Search NASA⌕ Search

SEARCH · Search NASA

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.

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

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2020

Machine Learning-Based Predictive Analytics for Aircraft Engine Conceptual Design

Big data and artificial intelligence/machine learning are transforming the global business environment. Data is now the most valuable asset for enterprises in every industry. Companies are using data-driven insights for competitive advantage. With that, the adoption of machine learning-based data analytics is rapidly taking hold across various industries, producing autonomous systems that support human decision-making. This work explored the application of machine learning to aircraft engine conceptual design. Supervised machine-learning algorithms for regression and classification were employed to study patterns in an existing, open-source database of production and research turbofan engines, and resulting in predictive analytics for use in predicting performance of new turbofan designs. Specifically, the author developed machine learning-based analytics to predict cruise thrust specific fuel consumption (TSFC) and core sizes of high-efficiency turbofan engines, using engine design parameters as the input. The predictive analytics were trained and deployed in Keras, an open-source neural networks application program interface (API) written in Python, with Google’s TensorFlow (an open source library for numerical computation) serving as the backend engine. The promising results of the predictive analytics show that machine-learning techniques merit further exploration for application in aircraft engine conceptual design.

deep-learning↗
DOE OSTI2021

Risk-informed Predictive Analytics To Achieve Cost-effective Condition-based Monitoring And Maintenance Strategy

The research involves developing risk-informed predictive analytic capabilities to achieve condition-based monitoring and maintenance strategies to reduce overall maintenance costs. The research utilizes data (real-time data, periodic data, and institutional knowledge) related to a particular plant asset from a specific nuclear plant site to develop risk-informed predictive analytic algorithms. The developed algorithms and codes are used to optimize the maintenance strategy and estimate/forecast generation costs based on the state of health of the plant asset. Developed codes specifically include 1. Parameter estimation code based on Bayesian inference 2. Statistical data analysis code 3. Feature engineering code 4. Health classifier code 5. Diagnosis code 6. Prognosis code 7. Hazard code 8. Generation risk code 9. Economic code

Agarwal, Vivek↗
DOE OSTI2024

Enabling Efficient Surveillance, Control, and Automation of Geothermal Operations with Advanced Predictive Analytics

Automation and control of geothermal energy production and operations require reliable and efficient predictive tools. While physics-based simulation offers a comprehensive tool for predicting energy production performance in geothermal systems, predicting the behavior of geothermal reservoirs involves complex multi-physics processes with coupling effects, highly uncertain input parameters and subsurface descriptions. Moreover, building, running, and integrating simulation models into standard model calibration and optimization workflows entail significant technical and computational efforts. An emerging alternative to physics-based simulation is data-driven predictive analytics models that have gained popularity in energy industry. In this report, we develop novel predictive models for integration into real-time fault diagnosis and model predictive control algorithms to improve the efficiency of energy production operations in geothermal reservoirs. The report includes two major research Thrust Areas, that is, the surface power plant and the subsurface reservoir.

15 GEOTHERMAL ENERGY↗
NASA NTRS2019

Predictive Analytics for ATD-2

This presentation describes on-going work to leverage high quality data and predictive analytics to improve understanding and performance of IADS system.

ATD-2↗
NASA NTRS1982

An analytical prediction of pilot ratings utilizing human pilot model

In order to analytically predict pilot ratings, an evaluation method of a manual control system which consists of an aircraft and a human pilot, is proposed and examined. The method is constructed upon the assumptions that the control mission determines the critical frequency the pilot should bring to his focus, and that the degree of closed-loop stability and the human compensation necessary to attain the stability determine the human subjective evaluation of the system. As a result, a simple evaluation chart is introduced. The chart enables prediction of the subjective evaluation, if the controlled element dynamics and the mission are given. The chart is in good accord with almost all of the existing results of pilot ratings. This method has the following advantages: (1) simplicity, in a sense that the method needs to evaluate only two typical controlled element parameters, namely, the gain slope and the phase at the critical control frequency; (2) applicability to unstable controlled elements; (3) predictability of controllability limits of manual control; (4) possibility of estimating human compensatory dynamics.

Tanaka, K.↗
NASA NTRS1985

Analytical prediction of labyrinth-seal-flow-induced arotor excitation forces

An analytical method to calculate the rotor excitation forces arising from labyrinth seals is presented. The objective is to model the gas flow through the seal clearance passages and cavities when the rotor is positioned eccentricly relative to the stator center. The seal flow model used in the analysis yields solutions which validate the experimentally observed influence of seal parameters on seal forces reported in the literature. The analytically predicted seal pressure distributions and forces were compared with published experimental results.

Rajakumar, C.↗
DOE OSTI2025

A predictive analytical model of electrical transport in multi-principal-element alloys

A predictive analytical model is presented for the electrical conductivity of multi-principal-element alloys (MPEAs), including those containing aluminum, transition metals, and refractory metals. Given that the lattice parameter of the Wigner-Seitz cell of an MPEA is similarly variable to a bulk metallic glass, it is postulated that electron scattering can be approximated by a series of two-level systems. Here, the resulting reduced-order model enabled an accurate determination of electrical resistivity and electron thermal conductivity based on the scattering of electrons in a two-level system across a Bloch-potential-based virtual crystal approximation. Model results are compared to experimental four-point probe electrical resistivity measurements between 300 K and 700 K for Al 0.3 CoCrCuFeNi, CoCrFeMnNi, (CoCrFeMnNi) 0.98 W 0.02 , (CoCrFeMnNi) 0.95 W 0.05 , and Nb 4 Ta 4 V 3 Ti, for model validation.

Analytical model↗
NASA NTRS1970

Analytical prediction of reverse buckling pressure for thin shells

Analytical technique is developed for prediction of reverse buckling in thin curved shells. Test data indicate technique predicts actual reverse buckling pressure within 10 percent, and should be useful for analytical prediction of reversed condition failure for problems such as explosive decomposition through vacuum failure.

Martindale, D. L.↗
NASA NTRS1982

Comparison of analytical predictions of longitudinal short period pilot-induced oscillations with results from a simulation study of the space shuttle orbiter

An analytical analysis of conditions producing pilot induced oscillations (PIO's) was made for the space shuttle orbiter in a landing approach configuration for the task of milling the elevation angle of the line of sight to a target vehicle. The analysis yielded a value of PIO frequency and a value for the amount of total system time delay (pilot + control system) that can be tolerated before instability results. Calculations were performed showing the effect of varying the range to the target and of varying the handling qualities of the orbiter vehicle. Analytical predictions were compared with simulation results obtained using a visual motion simulator.

Riley, D. R.↗
DOE OSTI2022

A graph signal processing‐based multiple model Kalman filter ( GSP‐MMKF ) tool for predictive analytics: An air separation unit process application

Abstract The industrial Air Separations Unit (ASU) is a complicated and tightly operated process. The use of dynamic process analytics is also a key element of safe and economic operation of these processes, with increasing focus on predictive analytics to take preemptive actions. With the availability of real‐time data from hundreds of sensors, the data analysis process should also consider the topology of the data, as seen in sensor networks. In this paper, a novel tool is presented that considers the complex connectivity patterns in the sensor network and uses local adaptive disturbance estimations to predict global network‐scale trends. The paper introduces the emerging field of Graph Signal Processing (GSP) and presents a rigorous derivation of the tool starting from the extraction of the sensor‐network (in a graph theoretical sense) from the data. This network, which is in the form of a matrix, is then used to derive a Kalman‐filter type of state‐space model driven by input disturbances. Multiple disturbance models (e.g., step, ramp, periodic) are included to allow the model to have different kinds of disturbance propagation. Each graph node (representing the sensors used) dynamically adapts to the most recent detected disturbance individually. These estimated disturbances are propagated to the global network using the graph. Modifications to ensure stability are also discussed. The fidelity of the tool is tested on certain downtime events and the paper concludes by discussing the advantages of the method and planned future improvements.

Ghosh, Sambit↗
NASA NTRS1971

Motion effects on an IFR hovering task: Analytical predictions and experimental results

An analytical pilot model incorporating the effects of motion cues and display scanning and sampling is tested by comparing predictions against experimental results on a moving base simulator. The simulated task is that of precision hovering of a VTOL having varying amounts of rate damping, and using separated instrument displays. Motion cue effects are investigated by running the experiment under fixed and moving base conditions, the latter in two modes; full motion, and angular motion only. Display scanning behavior is measured on some of the runs. The results of the program show that performance is best with angular motion only, most probably because a g-vector tilt cue is available to the pilot in this motion condition. This provides an attitude indication even when not visually fixating the attitude display. Vestibular threshold effects are also present in the results because of the display scaling used to permit hovering position control within the motion simulator limits; no washouts are used in the simulator drive signals. The IFR nature of the task results in large decrements in pilot opinion and performance relative to VFR conditions because of the scanning workload. Measurements of scanning behavior are sensitive to motion conditions and show more attention to attitude control under fixed base conditions.

Ringland, R. F.↗
NASA NTRS1981

Analytical prediction of aerospace vehicle vibration environments

Considerable attention has been given recently to the formulation and validation of analytical models for the prediction of aerospace vehicle vibration response to acoustic and fluctuating pressures. This paper summarizes the development of such analytical models for two applications, (1) structural vibrations of the Space Shuttle orbiter vehicle due to broadband rocket noise and aerodynamic boundary layer turbulence, and (2) structural vibrations of general aviation aircraft due to discrete frequency propeller and reciprocating engine exhaust noise. In both cases, the spatial exterior excitations are convected pressure fields which are described on the basis of measured cross spectra (coherence and phase) information. Structural modal data are obtained from analytical predictions, and structural responses to appropriate excitation fields are calculated. The results are compared with test data, and the strengths and weaknesses of the analytical models are assessed.

Wilby, J. F.↗
NASA NTRS2012

First-and Second-Order Displacement Transfer Functions for Structural Shape Calculations Using Analytically Predicted Surface Strains

New first- and second-order displacement transfer functions have been developed for deformed shape calculations of nonuniform cross-sectional beam structures such as aircraft wings. The displacement transfer functions are expressed explicitly in terms of beam geometrical parameters and surface strains (uniaxial bending strains) obtained at equally spaced strain stations along the surface of the beam structure. By inputting the measured or analytically calculated surface strains into the displacement transfer functions, one could calculate local slopes, deflections, and cross-sectional twist angles of the nonuniform beam structure for mapping the overall structural deformed shapes for visual display. The accuracy of deformed shape calculations by the first- and second-order displacement transfer functions are determined by comparing these values to the analytically predicted values obtained from finite element analyses. This comparison shows that the new displacement transfer functions could quite accurately calculate the deformed shapes of tapered cantilever tubular beams with different tapered angles. The accuracy of the present displacement transfer functions also are compared to those of the previously developed displacement transfer functions.

Ko, William L.↗
NASA NTRS2014

Shielding Characteristics Using an Ultrasonic Configurable Fan Artificial Noise Source to Generate Modes - Experimental Measurements and Analytical Predictions

An Ultrasonic Configurable Fan Artificial Noise Source (UCFANS) was designed, built, and tested in support of the NASA Langley Research Center's 14x22 wind tunnel test of the Hybrid Wing Body (HWB) full 3-D 5.8% scale model. The UCFANS is a 5.8% rapid prototype scale model of a high-bypass turbofan engine that can generate the tonal signature of proposed engines using artificial sources (no flow). The purpose of the program was to provide an estimate of the acoustic shielding benefits possible from mounting an engine on the upper surface of a wing; a flat plate model was used as the shielding surface. Simple analytical simulations were used to preview the radiation patterns - Fresnel knife-edge diffraction was coupled with a dense phased array of point sources to compute shielded and unshielded sound pressure distributions for potential test geometries and excitation modes. Contour plots of sound pressure levels, and integrated power levels, from nacelle alone and shielded configurations for both the experimental measurements and the analytical predictions are presented in this paper.

Artifical Noise↗