Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 487 records · Page 27

Aircraft Anomaly Detection Using Performance Models Trained on Fleet Data

This paper describes an application of data mining technology called Distributed Fleet Monitoring (DFM) to Flight Operational Quality Assurance (FOQA) data collected from a fleet of commercial aircraft. DFM transforms the data into aircraft performance models, flight-to-flight trends, and individual flight anomalies by fitting a multi-level regression model to the data. The model represents aircraft flight performance and takes into account fixed effects: flight-to-flight and vehicle-to-vehicle variability. The regression parameters include aerodynamic coefficients and other aircraft performance parameters that are usually identified by aircraft manufacturers in flight tests. Using DFM, the multi-terabyte FOQA data set with half-million flights was processed in a few hours. The anomalies found include wrong values of competed variables, (e.g., aircraft weight), sensor failures and baises, failures, biases, and trends in flight actuators. These anomalies were missed by the existing airline monitoring of FOQA data exceedances.

Gorinevsky, Dimitry↗

Optimization of the deep neural network parameters for generating homogenized fuel assembly data for nodal codes

Homogenized fuel assembly (FA) data is a typical input data for nodal codes. Generating that data, however, could be time-consuming. One of promising ways to mitigate the computational burden of generating macroscopic cross-sections is to use trained artificial neural network (ANN) models for predicting nuclear data. However, there is a challenge to make the model support variable FA geometry. In this work, two most common types of FA were combined in one ANN model. Since there could be multiple ways of converting 2-dimensional FA data into 1-dimensional input vector for ANN, three different approaches of data flattening were evaluated. The input parameters included each fuel pin enrichment, fuel temperature, moderator temperature and boron concentration. The output parameters were 2-group macroscopic cross-sections (XS) and pin power distribution (HFF). A fully connected deep neural network (DNN) model was trained and tested using pre-generated data obtained with lattice physics code STREAM. The results of this study showed no statistically significant difference in the accuracy of XS and HFF generation for all 3 tested input vector orders. This means that fully connected DNN for XS generation demonstrated input sequence invariance. Results of comparing predicted XS data with reference solutions were found sufficiently close considering the reduction of computation time offered by ANN. Mean relative difference (MRD) for all output XS parameters was found below 0.7%, while HFF MRD was found higher compared to XS values, in some cases slightly exceeding 1%, mostly near guide tube locations. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Optimization of Workload Distribution of Data Centers Based on a Self-Learning In Situ Adaptive Tabulation Model

Data center cooling typically involves non-uniform airflow and temperature distributions, which are affected by the IT workload distribution. It is helpful to simulate the airflow and temperature to optimize the workload distribution. Traditional computational fluid dynamics (CFD) simulation is usually time-consuming while conventional reduced order models (ROMs), though computationally fast, may generate inaccurate results even after being fully trained. In Situ Adaptive Tabulation (ISAT), contracting to conventional ROM, can make prediction with error lower than a user-specified tolerance. To demonstrate using of ISAT for optimal workload distribution in data center, this paper presents a preliminary study of an ISAT-based genetic algorithm optimization platform. The ISAT is trained offline by using the results from CFD simulations using a hypothetical simple data center. The optimal workload distribution determined by the platform leads to approximately 6.8% of energy savings when compared to the benchmark with a uniform workload distribution. We note that the time cost for the entire optimization process, including the training of ISAT is about 4 hours, which is acceptable in the design phase.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Multi-Agent Safe Policy Learning for Power Management of Networked Microgrids

This paper presents a supervised multi-agent safe policy learning (SMAS-PL) method for optimal power management of networked microgrids (MGs) in distribution systems. While unconstrained reinforcement learning (RL) algorithms are black-box decision models that could fail to satisfy grid operational constraints, our proposed method considers AC power flow equations and other operational limits. Accordingly, the training process employs the gradient information of operational constraints to ensure that the optimal control policy functions generate safe and feasible decisions. Furthermore, we have developed a distributed consensus-based optimization approach to train the agents’ policy functions while maintaining MGs’ privacy and data ownership boundaries. After training, the learned optimal policy functions can be safely used by the MGs to dispatch their local resources, without the need to solve a complex optimization problem from scratch. Lastly, numerical experiments have been devised to verify the performance of the proposed method.

, policy gradient↗

An adaptive Hessian approximated stochastic gradient MCMC method

Bayesian approaches have been successfully integrated into training deep neural networks. One popular family is stochastic gradient Markov chain Monte Carlo methods (SG-MCMC), which have gained increasing interest due to their ability to handle large datasets and the potential to avoid overfitting. Although standard SG-MCMC methods have shown great performance in a variety of problems, they may be inefficient when the random variables in the target posterior densities have scale differences or are highly correlated. Here, we present an adaptive Hessian approximated stochastic gradient MCMC method to incorporate local geometric information while sampling from the posterior. The idea is to apply stochastic approximation (SA) to sequentially update a preconditioning matrix at each iteration. The preconditioner possesses second-order information and can guide the random walk of a sampler efficiently. Instead of computing and saving the full Hessian of the log posterior, we use limited memory of the samples and their stochastic gradients to approximate the inverse Hessian-vector multiplication in the updating formula. Moreover, by smoothly optimizing the preconditioning matrix via SA, our proposed algorithm can asymptotically converge to the target distribution with a controllable bias under mild conditions. To reduce the training and testing computational burden, we adopt a magnitude-based weight pruning method to enforce the sparsity of the network. Our method is user-friendly and demonstrates better learning results compared to standard SG-MCMC updating rules. The approximation of inverse Hessian alleviates storage and computational complexities for large dimensional models. Numerical experiments are performed on several problems, including sampling from 2D correlated distribution, synthetic regression problems, and learning the numerical solutions of heterogeneous elliptic PDE. The numerical results demonstrate great improvement in both the convergence rate and accuracy.

97 MATHEMATICS AND COMPUTING↗

Biopolymer-Templated Titania Film Formation for Nanostructured Coatings Revealed by Machine Learning-Supported Time-Resolved Analysis

This study presents a machine learning approach to derive the film formation of biopolymer-templated titania nanostructures during spray deposition, in combination with in situ grazing-incidence small-angle X-ray scattering (GISAXS). A neural network trained on synthetic GISAXS data directly predicts domain-size distributions from experimental two-dimensional scattering patterns, capturing the full kinetics of nanostructure evolution with high temporal resolution. The predictions reveal hierarchical size distributions and periodic growth features, consistent with layer-by-layer spray deposition and validated by complementary scanning electron microscopy (SEM) imaging. Quantitative comparison with conventional parametric GISAXS fits shows good qualitative agreement, with systematic differences explained by domain-shape assumptions and resolved by applying a geometric scaling factor. Simulated SEM-like surfaces derived from neural network outputs reproduce the porous, foam-like nanoscale morphology observed experimentally, reinforcing the method’s credibility. This integrated approach enables real-time, nondestructive, statistically averaged monitoring of bulk nanostructure development in functional coatings, offering a scalable methodology to accelerate the characterization and process control of sustainably manufactured nanostructured titania films for energy-related applications such as photocatalysis and photovoltaics.

Heger, JulianEliah↗

MULTI-WAVELENGTH STUDY OF A COMPLETE IRAC 3.6 {mu}m SELECTED GALAXY SAMPLE: A FAIR CENSUS OF RED AND BLUE POPULATIONS AT REDSHIFTS 0.4-1.2

We present a multi-wavelength study of a 3.6 {mu}m selected galaxy sample in the Extended Groth Strip (EGS). The sample is complete for galaxies with stellar mass >10{sup 9.5} M{sub Sun} and redshift 0.4 < z < 1.2. In this redshift range, the Infrared Array Camera 3.6 {mu}m band measures the rest-frame near-infrared band, permitting nearly unbiased selection with respect to both quiescent and star-forming galaxies. The numerous spectroscopic redshifts available in the EGS are used to train an artificial neural network to estimate photometric redshifts. The distribution of photometric redshift errors is Gaussian with standard deviation {approx}0.025(1 + z), and the fraction of redshift failures (>3{sigma} errors) is about 3.5%. A new method of validation based on pair statistics confirms the estimate of standard deviation even for galaxies lacking spectroscopic redshifts. Basic galaxy properties measured include rest-frame U - B colors, B- and K-band absolute magnitudes, and stellar masses. We divide the sample into quiescent and star-forming galaxies according to their rest-frame U - B colors and 24-3.6 {mu}m flux density ratios and derive rest K-band luminosity functions and stellar mass functions for quiescent, star-forming, and all galaxies. The results show that massive, quiescent galaxies were in place by z Almost-Equal-To 1, but lower mass galaxies generally ceased their star formation at later epochs.

79 ASTRONOMY AND ASTROPHYSICS↗

Physicochemical signatures of nanoparticle-dependent complement activation

Nanoparticles are potentially powerful therapeutic tools that have the capacity to target drug payloads and imaging agents. However, some nanoparticles can activate complement, a branch of the innate immune system, and cause adverse side-effects. Recently, we developed an in vitro hemolytic assay protocol for measuring the nanoparticle-dependent complement activity of serum samples and applied this protocol to several nanoparticle formulations that differed in size, surface charge, and surface chemistry; quantifying the nanoparticle-dependent complement activity using a metric called Residual Hemolytic Activity (RHA). In the present work, we have used a decision tree learning algorithm to derive the rules for estimating nanoparticle-dependent complement response based on the data generated from the hemolytic assay studies. Our results indicate that physicochemical properties of nanoparticles, namely, size, polydispersity index, zeta potential, and mole percentage of the active surface ligand of a nanoparticle, can serve as good descriptors for prediction of nanoparticle-dependent complement activation in the decision tree modeling framework. The robustness and predictability of the model can be improved by training the model with additional data points that are uniformly distributed in the RHA/physicochemical descriptor space and by incorporating instability effects on nanoparticle physicochemical properties into the model.

informatics↗

Self-learning Monte Carlo method: Continuous-time algorithm

The recently introduced self-learning Monte Carlo method is a general-purpose numerical method that speeds up Monte Carlo simulations by training an effective model to propose uncorrelated configurations in the Markov chain. We implement this method in the framework of a continuous-time Monte Carlo method with an auxiliary field in quantum impurity models. We introduce and train a diagram generating function (DGF) to model the probability distribution of auxiliary field configurations in continuous imaginary time, at all orders of diagrammatic expansion. Furthermore, by using DGF to propose global moves in configuration space, we show that the self-learning continuous-time Monte Carlo method can significantly reduce the computational complexity of the simulation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

pnnl/SNAP

In this work, we detail two uncertainty quantification (UQ) methods that provide complementary information. Readout ensembling, by finetuning only the readout layers of an ensemble of foundation models, provides information about model uncertainty. Amending the final readout layer to predict upper and lower quantiles replaces point predictions with distributional predictions, which provide information about uncertainty within the underlying training data. We demonstrate our approach with the MACE-MP-0 model, applying UQ to both the foundation model and a series of finetuned models. The uncertainties produced by the ensemble and quantile methods are demonstrated to be distinct measures by which the quality of the NNP output can be judged.

Pope, Jenna (Bilbrey) [Pacific Northwest National ↗

Bayesian inverse modeling of the atmospheric transport and emissions of a controlled tracer release from a nuclear power plant

Probability distribution functions (PDFs) of model inputs that affect the transport and dispersion of a trace gas released from a coastal California nuclear power plant are quantified using ensemble simulations, machine-learning algorithms, and Bayesian inversion. The PDFs are constrained by observations of tracer concentrations and account for uncertainty in meteorology, transport, diffusion, and emissions. Meteorological uncertainty is calculated using an ensemble of simulations of the Weather Research and Forecasting (WRF) model that samples five categories of model inputs (initialization time, boundary layer physics, land surface model, nudging options, and reanalysis data). The WRF output is used to drive tens of thousands of FLEXPART dispersion simulations that sample a uniform distribution of six emissions inputs. Machine-learning algorithms are trained on the ensemble data and used to quantify the sources of ensemble variability and to infer, via inverse modeling, the values of the 11 model inputs most consistent with tracer measurements. We find a substantial ensemble spread in tracer concentrations (factors of 10 to 10 3 ), most of which is due to changing emissions inputs (about 80%), though the cumulative effects of meteorological variations are not negligible. The performance of the inverse method is verified using synthetic observations generated from arbitrarily selected simulations. When applied to measurements from a controlled tracer release experiment, the inverse method satisfactorily determines the location, start time, duration and amount. In a 2 km × 2 km area of possible locations, the actual location is determined to within 200m. The start time is determined to within 5min out of 2h, and the duration to within 50min out of 4h. Over a range of release amounts of 10 to 1000kg, the estimated amount exceeds the actual amount of 146kg by only 32kg. The inversion also estimates probabilities of different WRF configurations. In conclusion, to best match the tracer observations, the highest-probability cases in WRF are associated with using a late initialization time and specific reanalysis data products.

54 ENVIRONMENTAL SCIENCES↗

The influence of autocorrelation in signature extraction: An example from a geobotanical investigation of Cotter Basin, Montana

The presence of positive serial correlation (autocorrelation) in remotely sensed data results in an underestimate of the variance-covariance matrix when calculated using contiguous pixels. This underestimate produces an inflation in F statistics. For a set of Thematic Mapper Simulator data (TMS), used to test the ability to discriminate a known geobotanical anomaly from its background, the inflation in F statistics related to serial correlation is between 7 and 70 times. This means that significance tests of means of the spectral bands initially appear to suggest that the anomalous site is very different in spectral reflectance and emittance from its background sites. However, this difference often disappears and is always dramatically reduced when compared to frequency distributions of test statistics produced by the comparison of simulated training sets possessing equal means, but which are composed of autocorrelated observations.

Labovitz, M. L.↗

The influence of autocorrelation in signature extraction - An example from a geobotanical investigation of Cotter Basin, MT

The presence of positive serial correlation (autocorrelation) in remotely sensed data results in an underestimate of the variance-covariance matrix when calculated using contiguous pixels. This underestimate produces an inflation in F statistics. For a set of Thematic Mapper Simulator data (TMS), used to test the ability to discriminate a known geobotanical anomaly from its background, the inflation in F statistics related to serial correlation is between 7 and 70 times. This means that significance tests of means of the spectral bands initially appear to suggest that the anomalous site is very different in spectral reflectance and emittance from its background sites. However, this difference often disappears and is always dramatically reduced when compared to frequency distributions of test statistics produced by the comparison of simulated training sets possessing equal means, but which are composed of autocorrelated observations. Previously announced in STAR as N82-25602

Labovitz, M. L.↗

The influence of autocorrelation in signature extraction - An example from a geobotanical investigation of Cotter Basin, Montana

The presence of positive serial correlation (autocorrelation) in remotely sensed data results in an underestimate of the variance-covariance matrix when calculated using contiguous pixels. This underestimate produces an inflation in F statistics. For a set of Thematic Mapper Simulator data (TMS), used to test the ability to discriminate a known geobotanical anomaly from its background, the inflation in F statistics related to serial correlation is between 7 and 70 times. This means that significance tests of means of the spectal bands initially appear to suggest that the anomalous site is very different in spectral reflectance and emittance from its background sites. However, this difference often disappears and is always dramatically reduced when compared to frequency distributions of test statistics produced by the comparison of simulated training sets possessing equal means, but which are composed of autocorrelated observations.

Labovitz, M. L.↗

Remote voice training: A case study on space shuttle applications, appendix C

The Tile Automation System includes applications of automation and robotics technology to all aspects of the Shuttle tile processing and inspection system. An integrated set of rapid prototyping testbeds was developed which include speech recognition and synthesis, laser imaging systems, distributed Ada programming environments, distributed relational data base architectures, distributed computer network architectures, multi-media workbenches, and human factors considerations. Remote voice training in the Tile Automation System is discussed. The user is prompted over a headset by synthesized speech for the training sequences. The voice recognition units and the voice output units are remote from the user and are connected by Ethernet to the main computer system. A supervisory channel is used to monitor the training sequences. Discussions include the training approaches as well as the human factors problems and solutions for this system utilizing remote training techniques.

Mollakarimi, Cindy↗

Flight elements subpanel introduction and overview

Major objectives, milestones, key contacts, technology issues, accomplishments, and candidate programs are outlined. Topics addressed include: advanced avionics systems architectures; advanced information processing; avionics concepts; integrated Global Positioning System/guidance, navigation, and command concepts; advanced communication and telemetry; display and control concepts; advanced sensors and instrumentation; fault detection and fault management; advanced electric power, distribution, and control; EMA/power systems; and in-flight crew training. This presentation is represented by viewgraphs only.

Sollock, Paul E.↗

Mixing Enhancement by Tabs in Round Supersonic Jets

The objective of this study was to analyze jet plume mass flow entrainment rates associated with the introduction of counter-rotating streamwise vorticity by prism shaped devices (tabs) located at the lip of the nozzle. We have examined the resulting mixing process through coordinated experimental tests and numerical simulations of the supersonic flow from a model axisymmetric nozzle. In the numerical simulations, the total induced vorticity was held constant while varying the distribution of counter-rotating vorticity around the nozzle lip training edge. In the experiment, the number of tabs applied was varied while holding the total projected area constant. Evaluations were also conducted on initial vortex strength. The results of this work show that the initial growth rate of the jet shear layer is increasingly enhanced as more tabs are added, but that the lowest tab count results in the largest entrained mass flow. The numerical simulations confirm these results.

Seiner, John M.↗

Optimization of Training Sets for Neural-Net Processing of Characteristic Patterns from Vibrating Solids

Artificial neural networks have been used for a number of years to process holography-generated characteristic patterns of vibrating structures. This technology depends critically on the selection and the conditioning of the training sets. A scaling operation called folding is discussed for conditioning training sets optimally for training feed-forward neural networks to process characteristic fringe patterns. Folding allows feed-forward nets to be trained easily to detect damage-induced vibration-displacement-distribution changes as small as 10 nm. A specific application to aerospace of neural-net processing of characteristic patterns is presented to motivate the conditioning and optimization effort.

Decker, Arthur J.↗