Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network parameter error”

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 361 records · Page 20

A neural network based 3D/3D image registration quality evaluator for the head-and-neck patient setup in the absence of a ground truth

Purpose: To develop a neural network based registration quality evaluator (RQE) that can identify unsuccessful 3D/3D image registrations for the head-and-neck patient setup in radiotherapy. Methods: A two-layer feed-forward neural network was used as a RQE to classify 3D/3D rigid registration solutions as successful or unsuccessful based on the features of the similarity surface near the point-of-solution. The supervised training and test data sets were generated by rigidly registering daily cone-beam CTs to the treatment planning fan-beam CTs of six patients with head-and-neck tumors. Two different similarity metrics (mutual information and mean-squared intensity difference) and two different types of image content (entire image versus bony landmarks) were used. The best solution for each registration pair was selected from 50 optimizing attempts that differed only by the initial transformation parameters. The distance from each individual solution to the best solution in the normalized parametrical space was compared to a user-defined error threshold to determine whether that solution was successful or not. The supervised training was then used to train the RQE. The performance of the RQE was evaluated using the test data set that consisted of registration results that were not used in training. Results: The RQE constructed using the mutual information had very good performance when tested using the test data sets, yielding the sensitivity, the specificity, the positive predictive value, and the negative predictive value in the ranges of 0.960-1.000, 0.993-1.000, 0.983-1.000, and 0.909-1.000, respectively. Adding a RQE into a conventional 3D/3D image registration system incurs only about 10%-20% increase of the overall processing time. Conclusions: The authors' patient study has demonstrated very good performance of the proposed RQE when used with the mutual information in identifying unsuccessful 3D/3D registrations for daily patient setup. The classifier had very good generality and required only to be trained once for each implementation. When the RQE is incorporated with an automated 3D/3D image registration system, it can improve the robustness of the system.

60 APPLIED LIFE SCIENCES↗

Quantifying Effects of Departure and Flight Time Uncertainty on Urban Air Mobility Operations

Demand capacity balancing is a key mechanism for maintaining safe and efficient Urban Air Mobility (UAM) operations. However, uncertainties such as departure delays and flight time variation may reduce the effectiveness of algorithms used for balancing and detrimentally impact the safety and efficiency of UAM operations. In this paper, the effects of these uncertainties on UAM operations are quantified by modeling a distribution of departure and flight time errors. A route network in the Dallas/Fort Worth metropolitan area was used to simulate traffic demand with and without uncertainty. Simulations were conducted with three main models of uncertainty – first uncertainty in departure time delay resulting in late takeoffs, second with uncertainty in flight times in addition to departure delays, and finally, uncertainty in departure times that cause either late or early takeoffs. Each of these simulations were performed using varied standard deviations to fully understand the effects of uncertainties. Results from these simulations were compared to a baseline simulation using the same parameters, but without any uncertainty. The results suggest that both safety and efficiency are significantly impacted by uncertainty even with relatively low uncertainty introduced. These results work towards quantifying the effects of uncertainty in flight scheduling for UAM. They will also aid in the further development of the demand capacity balancing algorithms for UAM operations and associated air traffic management.

Urban Air Mobility↗

Quantifying the Effects of Departure and Flight Time Uncertainty on Urban Air Mobility Operations

Demand capacity balancing is a key mechanism for maintaining safe and efficient Urban Air Mobility (UAM) operations. However, uncertainties such as departure delays and flight time variation may reduce the effectiveness of algorithms used for balancing and detrimentally impact the safety and efficiency of UAM operations. In this paper, the effects of these uncertainties on UAM operations are quantified by modeling a distribution of departure and flight time errors. A route network in the Dallas/Fort Worth metropolitan area was used to simulate traffic demand with and without uncertainty. Simulations were conducted with three main models of uncertainty – first uncertainty in departure time delay resulting in late takeoffs, second with uncertainty in flight times in addition to departure delays, and finally, uncertainty in departure times that cause either late or early takeoffs. Each of these simulations were performed using varied standard deviations to fully understand the effects of uncertainties. Results from these simulations were compared to a baseline simulation using the same parameters, but without any uncertainty. The results suggest that both safety and efficiency are significantly impacted by uncertainty even with relatively low uncertainty introduced. These results work towards quantifying the effects of uncertainty in flight scheduling for UAM. They will also aid in the further development of the demand capacity balancing algorithms for UAM operations and associated air traffic management.

Urban Air Mobility↗

Evaluating pulse-shaping capabilities of next-generation pulsed power architectures

This project evaluated the pulse shaping capabilities of next-generation pulsed power (NGPP) architectures. NGPP architectures share several common attributes including multiple independent pulse-generation lines, a radial water-insulated impedance transformer, and a central vacuum insulated load region. A multi-module circuit model was developed, incorporating independent pulse-generation lines and a 2-D transmission line mesh of the radial impedance transformer to assess the effects of azimuthal asymmetry in pulse-shaped experiments. Circuit model simulations demonstrated that NGPP architectures are able to produce the the desired current pulse shapes for exemplar NGPP experiments. Additionally, the project explored automated methods for experiment design, including derivative -ree optimization and machine learning. Pulse-shaped experiments require designers to determine machine parameters that reliably produce the desired current pulse at the load, a process that typically relies on expert knowledge and iterative adjustments using the Z circuit model. Given the increased complexity of NGPP systems, this manual approach may be impractical. While the evaluated methods do not eliminate the need for manual iteration, they can reduce the time required for experiment design. Derivative-free optimization automates much of the trial-and-error process, providing a close starting point for manual adjustments or making small modifications to near-final designs. Meanwhile, deep neural network methods can generate a good qualitative match to the desired current pulse in under one second without requiring circuit model simulations.

42 ENGINEERING↗

Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters

Remote sensing of global ocean color is a valuable tool for understanding the ecology and biogeochemistry of the worlds oceans, and provides critical input to our knowledge of the global carbon cycle and the impacts of climate change. Ocean polarized reflectance contains information about the constituents of the upper ocean euphotic zone, such as colored dissolved organic matter (CDOM), sediments, phytoplankton, and pollutants. In order to retrieve the information on these constituents, remote sensing algorithms typically rely on radiative transfer models to interpret water color or remote-sensing reflectance; however, this can be resource-prohibitive for operational use due to the extensive CPU time involved in radiative transfer solutions. In this work, we report a fast model based on machine learning techniques, called Neural Network Reflectance Prediction Model (NNRPM), which can be used to predict ocean bidirectional polarized reflectance given inherent optical properties of ocean waters. This supervised model is trained using a large volume of data derived from radiative transfer simulations for coupled atmosphere and ocean systems using the successive order of scattering technique (SOS-CAOS). The performance of the model is validated against another large independent test dataset generated from SOS-CAOS. The model is able to predict both polarized and unpolarized reflectances with an absolute error (AE) less than 0.004 for 99% of test cases. We have also shown that the degree of linear polarization (DoLP) for unpolarized incident light can be predicted with an AE less than 0.002 for 99% of test cases. In general, the simulation time of SOS-CAOS depends on optical depth, and required accuracy. When comparing the average speeds of the NNRPM against the SOS-CAOS model for the same parameters, we see that the NNRPM is able to predict the Ocean BRDF 6000 times faster than SOS-CAOS. Both ultraviolet and visible wavelengths are included in the model to help differentiate between dissolved organic material and chlorophyll in the study of the open ocean and the coastal zone. The incorporation of this model into the retrieval algorithm will make the retrieval process more efficient, and thus applicable for operational use with global satellite observations.

radiative transfer↗

Machine learning methods for probabilistic locked-mode predictors in tokamak plasmas

A rotating tokamak plasma can interact resonantly with the external helical magnetic perturbations, also known as error fields. This can lead to locking and then to disruptions. We leverage machine learning (ML) methods to predict the locking events. We use a coupled third-order nonlinear ordinary differential equation model to represent the interaction of the magnetic perturbation and the plasma rotation with the error field. This model is sufficient to describe qualitatively the locking and unlocking bifurcations. Here, we explore using ML algorithms with the simulation data and experimental data, focusing on the methods that can be used with sparse datasets. These methods lead to the possibility of the avoidance of locking in real-time operations. We describe the operational space in terms of two control parameters: the magnitude of the error field and the rotation frequency associated with the momentum source that maintains the plasma rotation. The outcomes are quan- tified by order parameters that completely characterize the state, whether locked or unlocked. We use unsupervised ML methods to classify locked/unlocked states and note the usefulness of a certain normalization of the order parameters. Three supervised ML classifiers are used in suite to estimate the probability of locking in the region of control parameter space with hysteresis, i.e., the set of control parameters for which both locked and unlocked states can exist. The results show that a neural network gives the best estimate of the locking probability. An analogy of the present locking model with the van der Waals equation of state is also provided.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Predictive and Neural Predictive Control of Uncertain Systems

Accomplishments and future work are:(1) Stability analysis: the work completed includes characterization of stability of receding horizon-based MPC in the setting of LQ paradigm. The current work-in-progress includes analyzing local as well as global stability of the closed-loop system under various nonlinearities; for example, actuator nonlinearities; sensor nonlinearities, and other plant nonlinearities. Actuator nonlinearities include three major types of nonlineaxities: saturation, dead-zone, and (0, 00) sector. (2) Robustness analysis: It is shown that receding horizon parameters such as input and output horizon lengths have direct effect on the robustness of the system. (3) Code development: A matlab code has been developed which can simulate various MPC formulations. The current effort is to generalize the code to include ability to handle all plant types and all MPC types. (4) Improved predictor: It is shown that MPC design using better predictors that can minimize prediction errors. It is shown analytically and numerically that Smith predictor can provide closed-loop stability under GPC operation for plants with dead times where standard optimal predictor fails. (5) Neural network predictors: When neural network is used as predictor it can be shown that neural network predicts the plant output within some finite error bound under certain conditions. Our preliminary study shows that with proper choice of update laws and network architectures such bound can be obtained. However, much work needs to be done to obtain a similar result in general case.

Kelkar, Atul G.↗

Understanding Relationships Between Satellite, Model, and Ground-Based Surface Temperature Characterizations From Overcast to Clear Conditions in Support of Satellite Remote Sensing of Clouds and Radiation

Accurate and consistent global estimates of cloud coverage and their properties are fundamental to long-term Earth radiation budget (ERB) monitoring efforts like the Clouds and the Earth’s Radiant Energy System (CERES) project. Cloud detection algorithms often apply thresholding approaches to identify where clouds occur by comparing satellite-measured radiances with those that are expected under cloud-free conditions. In addition, once a cloud is detected, the derivation of cloud optical and microphysical properties also requires knowledge of the background radiances below the cloud. In the infrared, knowledge of the surface emissivity and the expected skin temperature under both cloudy and cloud-free conditions is needed. These traits are generally well known over the oceans. Over land, however, comparisons between satellite-derived land surface temperature (LST) with that characterized in numerical weather analyses reveal large differences in many parts of the world, often exceeding 5 K, which can lead to significant satellite cloud detection and cloud property retrieval errors. Furthermore, clouds have a dramatic influence on the LST, and therefore characterization of that model parameter also depends on the capability of the model to accurately resolve clouds. Thus, the LST characterized in models is, at times, a poor approximation for what would otherwise be observed, thereby impeding accurate satellite cloud retrievals. As a result, we seek to develop a more robust method for estimating the LST required for satellite cloud characterizations. This effort is accomplished through a combination of surface emission/air temperature relationship studies in all-sky conditions using ground measurement stations, along with deep neural network (DNN) estimates of expected LST under overcast and cloud-free conditions. We demonstrate that substituting DNN-predicted LST for that generated by numerical models can mitigate model-inherent diurnal dependencies and reduce overall bias and uncertainty relative to satellite/ground observations by 0.5–4 K and 0.5–2 K, respectively. It is expected that this work will lead to improved satellite cloud retrievals that enhance ERB monitoring efforts.

B Scarino↗

Extension of the PINN diffusion model to k-eigenvalue problems

This paper extends our recent work on the Physics-Informed Neural Networks (PINN) approach for the fixed source diffusion models and applies it to the diffusion theory based k-eigenvalue problems. To make the PINN equitable for the eigenvalue problems, we introduce a novel integral regularization term to the loss function in the framework, and allow the direct inference of the principal eigenvalue and the associated eigenfunction. The regularization term enforces a pre-defined value on the integration of the model predictions, and this value can be directly related to a physical property of the system. We also introduce an additional learnable parameter to approximate the principal eigenvalue. As a proof of principle, we solve the one-group two-dimensional k-eigenvalue neutron diffusion equation in this work. We then provide two numerical examples to demonstrate the applicability of the PINN approach. In each example, we solve the k-eigenvalue diffusion equation in a multi-region configuration constrained with a set of Robin boundary conditions for generality. We use a FEM solution based on the power-iteration method to verify the results of the PINN solution. The results showed relative percentage error in the predicted eigenvalue of about 0.77% and about 1.2% for example 1 and example 2, respectively. The mean absolute error in the predicted flux for example 1 is ∼ 0.002 and for example 2 is ∼ 0.0024. These results indicate some preliminary successes of the PINN application to k-eigenvalue problems. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Demonstration of precise estimation of polar motion parameters with the global positioning system: Initial results

Data from the Global Positioning System (GPS) were used to determine precise polar motion estimates. Conservatively calculated formal errors of the GPS least squares solution are approx. 10 cm. The GPS estimates agree with independently determined polar motion values from very long baseline interferometry (VLBI) at the 5 cm level. The data were obtained from a partial constellation of GPS satellites and from a sparse worldwide distribution of ground stations. The accuracy of the GPS estimates should continue to improve as more satellites and ground receivers become operational, and eventually a near real time GPS capability should be available. Because the GPS data are obtained and processed independently from the large radio antennas at the Deep Space Network (DSN), GPS estimation could provide very precise measurements of Earth orientation for calibration of deep space tracking data and could significantly relieve the ever growing burden on the DSN radio telescopes to provide Earth platform calibrations.

Lichten, S. M.↗

ADVANCED WAVEFORM SIMULATION FOR SEISMIC MONITORING EVENTS

This quarter, we have focused on several tasks: (1) Building a high-quality catalog of earthquake source parameters for the Middle East and East Asia. In East Asia, we computed source parameters using the CAP method for a set of events studied by Herrman et al., (MRR, 2006) using a complete waveform technique. Results indicated excellent agreement with the moment magnitudes in the range 3.5 -5.5. Below magnitude 3.5 the scatter increases. For events with more than 2-3 observations at different azimuths, we found good agreement of focal mechanisms. Depths were generally consistent, although differences of up to 10 km were found. These results suggest that CAP modeling provides estimates of source parameters at least as reliable as complete waveform modeling techniques. However, East Asia and the Yellow Sea Korean Paraplatform (YSKP) region studied are relatively laterally homogeneous and may not benefit from the CAP method’s flexibility to shift waveform segments to account for path-dependent model errors. A more challenging region to study is the Middle East where strong variations in sedimentary basin, crustal thickness and crustal and mantle seismic velocities greatly impact regional wave propagation. We applied the CAP method to a set of events in and around Iran and found good agreement between estimated focal mechanisms and those reported by the Global Centroid Moment Tensor (CMT) catalog. We found a possible bias in the moment magnitudes that may be due to the thick low-velocity crust in the Iranian Plateau. (2) Testing Methods on a Lifetime Regional Data Set. In particular, the recent 2/21/08 Nevada Event and Aftershock Sequence occurred in the middle of USArray, producing over a thousand records per event. The tectonic setting is quite similar to Central Iran and thus provides an excellent testbed for CAP+ at ranges out to 10°, including extensive observations of crustal thinning and thickening and various Pnl complexities. Broadband modeling in 1D, 2D, and 3D will be presented. (3) Shallow Crustal Structure and Sparse Network Source Inversions for Southern California. We conducted a detailed test of a recently developed technique, CAPloc, in recovering source parameters including location and depth based on tomographic maps. We tested two-station solutions against 160 well determined events which worked well except for paths crossing deep basins and along mountain ridges.

58 GEOSCIENCES↗

Mathematical modelling of flow distribution in the human cardiovascular system

The paper presents a detailed model of the entire human cardiovascular system which aims to study the changes in flow distribution caused by external stimuli, changes in internal parameters, or other factors. The arterial-venous network is represented by 325 interconnected elastic segments. The mathematical description of each segment is based on equations of hydrodynamics and those of stress/strain relationships in elastic materials. Appropriate input functions provide for the pumping of blood by the heart through the system. The analysis employs the finite-element technique which can accommodate any prescribed boundary conditions. Values of model parameters are from available data on physical and rheological properties of blood and blood vessels. As a representative example, simulation results on changes in flow distribution with changes in the elastic properties of blood vessels are discussed. They indicate that the errors in the calculated overall flow rates are not significant even in the extreme case of arteries and veins behaving as rigid tubes.

NASA Center JSC↗

Embedding physics domain knowledge into a Bayesian network enables layer-by-layer process innovation for photovoltaics

Process optimization of photovoltaic devices is a time-intensive, trial-and-error endeavor, which lacks full transparency of the underlying physics and relies on user-imposed constraints that may or may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach for gallium arsenide (GaAs) solar cells that identifies the root cause(s) of underperformance with layer-by-layer resolution and reveals alternative optimal process windows beyond traditional black-box optimization. Our Bayesian network approach links a key GaAs process variable (growth temperature) to material descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency). For this purpose, we combine a Bayesian inference framework with a neural network surrogate device-physics model that is 100× faster than numerical solvers. With the trained surrogate model and only a small number of experimental samples, our approach reduces significantly the time-consuming intervention and characterization required by the experimentalist. As a demonstration of our method, in only five metal organic chemical vapor depositions, we identify a superior growth temperature profile for the window, bulk, and back surface field layer of a GaAs solar cell, without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above traditional grid search methods.

14 SOLAR ENERGY↗

Monitoring solid metal structures with a nervous system embedded with ultrasonic 3D printing

Active and regular monitoring of structural components is a critical safety precaution, particularly as it concerns infrastructure, aerospace, industry, and many other applications. Solutions for effective structural health monitoring need to be able to probe surface and bulk properties using durable and low-power engineering. Towards these ends it is possible to build smarter, highly networked, and secure materials in order to enable remote real-time material sensing with a lesser-known form of 3D printing, ultrasonic consolidation (UC). This approach harnesses sound waves to weld metal layers in a low temperature process that does not damage sensors and electronics as they are embedded into a solid metal structure. This makes UC perfectly suited for designing solid metal parts with active embedded sensing components. However, the process parameters, material influences and mechanical factors that result in high-quality UC metal components are difficult to control or are loosely understood. The use of trial-and-error optimization during fabrication represents the chief hurdle between its current state of use and its potential to transform rapid prototyping and manufacturing of high-impact technologies (e.g., metal smart structures, wearable sensors, lab-on-a-chip, etc.). In this paper we will describe how embedded sensors may be used for in situ process monitoring and optimization. We will also discuss efforts towards standardizing UC welding for similar and dissimilar metal bonding and for embedding active sensors that can be used to create smart structures that will enable long-term structural health monitoring and other high impact applications.

Suter, Jonathan D.↗

Predicting thunderstorm evolution using ground-based lightning detection networks

Lightning measurements acquired principally by a ground-based network of magnetic direction finders are used to diagnose and predict the existence, temporal evolution, and decay of thunderstorms over a wide range of space and time scales extending over four orders of magnitude. The non-linear growth and decay of thunderstorms and their accompanying cloud-to-ground lightning activity is described by the three parameter logistic growth model. The growth rate is shown to be a function of the storm size and duration, and the limiting value of the total lightning activity is related to the available energy in the environment. A new technique is described for removing systematic bearing errors from direction finder data where radar echoes are used to constrain site error correction and optimization (best point estimate) algorithms. A nearest neighbor pattern recognition algorithm is employed to cluster the discrete lightning discharges into storm cells and the advantages and limitations of different clustering strategies for storm identification and tracking are examined.

Goodman, Steven J.↗

Precision X-band Doppler and ranging navigation for current and future Mars exploration missions

This paper describes a navigation error covariance analysis of two scenarios derived from the Mars Observer mission and the planned Mars Environmental SURvey (MESUR) Pathfinder mission, respectively. The analysis was performed to establish the potential navigational performance of the X-band tracking system in NASA's Deep Space Network, and to evaluate the sensitivity of the predicted performance to variations in the quantity of data acquired, the ground system error modeling assumptions, and data reduction schemes. The simulated data arcs used in the analysis are representative of the actual data arcs that will be used to predict the aim point for the Mars orbit insertion maneuver, in the case of Mars Observer, and the interplanetary trajectory aim point corresponding to the target Mars landing site in the case of MESUR Pathfinder. The results indicate that with a suitable sequential data reduction scheme and accurate calibrations of instrumentation, transmission media, and platform model parameters, navigation accuracies of 5 to 15 km (1 sigma) can be achieved, equivalent to 15 to 40 nrad in geocentric angle uncertainty.

Estefan, Jeffrey A.↗

Predictive model using artificial neural network to design phase change material-based ocean thermal energy harvesting systems for powering uncrewed underwater vehicles

Uncrewed Underwater Vehicles (UUVs) are a major beneficiary of the phase change material (PCM)-based ocean thermal energy harvesting technology for their mission needs. However, this technology relies on different parameters and energy conversion steps that could be critical to the general energy generation efficiency. Sea trials showed that the design performed lower than their laboratory design specifications. This underperformance results from different factors, mainly the UUV’s trajectory, travel time, underwater ocean currents, temperature fluctuations, and biofouling on the heat exchanger due to long term underwater operations. Therefore, there exists a need to continuously monitor the ambient energy harvesting system and predict system performance, for mission planning purposes. Two major parameters influencing the energy harvesting system include the final pressure inside the hydraulic energy storage vessel or accumulator, and the electrical load value. Here, this work focuses on the hydraulic to electric energy conversion system. Therefore, a combination of numerical model and experimental testing is used to develop a predictive model using artificial neural network using MATLAB. After validation with experimental testing, 1000 data samples obtained from the numerical model are used to train the ANN. Compared to the experimental results, the developed ANN model can predict in less than a second the designed benchtop system’s total efficiency with less than 15 percent maximum error range. This predictive model development represents a cost-effective way for optimization and a computational energy efficient mode aboard UUVs for mission planning for deployed UUVs using PCM-based ocean thermal energy harvesting technology.

30 DIRECT ENERGY CONVERSION↗

Very High Resolution, Altitude-Corrected, TMPA-Based Monthly Satellite Precipitation Product Over the CONUS

The Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA) product provided over 17 years of gridded precipitation datasets. However, the accuracy and spatial resolution of TMPA limits the applicability in hydrometeorological applications. We present a dataset that enhances the accuracy and spatial resolution of the TMPA monthly product (3B43). We resample the TMPA data to a 1 km grid and apply a correction function derived from the Parameter-elevation Regressions on Independent Slopes Model (PRISM) to reduce bias in the data. We confirm a linear relationship between bias and elevation above 1,500 meters where TMPA underestimates measured precipitation, providing a proof-of-concept of how simple linear scaling can be used to augment existing satellite datasets. The result of the correction is the High-Resolution Altitude-Corrected Precipitation product (HRAC-Precip) for the CONUS. Using 9,200 precipitation stations from the Global Historical Climatology Network (GHCN), we compare the accuracy of TMPA 3B43 versus the new HRAC-Precip product. The results show an improvement of the mean absolute error of 12.98% on average.

Hossein Hashemi↗