Search NASA⌕ Search

SEARCH · Search NASA

Results for “feature engineering”

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 73 records · Page 4

A materials-informatics based study of solid electrolytes and protective coatings for Li batteries

All-solid-state batteries with Li metal anode can address the safety issues surrounding traditional Li-ion batteries as well as the demand for higher energy densities. However, the development of solid electrolytes and protective coatings simultaneously possessing high ionic conductivity and wide electrochemical stability has proven to be a challenge. Here, we present a data-driven approach to explore the Li compound space for promising solid electrolytes and coatings. This is accomplished through the generation of a large database of battery-related materials properties of Li compounds by computing Li+ migration barriers using bond-valence-based pair potentials, and stability windows using density functional theory energies. Using this database, we implement machine learning models that can accurately predict migration barriers and electrochemical stability windows for any new Li compound. Through feature engineering, we ensure that our models are both accurate and interpretable. We perform feature importance analysis on our models to highlight materials properties that can be tuned for future design of coatings/electrolytes. Our database and informatics approach provide a valuable tool for the rapid discovery of new solid-state battery chemistries.

Solid state batteries↗

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗

The Nutating Engine-Prototype Engine Progress Report and Test Results

A prototype of a new, internal combustion (IC) engine concept has been completed. The Nutating Engine features an internal disk nutating (wobbling) on a Z-shaped power shaft. The engine is exceedingly compact, and several times more power dense than any conventional (reciprocating or rotary) IC engine. This paper discusses lessons learned during the prototype engine's development and provides details of its construction. In addition, results of the initial performance tests of the various components, as well as the complete engine, are summarized.

Meitner, Peter L.↗

Liquid rocket booster study. Volume 2, book 4, appendices 6-8: Reports of Rocketdyne, Pratt and Whitney, and TRW

For the pressure fed engines, detailed trade studies were conducted defining engine features such as thrust vector control methods, thrust chamber construction, etc. This was followed by engine design layouts and booster propulsion configuration layouts. For the pump fed engines parametric performance and weight data was generated for both O2/H2 and O2/RP-1 engines. Subsequent studies resulted in the selection of both LOX/RP-1 and O2/H2 propellants for the pump fed engines. More detailed analysis of the selected LOX/RP-1 and O2/H2 engines was conducted during the final phase of the study.

Source record↗

Feature selection with distance correlation

Choosing which properties of the data to use as input to multivariate decision algorithms—also known as feature selection—is an important step in solving any problem with machine learning. While there is a clear trend towards training sophisticated deep networks on large numbers of relatively unprocessed inputs (so-called automated feature engineering), for many tasks in physics, sets of theoretically well-motivated and well-understood features already exist. Working with such features can bring many benefits, including greater interpretability, reduced training and run time, and enhanced stability and robustness. We develop a new feature selection method based on distance correlation, and demonstrate its effectiveness on the tasks of boosted top- and W -tagging. Using our method to select features from a set of over 7,000 energy flow polynomials, we show that we can match the performance of much deeper architectures, by using only ten features and two orders-of-magnitude fewer model parameters. Published by the American Physical Society 2024

Astronomy & Astrophysics↗

Machine-learning error models for approximate solutions to parameterized systems of nonlinear equations

Here, this work proposes a machine-learning framework for constructing statistical models of errors incurred by approximate solutions to parameterized systems of nonlinear equations. These approximate solutions may arise from early termination of an iterative method, a lower-fidelity model, or a projection-based reduced-order model, for example. The proposed statistical model comprises the sum of a deterministic regression-function model and a stochastic noise model. The method constructs the regression-function model by applying regression techniques from machine learning (e.g., support vector regression, artificial neural networks) to map features (i.e., error indicators such as sampled elements of the residual) to a prediction of the approximate-solution error. The method constructs the noise model as a mean-zero Gaussian random variable whose variance is computed as the sample variance of the approximate-solution error on a test set; this variance can be interpreted as the epistemic uncertainty introduced by the approximate solution. This work considers a wide range of feature-engineering methods, data-set-construction techniques, and regression techniques that aim to ensure that (1) the features are cheaply computable, (2) the noise model exhibits low variance (i.e., low epistemic uncertainty introduced), and (3) the regression model generalizes to independent test data. Finally, numerical experiments performed on several computational-mechanics problems and types of approximate solutions demonstrate the ability of the method to generate statistical models of the error that satisfy these criteria and significantly outperform more commonly adopted approaches for error modeling.

97 MATHEMATICS AND COMPUTING↗

Techno-economic analysis of sugarcane bagasse and straw conversion into cellulosic ethanol via consolidated bioprocessing

Cellulosic biofuels offer a sustainable alternative to fossil fuels and a means to mitigate climate change. Consolidated bioprocessing (CBP) featuring engineered thermophilic bacteria, combined with mechanical disruption during fermentation (cotreatment), has potential to lower production costs compared to featuring thermochemical pretreatment and added cellulase. A techno-economic analysis was conducted (230 million L ethanol/year) from sugarcane bagasse and straw at stand-alone facilities generating electricity from residues. Three scenarios were evaluated: Conventional, featuring hydrothermal pretreatment, fungal cellulase, and yeast fermentation (current commercial standard); Mid-term CBP, relying on bagasse solubilization without pretreatment or cotreatment; and Mature CBP, incorporating cotreatment but no pretreatment. Results for these scenarios in this order were: fixed capital investment (CapEx) $\$$589M, $\$$658M, and $\$$472M; net annual revenue (EBITDA) $\$$56M, $\$$96M, and $\$$94M; and minimum ethanol selling price 0.73, 0.61, and 0.48 US$\$$/L. Payback periods were 10.5, 6.9, and 5.1 years, while all scenarios showed <5 years at European prices for scales >100M L/year. Sensitivity and risk analysis highlighted ethanol price as the most critical variable. It is notable that Mid-term CBP had shorter payback times and better overall economic feasibility compared to Conventional. Our results underscore opportunities for research-driven innovation on low-cost cellulosic ethanol technologies in Brazil and elsewhere.

Consolidated bioprocessing↗

Design study of RL10 derivatives. Volume 2: Engine design characteristics

The design characteristics of the RL-10 rocket engine are discussed. The results from critical elements evaluation, baseline engine design, parametric and special study tasks are presented. Critical element evaluation established the feasibility of various engine features such as tank head idle, pumped idle, autogenous tank pressurization, and two-phase pumping. Three baseline engines, derived from the RL-10 were conceptually designed. Parametric life and performance data were generated. Special studies were conducted to establish the impact on the engine design of environment, safety, interchangeability, and maintenance.

Adams, A.↗

The dynamics, mixing, and thermonuclear burn of compressed foams with varied gas fills

Inertial confinement fusion (ICF) implosions involve highly coupled physics and complex hydrodynamics that are challenging to model computationally. Due to the sensitivity of such implosions to small features, detailed simulations require accurate accounting of the geometry and dimensionality of the initial conditions, including capsule defects and engineering features such as fill tubes used to insert gas into the capsule, yet this is computationally prohibitive. It is therefore difficult to evaluate whether discrepancies between the simulation and experiment arise from inadequate fidelity to the capsule geometry and drive conditions, uncertainties in physical data used by simulations, or inadequate physics. We present results from detailed high-resolution three-dimensional simulations of ICF implosions performed as part of the MARBLE campaign on the National Ignition Facility [Albright et al., Phys. Plasmas 29, 022702 (2022)]. These experiments are foam-filled separated-reactant experiments, where deuterons reside in the foam and tritons reside in the capsule gas fill and deuterium–tritium (DT) fusion reactions only occur in the presence of mixing between these materials. Material mixing in these experiments is primarily seeded by shock interaction with the complex geometry of the foam and gas fill, which induces the Richtmyer–Meshkov instability. We compare results for experiments with two different gas fills (ArT and HT), which lead to significant differences in the hydrodynamic and thermodynamic developments of the materials in the implosion. Our simulation results show generally good agreement with experiments and demonstrate a substantial impact of hydrodynamic flows on measured ion temperatures. The results suggest that viscosity, which was not included in our simulations, is the most important unmodeled physics and qualitatively explains the few discrepancies between the simulation and experiment. The results also suggest that the hydrodynamic treatment of shocks is inadequate to predict the heating and yield produced during shock flash, when the shock converges at the center of the implosion. Alternatively, underestimation of the level of radiative preheat from the shock front could explain many of the differences between the experiment and simulation. Nevertheless, simulations are able to reproduce many experimental observables within the level of experimental reproducibility, including most yields, time-resolved X-ray self-emission images, and an increase in burn-weighted ion temperature and neutron down-scattered ratio in the line of sight that includes a jet seeded by the glue spot that joins capsule hemispheres.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

The structural information filtered features (SIFF) potential: Maximizing information stored in machine-learning descriptors for materials prediction

Machine learning inspired potentials continue to improve the ability for predicting structures of materials. However, many challenges still exist, particularly when calculating structures of disordered systems. These challenges are primarily due to the rapidly increasing dimensionality of the feature-vector space which in most machine-learning algorithms is dependent on the size of the structure. In this article, we present a feature-engineered approach that establishes a set of principles for representing potentials of physical structures (crystals, molecules, and clusters) in a feature space rather than a physically motivated space. Our goal in this work is to define guiding principles that optimize information storage of the physical parameters within the feature representations. In this manner, we focus on keeping the dimensionality of the feature space independent of the number of atoms in the structure. Our Structural Information Filtered Features (SIFF) potential represents structures by utilizing a feature vector of low-correlated descriptors, which correspondingly maximizes information within the descriptor. We present results of our SIFF potential on datasets composed of disordered (carbon and carbon–oxygen) clusters, molecules with C 7 O 2 H 2 stoichiometry in the GDB9-14B dataset, and crystal structures of the form (Al x Ga y In z ) 2 O 3 as proposed in the NOMAD Kaggle competition. Our potential's performance is at least comparable, sometimes significantly more accurate, and often more efficient than other well-known machine-learning potentials for structure prediction. However, primarily, we offer a different perspective on how researchers should consider opportunities in maximizing information storage for features.

36 MATERIALS SCIENCE↗

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data (Final Report)

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components: (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine.

20 FOSSIL-FUELED POWER PLANTS↗

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine

03 NATURAL GAS↗

Embedded Sensing in Additive Manufacturing Metal and Polymer Parts: A Comparative Study of Integration Techniques and Structural Health Monitoring Performance

This study presents a comparative evaluation of post-process sensor integration in additively manufactured (AM) metal and the in-situ process for polymer structures for structural health monitoring (SHM), with an emphasis on embedded sensors. Geometrically identical specimens were fabricated using copper via metal fused filament fabrication (FFF) and PLA via polymer FFF, with piezoelectric transducers (PZTs) inserted into internal cavities to assess the influence of material and placement on sensing fidelity. Mechanical testing under compressive and point loads generated signals that were transformed into time–frequency spectrograms using a Short-Time Fourier Transform (STFT) framework. An engineered RGB representation was developed, combining global amplitude scaling with an amplitude-envelope encoding to enhance contrast and highlight subtle wave features. These spectrograms served as inputs to convolutional neural networks (CNNs) for classification of load conditions and detection of damage-related features. Results showed reliable recognition in both copper and PLA specimens, with CNN classification accuracies exceeding 95%. Embedded PZTs were especially effective in PLA, where signal damping and environmental sensitivity often hinder surface-mounted sensors. This work demonstrates the advantages of embedded sensing in AM structures, particularly when paired with spectrogram-based feature engineering and CNN modeling, advancing real-time SHM for aerospace, energy, and defense applications.

additive manufacturing↗

High-Temperature Microphone With Fiber-Optic Output

Acoustic-pressure transducer (microphone) with fiber-optic output designed to withstand hot, loud, structurally vibrating environment like that of jet engine. Features flat frequency response out to frequencies well beyond several-kilohertz range needed to test for acoustic-pressure loads on engine structures.

Hellbaum, Richard F.↗

ATAT: Astronomical Transformer for time series and Tabular data

Context. The advent of next-generation survey instruments, such as theVera C. RubinObservatory and its Legacy Survey of Space and Time (LSST), is opening a window for new research in time-domain astronomy. The Extended LSST Astronomical Time-Series Classification Challenge (ELAsTiCC) was created to test the capacity of brokers to deal with a simulated LSST stream. Aims. Our aim is to develop a next-generation model for the classification of variable astronomical objects. We describe ATAT, the Astronomical Transformer for time series And Tabular data, a classification model conceived by the ALeRCE alert broker to classify light curves from next-generation alert streams. ATAT was tested in production during the first round of the ELAsTiCC campaigns. Methods. ATAT consists of two transformer models that encode light curves and features using novel time modulation and quantile feature tokenizer mechanisms, respectively. ATAT was trained on different combinations of light curves, metadata, and features calculated over the light curves. We compare ATAT against the current ALeRCE classifier, a balanced hierarchical random forest (BHRF) trained on human-engineered features derived from light curves and metadata. Results. When trained on light curves and metadata, ATAT achieves a macro F1 score of 82.9 ± 0.4 in 20 classes, outperforming the BHRF model trained on 429 features, which achieves a macro F1 score of 79.4 ± 0.1. Conclusions. The use of transformer multimodal architectures, combining light curves and tabular data, opens new possibilities for classifying alerts from a new generation of large etendue telescopes, such as theVera C. RubinObservatory, in real-world brokering scenarios.

Astronomy & Astrophysics↗

Machine learning bandgaps of double perovskites

The ability to make rapid and accurate predictions on bandgaps of double perovskites is of much practical interest for a range of applications. While quantum mechanical computations for high-fidelity bandgaps are enormously computation-time intensive and thus impractical in high throughput studies, informatics-based statistical learning approaches can be a promising alternative. Here we demonstrate a systematic feature-engineering approach and a robust learning framework for efficient and accurate predictions of electronic bandgaps of double perovskites. After evaluating a set of more than 1.2 million features, we identify lowest occupied Kohn-Sham levels and elemental electronegativities of the constituent atomic species as the most crucial and relevant predictors. As a result, the developed models are validated and tested using the best practices of data science and further analyzed to rationalize their prediction performance.

36 MATERIALS SCIENCE↗

Navigating Transition-Metal Chemical Space: Artificial Intelligence for First-Principles Design

Conspectus The variability of chemical bonding in open-shell transition-metal complexes not only motivates their study as functional materials and catalysts but also challenges conventional computational modeling tools. Here, tailoring ligand chemistry can alter preferred spin or oxidation states as well as electronic structure properties and reactivity, creating vast regions of chemical space to explore when designing new materials atom by atom. Although first-principles density functional theory (DFT) remains the workhorse of computational chemistry in mechanism deduction and property prediction, it is of limited use here. DFT is both far too computationally costly for widespread exploration of transition-metal chemical space and also prone to inaccuracies that limit its predictive performance for localized d electrons in transition-metal complexes. These challenges starkly contrast with the well-trodden regions of small-organic-molecule chemical space, where the analytical forms of molecular mechanics force fields and semiempirical theories have for decades accelerated the discovery of new molecules, accurate DFT functional performance has been demonstrated, and gold-standard methods from correlated wavefunction theory can predict experimental results to chemical accuracy. The combined promise of transition-metal chemical space exploration and lack of established tools has mandated a distinct approach. In this Account, we outline the path we charted in exploration of transition-metal chemical space starting from the first machine learning (ML) models (i.e., artificial neural network and kernel ridge regression) and representations for the prediction of open-shell transition-metal complex properties. The distinct importance of the immediate coordination environment of the metal center as well as the lack of low-level methods to accurately predict structural properties in this coordination environment first motivated and then benefited from these ML models and representations. Once developed, the recipe for prediction of geometric, spin state, and redox potential properties was straightforwardly extended to a diverse range of other properties, including in catalysis, computational “feasibility”, and the gas separation properties of periodic metal–organic frameworks. Interpretation of selected features most important for model prediction revealed new ways to encapsulate design rules and confirmed that models were robustly mapping essential structure–property relationships. Encountering the special challenge of ensuring that good model performance could generalize to new discovery targets motivated investigation of how to best carry out model uncertainty quantification. Distance-based approaches, whether in model latent space or in carefully engineered feature space, provided intuitive measures of the domain of applicability. With all of these pieces together, ML can be harnessed as an engine to tackle the large-scale exploration of transition-metal chemical space needed to satisfy multiple objectives using efficient global optimization methods. In practical terms, bringing these artificial intelligence tools to bear on the problems of transition-metal chemical space exploration has resulted in ML-model assessments of large, multimillion compound spaces in minutes and validated new design leads in weeks instead of decades.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

European Lean Gasoline Direct Injection Vehicle Benchmark

Lean Gasoline Direct Injection (LGDI) combustion is a promising technical path for achieving significant improvements in fuel efficiency while meeting future emissions requirements. Though Stoichiometric Gasoline Direct Injection (SGDI) technology is commercially available in a few vehicles on the American market, LGDI vehicles are not, but can be found in Europe. Oak Ridge National Laboratory (ORNL) obtained a European BMW 1-series fitted with a 2.0l LGDI engine. The vehicle was instrumented and commissioned on a chassis dynamometer. The engine and after-treatment performance and emissions were characterized over US drive cycles (Federal Test Procedure (FTP), the Highway Fuel Economy Test (HFET), and US06 Supplemental Federal Test Procedure (US06)) and steady state mappings. The vehicle micro hybrid features (engine stop-start and intelligent alternator) were benchmarked as well during the course of that study. The data was analyzed to quantify the benefits and drawbacks of the lean gasoline direct injection and micro hybrid technologies from a fuel economy and emissions perspectives with respect to the US market. Additionally that data will be formatted to develop, substantiate, and exercise vehicle simulations with conventional and advanced powertrains.

02 PETROLEUM↗