Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

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)↗
DOE OSTI2021

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↗
DOE OSTI2021

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↗
DOE OSTI2024

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↗
DOE OSTI2022

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↗
DOE OSTI2024

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↗
DOE OSTI2023

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↗
NASA NTRS1999

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↗
NASA NTRS2022

“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↗
NASA NTRS1993

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.↗
DOE OSTI2024

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↗
NASA NTRS1993

A preliminary empirical evaluation of virtual reality as an instructional medium for visual-spatial tasks

We explored the training potential of Virtual Reality (VR) technology. Thirty-one adults were trained and tested on spatial skills in a VR. They learned a sequence of button and knob responses on a VR console and performed flawlessly on the same console. Half were trained with a rote strategy; the rest used a meaningful strategy. Response times were equivalent for both groups and decreased significantly over five test trials indicating that learning continued on VR tests. The same subjects practiced navigating through a VR building, which had three floors with four rooms on each floor. The dependent measure was the number of rooms traversed on routes that differed from training routes. Many subjects completed tests in the fewest rooms possible. All subjects learned configurational knowledge according to the criterion of taking paths that were significantly shorter than those predicted by a random walk as determined by a Monte Carlo analysis. The results were discussed as a departure point for empirically testing the training potential of VR technology.

Regian, J. Wesley↗
NASA NTRSDate not supplied

Application of Support Vector Regression to Derive Crater Depth/Diameter From Satellite Images

Through the study of impact crater shapes, one can draw important conclusions about the nature and evolution of planetary surfaces [e.g., 1-4].In particular, studying the depth (d) to diameter (D)ratio (d/D) of a population of impact craters, in combination with crater count statistics, can yield valuable insights regarding rates of erosion and burial[5]. Motivated by the great abundance of available planetary surface image data, the goal of this project is to develop an efficient way to estimate d/D from satellite images of impact craters for which stereo information is not available [6]. We set out to develop and train a machine learning algorithm to extract d/D from a dataset of synthetic impact crater images for which model d/D is known. The applications of machine learning to planetary science are numerous and diverse [7], including automatic planetary surface mapping [8] and the detection of impact craters [9]. Our algorithm makes use of Support Vector Regression (SVR), which is a type of Support Vector Machine (SVM) [10, 11].SVMs are a branch of supervised machine learning valued for their straightforward implementation and versatility in solving both classification and regression problems. In regression analysis, an SVR algorithm produces a hyperplane function to fit the training data points, as well as an ε-tube that surrounds the hyperplane. Tunable hyperparameters include the width of the ε-tube (ε) and the amount an algorithm is penalized for points which fall outside the ε-tube.

L R Chin↗
DOE OSTI2023

FORCE Output Data Visualization

The Framework for Optimization of ResourCes and Economics (FORCE) is a collection of software tools, models, and datasets acquired and developed under the Integrated Energy Systems (IES) program to enable analysis of technical and economic viability of myriad IES configurations. Idaho National Laboratory is hosting a training session for FORCE users and developers, which is "Integrated Energy Systems Tools FORCE Overview and Training 2023." We will present data output visualization results with FORCE scenarios as examples and show how does the new design improve existing automated visualization for analysis results.

25 ENERGY STORAGE↗
DOE OSTI2026

Multi-Objective design of interlocking metasurfaces using conditional diffusion models

Unit cell design remains a major challenge for interlocking metasurfaces, a promising joining technology for dissimilar materials, due to the complex, competing, multivariate design space and the need for rapid adaptation to varying performance requirements. This study explores Conditional Diffusion Models as a design optimization tool for interlocking metasurfaces. Given the complex, competing, multivariate design space for interlocking metasurfaces, unit cell design remains a major challenge for this joining technology. We trained a conditional diffusion model on 25,000 finite element analysis-simulated interlocking metasurface unit cells to generate designs with tailored thermo-mechanical properties (tensile strength, shear strength, and thermal conductivity) based on specified performance criteria. The model demonstrated a success rate of approximately 72 % in producing designs that met specified property bounds. The conditional diffusion model generated both thermally resistive and conductive designs, revealing clear trends in design characteristics: taller, dendritic structures were advantageous for tensile loads, while shorter, robust designs excelled in shear applications. Our findings indicate that the model's performance is more influenced by the breadth of the design space than by the quantity of training data, highlighting the importance of expansive design domains for generating innovative solutions. This work establishes conditional diffusion models as a highly efficient and adaptable tool for rapid interlocking metasurface unit cell design, paving the way for advancements in multi-material joining technologies, as well as highlighting the justification to leverage conditional diffusion models as design tools across complex design domains.

Conditional diffusion models↗
NASA NTRS2006

Entry, Descent, and Landing Operations Analysis for the Stardust Re-Entry Capsule

On the morning of January 15, 2006, the Stardust capsule successfully landed at the Utah Test and Training range in northwest Utah returning cometary samples from the comet Wild-2. An overview of the entry, descent, and landing (EDL) trajectory analysis that was performed for targeting during the Stardust Mission Navigation Operations Phase upon final approach to Earth is described. In addition, how the predicted landing location and the resulting overall 99 percentile landing footprint ellipse obtained from a Monte Carlo analysis changed over the final days and hours prior to entry is also presented. The navigation and EDL operations effort accurately delivered the entry capsule to the desired landing site. The final landing location was 8.1 km from the target, which was well within the allowable landing area.

Desao, Prasun N.↗
DOE OSTI2021

Analysis-Specific Fast Simulation at the LHC with Deep Learning

Abstract We present a fast-simulation application based on a deep neural network, designed to create large analysis-specific datasets. Taking as an example the generation of W + jet events produced in $$\sqrt{s}=$$ s = 13 TeV proton–proton collisions, we train a neural network to model detector resolution effects as a transfer function acting on an analysis-specific set of relevant features, computed at generation level, i.e., in absence of detector effects. Based on this model, we propose a novel fast-simulation workflow that starts from a large amount of generator-level events to deliver large analysis-specific samples. The adoption of this approach would result in about an order-of-magnitude reduction in computing and storage requirements for the collision simulation workflow. This strategy could help the high energy physics community to face the computing challenges of the future High-Luminosity LHC.

Chen, C.↗
DOE OSTI2025

DONUT: physics-aware machine learning for real-time X-ray nanodiffraction analysis

Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample’s local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.

Materials science↗