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 829 records · Page 46

Prediction of the Cu oxidation state from EELS and XAS spectra using supervised machine learning

Abstract Electron energy loss spectroscopy (EELS) and X-ray absorption spectroscopy (XAS) provide detailed information about bonding, distributions and locations of atoms, and their coordination numbers and oxidation states. However, analysis of XAS/EELS data often relies on matching an unknown experimental sample to a series of simulated or experimental standard samples. This limits analysis throughput and the ability to extract quantitative information from a sample. In this work, we have trained a random forest model capable of predicting the oxidation state of copper based on its L-edge spectrum. Our model attains an R 2 score of 0.85 and a root mean square error of 0.24 on simulated data. It has also successfully predicted experimental L-edge EELS spectra taken in this work and XAS spectra extracted from the literature. We further demonstrate the utility of this model by predicting simulated and experimental spectra of mixed valence samples generated by this work. This model can be integrated into a real-time EELS/XAS analysis pipeline on mixtures of copper-containing materials of unknown composition and oxidation state. By expanding the training data, this methodology can be extended to data-driven spectral analysis of a broad range of materials.

36 MATERIALS SCIENCE↗

Final Report for Statistical Nonlinear Optics of High Energy Density Plasmas: The Physics of Multiple Crossing Laser Beams

The various implementations of the STUD pulse program (spike trains of uneven duration and delay) for LPI (laser-plasma instability) control were studied in depth, and novel regimes were found. How to generate STUD pulses with large time-bandwidth products, how to measure their optical scattering signatures, and how to experimentally demonstrate their usefulness were explored. Theoretical and numerical studies were conducted on Stimulated Brillouin Scattering (SBS) and Crossed Beam Energy Transfer (CBET) including statistical models. We established how LPI can be tamed and gain democratized in space and time. Implementing STUD pulses on NIF was also studied. Future high rep rate lasers and fast diagnostics will aid in the adoption of the whole STUD pulse program for LPI control in High Energy Density Plasmas (HEDP).

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Pyrotechnic hazards classification and evaluation program. Electrostatic vulnerability of the E8 and XM15/XM165 clusters, phase 2

An investigation into the electrostatic phenomena associated with the manufacturing and handling of explosives is discussed. The testing includes measurement of the severity of the primary charge generation mechanism, triboelectric effects between dissimilar surfaces; refinement of equivalent circuits of the XM15/XM165 and E8 fuse trains; evaluation of the electrostatic spark discharge characteristics predicted by an equivalent circuit analysis; and determination of the spark ignition sensitivity of materials, components, junctions, and subassemblies which compose the XM15/XM165 and E8 units. Special studies were also performed. These special tests included ignition sensitivity of the complete XM15 fuse train when subjected to discharges through its entire length, measurement of electrostatic potentials which occur during the E8 foaming operation during fabrication, and investigation of the inadvertent functioning of an XM15 cluster during manufacturing. The test results are discussed and related to the effectiveness of suggested modification to reduce the electrostatic ignition sensitivity.

Source record↗

Transitioning from Simulation to Reality: Applying Chatter Detection Models to Real-World Machining Data

Chatter, a self-excited vibration phenomenon, is a critical challenge in high-speed machining operations, affecting tool life, product surface quality, and overall process efficiency. While machine learning models trained on simulated data have shown promise in detecting chatter, their real-world applicability remains uncertain due to discrepancies between simulated and actual machining environments. The primary goal of this study is to bridge the gap between simulation-based machine learning models and real-world applications by developing and validating a Random Forest-based chatter detection system. This research focuses on improving manufacturing efficiency through reliable chatter detection by integrating Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL). The study applies a Random Forest classification model trained on over 140,000 simulated machining datasets, incorporating techniques like Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL) to adapt the model for real-world operational data. The model is validated against 1600 real-world machining datasets, achieving an accuracy of 86.1%, with strong precision and recall scores. The results demonstrate the model’s robustness and potential for practical implementation in industrial settings, highlighting challenges such as sensor noise and variability in machining conditions. This work advances the use of predictive analytics in machining processes, offering a data-driven solution to improve manufacturing efficiency through more reliable chatter detection.

42 ENGINEERING↗

Predicting Mechanical Properties from Microstructure Images in Fiber-Reinforced Polymers Using Convolutional Neural Networks

Evaluating the mechanical response of fiber-reinforced composites can be extremely time-consuming and expensive. Machine learning (ML) techniques offer a means for faster predictions via models trained on existing input–output pairs and have exhibited success in composite research. This paper explores a fully convolutional neural network modified from StressNet, which was originally used for linear elastic materials, and extended here for a non-linear finite element (FE) simulation to predict the stress field in 2D slices of segmented tomography images of a fiber-reinforced polymer specimen. The network was trained and evaluated on data generated from the FE simulations of the exact microstructure. The testing results show that the trained network accurately captures the characteristics of the stress distribution, especially on fibers, solely from the segmented microstructure images. The trained model can make predictions within seconds in a single forward pass on an ordinary laptop, given the input microstructure, compared to 92.5 h to run the full FE simulation on a high-performance computing cluster. These results show promise in using ML techniques to conduct fast structural analysis for fiber-reinforced composites and suggest a corollary that the trained model can be used to identify the location of potential damage sites in fiber-reinforced polymers.

Sun, Yixuan (ORCID:0000000311093380)↗

Deep Learning for Rapid Analysis of Spectroscopic Ellipsometry Data

High‐throughput experimental approaches to rapidly develop new materials require high‐throughput data analysis methods to match. Spectroscopic ellipsometry is a powerful method of optical properties characterization, but for unknown materials and/or layer structures the data analysis using traditional methods of nonlinear regression is too slow for autonomous, closed‐loop, high‐throughput experimentation. Herein, three methods (termed spectral, piecewise, and pointwise) of spectroscopic ellipsometry data analysis based on deep learning are introduced and studied. After initial training, the incremental time for inferring optical properties can be a thousand times faster than traditional methods. Results for multilayer sample structures with optically isotropic materials are presented, appropriate for high‐throughput studies of thin films of phase‐change materials such as GeSbTe (GST) alloys. Results for studies on highly birefringent layered materials are also presented, exemplified by the transition metal dichalcogenide MoS 2 . How the materials under test and the experimental objectives may guide the choice of analysis methods are discussed. The utility of our approach is demonstrated by analyzing data measured on a composition spread of GeSbTe phase‐change alloys containing 177 distinct compositions, and identifying the composition with optimal phase‐change figure of merit in only 1.4 s of analysis time.

Li, Yifei↗

ThickBrick: optimal event selection and categorization in high energy physics. Part I. Signal discovery

We provide a prescription called ThickBrick to train optimal machine-learning-based event selectors and categorizers that maximize the statistical significance of a potential signal excess in high energy physics (HEP) experiments, as quantified by any of six different performance measures. For analyses where the signal search is performed in the distribution of some event variables, our prescription ensures that only the information complementary to those event variables is used in event selection and categorization. This eliminates a major misalignment with the physics goals of the analysis (maximizing the significance of an excess) that exists in the training of typical ML-based event selectors and categorizers. In addition, this decorrelation of event selectors from the relevant event variables prevents the background distribution from becoming peaked in the signal region as a result of event selection, thereby ameliorating the challenges imposed on signal searches by systematic uncertainties. Our event selectors (categorizers) use the output of machine-learning-based classifiers as input and apply optimal selection cutoffs (categorization thresholds) that are functions of the event variables being analyzed, as opposed to flat cutoffs (thresholds). These optimal cutoffs and thresholds are learned iteratively, using a novel approach with connections to Lloyd’s k-means clustering algorithm. We provide a public, Python implementation of our prescription, also called ThickBrick, along with usage examples.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A search for the Higgs boson in H→WW→lvlv with 802 fb -1

This thesis documents a search for Standard Model (SM) Higgs boson to WW production in the final state of two charged leptons (e, μ) and two neutrino final state resulting from in pp collisions at √ s = 1.96 TeV. The data collected by the CDF II detector at the Tevatron collider at Fermilab, corresponds to an integrated luminosity of 8.2 fb -1 . This iteration of the analysis incorporated several improvements to increase Higgs sensitivity. We reevaluated lepton isolation values to recover signal events in which leptons mutually spoil each other’s isolation requirements. We additionally incorporated new lepton identification selections, namely likelihood based forward electrons and a better recovery of electrons passing through detector cracks. The base analysis searches for opposite-sign dilepton events. We employed three separately trained neural networks to distinguish signal from background processes for events with 0, one, or two jets. To further increase sensitivity for 0-jet events, we constructed a likelihood ratio discriminant based on Matrix Element calculations as an additional input to the neural network. For the base opposite-sign analysis, summing over all jet multiplicities, we observed 3513 events in data compared with a background expectation of 3409 ± 233 and a signal expectation of 53.6 ± 9.4 for a mass of 165 GeV/c 2 . To further increase signal acceptance, we incorporated several separate search regions in addition to the base analysis. We include subchannels searching for Higgs production in events with low dilepton invariant mass and in events having final states with either same-sign dileptons or trileptons With the combination of the separate analyses, we observed a 95% C.L. upper production limit of 0.77 times the SM expectation for a Higgs mass of 165 GeV/c 2 to be compared with the value for the median of the expected limit (0.78). We additionally present results for eighteen Higgs masses ranging from 110 GeV/c 2 to 200 GeV/c 2 . We excluded at the 95% C.L., a SM Higgs boson in the mass range between 156 and 175 GeV/c 2 .

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching

Diffusion MRI (dMRI) non-invasively maps brain white matter yet necessitates denoising due to low signal-to-noise ratios. Patch2Self (P2S) employing self-supervised techniques and regression on a Casorati matrix effectively denoises dMRI images and has become the new de-facto standard in this field. P2S however is resource intensive both in terms of running time and memory usage as it uses all voxels (n) from all-but-one held-in volumes (d-1) to learn a linear mapping Phi : \mathbb R ^ n x(d-1) \mapsto \mathbb R ^ n for denoising the held-out volume. The increasing size and dimensionality of higher resolution dMRI acquisitions can make P2S infeasible for large-scale analyses. This work exploits the redundancy imposed by P2S to alleviate its performance issues and inspect regions that influence the noise disproportionately. Specifically this study makes a three-fold contribution: (1) We present Patch2Self2 (P2S2) a method that uses matrix sketching to perform self-supervised denoising. By solving a sub-problem on a smaller sub-space so called coreset we show how P2S2 can yield a significant speedup in training time while using less memory. (2) We present a theoretical analysis of P2S2 focusing on determining the optimal sketch size through rank estimation a key step in achieving a balance between denoising accuracy and computational efficiency. (3) We show how the so-called statistical leverage scores can be used to interpret the denoising of dMRI data a process that was traditionally treated as a black-box. Experimental results on both simulated and real data affirm that P2S2 maintains denoising quality while significantly enhancing speed and memory efficiency achieved by training on a reduced data subset.

Fadnavis, Shreyas↗

Expanded analysis of machine learning models for nuclear transient identification using TPOT

Industries around the world are becoming more and more data driven. The nuclear field is no exception with several different applications being proposed. One popular area of research is the use of machine learning in transient detection. This paper seeks to build upon a previous study which made use of the AutoML package TPOT to train traditional machine learning models to classify transient events occurring with a reactor. Synthetic data was once again collected using a GPWR reactor simulator. Data on 12 different events was collected using 15 different initial conditions. Here, a dataset consisting of over 100,000 data points was compiled and used to train 7 different machine learning models using a pre-defined TPOT dictionary with 12 different preprocessing techniques. Three of the trained models were able to produce validation results in the 90s with the expanded dataset. Once the models were trained, it was possible to look into where during the simulation, misclassifications occurred. Using these three models, analysis was done to determine if TPOT could be used to train models that were effective if important features were missing. The results from this were positive with the newly trained models scoring close to the original models. Finally, to conclude this study, the three high performing models were retrained using different random states to see if there was any major variation when different states were used.

42 ENGINEERING↗

Innovating the next generation of commercial smart building software

Nearly 30% of commercial building energy use is wasted due to equipment faults and HVAC controls problems. The result is increased emissions, compromised comfort and productivity, and less reliable coordination of building power needs with a clean grid. The energy impact alone represents $17 billion in potential savings. Today’s smart building software provides a robust solution to address these operational deficiencies. Energy management and information systems (EMIS) are saving up to 9% on average, with two-year paybacks. They are being incorporated into energy management processes, commissioning services, and utility programs. As effective as they are, two barriers prevent even deeper benefits; limited personnel to fix problems once they are identified, and the expense and time to manually implement changes in control systems. In partnership with the research community, the EMIS industry is developing new capabilities to overcome these barriers. Moving beyond siloed products for either fault detection and diagnostics, or optimal control, these new capabilities empower users to not only automatically identify faults, but also to push corrective action, and control improvements to their buildings. In this paper, several areas for enhancements are documented: ‘one-time’ correction of faults such as setpoints, schedules, and economizer lockouts; short-term active testing for automated proportional integral derivative (PID) loop tuning and functional testing; and continuous supervisory control for demand flexibility and year-round efficiency. Results are presented from a pair of partner implementations out of a dozen providers integrating these enhancements into their products, including field tests from across the country, and insights into operator acceptance and integration into operations and maintenance practices.

Casillas, Armando↗

Great Plains Wind Energy Transmission Development Project

In fiscal year 2005, the Energy & Environmental Research Center (EERC) received funding from the U.S. Department of Energy (DOE) to undertake a broad array of tasks to either directly or indirectly address the barriers that faced much of the Great Plains states and their efforts to produce and transmit wind energy at the time. This program, entitled Great Plains Wind Energy Transmission Development Project, was focused on the central goal of stimulating wind energy development through expansion of new transmission capacity or development of new wind energy capacity through alternative market development. The original task structure was as follows: Task 1 - Regional Renewable Credit Tracking System (later rescoped to Small Wind Turbine Training Center); Task 2 - Multistate Transmission Collaborative; Task 3 - Wind Energy Forecasting System; and Task 4 - Analysis of the Long-Term Role of Hydrogen in the Region. As carried out, Task 1 involved the creation of the Small Wind Turbine Training Center (SWTTC). The SWTTC, located Grand Forks, North Dakota, consists of a single wind turbine, the Endurance S-250, on a 105-foot tilt-up guyed tower. The S-250 is connected to the electrical grid on the 'load side' of the electric meter, and the power produced by the wind turbine is consumed locally on the property. Establishment of the SWTTC will allow EERC personnel to provide educational opportunities to a wide range of participants, including grade school through college-level students and the general public. In addition, the facility will allow the EERC to provide technical training workshops related to the installation, operation, and maintenance of small wind turbines. In addition, under Task 1, the EERC hosted two small wind turbine workshops on May 18, 2010, and March 8, 2011, at the EERC in Grand Forks, North Dakota. Task 2 involved the EERC cosponsoring and aiding in the planning of three transmission workshops in the midwest and western regions. Under Task 3, the EERC, in collaboration with Meridian Environmental Services, developed and demonstrated the efficacy of a wind energy forecasting system for use in scheduling energy output from wind farms for a regional electrical generation and transmission utility. With the increased interest at the time of project award in the production of hydrogen as a critical future energy source, many viewed hydrogen produced from wind-generated electricity as an attractive option. In addition, many of the hydrogen production-related concepts involve utilization of energy resources without the need for additional electrical transmission. For this reason, under Task 4, the EERC provided a summary of end uses for hydrogen in the region and focused on one end product in particular (fertilizer), including several process options and related economic analyses.

08 HYDROGEN↗

Integrating Learning and Physics based Computation for Fast Online Transient Analysis

In this work, a novel method that integrates learning and physics based computation is developed for greatly accelerating the simulation of full power system transient trajectories. To solve the dynamic algebraic equations, the method replaces the time-consuming dynamic computation for generator dynamics with trained predictors, while retaining the time-efficient algebraic computation of solving AC-power flow (PF) for power systems. In particular, a predictor is trained for each generator, and the system trajectories are computed by alternating steps of calling the predictors and solving AC-PF. The proposed method also allows fully parallelizable training strategies and a flexible trade-off between training time and testing accuracy. Comprehensive evaluations of the proposed method for transient/dynamic contingency analysis of the New York/New England 16-machine 68-bus power systems demonstrate excellent performance and significant acceleration of computation.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Ninth Thermal and Fluids Analysis Workshop Proceedings

The Ninth Thermal and Fluids Analysis Workshop (TFAWS 98) was held at the Ohio Aerospace Institute in Cleveland, Ohio from August 31 to September 4, 1998. The theme for the hands-on training workshop and conference was "Integrating Computational Fluid Dynamics and Heat Transfer into the Design Process." Highlights of the workshop (in addition to the papers published herein) included an address by the NASA Chief Engineer, Dr. Daniel Mulville; a CFD short course by Dr. John D. Anderson of the University of Maryland; and a short course by Dr. Robert Cochran of Sandia National Laboratories. In addition, lectures and hands-on training were offered in the use of several cutting-edge engineering design and analysis-oriented CFD and Heat Transfer tools. The workshop resulted in international participation of over 125 persons representing aerospace and automotive industries, academia, software providers, government agencies, and private corporations. The papers published herein address issues and solutions related to the integration of computational fluid dynamics and heat transfer into the engineering design process. Although the primary focus is aerospace, the topics and ideas presented are applicable to many other areas where these and other disciplines are interdependent.

Sakowski, Barbara↗

“Just Do It” Mission Operations Training in a COVID World

“No”- “not”- “can’t do it” – these words don’t fly in M2020 Mission Operations. The M2020 Surface Mission Operations Team trained for landing the Perseverance Rover under COVID-19 remote work/mandatory stay-at-home conditions. Training activities included presenting Flight Schools to the team via video conferencing, training COVID personal safety requirements to on-premises staff, and constantly updating and communicating COVID restrictions to the team as safety requirements changed. This paper explores the impact of COVID on the Mission System Training for M2020 Mission Operations. The layers of COVID, aptly named the “COVID Tax” by team management, affected project roles, communications, personnel interactions, operations facility usage and training exercises practiced by the team. Flight Schools and Operational Readiness Tests (ORTs) are driving forces behind the surface mission operations training. These activities work hand-in-hand to prepare the team for landing day, surface operations that transition from cruise to nominal operations, and nominal operations. Under normal training conditions, Flight Schools and ORTs are only concerned with tactical operations for the Uplink (Command) Downlink (Analysis) and Campaign Implementation (Planning) Teams of scientists and system engineers. Due to COVID, and the necessity to maintain physical distance between people, training for the landing team needed to include the new category of COVID personal safety. COVID also necessitated remote teams and video conferencing of the entirety of Flight Schools. This reliance on distance learning had not been done on previous missions. We will explore the advantages and disadvantages of video conferencing as a training platform; training effectiveness in communicating and practicing the multiple changes to the COVID safety protocols; and the timing in which we received and responded to COVID directives. Additionally, this paper will review the practical measures taken by the on-premises team and how the team adapted during the readiness tests, landing, and early mission operations, as well as how the team responded to the post-vaccine ramping down of COVID Protocols. The M2020 Surface Mission Operations Team responded very well to the challenges of COVID. All pre-landing operational and COVID-related training was completed. Post-landing COVID Training was provided as needed to new on-premises personnel. Training presented on COVID for the first operational readiness test (ORT) consisted of 2.5 hours of training. Each ORT had COVID Training. A person who had participated in all of the ORTs from September 2020 – February 2021 would have received over 7 hours of COVID Training. By ORT-12 (approximately 8 weeks after the first ORT), the Training team consolidated the original COVID training to a one-hour COVID Basic Training course, with additional recommended training. The Basic training course was updated after landing, as vaccines became available. COVID Training had multiple Flight Schools in the self-directed Blackboard Learning system, as well as a Quick Reference Wiki for Onboarding of new on-premises personnel and keeping on-premises personnel up-to-date. COVID Training covered many topics including practical methods of 6-foot distancing, how to interact with an IT professional when help was needed at a workstation, and challenging indoor meal-eating protocols. COVID Training continued to be updated, as the lab and the project respond to the virus variants and federal, state and local ordinances.

Rosette, Theresa↗

Forecasting the impact of virtual environment technology on maintenance training

To assist NASA and the Air Force in determining how and when to invest in virtual environment (VE) technology for maintenance training, we identified possible roles for VE technology in such training, assessed its cost-effectiveness relative to existing technologies, and formulated recommendations for a research agenda that would address instructional and system development issues involved in fielding a VE training system. In the first phase of the study, we surveyed VE developers to forecast capabilities, maturity, and estimated costs for VE component technologies. We then identified maintenance tasks and their training costs through interviews with maintenance technicians, instructors, and training developers. Ten candidate tasks were selected from two classes of maintenance tasks (seven aircraft maintenance and three space maintenance) using five criteria developed to identify types of tasks most likely to benefit from VE training. Three tasks were used as specific cases for cost-benefit analysis. In formulating research recommendations, we considered three aspects of feasibility: technological considerations, cost-effectiveness, and anticipated R&D efforts. In this paper, we describe the major findings in each of these areas and suggest research efforts that we believe will help achieve the goal of a cost-effective VE maintenance training system by the next decade.

Schlager, Mark S.↗

Blueprints for Training Information Bottlenecks for Collider Analyses

Dimensionality reduction is a crucial aspect of data analysis in high energy physics, even if accompanied by information loss. Several methods, including histogram- and kernel-based analyses, are only computationally feasible for low-dimensional data. Furthermore, simulation models used in HEP can often only be validated for low-dimensional data. We provide several blueprints for using machine learning to create low-dimensional data representations (continuous event variables and discrete classification labels) for use in signal discovery and parameter estimation tasks. We also describe how to design the learned representation to facilitate a) searches with unknown model parameters and b) validation of simulation models in data control regions.

43 PARTICLE ACCELERATORS↗

Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks

Land cover datasets are essential for modeling and analysis of Arctic ecosystem structure and function and for understanding land–atmosphere interactions at high spatial resolutions. However, most Arctic land cover products are generated at a coarse resolution, often limited due to cloud cover, polar darkness, and poor availability of high-resolution imagery. A multi-sensor remote sensing-based deep learning approach was developed for generating high-resolution (5 m) vegetation maps for the western Alaskan Arctic on the Seward Peninsula, Alaska. The fusion of hyperspectral, multispectral, and terrain datasets was performed using unsupervised and supervised classification techniques over a ~343 km 2 area, and a high-resolution (5 m) vegetation classification map was generated. An unsupervised technique was developed to classify high-dimensional remote sensing datasets into cohesive clusters. We employed a quantitative method to add supervision to the unlabeled clusters, producing a fully labeled vegetation map. We then developed convolutional neural networks (CNNs) using the multi-sensor fusion datasets to map vegetation distributions using the original classes and the classes produced by the unsupervised classification method. To validate the resulting CNN maps, vegetation observations were collected at 30 field plots during the summer of 2016, and the resulting vegetation products developed were evaluated against them for accuracy. Our analysis indicates the CNN models based on the labels produced by the unsupervised classification method provided the most accurate mapping of vegetation types, increasing the validation score (i.e., precision) from 0.53 to 0.83 when evaluated against field vegetation observations.

54 ENVIRONMENTAL SCIENCES↗