Search NASA⌕ Search

SEARCH · Search NASA

Results for “Training Analysis”

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 397 records · Page 22

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗

Physics-based statistical learning approach to mesoscopic model selection

In materials science and many other research areas, models are frequently inferred without considering their generalization to unseen data. Here, we apply statistical learning using cross-validation to obtain an optimally predictive coarse-grained description of a two-dimensional kinetic nearest-neighbor Ising model with Glauber dynamics (GD) based on the stochastic Ginzburg-Landau equation (sGLE). The latter is learned from GD “training” data using a log-likelihood analysis, and its predictive ability for various complexities of the model is tested on GD “test” data independent of the data used to train the model on. Using two different error metrics, we perform a detailed analysis of the error between magnetization time trajectories simulated using the learned sGLE coarse-grained description and those obtained using the GD model. We show that both for equilibrium and out-of-equilibrium GD training trajectories, the standard phenomenological description using a quartic free energy does not always yield the most predictive coarse-grained model. Moreover, increasing the amount of training data can shift the optimal model complexity to higher values. Our results are promising in that they pave the way for the use of statistical learning as a general tool for materials modeling and discovery.

36 MATERIALS SCIENCE↗

In-flight crew training

The Helmet Mounted Display system and Part Task Trainer are two projects currently underway that are closely related to the in-flight crew training concept. The first project is a training simulator and an engineering analysis tool. The simulator's unique helmet mounted display actually projects the wearer into the simulated environment of 3-D space. Miniature monitors are mounted in front of the wearers eyes. Partial Task Trainer is a kinematic simulator for the Shuttle Remote Manipulator System. The simulator consists of a high end graphics workstation with a high resolution color screen and a number of input peripherals that create a functional equivalent of the RMS control panel in the back of the Orbiter. It is being used in the training cycle for Shuttle crew members. Activities are underway to expand the capability of the Helmet Display System and the Partial Task Trainer.

Gott, Charles↗

NEUROSPF: A Tool For the Symbolic Analysis of Neural Networks

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model’s parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis and testing approaches from software engineering to the field of machine learning. For instance, NEUROSPF can be used for coverage-based testing and test generation, finding adversarial examples and also constraint-based repair of neural networks, thus improving the reliability of neural networks and of the applications that use them.

neural networks↗

Isolator Shock Train Response to Dual-Mode Scramjet Throttling-Like Forcing

Typical dual-mode scramjet designs employ an isolator component situated between the inlet and combustor. The isolator fluidically buffers the inlet from the combustor via the formation of a shock train, an interconnected series of shock-boundary layer interactions. The isolator is required during ramjet-engine operation and at the lower edges of the scramjet operational envelope. In an operational engine, transient behavior imposes fluidic dynamics due to attitude adjustments, combustor throttling, aberrant resonances within the combustor, etc. To accommodate these transients, the shock train adjusts on both temporal and spatial scales. Sufficiently large downstream pressure increases in the combustor play a critical role during unstart, whereby strong compression waves propagate upstream in the isolator to ultimately force the shock train out the inlet, if it cannot stabilize to the pressure increase. This critically reduces the engine mass flow rate, potentially causing a catastrophic reduction in thrust and loss of the vehicle. A nearly instantaneous unstart can, in principle, be predicted by a ratio of the normal shock pressure jump in an inviscid isolator. However, lower-magnitude perturbations, below this bound, also induce unstarts. Understanding the transient behavior inherent in unsteady isolator operation is critical to reducing safety margin in isolator length and refining engine control algorithms to improve engine performance. The Isolator Dynamics Research Lab (IDRL) is a cold-flow, direct-connect isolator facility ideal for assessing the fundamental fluid dynamics of shock trains. The internal flow of a scramjet isolator is modeled using a 2D, symmetric Mach 2.5 nozzle followed by a 695 mm long, 25.4x50.8 mm rectangular isolator test section. A blockage cone on a high-speed ball screw actuator downstream of the isolator is pulsed to simulate the throttling behavior in an operational combustor. Wall flush high-speed static pressure transducers detect the streamwise shock train within the isolator. Time delays between the onset of the throttling and the response motion of the shock train are analyzed to assess the controlling scales and parameters. From this analysis, the response time of the isolator shock train system is found to depend primarily on the isolator back pressure time-rate-of-change but quickly saturates to a maximum propagation speed along the isolator. These results inform dual-mode scramjet engine designers of the critical parameters and limits of an unstart resistant engine.

scramjet↗

Development of a utility computer-based training program on setpoint methodology for nuclear power plants - 129

The purpose of this paper is to provide an overview of the development of the Computer- Based Training (CBT) Program for utility engineers on Setpoint Methodology for nuclear power plants. This computer based training module was prepared by the Advanced Engineering Training initiative. The Advanced Engineering Training initiative is a nuclear industry effort to develop technical computer-based training modules for targeted areas of engineering expertise. The target audience is engineers at commercial nuclear power facilities in the U. S. These modules are being developed using the systematic approach to training and are being designed to maintain industry engineering expertise and to facilitate engineering knowledge transfer. The objective of this training effort is to support the development of the next generation of site technical experts for specific topic areas. The training is one part of three key components that would facilitate knowledge transfer to the future site Subject Matter Expert (SME). The following are the major focus areas covered in the Setpoint Methodology CBT: Chapter 1 provides an overview of the role instrument setpoints perform in the defense-in-depth safety analysis for the plant as well introducing key definitions related to setpoints. Chapter 2 provides the history and current regulatory requirements related to setpoint control including the laws and guidance provided by the U.S. NRC. Chapter 3 provides describes the setpoint methodology including terms, formulae, methods of combination, graded approach and methods for drift analysis. This is a major part of the training module in covering the incremental uncertainty terms that need to be considered and how they are combined. Chapter 4 provides and overview of the role of setpoints in Technical Specifications and associated documents. Chapter 5 describes how the regulatory process, related to setpoint control, has been implemented in NRC inspections and how the major elements of the 10 CFR 50.59 reviews apply to the performance of a new or revised setpoint calculation. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Test and validation for robot arm control dynamics simulation

The Flight Telerobotic Servicer (FTS) program will require an ability to develop, in a cost effective manner, many simulation models for design, analysis, performance evaluation, and crew training. Computational speed and the degree of modeling fidelity associated with each simulation must be commensurate with problem objectives. To demonstrate evolving state-of-the-art general purpose multibody modeling capabilities, to validate these by laboratory testing, and to expose their modeling shortcomings, two focus problems at the opposite ends of the simulation spectrum are defined: (1) Coarse Acquisition Control Dynamics. Create a real time man-in-the-control-loop simulator. Provide animated graphical display of robot arm dynamics and tactile feedback sufficient for cueing the operator. Interface simulator software with human operated tactile feedback controller; i.e., the Kraft mini-master. (2) Fine, Precision Mode Control Dynamics. Create a high speed, high fidelity simulation model for the design, analysis, and performance evaluation of autonomous 7 degree-of-freedom (DOF) trajectory control algorithms. This model must contain detail dynamic models for all significant dynamics elements within the robot arm, such as joint drive mechanisms.

Yae, K. Harold↗

Measurement and Analysis of Atmospheric Spectral Optical Depths with NASA Ames Airborne Sunphotometers During TARFOX and ACE-2

In accordance with the scope of work of this contract, the following tasks were undertaken and completed during the course of the contract: (1) Participation in the design and development of the 14-channel Ames Airborne Tracking Sunphotometer (AATS-14), including the development and implementation of Visual Basic software for real-time data processing and display and post-acquisition data reduction and analysis. (2) Operation of the six-channel Ames Airborne Tracking Sunphotometer (AATS-6) aboard the University of Washington C-131A during TARFOX and in-field analysis and presentation of data acquired with the AATS-6. (3) Post-mission analysis of data acquired during TARFOX with the AATS-6 and the AATS-14. (4) Pre-TARFOX calibration of the AATS-6 at Mauna Loa Observatory in May 1996, and post-TARFOX calibration of the AATS-6 and AATS- 14 at Zugspitze, Germany in October 1996, including analyses of all data sets. (5) Analysis of AATS-14 airborne calibration data acquired on 17 November 1996 during a late afternoon Pelican flight over the central California coast. (6) Operational training, instrument preparation, field coordination, and analysis of shipboard measurements of aerosol optical depth with the AATS-6 during ACE-2. (7) Coordination of data acquisition with the AATS-14 aboard the Pelican during ACE-2 and in-field preliminary data analysis and presentation. (8) Calibration of the AATS-6 and AATS-14 in April/May 1997 at Mauna Loa prior to ACE-2, and post-mission calibration of the AATS-6 at Mauna Loa in August 1997.

Livingston, John M.↗

FIND: A Synthetic weather generator to control drought Frequency, Intensity, and Duration

Water systems worldwide are experiencing climate change-induced shifts in drought properties like frequency, intensity, and duration, affecting water security and reliability. To develop and test effective drought preparedness plans, researchers often use synthetic weather generators to create hydrological scenarios that explore drought variability beyond historical records. Existing weather generators typically allow users to adjust streamflow statistics like percentiles or temporal correlation but do not directly control drought properties of frequency, intensity, and duration. To fill this gap, we propose FIND (Frequency, INtensity, and Duration) synthetic weather generator. FIND incorporates a standardized drought index to directly and in dependently control drought frequency, intensity, and duration in generated streamflow time series while preserving observed hydrological variability. Use cases for FIND include i) water systems analysis applications that seek to train and test drought strategies under historical and plausible future drought conditions, and ii) bottom-up vulnerability studies relating system vulnerability outcomes to specific changes in drought properties of frequency, intensity, and duration. Here, we demonstrate FIND’s versatility through three experiments: replicating historically observed drought properties, generating streamflow scenarios for multiple sites preserving correlation between their drought conditions, and generating a set of scenarios with direct and independent changes in drought properties. FIND source code is openly available for applications beyond the scope of this paper.

42 ENGINEERING↗

Computer-aided detection of breast masses: Four-view strategy for screening mammography

Purpose: To improve the performance of a computer-aided detection (CAD) system for mass detection by using four-view information in screening mammography. Methods: The authors developed a four-view CAD system that emulates radiologists' reading by using the craniocaudal and mediolateral oblique views of the ipsilateral breast to reduce false positives (FPs) and the corresponding views of the contralateral breast to detect asymmetry. The CAD system consists of four major components: (1) Initial detection of breast masses on individual views, (2) information fusion of the ipsilateral views of the breast (referred to as two-view analysis), (3) information fusion of the corresponding views of the contralateral breast (referred to as bilateral analysis), and (4) fusion of the four-view information with a decision tree. The authors collected two data sets for training and testing of the CAD system: A mass set containing 389 patients with 389 biopsy-proven masses and a normal set containing 200 normal subjects. All cases had four-view mammograms. The true locations of the masses on the mammograms were identified by an experienced MQSA radiologist. The authors randomly divided the mass set into two independent sets for cross validation training and testing. The overall test performance was assessed by averaging the free response receiver operating characteristic (FROC) curves of the two test subsets. The FP rates during the FROC analysis were estimated by using the normal set only. The jackknife free-response ROC (JAFROC) method was used to estimate the statistical significance of the difference between the test FROC curves obtained with the single-view and the four-view CAD systems. Results: Using the single-view CAD system, the breast-based test sensitivities were 58% and 77% at the FP rates of 0.5 and 1.0 per image, respectively. With the four-view CAD system, the breast-based test sensitivities were improved to 76% and 87% at the corresponding FP rates, respectively. The improvement was found to be statistically significant (p<0.0001) by JAFROC analysis. Conclusions: The four-view information fusion approach that emulates radiologists' reading strategy significantly improves the performance of breast mass detection of the CAD system in comparison with the single-view approach.

60 APPLIED LIFE SCIENCES↗

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model’s predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Data and scripts associated with the manuscript "Encoding Diel Hysteresis and the Birch Effect in Dryland Soil Respiration Models through Knowledge-Guided Deep Learning"

This package contains the data and scripts used in "Encoding Diel Hysteresis and the Birch Effect in Dryland Soil Respiration Models through Knowledge-Guided Deep Learning" (Jiang et al., 2022). The data.zip file contains the flux tower and automated chamber observations used for developing the deep learning model for modeling soil respiration. The scripts.zip file contains the Jupyter notebooks and python scripts for preprocessing the data, training the deep learning models, and postprocessing the results. The src.zip contains the source code for training the deep learning model, performing mutual information analysis, and plotting functions. The trained_models.zip contains multiple folders used for hosting the trained deep-learning models and the associated soil respiration predictions. The whole process is performed using python. We include the REAMD.md to document the python package requirements.Soil respiration in dryland ecosystems is challenging to model due to its complex interactions with environmental drivers. Knowledge-guided deep learning provides a much more effective means of accurately representing these complex interactions than traditional Q10-based models. Mutual information analysis revealed that future soil temperature shares more information with soil respiration than past soil temperature, consistent with their clockwise diel hysteresis. We explicitly encoded diel hysteresis, soil drying, and soil rewetting effects on soil respiration dynamics in a newly designed Long Short Term Memory (LSTM) model. The model takes both past and future environmental drivers as inputs to predict soil respiration. The new LSTM model substantially outperformed three Q10-based models and the Community Land Model when reproducing the observed soil respiration dynamics in a semi-arid ecosystem. The new LSTM model clearly demonstrated its superiority for temporally extrapolating soil respiration dynamics, such that the resulting correlation with observational data is up to 0.7 while the correlations of both Q10-based models and the Community Land Model (CLM) are less than 0.4. Our results underscore the high potential for knowledge-guided deep learning to replace Q10-based soil respiration modules in Earth system models.

54 ENVIRONMENTAL SCIENCES↗

Naturalistic Decision Making for Power System Operators

Motivation – Investigations of large-scale outages in the North American interconnected electric system often attribute the causes to three T’s: Trees, Training and Tools. To document and understand the mental processes used by expert operators when making critical decisions, a naturalistic decision making (NDM) model was developed. Transcripts of conversations were analyzed to reveal and assess NDM-based performance criteria. Findings/Design – An item analysis indicated that the operators’ Situation Awareness Levels, mental models, and mental simulations can be mapped at different points in the training scenario. This may identify improved training methods or analytical/ visualization tools. Originality/Value – This study applies for the first time, the concepts of Recognition Primed Decision Making, Situation Awareness Levels and Cognitive Task Analysis to training of electric power system operators. Take away message – The NDM approach provides a viable framework for systematic training management to accelerate learning in simulator-based training scenarios for power system operators and teams.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Comparison of classical statistical methods and artificial neural network in traffic noise prediction

Traffic is the main source of noise in urban environments and significantly affects human mental and physical health and labor productivity. Therefore it is very important to model the noise produced by various vehicles. Techniques for traffic noise prediction are mainly based on regression analysis, which generally is not good enough to describe the trends of noise. In this paper the application of artificial neural networks (ANNs) for the prediction of traffic noise is presented. As input variables of the neural network, the proposed structure of the traffic flow and the average speed of the traffic flow are chosen. The output variable of the network is the equivalent noise level in the given time period L{sub eq}. Based on these parameters, the network is modeled, trained and tested through a comparative analysis of the calculated values and measured levels of traffic noise using the originally developed user friendly software package. It is shown that the artificial neural networks can be a useful tool for the prediction of noise with sufficient accuracy. In addition, the measured values were also used to calculate equivalent noise level by means of classical methods, and comparative analysis is given. The results clearly show that ANN approach is superior in traffic noise level prediction to any other statistical method. - Highlights: • We proposed an ANN model for prediction of traffic noise. • We developed originally designed user friendly software package. • The results are compared with classical statistical methods. • The results are much better predictive capabilities of ANN model.

54 ENVIRONMENTAL SCIENCES↗

CMLM (Co-Optimized Machine-Learned Manifolds) [SWR-23-41]

Co-optimized Machine-Learned Manifolds (CMLM) is a data-driven approach for developing reduced-order manifold models for high-dimensional chemically reacting systems. It involves a specially designed neural network, the training of which simultaneously optimizes linear combinations of species that define the manifold, nonlinear mapping to outputs of interest such as reaction rates, and (optionally) subfilter closure for large eddy simulation. This software package provides an implementation of the CMLM approach in Python using the PyTorch machine learning library. A few example cases are included, showing how the tool can be applied to different types of data from 0D and 1D reacting simulations performed using Cantera. The neural networks can be saved in a format that is readable by the Pele suite of combustion solvers for use in reacting computational fluid dynamics simulations. This software repository contains several python scripts to perform various tasks associated with the Co-optimized Machine Learned Manifolds (CMLM) model, which is described in Perry, Henry de Frahan, and Yellapantula, CNF, 2022 (https://doi.org/10.1016/j.combustflame.2022.112286). This includes not only the code that defines the CMLM model, but also scripts to generate suitable training data, scripts to pre-process the data, scripts to train the CMLM model, and scripts to plot the output, as well as various other helper files. The scripts depend on several commonly used python libraries for data analysis and chemical reaction computations. The trained models that result from this tool are designed to work with the an interface being implemented in the Pele suite of reacting flow solvers (https://github.com/AMReX-Combustion).

Perry, Bruce↗

Comparative study of career development and training programs

Improvement of human capital has been identified as the key to any further increase of productivity for any country engaged in the global economic competition. The same can be said of any organization seeking to enhance its overall performance. This study is aimed at: (1) surveying the current practices of career development and training programs at major corporations and government research organizations; (2) presenting the distributions of various program features among survey respondents; (3) identifying the profile of the training program of a typical research organization, against which each organization can check and identify its relative strengths as well as areas needing further strengthening; (4) conducting an economic analysis of the effectiveness of the training programs at Langley Research Center; and (5) making recommendations as to how to enhance existing training programs.

Tsao, Alan↗

On the role of fluids in stick-slip dynamics of saturated granular fault gouge using a coupled computational fluid dynamics-discrete element approach: STICK-SLIP IN SATURATED FAULT GOUGE

The presence of fault gouge has considerable influence on slip properties of tectonic faults and the physics of earthquake rupture. The presence of fluids within faults also plays a significant role in faulting and earthquake processes. In this study, we present 3-D discrete element simulations of dry and fluid-saturated granular fault gouge and analyze the effect of fluids on stick-slip behavior. Fluid flow is modeled using computational fluid dynamics based on the Navier-Stokes equations for an incompressible fluid and modified to take into account the presence of particles. Analysis of a long time train of slip events shows that the (1) drop in shear stress, (2) compaction of granular layer, and (3) the kinetic energy release during slip all increase in magnitude in the presence of an incompressible fluid, compared to dry conditions. We also observe that on average, the recurrence interval between slip events is longer for fluid-saturated granular fault gouge compared to the dry case. This observation is consistent with the occurrence of larger events in the presence of fluid. It is found that the increase in kinetic energy during slip events for saturated conditions can be attributed to the increased fluid flow during slip. Finally, our observations emphasize the important role that fluid flow and fluid-particle interactions play in tectonic fault zones and show in particular how discrete element method (DEM) models can help understand the hydromechanical processes that dictate fault slip.

58 GEOSCIENCES↗

Single Bimodular Sensor for Differentiated Detection of Multiple Oxidative Gases

Semiconductive metal-oxide sensors suffer from cross-sensitivities under mixed chemical condition, specifically upon mixture of multiple oxidative or reductive gases. Herein, a single bimodular sensor is demonstrated for smart differentiation of multiple oxidative analytes by relating the resistance-metric mode to impedance-metric mode. The sensor construct based on ZnO nanorods readily outputs three response datasets upon exposure of oxidative-gas mixture including O 2 , SO 2 , and NO 2 , the resistance, real part impedance, and imaginary part impedance. The differentiative and correlated nature between these response signals allows such a single sensor platform to differentiate these oxidative gases accurately and robustly. Linear and non-linear decision boundaries are established over a large gas-concentration range from 2 ppm to 3% through a combination of principal component analysis and artificial neural network training. A facile user interface is demonstrated for recognition and measurement of unknown gas analytes, with the error of the predicted analyte-concentration as low as 2%.

36 MATERIALS SCIENCE↗