Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Prediction Accuracy”

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 757 records · Page 42
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

The Solar Influencer Next Door: Predicting Low-Income Solar Referrals and Leads

Increasing the adoption of solar among low-to-moderate income (LMI) households remains an important policy goal because of its promise to simultaneously reduce energy burden and support the just distribution of benefits of renewable energy. However, scaling LMI solar remains challenging due to affordability and access issues. Most existing LMI adoption has occurred under public-funded programs, highlighting the importance of increasing the cost-effectiveness of these programs at scale. We develop a new household-level data set on LMI solar lead acquisition, referrals, and adoption to understand the processes through which LMI solar uptake has occurred in California. Then, we develop models to predict two sub-mechanisms in the solar adoption process: whether an otherwise qualified lead becomes "lost" i.e. non-responsive to outreach and, for existing clients, whether they refer solar to others. For the program analyzed, participants received their solar system at no cost, which deemphasizes economic drivers of solar adoption and could differ from other program experiences. Both models substantially improved the accuracy of prediction relative to a baseline. Overall, we find that peer effects and solar economics are important to predicting referrals, and household demographic factors in lead loss prediction. Finally, we find that referrals are both the highest quality and largest source of LMI solar leads, providing a promising mechanism to expand LMI programs further.

customer acquisition costs↗
DOE OSTI2021

AI-Improved Resolution Projections of Population Characteristics and Imperviousness Can Improve Resolution and Accuracy of Urban Flood Predictions

Focal Area: (2) Predictive modeling through the use of AI techniques and AI-derived model components. Specifically, we call for the use of deep generative models from ML for providing high-resolution projections of impervious surface area, as well as neural network solvers for fast approximation of urban hydrodynamics to provide greatly enhanced forecasts of future urban flood dynamics.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1985

Effect of accuracy of wind power prediction on power system operator

This research project proposed a modified unit commitment that schedules connection and disconnection of generating units in response to load. A modified generation control is also proposed that controls steam units under automatic generation control, fast responding diesels, gas turbines and hydro units under a feedforward control, and wind turbine array output under a closed loop array control. This modified generation control and unit commitment require prediction of trend wind power variation one hour ahead and the prediction of error in this trend wind power prediction one half hour ahead. An improved meter for predicting trend wind speed variation is developed. Methods for accurately simulating the wind array power from a limited number of wind speed prediction records was developed. Finally, two methods for predicting the error in the trend wind power prediction were developed. This research provides a foundation for testing and evaluating the modified unit commitment and generation control that was developed to maintain operating reliability at a greatly reduced overall production cost for utilities with wind generation capacity.

Schlueter, R. A.↗
NASA NTRS1990

Prediction of the aerodynamic and thermal environment in turbines

A numerical study of the steady, viscous flow prediction capabilities of the three-dimensional turbine stage code ROTOR3 is presented. Computations were performed with RAI3DC, a cascade version of ROTOR3 capable of being run in a planar or annular mode. Computed results are compared with experimental data obtained for Hodson's cascade, Kopper's cascade, and United Technologies Research Center's Large Scale Rotating Rig (LSRR) first-stage stator. The code's predictive capability is assessed in terms of the accuracy of predicted airfoil loadings, performance (including secondary flows in the LSRR case), boundary layers, and heat transfer. A grid refinement study was conducted in the LSRR case in an effort to more accurately model the boundary layers on the airfoil and endwall surfaces. The effects of the inlet total pressure profile in secondary flow prediction were also assessed.

Griffin, Lisa W.↗
NASA NTRS1998

The Role of Computational Fluid Dynamics at Marshall Space Flight Center

The Marshall Space Flight Center (MSFC) is the Center of Excellence for Space Propulsion Technology within NASA. One of MSFC's goals is to lower the cost of access to space. MSFC's Fluid Dynamics Division, a part of the Structures and Dynamics Lab, assists in accomplishing this goal. This division is divided into two branches: experimental and analytical, whose work is complimentary and integrated. In the analysis branch, the emphasis is to apply, rather than develop computational fluid dynamics (CFD), to reduce the cost of design and development of: (1) pump and turbine feedlines and feed manifolds; (2) all primary and secondary flow paths in pumps; (3) all primary and secondary flow paths in turbines; (4) combustion chambers; (5) rocket engine nozzles and plumes; and (6) launch vehicles ascent. The broad range of applications imposes unique constraints on the software. The use of CFD in evaluating rocket engine hardware, specifically, is of value due to several reasons: (1) Rocket engine hardware is extremely expensive to build and test; (2) high engineering and development cost is due to limited production; (3) the cost of one engine test is greater than the average yearly hardware and software cost; (4) CFD represents a relatively small investment relative to the impact it has on the engine development; and (5) computing costs are continuously decreasing. In terms of accuracy the predictable error is more useful than the inconsistent accuracy. The achievable accuracy varies from application to application. The lack of accuracy is often caused by improper analyses: such as improperly applied or located boundary conditions, or attempting steady analysis of unsteady flows. This report is in viewgraph format.

Garcia, Roberto↗
DOE OSTI2024

SSTDR and FDR Detection of Un-Energized and Energized Cable Anomalies Including Thermal Degradation Using Machine Learning

Historically, cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, continued use of these cables must shift to a performance-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. A variety of cable tests are available and are commonly applied during outages when the cables can be taken out of service. Frequency domain reflectometry (FDR) is one of these test methods that is being more broadly accepted and used because it not only detects anomalies along the cable with a low-voltage signal that does not stress the cable insulation, but the technique also locates the anomalies. This supports follow-up local inspection and local repair or partial replacement of a damaged cable segment. Currently, FDR testing is only applied to cables that are taken out of service since the test instrument would be damaged by operational voltages. A related technology that has found some acceptance in the aircraft and rail industry is spread spectrum time domain reflectometry (SSTDR). This technology has been implemented with a custom commercial instrument by LiveWire Innovation that is designed to operate on live cables up to 1000 volts and with a bandwidth of 48 MHz. Initial evaluation by the Pacific Northwest National Laboratory (PNNL) of the Live Wire system indicated that a broader bandwidth (BW) SSTDR may be better for many kinds of flaws. This led PNNL to develop an SSTDR laboratory instrument suitable for tests up to 500 MHz bandwidth. Testing on energized cables is also desirable for online monitoring systems so an inductive clamshell coupler was developed that allows energized cables to be tested up to at least 5 kV and likely higher voltage levels. Dielectric spectroscopy and tan delta testing plus various laboratory destructive tests were included in this data acquisition campaign directed to feed a machine learning (ML) study. With these kinds of developments, online energized cable tests may be possible with industrial adoption of such hardware advances but it will be completely impractical to have highly skilled data analysts continually examine these complex signals for indications of damage or compromised conditions. If online testing is to be implemented in new test hardware, it must be accompanied by software that can interpret the signals and alert plant operators of changing or degraded conditions. The thermally aged, shielded cable investigated here was separately treated for ML analysis. Visual analysis of electrical data showed generally increasing peaks where the cable entered and exited the oven. These peaks were not exactly aligned with expected locations, but these differences were attributed to velocity of propagation calibration errors. Only supervised ML was applied to the thermally aged data as this data was only available shortly before the committed publication date of this report. The supervised ML was structured to divide the 0 to 70-day responses as ‘normal’ from 0 to 35 days or ‘anomalous’ from 36 to 70 days, based on cable tensile elongation at break (EAB) insulation characterization. Using 80% of the data for training and 20% for testing, the supervised ML predicted normal versus anomalous was 70% accurate. Important conclusions include: • Accuracy to predict the presence of cable damage is improved from the 2023 effort by more training data. Weighted accuracies for comparisons among the instruments ranged from 67 to 89 % for unsupervised ML and 71 to 99% for supervised ML. • Based on the synthetic data tests, the unsupervised models are more generalizable to unseen anomalies. The Multi-Layer Perceptron classifier (MLP) model reported as high as 99.7% accuracy on the test data, but this dropped to 58.3% when tested on the synthetic data. In contrast, the unsupervised Pointwise model only achieved 89.7% accuracy on the experimental data but reported 78.3% accuracy on the synthetic data. • The best anomaly indicators are higher frequency (400 MHz BW) FDR data. Other tests may be interesting but for this study, this was the best predicter.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1999

Navigating Mars Global Surveyor Through the Martian Atmosphere: Aerobraking 2

The Mars Global Surveyor (MGS) spacecraft was successfully inserted into an elliptical orbit around Mars on 9/12/97, 01:53:49 UTC. This orbit was near polar (inclination=93.26 deg) with an orbital period of 44.993 hours and apoapsis and periapsis altitudes of 54,025.9 km and 262.9 km respectively. After 201 orbits and 196 days after Mars orbit insertion, the first phase of aerobraking (AB), called AB 1, has ended; after the AB 1 termination maneuver, the orbital period was 11.64 hours with apoapsis and periapsis altitudes of 17,870.3 and 170.7 Ian respectively. Thereafter, MGS was in a science phasing orbit (SPO) and acquired data from the science instruments from 3/28/98 to 9/22/98 (orbits 202 through 572). The second phase of aerobraking (AB2) began on 9/23/98 with the first descent into the atmosphere on P574 and ended with the aerobraking termination maneuver (ABX) on 2/4/99 on A 1284. Just prior to ABX, the apoapsis and periapsis altitudes were 456.5 km and 116.7 km respectively with an orbit period of 1.973 hours, a local mean solar time (LMST) at the descending node of 2 hours, 3.6 minutes and an inclination of 92.9 degrees. AB was responsible for circularization of the MGS orbit. However, two additional orbital conditions had to be satisfied simultaneously. These were a) complete AB2 when the LMST at the descending node was close to 2:00 am and b) the inclination was at 93.0 degrees. This paper describes the navigation of MGS throughout AB2; a companion paper describes the strategy and plan for aerobraking. Navigation challenges involved: a) the estimation of an atmospheric density model for every drag pass or periapsis-passage by analyzing doppler tracking data, b) the generation of a short-term, that is over one to several orbits, accurate atmospheric density predictions, c) maintaining the spacecraft's orbit within upper and lower bounds of atmospheric density or dynamic pressure during each periapsis-passage, and d) the prediction of accurate periapsis-passage times (Tp) over one to fifteen orbits. The density estimation and analysis procedure, evaluation of almost 700 atmospheric densities throughout AB2, the variation and accuracy of density predictions, the Tp prediction accuracy and how effectively we terminated AB2 are the basis of this paper and shall be presented in detail. A summary overview of AB2 is given.

Esposito, P.↗
DOE OSTI2024

Invariant Features for Accurate Predictions of Quantum Chemical UV-vis Spectra of Organic Molecules

Including invariance of global properties of a phys-ical system as an intrinsic feature in graph neural networks (GNNs) enhances the model's robustness and generalizability and reduces the amount of training data required to obtain a desired accuracy for predictions of these properties. Existing open source GNN libraries construct invariant features only for specific GNN architectures. This precludes the generalization of invariant features to arbitrary message passing neural network (MPNN) layers which, in turn, precludes the use of these libraries for new, user-specified predictive tasks. To address this limitation, we implement invariant MPNNs into the flexible and scalable HydraGNN architecture. HydraGNN enables a seamless switch between various MPNNs in a unified layer sequence and allows for a fair comparison between the predictive performance of different MPNNs. We trained this enhanced HydraGNN archi-tecture on the ultraviolet-visible (UV-vis) spectrum of GDB-9 molecules, a feature that describes the molecule's electronic exci-tation modes, computed with time-dependent density functional tight binding (TD-DFTB) and available open source through the GDB-9-Ex dataset. We assess the robustness (i.e., accuracy and generalizability) of the predictions obtained using different invariant MPNNs with respect to different values of the full width at half maximum (FWHM) for the Gaussian smearing of the theoretical peaks. Our numerical results show that incorporating invariance in the HydraGNN architecture significantly enhances both accuracy and generalizability in predicting UV-vis spectra of organic molecules.

Baker, Justin↗
DOE OSTI2022

Trajectory prediction dimensionality reduction for low-cost connected automated vehicle systems

Here, to facilitate low-cost connected automated vehicle (CAV) system development, this study proposes two interpretable dimensionality reduction techniques in vehicle trajectory prediction, i.e., the piecewise Taylor series approximation (PTA) and the piecewise Fourier series approximation (PFA), to lower computation complexity, reduce device investment, and decrease computation energy consumption. Two benchmarks are developed, the long short-term memory (LSTM)-based model without dimensionality reduction and the LSTM-based model with encoder-decoder (a widely used dimensionality reduction technique). Results show that the four predictions have similar accuracy, and the training time (proportional to computation energy consumption) of models with dimensionality reduction techniques is greatly reduced. The reduction is even more significant when PTA/PFA is used. Sensitivity analysis advises PFA/PTA parameter selections to reduce computation complexity without significant loss of prediction accuracy. Further, the robustness of the LSTM PTA/PFA is proven by the investigation of data noises.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Integrating Predictions for Improving Defect Classification Accuracy in NDT-based Assessment of Concrete - 20229

There is an increasing need to create predictive models for defect classification in concrete using the output of non-destructive testing (NDT) techniques. Recent advancement of machine-learning algorithms has offered several techniques for developing classification models for different types of data sets. However, the performance of these algorithms is very uncertain, mainly when applied to small and noisy datasets. For example, when human access is limited (e.g., nuclear facility), robot-based NDT is preferred. But compared to manual tests with humans present on site, the data sets are small, and more noise can exist. Therefore, it is imperative to develop new approaches to ensure a consistently high classification accuracy for inadequate data sets. This study explores the classification performance on NDT dataset using classifiers from different machine-learning algorithms, namely k-Nearest Neighbor (kNN), Decision Tree, Naive Bayes, Logistic Regression, and Support Vector Machine (SVM). The authors further integrated the predictions from these classifiers using proposed methods. The integration strategy combines the output of the classifiers based on two different measures, accuracy, and performance (ACC and PERF), using equations such as sum, average, and square-root-of-sums-of-squares (SRSS). Our results reveal varying classification accuracies across individual classifiers with different misclassifications across the test data set. The integration strategy provided significant improvement in the classification accuracy compared to the individual classifiers. Furthermore, the results indicate minimal variation across the integration methods as compared to the variation across the individual classifiers. To conclude, prediction integration offers a unique approach for combining the output of multiple classifiers to create redundancies with the potential of achieving high classification performance and improved reliability in predictive models for defect detection in concrete. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

Protein-ligand binding affinity prediction using multi-instance learning with docking structures

Recent advances in 3D structure-based deep learning approaches demonstrate improved accuracy in predicting protein-ligand binding affinity in drug discovery. These methods complement physics-based computational modeling such as molecular docking for virtual high-throughput screening. Despite recent advances and improved predictive performance, most methods in this category primarily rely on utilizing co-crystal complex structures and experimentally measured binding affinities as both input and output data for model training. Nevertheless, co-crystal complex structures are not readily available and the inaccurate predicted structures from molecular docking can degrade the accuracy of the machine learning methods. We introduce a novel structure-based inference method utilizing multiple molecular docking poses for each complex entity. Our proposed method employs multi-instance learning with an attention network to predict binding affinity from a collection of docking poses. We validate our method using multiple datasets, including PDBbind and compounds targeting the main protease of SARS-CoV-2. The results demonstrate that our method leveraging docking poses is competitive with other state-of-the-art inference models that depend on co-crystal structures. This method offers binding affinity prediction without requiring co-crystal structures, thereby increasing its applicability to protein targets lacking such data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Multiclass classification experiments

We seek a multiclass classifier that can satisfy the following requirements. 1. Predict among at least three classes. 2. Handle a moderately large number of correlated predictors. 3. Handle mixed categorical and continuous predictors. 4. Handle missing values (in some way). 5. Be trained with about n = 1,000 responses, and 6. Quantify prediction uncertainty. Based on 5. above, it is assumed that accuracy of prediction is paramount (relative to, say, runtime). All methods considered in this document take on the order of minutes (most take seconds) on a 2.8 GHz Quad-Core Intel Core i7 processor with 16GB RAM. Secondly, quantification of uncertainty is assumed to be a secondary task, since, with this small data size, resampling methods (i.e. bootstrapping) are possible. Further studies should quantify the feasibility and accuracy of resampling methods, and/or other methods, for quantifying uncertainty. R was used for all software.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1983

Accuracy of measurement of star images on a pixel array

Algorithms are developed for predicting the accuracy with which the brightness of a star can be determined from its image on a digital detector array, as a function of the brightness of the background. The assumption is made that a known profile is being fitted by least squares. The two profiles used correspond to ST images and to ground-based observations. The first result is an approximate rule of thumb for equivalent noise area. More rigorous results are then given in tabular form. The size of the pixels, relative to the image size, is taken into account. Astronometric accuracy is also discussed briefly; the error, relative to image size, is very similar to the photometric error relative to brightness.

King, I. R.↗
DOE OSTI2020

A CALPHAD-informed approach to modeling constituent redistribution in Zr-based metallic fuels using BISON

Here, a CALPHAD-informed (Computer Coupling of Phase Diagrams and Thermochemistry) constituent redistribution model was developed for Zr-based metallic fuels and incorporated into the BISON fuel performance code. Three uncertain model parameters associated with β and γ phase kinetics were calibrated using integral test data from U-Zr fuel elements irradiated in Experimental Breeder Reactor II. The calibrated constituent redistribution model was shown to predict the behavior of U-Zr fuels with excellent accuracy. Model predictions for U-Pu-Zr fuels were physically reasonable but less accurate. Reduction of uncertainties in the ternary phase transition temperatures and collection of kinetic data for the ζ phase are expected to improve the model’s ternary predictions. Finally, the new model was coupled to existing thermomechanics models in BISON to simulate irradiation of an entire U-Zr fuel element, demonstrating its ability to accurately predict the behavior of U-Zr fuels with realistic geometries and mesh resolutions at the engineering scale.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
NASA NTRS1991

The in-flight calibration of the Hubble Space Telescope attitude sensors

A detailed review of the in-flight calibration of the Hubble Space Telescope attitude sensors is presented. The review, which covers the period from the April 24, 1990, launch of the spacecraft until the time of this writing (June 1991), describes the calibrations required and accuracies achieved for the four principal attitude sensing systems on the spacecraft: the magnetometers, the fixed head star trackers, the gyroscopes, and the fine guidance sensors (FGS's). In contrast to the other three sensor groups, the Hubble Telecope's FGS's are unique in the precision and performance levels being attempted; spacecraft control and astrometric research at the near-milliarcsecond level are the ultimate goals. FGS calibration accuracies at the 20-milliarcsecond level have already been achieved, and plans for new data acquisitions and reductions that should substantially improve these results are in progress. A summary of the basic attributes of each of the four sensor groups with respect to its usage as an attitude measuring system is presented, followed by a discussion of the calibration items of interest for that group. The calibration items are as follows: for the magnetometers, the corrections for the spacecraft's static and time-varying magnetic fields; for the fixed-head star trackers, their relative alignments and use in performing onboard attitude updates; for the gyroscopes, their scale factors, alignments, and drift rate biases; and for the FGS's, their magnifications, optical distortions, and alignments. The discussion covers the procedures used for each calibration, as well as the order of the calibrations within the general flow of orbital verification activities. It also includes a synopsis of current plans for the eventual calibration of the FGS's to achieve their near-milliarcsecond design accuracy. The conclusions include a table indicating the current and predicted ultimate accuracies for each of the calibration items.

Welter, Gary L.↗
DOE OSTI2022

Enhanced physics-constrained deep neural networks for modeling vanadium redox flow battery

Numerical simulation has become indispensable in advancing cost-effective process optimization and control of flow batteries. We propose an enhanced version of the physics-constrained deep neural network (PCDNN) approach to provide high-accuracy voltage predictions in the vanadium redox flow batteries (VRFBs). The purpose of the PCDNN approach is to enforce the physics-based zero-dimensional (0D) VRFB model in a neural network to assure model generalization for various battery operation conditions. However, limited by the simplifications of the 0D model, the PCDNN cannot capture sharp voltage changes in the extreme SOC regions. To improve the accuracy of voltage prediction at extreme ranges, we introduce a second (enhanced) DNN to mitigate the prediction errors carried from the 0D model itself and call the resulting approach enhanced PCDNN (ePCDNN). By comparing with experimental data, we demonstrate that the ePCDNN approach can accurately capture the voltage response throughout the charge–discharge cycle, including the tail region of the voltage discharge curve. The loss function for training the ePCDNN is designed to be flexible by adjusting the weights of the physics-constrained DNN and the enhanced DNN. In conclusion, this allows the ePCDNN framework to be transferable to battery systems with variable physical model fidelity.

25 ENERGY STORAGE↗
DOE OSTI2021

Prediction of protein assemblies, the next frontier: The CASP14-CAPRI experiment

Here we present the results for CAPRI Round 50, the fourth joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of twelve targets, including six dimers, three trimers, and three higher-order oligomers. Four of these were easy targets, for which good structural templates were available either for the full assembly, or for the main interfaces (of the higher-order oligomers). Eight were difficult targets for which only distantly related templates were found for the individual subunits. Twenty-five CAPRI groups including eight automatic servers submitted ~1250 models per target. Twenty groups including six servers participated in the CAPRI scoring challenge submitted ~190 models per target. The accuracy of the predicted models was evaluated using the classical CAPRI criteria. The prediction performance was measured by a weighted scoring scheme that takes into account the number of models of acceptable quality or higher submitted by each group as part of their five top-ranking models. Compared to the previous CASP-CAPRI challenge, top performing groups submitted such models for a larger fraction (70–75%) of the targets in this Round, but fewer of these models were of high accuracy. Scorer groups achieved stronger performance with more groups submitting correct models for 70–80% of the targets or achieving high accuracy predictions. Servers performed less well in general, except for the MDOCKPP and LZERD servers, who performed on par with human groups. In addition to these results, major advances in methodology are discussed, providing an informative overview of where the prediction of protein assemblies currently stands.

protein complexes↗