Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS2018

Earth Science Deep Learning: Applications and Lessons Learned

Deep Learning: A subfield of machine learning; Algorithms inspired by function of the brain; Scales with amount of training data; Powerful tool without the need for feature engineering; Suitable for Earth Science applications. Deep Learning for Earth science at MSFC (Marshall Space Flight Center): Phenomena identification; Hurricane intensity (wind speed) estimation; Severe storm (hailstorm) detection; Transverse bands detection; Entity extraction for knowledge graph creation; Ephemeral water detection.

Labeled Data↗
NASA NTRSDate not supplied

Data Science and the Knowledge Discovery Adventure

This talk will cover the important steps involved in the data science and knowledge discovery process: • Initial fact gathering (interview domain experts, review reports, articles, state-of-the-art) • Identify the problem (prediction, classification, statistical analysis, etc.) • Survey supporting data sources • Understand the data (numerical, categorical, text, sampling rate, data quality issues, etc.) • Selecting relevant features and sources • Acquire the data (set up agreements with the data stewards, APIs to download, etc.) • Merge data sources (temporal, spatial, common key, other ontologies...) • Feature Engineering (non linear domain knowledge or physics-based relationships) • Build data processing pipeline (may need to tap into data stream, develop parallel processing algorithm, federated learning etc.) • Build model and test (tune hyper-parameters, cross validation.) • Analyze/Validate results (do the results make sense. Does it answer the original question). • Deploy/Publish (Monitor and assess benefits)

Data science↗
NASA NTRS2022

Remote sensing-based vegetation and soil moisture constraints reduce irrigation estimation uncertainty

Understanding the human water footprint and its impact on the hydrological cycle is essential to inform water management under climate change. Despite efforts in estimating irrigation water withdrawals in earth system models, uncertainties and discrepancies exist within and across modeling systems conditioned by model structure, irrigation parameterization, and the choice of input datasets. Achieving model reliability could be much more challenging for data-sparse regions, given limited access to ground truth for parameterization and validation. Here, we demonstrate the potential of utilizing remotely sensed vegetation and soil moisture observations in constraining irrigation estimation in the Noah-MP land surface model. Results indicate that the two constraints together can effectively reduce model sensitivity to the choice of irrigation parameterization by 7%–43%. It also improves the characterization of the spatial patterns of irrigation and its impact on evapotranspiration and surface soil moisture by correcting for vegetation conditions and irrigation timing. This study highlights the importance of utilizing remotely sensed soil moisture and vegetation measurements in detecting irrigation signals and correcting for vegetation growth. Integrating the two remote sensing datasets into the model provides an effective and less feature engineered approach to constraining the uncertainty of irrigation modeling. Such strategies can be potentially transferred to other modeling systems and applied to regions across the globe.

Wanshu Nie↗
NASA NTRSDate not supplied

Curating AI-Ready Datasets for Equity and Environmental Justice: A Data-Centric AI Case Study

An equitable and environmentally just community is essentialin order to avoid disproportionate burden borne by vulnerablecommunities. This need becomes pressing in the aftermathof an extreme event such as disaster or hazard when it is diffi-cult for the governing bodies to implement resource allocationas per the need. Artificial Intelligence (AI) algorithms canhelp surface Equity and Environmental Justice (EEJ) issueswhen trained on EEJ datasets. However, curating AI-readyEEJ training datasets is challenging due to differences in fac-tors such as heterogeneity, resolution, modality, and level ofexpertise in labeling. Additionally, EEJ issues involve sensi-tive information where uncertainties and errors could degradethe performance of AI algorithms. For eg. Error in seasonalcrop yield information can highly affect the prediction of an-nual crop yield. To address these challenges, Data-centricAI (DCAI) methods are employed, which enhance AI algo-rithm performance even with limited training samples. DCAIprioritizes data quality, thereby reducing the adverse effectsof uncertainties and errors during the model training process.This research proposes a novel dataset and benchmark for an-alyzing the effect of the Maui Wildfire of 2023 for Equityand Environmental Justice (EEJ) issues. The proposed datasetaligns with the concepts of DCAI such as annotation quality,data preprocessing, privacy, feature engineering, governanceand provenance. We firmly believe that the proposed datasetwould lay a foundation to implement robust and reliable mod-ern AI algorithms for addressing EEJ issues.

Paridhi Parajuli↗
DOE OSTI2025

Tandem Predictions for HPC Jobs: Preprint

At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1973

The Space Shuttle Main Engine and its maintenance features

The Space Shuttle Main Engine (SSME) is a reusable, high-performance rocket engine being developed to satisfy the performance, life, reliability, and operational requirements of the Space Shuttle Orbiter. The design includes simple, low-cost maintenance features resulting from a viable maintainability program dedicated to minimizing engine cost per flight.

Wheelock, V. J.↗
NASA NTRS1977

Space Shuttle Main Engine

Significant features of the Space Shuttle Main Engine (SSME) include a staged combustion power cycle, high area ratio nozzle expansion, throttling capability, and a computer operated control system. These main design features are discussed along with development test results.

Thompson, J. R., Jr.↗
NASA NTRS1980

Space Shuttle Main Engine

Significant features of the Space Shuttle Main Engine (SSME) include a staged combustion power cycle developing chamber pressure in excess of 3000 psia, high area ratio nozzle expansion, throttling capability, and a computer-operated engine control system. This paper examines the current status of the SSME with attention given to engine performance, system characteristics, and test results. A comparison of the SSME development and certification programs with engines successfully used in the Saturn Program is presented.

Thompson, J. R., Jr.↗
NASA NTRS1984

Dynamic property studies of Sterling engines

A description is given of the results of dynamic property tests that were carried out using a trial produced prototype of a 50 KW Sterling engine. The features of the engine are shown graphically. A high thermal efficiency is found in the low rotation region.

Tani, Y.↗
NASA NTRS1992

A survey of instabilities within centrifugal pumps and concepts for improving the flow range of pumps in rocket engines

Design features and concepts that have primary influence on the stable operating flow range of propellant-feed centrifugal turbopumps in a rocket engine are discussed. One of the throttling limitations of a pump-fed rocket engine is the stable operating range of the pump. Several varieties of pump hydraulic instabilities are mentioned. Some pump design criteria are summarized and a qualitative correlation of key parameters to pump stall and surge are referenced. Some of the design criteria were taken from the literature on high pressure ratio centrifugal compressors. Therefore, these have yet to be validated for extending the stable operating flow range of high-head pumps. Casing treatment devices, dynamic fluid-damping plenums, backflow-stabilizing vanes and flow-reinjection techniques are summarized. A planned program was undertaken at LeRC to validate these concepts. Technologies developed by this program will be available for the design of turbopumps for advanced space rocket engines for use by NASA in future space missions where throttling is essential.

Veres, Joseph P.↗
NASA NTRS1979

Advanced General Aviation Turbine Engine (GATE) study

The small engine technology requirements suitable for general aviation service in the 1987 to 1988 time frame were defined. The market analysis showed potential United States engines sales of 31,500 per year providing that the turbine engine sales price approaches current reciprocating engine prices. An optimum engine design was prepared for four categories of fixed wing aircraft and for rotary wing applications. A common core approach was derived from the optimum engines that maximizes engine commonality over the power spectrum with a projected price competitive with reciprocating piston engines. The advanced technology features reduced engine cost, approximately 50 percent compared with current technology.

Smith, R.↗
NASA NTRS1980

AiResearch QCGAT engine, airplane, and nacelle design features

The quiet, clean, general aviation turbofan engine and nacelle system was designed and tested. The engine utilized the core of the AiResearch model TFE731-3 engine and incorporated several unique noise- and emissions-reduction features. Components that were successfully adapted to this core include the fan, gearbox, combustor, low-pressure turbine, and associated structure. A highly versatile workhorse nacelle incorporating interchangeable acoustic and hardwall duct liners, showed that large-engine attenuation technology could be applied to small propulsion engines. The application of the mixer compound nozzle demonstrated both performance and noise advantages on the engine. Major performance, emissions, and noise goals were demonstrated.

Heldenbrand, R. W.↗
NASA NTRS1978

Gas turbine engine with convertible accessories

Drive means for connecting a gas turbine engine to its accessories are so constructed as to allow the accessories to be selectively positioned to any one of several predetermined circumferential positions about the perimeter of the engine. This feature permits convenient mounting of the same engine upon vehicles demanding radically different engine mounting arrangements.

Sargisson, D. F.↗
NASA NTRS1980

Orbit transfer vehicle engine study, phase A extension. Volume 1: Executive summary

A 1980 state-of-the-art advanced expander engine was configured that delivers near-optimum payload-performance and exhibits the simplicity reliability, and life characteristics required of the OTV mission. Engine optimization studies indicate that the performance of the conventional expander cycle engine can be improved substantially through combustion chamber surface area enhancement, thermal enhancement, turbine regeneration, and power cycle efficiency enhancement procedures. The 20K lb. thrust staged combustion engine can be adapted to operate at extended periods in the 1 to 2K lb. thrust regime. The study results indicate that long-life, high performnce operation in the low thrust mode can be achieved with minimum modifications (kitting) of the engine. Although the main contribution to mission success and crew safety stems from propulsion system redundancy, significant reliability can be gained from engine component redundancy, specific engine design features ensuring safety and reliability, including an engine health monitoring system, and from a total program approach to safety and reliability, such as that presently applied to the space shuttle.

Source record↗
NASA NTRS1991

Simulation of a combined-cycle engine

A FORTRAN computer program was developed to simulate the performance of combined-cycle engines. These engines combine features of both gas turbines and reciprocating engines. The computer program can simulate both design point and off-design operation. Widely varying engine configurations can be evaluated for their power, performance, and efficiency as well as the influence of altitude and air speed. Although the program was developed to simulate aircraft engines, it can be used with equal success for stationary and automative applications.

Vangerpen, Jon↗
NASA NTRS1972

The NASA Quiet Engines.

The present status of the Quiet Engine Program is reviewed, and the future prospects suggested by recent quiet engine test results are discussed. Following a brief survey of noise sources, quiet engine design features, and the major elements of the Quiet Engine Program, a review is presented of specific quiet engine test that includes the two baseline quiet engines tested and flyover noise comparison results. It is shown that the application to future aircraft of the developed and demonstrated engine noise reduction technology can bring about a substantial reduction in aircraft noise levels. The minimization of the economic penalty associated with this noise reduction technology is being studied.

Ciepluch, C. C.↗
NASA NTRS2019

Scaling Evaluation of Ice-Crystal Icing on a Modern Turbofan Engine in PSL Using the COMDES-MELT Code

This paper presents preliminary ice-crystal icing (ICI) altitude scaling evaluation results of a Honeywell Uncertified Research Engine (HURE) that was tested in the NASA Glenn Research Center Propulsion Systems Laboratory (PSL) during January of 2018. This engine geometry features a hidden core design to keep the core less exposed. The engine was fitted with internal video cameras to observe various ice buildup processes at multiple selected locations within the engine core flow path covering the fan stator, the splitter-lip/shroud/strut, and the high pressure compressor (HPC) variable inlet guide vane (IGV) regions. The potential ice accretion risk was pre-determined to occur by using NASA’s in-house 1D Engine Icing Risk assessment code, COMDES-MELT. The code was successful in predicting the risk of ice accretion in adiabatic regions like the fan-stator of the HURE at specific engine operating points. However at several operating points during the test, liquid water was observed running along the shroud toward the variable IGV of the HPC regions with an air temperature well below freezing, thus no particle melting could have occurred due to heating from the air alone. It was reasoned that other sources of heat were present in that region. To account for these heat sources the inlet total temperature was adjusted to give a wet bulb temperature of 24 F below the standard minimum wet bulb temperature of 492 R to allow ice to accrete in the splitter-lip/shroud/strut region, which was determined from a reference case where hard ice was observed in that region. With that adjustment the COMDES-MELT code was successful in providing operating points where there was a risk of ice accretion during the test campaign. In addition to calculating possible conditions at different selected lower altitudes, simulations were run to determine potential inlet conditions that could lead to ice-crystal accretion along the prescribed stations where the cameras were available. From there, scaled test conditions were determined by best matching the following three icing related parameters of the reference condition: (1) the local air total wet bulb temperature, (2) the local ice crystal cloud melt ratio and (3) the engine fan face ice/water to air mass flux ratio of the ice crystal cloud. Instantaneous images taken from the time-lapsed movies of ice buildup were used along with the relevant thermodynamic data of air, water vapor and local icing condition to help evaluate how closely the proposed altitude scaling method could be used in ground based test facility to duplicate selected reference ICI features observed at specific location inside this engine at different scale altitudes. Discussions on observed limitation for engine icing scaling application from this test campaign and needed improvement are provided. A scaling test procedure to help identify potential ICI risk conditions and possible ice accretion locations of a new turbofan engine is evaluated in PSL.

Engine Testing in PSL↗