SEARCH · Engineering Papers

Results for “predictive analytics”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

NASA NTRS1984

Comparison of experimental and analytical predictions of rotor blade-vortex interactions using model scale acoustic data

Helicopter blade-vortex interaction (BVI) noise is studied using a model scale rotor acoustic data base and an analytical rotor wake prediction method. The variation of BVI acoustic levels with vehicle flight conditions (forward speed and disk attitude) is presented. Calculations of probable BVI locations on the rotor disk are made for a range of operating conditions using the measured acoustic signals and an acoustic ray tracing technique. Analytical predictions of possible BVI locations on the rotor disk are made using a generalized distorted wake analysis program. Comparisons of the interaction locations are made with the results of both the analytic approach and the acoustic ray tracing technique.

Martin, R. M.↗

NASA NTRS1978

Analytical prediction of agricultural aircraft wakes

An analytical technique has been developed to understand the formation, interaction, and decay of lift-generated vortices. It is possible, by use of a computer code, to give a complete description of the viscous rollup of individual vortices from a wing. That the interaction of the vortex wake with the ground is a viscous interaction is demonstrated. Comparisons are given of experimental model data and predictions of vortex location for agricultural aircraft. The future of these codes in guiding wind-tunnel and flight research and in providing operational mission guidance is discussed.

Morris, D. J.↗

NASA NTRS1991

Analytical prediction of EM scattering by complex obstacles within electrically large open cavities

An analytical technique is described for predicting the electromagnetic (EM) scattering by complex obstacles within electrically large open waveguide cavities. This topic is of relevance to EM scattering and EMC type applications. A general open ended waveguide cavity is illustrated and is assumed to be relatively arbitrarily shaped, and the open front end of the cavity is illuminated by an arbitrarily polarized external plane wave field. The interior obstacle is assumed to be located within the cavity near the back end, and it generally contributes significantly to the fields scattered into the exterior by the entire cavity configuration. The present scattering analysis is restricted to within approximately 70 degs from boresight with respect to the open front end; outside of this region, the scattering by the external features of the cavity are generally more significant than from the interior of the cavity. The scattering analysis is composed of two main parts. One analysis is of the coupling of the incident plane wave field, via the open front end using the high frequency ray or beam shooting methods. The other analysis deals with separately obtaining the plane wave scattering characteristics of the interior obstacle. Thus the present analysis represents a hybrid combination of an asymptotic high frequency ray/beam method for tracking the fields through the cavity, together with any suitable method for obtaining a plane wave characterization of the interior obstacle.

Pathak, Prabhakar H.↗

NASA NTRS1972

Analytic prediction of dynamic stall characteristics.

A new approach is presented for solving the problem of predicting dynamic stall characteristics. In this approach, the unsteady aerodynamic characteristics are related theoretically to static aerodynamic characteristics which are readily available for a great number of airfoil shapes. Using these static experimental data as an input, the developed analytical method predicts dynamic stall characteristics that are in good agreement with available experimental data. The analysis is also extended to include frequency and amplitude modulation effects.

Ericsson, L. E.↗

NASA NTRS1980

Analytical prediction of the interior noise for cylindrical models of aircraft fuselages for prescribed exterior noise fields. Phase 1: Development and validation of preliminary analytical models

The basic theoretical work required to understand sound transmission into an enclosed space (that is, one closed by the transmitting structure) is developed for random pressure fields and for harmonic (tonal) excitation. The analysis is used to predict the noise reducton of unpressurized unstiffened cylinder, and also the interior response of the cylinder given a tonal (plane wave) excitation. Predictions and measurements are compared and the transmission is analyzed. In addition, results for tonal (harmonic) mechanical excitation are considered.

Pope, L. D.↗

DOE OSTI2024

Structure-aware graph neural network based deep transfer learning framework for enhanced predictive analytics on diverse materials datasets

Abstract Modern data mining methods have demonstrated effectiveness in comprehending and predicting materials properties. An essential component in the process of materials discovery is to know which material(s) will possess desirable properties. For many materials properties, performing experiments and density functional theory computations are costly and time-consuming. Hence, it is challenging to build accurate predictive models for such properties using conventional data mining methods due to the small amount of available data. Here we present a framework for materials property prediction tasks using structure information that leverages graph neural network-based architecture along with deep-transfer-learning techniques to drastically improve the model’s predictive ability on diverse materials (3D/2D, inorganic/organic, computational/experimental) data. We evaluated the proposed framework in cross-property and cross-materials class scenarios using 115 datasets to find that transfer learning models outperform the models trained from scratch in 104 cases, i.e., ≈90%, with additional benefits in performance for extrapolation problems. We believe the proposed framework can be widely useful in accelerating materials discovery in materials science.

Chemistry↗

NASA NTRS1972

Analytical prediction of digital signal crosstalk of FCC

The results are presented of study effort whose aim was the development of accurate means of analyzing and predicting signal cross-talk in multi-wire digital data cables. A complete analytical model is developed n + 1 wire systems of uniform transmission lines with arbitrary linear boundary conditions. In addition, a minimum set of parameter measurements required for the application of the model are presented. Comparisons between cross-talk predicted by this model and actual measured cross-talk are shown for a six conductor ribbon cable.

Belleisle, A. P.↗

NASA NTRS1971

Analytical prediction of the heat transfer from a blood vessel near the skin surface when cooled by a symmetrical cooling strip

An analytical method was developed to estimate the amount of heat extracted from an artery running close to the skin surface which is cooled in a symmetrical fashion by a cooling strip. The results indicate that the optimum width of a cooling strip is approximately three times the depth to the centerline of the artery. The heat extracted from an artery with such a strip is about 0.9 w/m-C which is too small to affect significantly the temperature of the blood flow through a main blood vessel, such as the carotid artery. The method is applicable to veins as well.

Chato, J. C.↗

DOE OSTI2021

Cross-property deep transfer learning framework for enhanced predictive analytics on small materials data

Abstract Artificial intelligence (AI) and machine learning (ML) have been increasingly used in materials science to build predictive models and accelerate discovery. For selected properties, availability of large databases has also facilitated application of deep learning (DL) and transfer learning (TL). However, unavailability of large datasets for a majority of properties prohibits widespread application of DL/TL. We present a cross-property deep-transfer-learning framework that leverages models trained on large datasets to build models on small datasets of different properties. We test the proposed framework on 39 computational and two experimental datasets and find that the TL models with only elemental fractions as input outperform ML/DL models trained from scratch even when they are allowed to use physical attributes as input, for 27/39 (≈ 69%) computational and both the experimental datasets. We believe that the proposed framework can be widely useful to tackle the small data challenge in applying AI/ML in materials science.

36 MATERIALS SCIENCE↗

NASA NTRS1972

Analytic prediction of airplane equilibrium spin characteristics

The nonlinear equations of motion are solved algebraically for conditions for which an airplane is in an equilibrium spin. Constrained minimization techniques are employed in obtaining the solution. Linear characteristics of the airplane about the equilibrium points are also presented and their significance in identifying the stability characteristics of the equilibrium points is discussed. Computer time requirements are small making the method appear potentially applicable in airplane design. Results are obtained for several configurations and are compared with other analytic-numerical methods employed in spin prediction. Correlation with experimental results is discussed for one configuration for which a rather extensive data base was available. A need is indicated for higher Reynolds number data taken under conditions which more accurately simulate a spin.

Adams, W. M., Jr.↗

NASA NTRS1981

Analytical prediction and experimental verification of performance at various operating conditions of a dual-mode traveling wave tube with multistage depressed collectors

A comparison of analytical and experimental results is presented for a high performance dual-mode traveling wave tube (TWT) operated over a wide range conditions. The computations are carried out with advanced multidimensional computer programs. These programs model the electron beam as a series of disks or rings of charge and follow their trajectories from the rf input of the TWT through the slow-wave structure refocusing system to their points of impacts in the depressed collector. TWT performance, collector efficiency, and collector current distribution are computed and compared with measurements. Very good agreement was obtained between computed and measured TWT performance and collector efficiencies, and the computer design of a highly efficient collector was demonstrated.

Dayton, J. A., Jr.↗

NASA NTRS1979

Analytical prediction with multidimensional computer programs and experimental verification of the performance, at a variety of operating conditions, of two traveling wave tubes with depressed collectors

Experimental and analytical results are compared for two high performance, octave bandwidth TWT's that use depressed collectors (MDC's) to improve the efficiency. The computations were carried out with advanced, multidimensional computer programs that are described here in detail. These programs model the electron beam as a series of either disks or rings of charge and follow their multidimensional trajectories from the RF input of the ideal TWT, through the slow wave structure, through the magnetic refocusing system, to their points of impact in the depressed collector. Traveling wave tube performance, collector efficiency, and collector current distribution were computed and the results compared with measurements for a number of TWT-MDC systems. Power conservation and correct accounting of TWT and collector losses were observed. For the TWT's operating at saturation, very good agreement was obtained between the computed and measured collector efficiencies. For a TWT operating 3 and 6 dB below saturation, excellent agreement between computed and measured collector efficiencies was obtained in some cases but only fair agreement in others. However, deviations can largely be explained by small differences in the computed and actual spent beam energy distributions. The analytical tools used here appear to be sufficiently refined to design efficient collectors for this class of TWT. However, for maximum efficiency, some experimental optimization (e.g., collector voltages and aperture sizes) will most likely be required.

Dayton, J. A., Jr.↗

DOE OSTI2024

Predictive analytics of selections of russet potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato (Solanum tuberosum L.) clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013 to 2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a feedforward neural network classifier (Neural Net), a histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conducted a simulation study using the aims, data-generating mechanisms, estimands, methods, and performance measures (ADEMP) framework, simulating different data-generating scenarios to assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression, thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

60 APPLIED LIFE SCIENCES↗

NASA NTRS2001

Absorbed Dose Determination Using Experimental and Analytical Predictions of X-Ray Spectra

Electron beam welding in a vacuum is a technology that NASA is investigating as a joining technique for manufacture of space structures. This investigation characterizes the x-ray environment due to operation of an in-vacuum electron beam welding tool and provides recommendations for adequate shielding for astronauts performing the in-vacuum electron beam welding. NASA, in a joint venture with the Russian Space Agency, was scheduled to perform a series of welding in space experiments on board the U.S. Space Shuttle. This series of experiments was named the international space welding experiment (ISWE). The hardware associated with the ISWE was leased to NASA by the Paton Welding Institute (PWI) in Ukraine for ground-based welding experiments in preparation for flight. Two ground tests were scheduled, using the ISWE electron beam welding tool, to characterize the radiation exposure to an astronaut during the operation of the ISWE. These radiation exposure tests used thermoluminescence dosimeters (TLD's) shielded with material currently used by astronauts during extravehicular activities to measure the radiation dose. The TLD's were exposed to x-ray radiation generated by operation of the ISWE in-vacuum electron beam welding tool. This investigation was the first known application of TLD's to measure absorbed dose from x rays of energy less than 10 keV. The ISWE hardware was returned to Ukraine before the issue of adequate shielding for the astronauts was completely verified. Therefore, alternate experimental and analytical methods were developed to measure and predict the x-ray spectral and intensity distribution generated by ISWE electron beam impact with metal. These x-ray spectra were normalized to an equivalent ISWE exposure, then used to calculate the absorbed radiation dose to astronauts. These absorbed dose values were compared to TLD measurements obtained during actual operation of the ISWE in-vacuum electron beam welding tool. The calculated absorbed dose values were found to be in agreement with the measured TLD values.

Edwards, D. L.↗

NASA NTRS1983

Analytical prediction of aerothermal environment in a wing-elevon cove

The fluid/thermal environment in the cove between the wing and elevon surfaces was a concern throughout the design and initial operational phases of the space shuttle. Experimenal and analytical investigations provided some understanding of the environmental in the wing-elevon cove. An incompressible finite element analysis of flow through straight parallel walls and curved parallel walls to determine the effects of cove geomtry on the fluid/thermal environment is described. Results from this analysis agree qualitatively with experimental data. The centerline gas temperatures and cold wall heating rates are virtually identical for the two cases indicating that the slight curvature has little effect on the overall thermal environment.

Bey, K. S.↗

DOE OSTI2023

Predictive Analytics for Hydropower Fleet Intelligence

A primary challenge in hydropower industry is the ability to maintain cost-competitiveness, reliability, and security of hydropower assets through evolving power system contexts and aging of the fleet. Maintaining cost-effective and reliable operations under these conditions is expected to require new modernization and maintenance paradigms for changing contexts. Changes in existing practices for O&M will require an understanding of the current state and health of hydropower assets, and the impact of changing paradigms on asset health and reliability. The Hydropower Fleet Intelligence project is developing and evaluating standardized methodologies and analysis tools for data-driven asset reliability and management technologies for hydropower, leading to eventual predictive maintenance planning, repair/replacement decision making, and asset-reliability and cost-optimized operations. A key question is the feasibility of using existing data sets at hydropower facilities to perform assessments of asset reliability. This document uses data from hydropower facilities to assess the potential for using available analytics methods for asset reliability estimates. In addition to reliability assessments, the feasibility of using existing analytics techniques for several other potential applications is discussed. Finally, a case study that a data-driven model is trained to learn nominal operations via vibration data from an asset of a certain plant, and then utilized to identify anomalies on a similar asset from a different plant, highlighting the generic use of proposed Prognostics and Health Management (PHM) approaches.

Yucesan, Yigit↗

NASA NTRS1977

Analytical prediction of the performance and stability of a J85-13 compressor with distorted inlet flow

The parallel compressor concept was studied using a compressor model based on the overall clean-inlet performance map obtained from experimental tests in an altitude chamber using a General Electric J85-13 turbojet engine. The model, which includes a static-pressure balance calculation at compressor discharge, was exercised at conditions corresponding to 10 different screen-induced distortion patterns included in the experimental data base. The spoiled area of these patterns ranged from 30 deg to 180 deg, and the distortion screen density, or the area blocked by the screen wire per unit area of screen, varied from 26 to 69 percent. The study indicates that at the higher corrected speeds, the analytical surge lines obtained are good representations of the corresponding experimental surge lines and are independent of distortion angle or distortion angle or distortion level.

Milner, E. J.↗

DOE OSTI2021

Sensor enabled data-driven predictive analytics for modeling and control with high penetration of DERs in distribution systems

The electric power grid is undergoing a tremendous transformation due to the increasing penetration of renewable energy resources beginning with wind and more recently with the distributed energy resources (DERs) such as solar and battery storage. DERs have dramatically changed the role of the distribution systems in the overall power grid, and they are expected to contribute a significant portion of power generation in the future. If current trends for DERs continue, system operation and control will need to change dramatically for improved grid reliability and resiliency. As renewable resources increase in penetration, new and challenging operational, planning, and design problems are expected to emerge. Some of the key challenges that arise in the planning and operation of the future grid are: 1) Quantifying the impact of high DER penetration in distribution systems on bulk grid behavior over multiple time scales. 2) Identifying whether a particular DER configuration/settings have a large impact on the overall grid behavior. These challenges can be addressed in an offline manner using detailed T&D grid models and they can also be addressed in an online manner using sensor measurements. In particular, the advancement and planned growth in sensor technology in power grid over various voltage levels provide us with a unique opportunity to tackle these challenges from a data analytic perspective without needing detailed T&D grid models. A few questions that naturally arise when addressing the challenges from DERs using sensor data are: 1) How can we use limited sensor measurements to monitor & control voltage stability and small signal stability of the bulk system? 2) How can we ensure that the developed data analytic methods are robust to data availability and quality issues? 3) How can we compute the developed analytics in a scalable manner using streaming measurements? In this project, we addressed the aforementioned challenges arising from DERs and answered the questions raised above on how to effectively use the sensor measurements to enhance the reliability and performance of the electric grid. Thus, the overarching goal of this project is to develop effective reduced/representative system models from data that make the computational complexity sufficiently manageable so as to be useful to simulate, analyze, and even control complex non-linear power systems dynamics with large penetrations of DERs. In order to achieve the objective, the project team established a four-fold technical approach 1) Formulated a combined transmission-distribution co-simulation framework for data generation and validation, 2) Derived reduced/representative models of power systems based on data-driven methods for efficient computation and appropriate representation of system behavior, 3) Developed data driven characterization of power system behavior based on transfer operator theory, machine learning and optimization for model estimation, 4) Incorporated a scalable data management and processing architecture using distributed Kafka streaming applications that coordinate input data streams to the developed data analytics. The key accomplishments of the project are: 1) Development of a scalable multi-timescale T&D co-simulation framework (both for steady state and for dynamic co-simulation) using commercial solvers (PSSE and GridLAB-D). The steady-state T&D co-simulation interface is shared with our industry partner (PJM). 2) A structured reduced order dynamic model of distribution systems that can represent partial motor stalling along with a systematic procedure to derive the model parameters. 3) A PMU based online method to monitor, localize and mitigate fault-induced delayed voltage recovery using DER reactive support and load control in distribution systems. 4) Development of linear operator based robust methodologies for dynamic state estimation, uncertainty quantification, system identification and trajectory prediction for power system dynamics. 5) An adaptive damping control for utilizing wind energy resources to provide oscillation damping and system stability. 6) Implementation of Kafka-based framework for efficient processing of streaming data using Linux-based local virtual environment.

DER integration↗