Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network performance evaluation”

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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

Physics-informed neural networks (PINNs) have shown to be effective tools for solving both forward and inverse problems of partial differential equations (PDEs). PINNs embed the PDEs into the loss of the neural network using automatic differentiation, and this PDE loss is evaluated at a set of scattered spatio-temporal points (called residual points). The location and distribution of these residual points are highly important to the performance of PINNs. However, in the existing studies on PINNs, only a few simple residual point sampling methods have mainly been used. Here, we present a comprehensive study of two categories of sampling for PINNs: non-adaptive uniform sampling and adaptive nonuniform sampling. We consider six uniform sampling methods, including (1) equispaced uniform grid, (2) uniformly random sampling, (3) Latin hypercube sampling, (4) Halton sequence, (5) Hammersley sequence, and (6) Sobol sequence. We also consider a resampling strategy for uniform sampling. To improve the sampling efficiency and the accuracy of PINNs, we propose two new residual-based adaptive sampling methods: residual-based adaptive distribution (RAD) and residual-based adaptive refinement with distribution (RAR-D), which dynamically improve the distribution of residual points based on the PDE residuals during training. Hence, we have considered a total of 10 different sampling methods, including six non-adaptive uniform sampling, uniform sampling with resampling, two proposed adaptive sampling, and an existing adaptive sampling. We extensively tested the performance of these sampling methods for four forward problems and two inverse problems in many setups. Our numerical results presented in this study are summarized from more than 6000 simulations of PINNs. Here, we show that the proposed adaptive sampling methods of RAD and RAR-D significantly improve the accuracy of PINNs with fewer residual points for both forward and inverse problems. Furthermore, the results obtained in this study can also be used as a practical guideline in choosing sampling methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Neural Architecture Search Benchmarks: Insights and Survey

Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful in discovering efficient models for various Computer Vision, Natural Language Processing, etc. The major obstacles to the advancement of NAS techniques are the demand for large computation resources and fair evaluation of various search methods. The differences in training pipeline and setting make it challenging to compare the efficiency of two NAS algorithms. A large number of NAS Benchmarks to simulate the architecture evaluation in seconds have been released over the last few years to ease the computation burden of training neural networks and can aid in the unbiased assessment of different search methods. This paper provides an extensive review of several publicly available NAS Benchmarks in the literature. We provide technical details and a deeper understanding of each benchmark and point out future directions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

An a priori evaluation of a principal component and artificial neural network based combustion model in diesel engine conditions

A principal component analysis (PCA) and artificial neural network (ANN) based chemistry tabulation approach is presented. ANNs are used to map the thermochemical state onto a low-dimensional manifold consisting of five control variables that have been identified using PCA. Three canonical configurations are considered to train the PCA-ANN model: a series of homogeneous reactors, a nonpremixed flamelet, and a two-dimensional lifted flame. The performance of the model in predicting the thermochemical manifold of a spatially-developing turbulent jet flame in diesel engine thermochemical conditions is a priori evaluated using direct numerical simulation (DNS) data. The PCA-ANN approach is compared with a conventional tabulation approach (tabulation using ad hoc defined control variables and linear interpolation). The PCA-ANN model provides higher accuracy and requires several orders of magnitude less memory. Here, these observations indicate that the PCA-ANN model is superior for chemistry tabulation, especially for modelling complex chemistries that present multiple combustion modes as observed in diesel combustion. The performance of the PCA-ANN model is then compared to the optimal estimator, i.e. the conditional mean from the DNS. The results indicate that the PCA-ANN model gives high prediction accuracy, comparable to the optimal estimator, especially for major species and the thermophysical properties. Higher errors are observed for the minor species and reaction rate predictions when compared to the optimal estimator. It is shown that the prediction of minor species and reaction rates can be improved by using training data that exhibits a variation of parameters as observed in the turbulent flame. The output of the ANN is analysed to assess mass conservation. It is observed that the ANN incurs a mean absolute error of 0.05% in mass conservation. Furthermore, it is demonstrated that this error can be reduced by modifying the cost function of the ANN to penalise for deviation from mass conservation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2020

Appraisal of SMAP Operational Soil Moisture Product from a Global Perspective

Space-borne soil moisture (SM) satellite products such as those available from Soil Moisture Active Passive (SMAP) offer unique opportunities for global and frequent monitoring of SM and also to understand its spatiotemporal variability. The present study investigates the performance of the SMAP L4 SM product at selected experimental sites across four continents, namely North America, Europe, Asia and Australia. This product provides global scale SM estimates at 9 km × 9 km spatial resolution at daily intervals. For the product evaluation, co-orbital in situ SM measurements were used, acquired at 14 test sites in North America, Europe, and Australia belonging to the International Soil Moisture Network (ISMN) and local networks in India. The satellite SM estimates of up to 0–5 cm soil layer were compared against collocated ground measurements using a series of statistical scores. Overall, the best performance of the SMAP product was found in North America (RMSE = 0.05 m(exp 3)/m(exp 3)) followed by Australia (RMSE = 0.08 m(exp 3)/m(exp 3)), Asia (RMSE = 0.09 m(exp 3)/m(exp 3)) and Europe (RMSE = 0.14 m(exp 3)/m(exp 3)). Our findings provide important insights into the spatiotemporal variability of the specific operational SM product in different ecosystems and environments. This study also furnishes an independent verification of this global product, which is of international interest given its suitability for a wide range of practical and research applications.

Soil moisture↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗
NASA NTRS1999

Intercomparison of Various Algorithms in Determining Convective and Stratiform Precipitation

The paper presents the intercomparison of various algorithms in determining the convective and stratiform precipitation in tropical convection. The latent heat released from precipitation is the driving mechanism for the general circulation of the atmosphere and exhibits different vertical profile in convective and stratiform regimes of the tropical convection. The primary goal of this paper is to evaluate the performance of the operational convective/stratiform algorithm that is employed by the NASA Tropical Rainfall Measuring Mission (TRMM) ground validation program. The operational algorithm is based on the texture of radar reflectivity field at constant altitude. The TRMM ground validation program continuously monitors the tropical convection through ground based radar and rain gauge network at selected sites around the tropics and generates the rainfall products including the convective/stratiform rainfall map that can readily be used by the TRMM satellite program. An evaluation and improvement of these rainfall products requires additional measurements that can be available through field campaigns. The data used in this study was collected during the second phase of the Texas Florida Underflights (TEFLUN-B) field campaign in East Central Florida, a primary site of the TRMM ground validation program. The TEFLUN-B field campaign was conducted in August and September 1998 in support of the NASA Tropical Rainfall Measuring Mission (TRMM) satellite observations. An objective of the TEFLUN-B field campaign was to obtain the ground based precipitation measurements of Florida convection at different temporal and spatial scales. The field campaign had various components of precipitation measurements including dual wavelength precipitation profiler, various types of disdrometers and rain gauges, collocated about 40 km southwest of Melbourne NEXRAD radar. In this study, we examine the profiler based reflectivity and Doppler velocity and the disdrometer based drop size distribution observations to evaluate the operational scanning radar (i.e. NEXRAD) based convective/stratiform algorithm.

Tokay, Ali↗
DOE OSTI2021

Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting

A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%.

14 SOLAR ENERGY↗
NASA NTRS1990

Neural networks as a control methodology

While conventional computers must be programmed in a logical fashion by a person who thoroughly understands the task to be performed, the motivation behind neural networks is to develop machines which can train themselves to perform tasks, using available information about desired system behavior and learning from experience. There are three goals of this fellowship program: (1) to evaluate various neural net methods and generate computer software to implement those deemed most promising on a personal computer equipped with Matlab; (2) to evaluate methods currently in the professional literature for system control using neural nets to choose those most applicable to control of flexible structures; and (3) to apply the control strategies chosen in (2) to a computer simulation of a test article, the Control Structures Interaction Suitcase Demonstrator, which is a portable system consisting of a small flexible beam driven by a torque motor and mounted on springs tuned to the first flexible mode of the beam. Results of each are discussed.

Mccullough, Claire L.↗
NASA NTRS2001

Performance of Power Converters at Cryogenic Temperatures

Power converters capable of operation at cryogenic temperatures are anticipated to play an important role in the power system architecture of future NASA deep space missions. Design of such converters to survive cryogenic temperatures will improve the power system performance and reduce development and launch costs. Aerospace power systems are mainly a DC distribution network. Therefore, DC/DC and DC/AC converters provide the outputs needed to different loads at various power levels. Recently, research efforts have been performed at the NASA Glenn Research Center (GRC) to design and evaluate DC/DC converters that are capable of operating at cryogenic temperatures. This paper presents a summary of the research performed to evaluate the low temperature performance of five DC/DC converters. Various parameters were investigated as a function of temperature in the range of 20 to -196 C. Data pertaining to the output voltage regulation and efficiency of the converters is presented and discussed.

Elbuluk, Malik E.↗
NASA NTRS2022

Microstructure Segmentation with Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset

This study examined the improvement of microscopy segmentation accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures, including VGG, Inception, and ResNet, were trained on over 100,000 labelled microscopy images from 54 classes. These pre-trained encoders were then embedded into multiple segmentation architectures including U-Net and DeepLabV3+ to evaluate segmentation performance on newly created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2 percent reduction in relative segmentation error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.

machine learning↗
DOE OSTI2023

SyReNN: A tool for analyzing deep neural networks

Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Unfortunately, modern DNNs have been shown to be vulnerable to a variety of attacks and buggy behavior. This has motivated recent work in formally analyzing the properties of such DNNs. Furthermore, this paper introduces SyReNN, a tool for understanding and analyzing a DNN by computing its symbolic representation. The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses using low-dimensional subsets of the input space, a unique design point in the space of DNN analysis tools. We describe the tool and the underlying theory, then evaluate its use and performance on three case studies: computing Integrated Gradients, visualizing a DNN’s decision boundaries, and repairing buggy DNNs.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1984

Improved Carrier Tracking by Smoothing Estimators

Smoothing as a way to improve the carrier phase estimation is proposed and analyzed. The performance of first and second order Kalman optimum smoothers are investigated. This performance is evaluated in terms of steady state covariance error computation, dynamic tracking, and noise response. It is shown that with practical amounts of memory, a second order smoother can have a position error due to an acceleration or jerk step input less than any prescribed maximum. As an example of importance to the NASA Deep Space Network, a second order smoother can be used to track the Voyager spacecraft at Uranus and Neptune encounters with significantly better performance than a second order phase locked loop.

Raez, C. A. P.↗
NASA NTRS1985

Improved carrier tracking by smoothing estimators

Smoothing as a way to improve the carrier phase estimation is proposed and analyzed. The performance of first and second order Kalman optimum smoothers are investigated. This performance is evaluated in terms of steady state covariance error computation, dynamic tracking, and noise response. It is shown that with practical amounts of memory, a second order smoother can have a position error due to an acceleration or jerk step input less than any prescribed maximum. As an example of importance to the NASA Deep Space Network, a second order smoother can be used to track the Voyager spacecraft at Uranus and Neptune encounters with significantly better performance than a second order phase locked loop.

Pomalaza-Raez, C. A.↗
NASA NTRS2012

Interuser Interference Analysis for Direct-Sequence Spread-Spectrum Systems Part I: Partial-Period Cross-Correlation

This presentation discusses an analysis approach to evaluate the interuser interference for Direct-Sequence Spread-Spectrum (DSSS) Systems for Space Network (SN) Users. Part I of this analysis shows that the correlation property of pseudo noise (PN) sequences is the critical factor which determines the interuser interference performance of the DSSS system. For non-standard DSSS systems in which PN sequence s period is much larger than one data symbol duration, it is the partial-period cross-correlation that determines the system performance. This study reveals through an example that a well-designed PN sequence set (e.g. Gold Sequence, in which the cross-correlation for a whole-period is well controlled) may have non-controlled partial-period cross-correlation which could cause severe interuser interference for a DSSS system. Since the analytical derivation of performance metric (bit error rate or signal-to-noise ratio) based on partial-period cross-correlation is prohibitive, the performance degradation due to partial-period cross-correlation will be evaluated using simulation in Part II of this analysis in the future.

Ni, Jianjun (David)↗
DOE OSTI2025

A generative artificial intelligence framework for long-time plasma turbulence simulations

Generative deep learning techniques are employed in a novel framework for the construction of surrogate models capturing the spatiotemporal dynamics of 2D plasma turbulence. The proposed Generative Artificial Intelligence Turbulence (GAIT) framework enables the acceleration of turbulence simulations for long-time transport studies. GAIT leverages a convolutional variational auto-encoder and a recurrent neural network to generate new turbulence data from existing simulations, extending the time horizon of transport studies with minimal computational cost. The application of the GAIT framework to plasma turbulence using the Hasegawa–Wakatani (HW) model is presented, evaluating its performance via various analyses. Very good agreement is found between the GAIT and the HW models in the spatiotemporal Fourier and Proper Orthogonal Decomposition spectra, the flow topology characterized by the Okubo–Weiss parameter, and the time autocorrelation function of turbulent fluctuations. Excellent agreement has also been obtained in the probability distribution function of particle displacements and the effective turbulent diffusivity. In-depth analyses of the latent space of turbulent states, choice of hyperparameters and alternative deep learning models for the time prediction are presented. Our results highlight the potential of Artificial Intelligence-based surrogate models to overcome the computational challenges in turbulence simulation, which can be extended to other situations such as geophysical fluid dynamics.

Artificial intelligence↗
NASA NTRS1986

Performance characteristics of wind profiling radars

Doppler radars used to measure winds in the troposphere and lower stratosphere for weather analysis and forecasting are lower-sensitivity versions of mesosphere-stratosphere-troposphere radars widely used for research. The term wind profiler is used to denote these radars because measurements of vertical profiles of horizontal and vertical wind are their primary function. It is clear that wind profilers will be in widespread use within five years: procurement of a network of 30 wind profilers is underway. The Wave Propagation Laboratory (WPL) has operated a small research network of radar wind profilers in Colorado for about two and one-half years. The transmitted power and antenna aperture for these radars is given. Data archiving procedures have been in place for about one year, and this data base is used to evaluate the performance of the radars. One of the prime concerns of potential wind profilers users is how often and how long wind measurements are lacking at a given height. Since these outages constitute an important part of the performance of the wind profilers, they are calculated at three radar frequencies, 50-, 405-, and 915-MHz, (wavelengths of 6-, 0.74-, and 0.33-m) at monthly intervals to determine both the number of outages at each frequency and annual variations in outages.

Strauch, R. G.↗
DOE OSTI2024

Integration of CeO 2 -Based Memristor with Vertically Aligned Nanocomposite Thin Film: Enabling Selective Conductive Filament Formation for High-Performance Electronic Synapses

The CeO 2 -based memristor has attracted significant attention due to its intrinsic resistive switching (RS) properties, large on/off ratio, and great plasticity, making it a promising candidate for artificial synapses. However, significant challenges such as high power consumption and poor device reliability hinder its broad application in neuromorphic microchips. To tackle these issues, in this work, we design a novel bilayer (BL) memristor by integrating a CeO 2 -based memristor with a Co-CeO 2 vertically aligned nanocomposite (VAN) layer and compare it with the single layer (SL) memristor. Preliminary electrical testing reveals that the BL memristor offers a reduced set/reset voltage (~67% lower), a higher on/off ratio (~5 × 10 2 ), enhanced device reliability, and improved device-to-device variation compared to the SL memristor. Insight from COMSOL simulation, coupled with microstructural analysis, provides a comprehensive elucidation on how the VAN layer facilitates the selective conductive filament (CF) formation. Subsequently, the plasticity of the BL memristor is evaluated through long-term potentiation/depression (LTP/LTD), paired-pulse facilitation (PPF), and spike-time-dependent plasticity (STDP). The spiking neural network (SNN) built upon the BL memristor achieves remarkable accuracy (~94%) after only 12 iterations, underscoring its potential for high-performance neural networks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Augmenting machine learning of Grad–Shafranov equilibrium reconstruction with Green's functions

This work presents a method for predicting plasma equilibria in tokamak fusion experiments and reactors. The approach involves representing the plasma current as a linear combination of basis functions using principal component analysis of plasma toroidal current densities (J t ) from the EFIT-AI equilibrium database. Then utilizing EFIT's Green's function tables, basis functions are created for the poloidal flux (ψ) and diagnostics generated from the toroidal current (J t ). Similar to the idea of a physics-informed neural network (NN), this physically enforces consistency between ψ, J t , and the synthetic diagnostics. First, the predictive capability of a least squares technique to minimize the error on the synthetic diagnostics is employed. The results show that the method achieves high accuracy in predicting ψ and moderate accuracy in predicting J t with median R 2 = 0.9993 and R 2 = 0.978, respectively. A comprehensive NN using a network architecture search is also employed to predict the coefficients of the basis functions. The NN demonstrates significantly better performance compared to the least squares method with median R 2 = 0.9997 and 0.9916 for J t and ψ, respectively. The robustness of the method is evaluated by handling missing or incorrect data through the least squares filling of missing data, which shows that the NN prediction remains strong even with a reduced number of diagnostics. Additionally, the method is tested on plasmas outside of the training range showing reasonable results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗