SEARCH · Engineering Papers
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.
A prototype Optical Plume Anomaly Detection (OPAD) system is now installed on the space shuttle main engine (SSME) Technology Test Bed (TTB) at MSFC. The OPAD system requirements dictate the need for fast, efficient data processing techniques. To address this need of the OPAD system, a study was conducted into how artificial neural networks could be used to assist in the analysis of plume spectral data.
The Advanced Energetic Pair Telescope gamma-ray polarimeter uses a time projection chamber for measuring pair production events and is expected to generate a raw instrument data rate four orders of magnitude greater than is transmittable with typical satellite data communications. GammaNet, a convolutional neural network, proposes to solve this problem by performing event classification on-board for pair production and background events, reducing the data rate to a level that can be accommodated by typical satellite communication systems. In order to train GammaNet, a set of 1.1 × 10(exp 6) pair production events and 10(exp 6) background events were simulated for the Advanced Energetic Pair Telescope using the Geant4 Monte Carlo code. An additional set of 10(exp 6) pair production and 10 background events were simulated to test GammaNet’s capability for background discrimination. With optimization, GammaNet has achieved the proposed background rejection requirements for Galactic Cosmic Ray proton events. Given the best case assumption for downlink speeds, signal sensitivity for pair production ranged between 1.1 ± 0.5% to 69 ± 2% for 5 and 250 MeV incident gamma rays. This range became 0.1 ± 0.1% to 17 ± 2% for the worst case scenario of downlink speeds. The application of a feature visualization algorithm to GammaNet demonstrated decreased response to electronic noise and events exiting or entering the frame and increased response to parallel tracks that are close in proximity. GammaNet has been successfully implemented and shows promising results.
Transcribing voice communications in NASA’s launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch control center will help the machine analyze information and accelerate knowledge generation.
Space science information systems involve accessing vast data bases. There is a need for an automatic process by which properties of the whole data set can be assimilated and presented to the user. Where data are in the form of spectrograms, phenomena can be detected by pattern recognition techniques. Presented are the first results obtained by applying unsupervised Artificial Neural Networks (ANN's) to the classification of magnetospheric wave spectra. The networks used here were a simple unsupervised Hamming network run on a PC and a more sophisticated CALM network run on a Sparc workstation. The ANN's were compared in their geophysical data recognition performance. CALM networks offer such qualities as fast learning, superiority in generalizing, the ability to continuously adapt to changes in the pattern set, and the possibility to modularize the network to allow the inter-relation between phenomena and data sets. This work is the first step toward an information system interface being developed at Sussex, the Whole Information System Expert (WISE). Phenomena in the data are automatically identified and provided to the user in the form of a data occurrence morphology, the Whole Information System Data Occurrence Morphology (WISDOM), along with relationships to other parameters and phenomena.
Improved estimates of near-surface air temperature and air humidity are critical to the development of more accurate turbulent surface heat fluxes over the ocean. Recent progress in retrieving these parameters has been made through the application of artificial neural networks (ANN) and the use of multi-sensor passive microwave observations. Details are provided on the development of an improved retrieval algorithm that applies the nonlinear statistical ANN methodology to a set of observations from the Advanced Microwave Scanning Radiometer (AMSR-E) and the Advanced Microwave Sounding Unit (AMSU-A) that are currently available from the NASA AQUA satellite platform. Statistical inversion techniques require an adequate training dataset to properly capture embedded physical relationships. The development of multiple training datasets containing only in-situ observations, only synthetic observations produced using the Community Radiative Transfer Model (CRTM), or a mixture of each is discussed. An intercomparison of results using each training dataset is provided to highlight the relative advantages and disadvantages of each methodology. Particular emphasis will be placed on the development of retrievals in cloudy versus clear-sky conditions. Near-surface air temperature and humidity retrievals using the multi-sensor ANN algorithms are compared to previous linear and non-linear retrieval schemes.
AE flaw growth activity was monitored in aluminum-lithium weld specimens from the onset of tensile loading to failure. Data on actual ultimate strengths together with AE data from the beginning of loading up to 25 percent of the expected ultimate strength were used to train a backpropagation neural network to predict ultimate strengths. Architecturally, the fully interconnected network consisted of an input layer for the AE amplitude data, a hidden layer to accommodate failure mechanism mapping, and an output layer for ultimate strength prediction. The trained network was then applied to the prediction of ultimate strengths in the remaining six specimens. The worst case prediction error was found to be +2.6 percent.
We here propose a segmentation algorithm of texture image for a computer vision system on a space robot. An improved adaptive resonance theory (ART2) for analog input patterns is adapted to classify the image based on a set of texture image features extracted by a fast spatial gray level dependence method (SGLDM). The nonlinear thresholding functions in input layer of the neural network have been constructed by two parts: firstly, to reduce the effects of image noises on the features, a set of sigmoid functions is chosen depending on the types of the feature; secondly, to enhance the contrast of the features, we adopt fuzzy mapping functions. The cluster number in output layer can be increased by an autogrowing mechanism constantly when a new pattern happens. Experimental results and original or segmented pictures are shown, including the comparison between this approach and K-means algorithm. The system written in C language is performed on a SUN-4/330 sparc-station with an image board IT-150 and a CCD camera.
Acoustic Emission (AE) flaw growth activity was monitored in aluminum-lithium weld specimens from the onset tensile loading to failure. Data on actual ultimate strengths together with AE data from the beginning of loading up to 25 percent of the expected ultimate strength were used to train a backpropagation neural network to predict ultimate strengths. Architecturally, the fully interconnected network consisted of an input layer for the AE amplitude data, a hidden layer to accommodate failure mechanism mapping, and an output layer for ultimate strength prediction. The trained network was the applied to the prediction of ultimate strengths in the remaining six specimens. The worst case prediction error was found to be +2.6 percent.
The fundamental problem in the evolution of matter is to understand how structure-function relationships are formed and increase in complexity from the molecular level all the way to a genetic system. We have created a system where structure-function relationships arise naturally and without the need of ad hoc function assignments to given structures. The idea was inspired by neural networks, where the structure of the net embodies specific computational properties. In this system networks interact with other networks to create connections between the inputs of one net and the outputs of another. The newly created net then recomputes its own synaptic weights, based on anti-hebbian rules. As a result some connections may be cut, and multiple nets can emerge as products of a 'reaction'. The idea is to study emergent reaction behaviors, based on simple rules that constitute a pseudophysics of the system. These simple rules are parameterized to produce behaviors that emulate chemical reactions. We find that these simple rules show a gradual increase in the size and complexity of molecules. We have been building a virtual artificial chemistry laboratory for discovering interesting reactions and for testing further ideas on the evolution of primitive molecules. Some of these ideas include the potential effect of membranes and selective diffusion according to molecular size.
The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. The 'pressure difference rule,' which states that the maximum lift condition corresponds to a certain pressure difference between the peak suction pressure and the pressure at the trailing edge of the element, was applied and verified with experimental observations for this configuration. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural nets were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 44% compared with traditional gradient-based optimization procedures for multiple optimization runs.
Accurate real-time pose estimation of spacecraft or object in space is a key capability necessary for on orbit spacecraft servicing and assembly tasks. Pose estimation of objects in space is more challenging than for objects on Earth due to space images containing widely varying illumination conditions, high contrast, and poor resolution in addition to power and mass constraints. In this paper, a convolutional neural network is leveraged to uniquely determine the translation and rotation of an object of interest relative to the camera. The main idea of using CNN model is to assist object tracker used in on space assembly tasks where only feature based method is always not sufficient. The simulation framework designed for assembly task is used to generate dataset for training the modified CNN models and, then results of different models are compared with measure of how accurately models are predicting the pose. Unlike many current approaches for spacecraft or object in space pose estimation, the model does not rely on hand-crafted object-specific features which makes this model more robust and easier to apply to other types of spacecraft. It is shown that the model performs comparable to the current feature-selection methods and can therefore be used in conjunction with them to provide more reliable estimates.
A supervised deep learning approach is coupled with heuristic convergence criteria to construct a classification model for detecting the completion (convergence) of computational fluid dynamics (CFD) simulations. Heuristic convergence criteria alone are not always sufficient and more complex decisions are often left to a human analyst. The proposed approach leverages heuristic convergence criteria as well as two deep neural network (DNN) models, one binary and one multi-class, to improve the efficiency and consistency of convergence classification across a wide range of flight regimes. The DNN models presented are each trained on a subset of ascent aerodynamic CFD simulations for NASA’s Space Launch System and were produced using NASA’s unstructured Navier-Stokes solver FUN3D. Individual solutions are analyzed intermittently and are classified as sufficiently converged, further iterations required, or switch from steady Reynolds Averaged Navier-Stokes (RANS) to unsteady RANS CFD based on the iterative histories of four aerodynamic coefficients. The implemented classification model is shown to produce solutions that closely correlate to solutions produced by a human analyst. This work lays groundwork for expanding the capabilities of DNNs for automating and improving more of the CFD process.
This paper presents an approach to interpretive modeling of LP based control allocation in intelligent flight control. The emphasis is placed on a nonlinear interpretation of the LP allocation process as a static map to support analytical study of the resulting closed loop system, albeit in approximate form. The approach makes use of a bi-layer neural network to capture the essential functioning of the LP allocation process. It is further shown via Lyapunov based analysis that under certain relatively mild conditions the resulting closed loop system is stable. Some preliminary conclusions from a study at Ames are stated and directions for further research are given at the conclusion of the paper.
Remote sensing atmospheric correction methods have primarily focused on imagery over land. However, accurate correction over water is important for monitoring and research of aquatic environments. More research in this area is ongoing, though one of the biggest challenges is enough quality data to develop and validate correction methods. This is especially true for neural network (NN) -based models which have shown promise in this area given enough quality data. To address this deficiency of data, we are leveraging a synthetic dataset produced by a model called SWIPE that uses radiative transfer modeling to simulate the atmospheric effects on water-leaving (WL) reflectance to estimate top-of-atmosphere (TOA) reflectance. This allows us to produce almost unlimited pairs of WL reflectance and corresponding TOA reflectance for model training across a variety of atmospheric conditions. We use two approaches for our atmospheric correction model. One uses a conditional variational autoencoder (VAE) to estimate a single WL reflectance value from a single TOA reflectance value. The second is based on a UNET architecture and estimates an array of WL reflectance values from an array of TOA reflectance values. The goal of the second method is to capture atmospheric effects that occur spatially between values within the array as compared to the first method.
Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.
Acousto-ultrasonics (AU) is a nondestructive evaluation (NDE) technique that was devised for the testing of various types of composite materials. A study has been done to determine how effectively the AU technique may be applied to metal-matrix composites (MMCs). The authors use the results and data obtained from that study and apply neural networks to them, particularly in the assessment of mechanical property variations of a specimen from AU measurements. It is assumed that there is no information concerning the important features of the AU signal which relate to the mechanical properties of the specimen. Minimally processed AU measurements are used while relying on the network's ability to extract the significant features of the signal.
We present a classification of an AVIRIS spectral image of the Lunar Crater Volcanic Field (LCVF). Geologic mapping from such data is made possible by distinctive mineral signatures: absorption features and the shape of the spectral continuum. The subtle spectral shape differences between some of the geological units in this scene along with the high dimensionality of the spectral presents a challenging pattern recognition task. We found an artificial neural network powerful in separating 13 geological units based on the full spectral resolution. The LCVF, in northern Nye County, Nevada, was the primary focus of the NASA-sponsored Geologic Remote Sensing Field Experiment in the summer of 1989. It consists of over 100 square miles of Quaternary basaltic pyroclastic and flow deposits. These deposits lie atop ignimbrites and silicic lava flows of Tertiary age and in turn are overlain by Quaternary alluvial and playa deposits. This AVIRIS image was collected on September 29, 1989 at 11:44 at 11:44 PDT. The 256-by-256 pixel subsection in this study contains oxidized basaltic cinder deposits, the southern half of the Lunar Lake playa, and outcrops of the Rhyollite of Big Sand Spring Valley. Vegetation in LCVF is sparse, but locally abundant within washes and near springs.
The turbulent latent and sensible heat fluxes are necessary to study heat budget of the upper ocean or initialize ocean general circulation models. In order to retrieve the latent heat flux from satellite observations authors mostly use a bulk approximation of the flux whose parameters are derived from different instrument. In this paper, an approach based on artificial neural networks is proposed and compared to the bulk method on a global data set and 3 local data sets.