) is modular in design and can be upgraded by closely following technological advancements as they occur in various fields. This approach to manufacturing automation enhances the financial justification and ensures the long-term profitability and most efficient implementation of robotic technology. The new system also addresses a broad spectrum of manufacturing demand and has the potential to address both complex jobs as well as highly labor-intensive tasks. The ARS prototype employs the decomposed optimization technique in spatial planning. This technique is implemented to the framework of the sensor-actuator network to establish the general-purpose geometric reasoning system. The development computer system is a multiple microcomputer network system, which provides the architecture for executing the modular network computing algorithms. The knowledge-based approach used in both the robot vision subsystem and the manipulation control subsystems results in the real-time image processing vision-based capability. The vision-based task environment analysis capability and the responsive motion capability are under the command of the local intelligence centers. An array of ultrasonic, proximity, and optoelectronic sensors is used for path planning. The ARS currently has 18 degrees of freedom made up by two articulated arms, one movable robot head, and two charged coupled device (CCD) cameras for producing the stereoscopic views, and articulated cylindrical-type lower body, and an optional mobile base. A functional prototype is demonstrated.

Marzwell, Neville I.↗

NASA NTRS1992

Neural networks for structural design - An integrated system implementation

The development of powerful automated procedures to aid the creative designer is becoming increasingly critical for complex design tasks. In the work described here Artificial Neural Nets are applied to acquire structural analysis and optimization domain expertise. Based on initial instructions from the user an automated procedure generates random instances of structural analysis and/or optimization 'experiences' that cover a desired domain. It extracts training patterns from the created instances, constructs and trains an appropriate network architecture and checks the accuracy of net predictions. The final product is a trained neural net that can estimate analysis and/or optimization results instantaneously.

Berke, Laszlo↗