Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Architecture Identification”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

High-bandwidth image-based predictive laser stabilization via optimized Fourier filters

Controlling the delivery of kHz-class pulsed lasers is of interest in a variety of industrial and scientific applications, from next-generation laser-plasma acceleration to laser-based x-ray emission and high-precision manufacturing. The transverse position of the laser pulse train on the application target is often subject to fluctuations by external drivers (e.g., room cooling and heating systems, motorized optics stages and mounts, vacuum systems, chillers, and/or ground vibrations). For typical situations where the disturbance spectrum exhibits discrete peaks on top of a broad-bandwidth lower-frequency background, traditional PID (proportional-integral-derivative) controllers may struggle, since as a general rule PID controllers can be used to suppress vibrations up to only about 5%–10% of the sampling frequency. Here, a predictive feed-forward algorithm is presented that significantly enhances the stabilization bandwidth in such laser systems (up to the Nyquist limit at half the sampling frequency) by online identification and filtering of one or a few discrete frequencies using optimized Fourier filters. Furthermore, the system architecture demonstrated here uses off-the-shelf CMOS cameras and piezo-electric actuated mirrors connected to a standard PC to process the alignment images and implement the algorithm. To avoid high-end, high-cost components, a machine-learning-based model of the piezo mirror’s dynamics was integrated into the system, which enables high-precision positioning by compensating for hysteresis and other hardware-induced effects. A successful demonstration of the method was performed on a 1 kHz laser pulse train, where externally-induced vibrations of up to 400 Hz were attenuated by a factor of five, far exceeding what could be done with a standard PID scheme.

Natal, Joseph↗
DOE OSTI2021

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1990

Neuromorphic learning of continuous-valued mappings from noise-corrupted data. Application to real-time adaptive control

The ability of feed-forward neural network architectures to learn continuous valued mappings in the presence of noise was demonstrated in relation to parameter identification and real-time adaptive control applications. An error function was introduced to help optimize parameter values such as number of training iterations, observation time, sampling rate, and scaling of the control signal. The learning performance depended essentially on the degree of embodiment of the control law in the training data set and on the degree of uniformity of the probability distribution function of the data that are presented to the net during sequence. When a control law was corrupted by noise, the fluctuations of the training data biased the probability distribution function of the training data sequence. Only if the noise contamination is minimized and the degree of embodiment of the control law is maximized, can a neural net develop a good representation of the mapping and be used as a neurocontroller. A multilayer net was trained with back-error-propagation to control a cart-pole system for linear and nonlinear control laws in the presence of data processing noise and measurement noise. The neurocontroller exhibited noise-filtering properties and was found to operate more smoothly than the teacher in the presence of measurement noise.

Troudet, Terry↗
NASA NTRS2004

Selection of a Data Acquisition and Controls System Communications and Software Architecture for Johnson Space Center's Space Environment Simulation Laboratory Thermal and Vacuum Test Facilities

Upgrade of data acquisition and controls systems software at Johnson Space Center's Space Environment Simulation Laboratory (SESL) involved the definition, evaluation and selection of a system communication architecture and software components. A brief discussion of the background of the SESL and its data acquisition and controls systems provides a context for discussion of the requirements for each selection. Further framework is provided as upgrades to these systems accomplished in the 1990s and in 2003 are compared to demonstrate the role that technological advances have had in their improvement. Both of the selections were similar in their three phases; 1) definition of requirements, 2) identification of candidate products and their evaluation and testing and 3) selection by comparison of requirement fulfillment. The candidates for the communication architecture selection embraced several different methodologies which are explained and contrasted. Requirements for this selection are presented and the selection process is described. Several candidates for the software component of the data acquisition and controls system are identified, requirements for evaluation and selection are presented, and the evaluation process is described.

Jordan, Eric A.↗
NASA NTRS2016

Considerations for the Next Revision of NASA's Space Telecommunications Radio System Architecture

Development of NASA's Software Defined Radio architecture, the Space Telecommunication Radio System (STRS), was initiated in 2004 with a goal of reducing the cost, risk and schedule when implementing Software Defined Radios (SDR) for National Aeronautics and Space Administration (NASA) space missions. Since STRS was first flown in 2012 on three Software Defined Radios on the Space Communication and Navigation (SCaN) Testbed, only minor changes have been made to the architecture. Multiple entities have since implemented the architecture and provided significant feedback for consideration for the next revision of the standard. The focus for the first set of updates to the architecture is items that enhance application portability. Items that require modifications to existing applications before migrating to the updated architecture will only be considered if there is compelling reasons to make the change. The significant suggestions that were further evaluated for consideration include expanding and clarifying the timing Application Programming Interfaces (APIs), improving handle name and identification (ID) definitions and use, and multiple items related to implementation of STRS Devices. In addition to ideas suggested while implementing STRS, SDR technology has evolved significantly and this impact to the architecture needs to be considered. These include incorporating cognitive concepts - learning from past decisions and making new decisions that the radio can act upon. SDRs are also being developed that do not contain a General Purpose Module - which is currently required for the platform to be STRS compliant. The purpose of this paper is to discuss the comments received, provide a summary of the evaluation considerations, and examine planned dispositions.

transmitters receivers↗
NASA NTRS2016

Considerations for the Next Revision of STRS

Development of NASAs Software Defined Radio architecture, the Space Telecommunication Radio System (STRS), was initiated in 2004 with a goal of reducing the cost, risk and schedule when implementing Software Defined Radios (SDR) for NASA space missions. Since STRS was first flown in 2012 on three Software Defined Radios on the Space Communication and Navigation (SCaN) Testbed, only minor changes have been made to the architecture. Multiple entities have since implemented the architecture and have provided significant feedback for consideration for the next revision of the standard. The focus for the first set of updates to the architecture is items that enhance application portability. Items that require modifications to existing applications before migrating to the updated architecture will only be considered if there is compelling reasons to make the change. The significant suggestions that were further evaluated for consideration include expanding and clarifying the timing Application Programming Interfaces (APIs), improving handle name and identification (ID) definitions and use, and multiple items related to implementation of STRS Devices. In addition to ideas suggested while implementing STRS, SDR technology has evolved significantly and this impact to the architecture needs to be considered. These include incorporating cognitive concepts - learning from past decisions and making new decisions that the radio can act upon. SDRs are also being developed that do not contain a General Purpose Module which is currently required for the platform to be STRS compliant. The purpose of this paper is to discuss the comments received, provide a summary of the evaluation considerations, and examine planned dispositions

waveforms↗
DOE OSTI2025

Scalable Hybrid Large-Scale dc-ac Grid Analysis Methods (Phase II)

The goals of the project included the identification and evaluation of a voltage source converter multiterminal high-voltage direct current (VSC-MTdc) system architecture suitable for a high amount of power transfer through long transmission lines.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1989

Neuromorphic learning of continuous-valued mappings in the presence of noise: Application to real-time adaptive control

The ability of feed-forward neural net architectures to learn continuous-valued mappings in the presence of noise is demonstrated in relation to parameter identification and real-time adaptive control applications. Factors and parameters influencing the learning performance of such nets in the presence of noise are identified. Their effects are discussed through a computer simulation of the Back-Error-Propagation algorithm by taking the example of the cart-pole system controlled by a nonlinear control law. Adequate sampling of the state space is found to be essential for canceling the effect of the statistical fluctuations and allowing learning to take place.

Troudet, Terry↗
NASA NTRS2009

Development of a Relay Performance Web Tool for the Mars Network

Modern Mars surface missions rely upon orbiting spacecraft to relay communications to and from Earth systems. An important component of this multi-mission relay process is the collection of relay performance statistics supporting strategic trend analysis and tactical anomaly identification and tracking.

data accountability↗
NASA NTRS2012

A Miniature Laser Desorption/Ionization Time-of-Flight Mass Spectrometer for in Situ Analysis of Mars Surface Composition and Identification of Hazard in Advance of Future Manned Exploration

Future landed missions to Mars will be guided by two strategic directions: (1) sample return to Earth, for comprehensive compositional analyses, as recommended by the 2011 NRC Planetary Decadal Survey; and (2) preparation for human exploration in the 2030s and beyond, as laid out by US space policy. The resultant mission architecture will likely require high-fidelity in situ chemical/organic sample analyses within an extremely constrained resource envelope. Both science goals (e.g., MEPAG Goal 1, return sample selection, etc.) as well as identification of any potential toxic and biological hazards to humans, must be addressed. Over the past several years of instrument development, we have found that the adaptable, compact, and highly capable technique of laser desorption/ionization time-of-flight mass spectrometry (LD-TOF-MS) has significant potential to contribute substantially to these dual objectives. This concept thus addresses Challenge Area 1: instrumentation and Investigation Approaches.

Getty, S. A.↗
DOE OSTI2022

Identifying Transient Candidates in the Dark Energy Survey Using Convolutional Neural Networks

The ability to discover new transient candidates via image differencing without direct human intervention is an important task in observational astronomy. For these kind of image classification problems, machine learning techniques such as Convolutional Neural Networks (CNNs) have shown remarkable success. In this work, we present the results of an automated transient candidate identification on images with CNNs for an extant data set from the Dark Energy Survey Supernova program, whose main focus was on using Type Ia supernovae for cosmology. By performing an architecture search of CNNs, we identify networks that efficiently select non-artifacts (e.g., supernovae, variable stars, AGN, etc.) from artifacts (image defects, mis-subtractions, etc.), achieving the efficiency of previous work performed with random Forests, without the need to expend any effort in feature identification. The CNNs also help us identify a subset of mislabeled images. Performing a relabeling of the images in this subset, the resulting classification with CNNs is significantly better than previous results, lowering the false positive rate by 27% at a fixed missed detection rate of 0.05.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1990

Flight elements: Fault detection and fault management

Fault management for an intelligent computational system must be developed using a top down integrated engineering approach. An approach proposed includes integrating the overall environment involving sensors and their associated data; design knowledge capture; operations; fault detection, identification, and reconfiguration; testability; causal models including digraph matrix analysis; and overall performance impacts on the hardware and software architecture. Implementation of the concept to achieve a real time intelligent fault detection and management system will be accomplished via the implementation of several objectives, which are: Development of fault tolerant/FDIR requirement and specification from a systems level which will carry through from conceptual design through implementation and mission operations; Implementation of monitoring, diagnosis, and reconfiguration at all system levels providing fault isolation and system integration; Optimize system operations to manage degraded system performance through system integration; and Lower development and operations costs through the implementation of an intelligent real time fault detection and fault management system and an information management system.

Lum, H.↗
NASA NTRS1995

Clouds and the Earth's Radiant Energy System (CERES) Algorithm Theoretical Basis Document: Cloud Analyses and Determination of Improved Top of Atmosphere Fluxes (Subsystem 4) - Volume 3

The theoretical bases for the Release 1 algorithms that will be used to process satellite data for investigation of the Clouds and Earth's Radiant Energy System (CERES) are described. The architecture for software implementation of the methodologies is outlined. Volume 3 details the advanced CERES methods for performing scene identification and inverting each CERES scanner radiance to a top-of-the-atmosphere (TOA) flux. CERES determines cloud fraction, height, phase, effective particle size, layering, and thickness from high-resolution, multispectral imager data. CERES derives cloud properties for each pixel of the Tropical Rainfall Measuring Mission (TRMM) visible and infrared scanner and the Earth Observing System (EOS) moderate-resolution imaging spectroradiometer. Cloud properties for each imager pixel are convolved with the CERES footprint point spread function to produce average cloud properties for each CERES scanner radiance. The mean cloud properties are used to determine an angular distribution model (ADM) to convert each CERES radiance to a TOA flux. The TOA fluxes are used in simple parameterization to derive surface radiative fluxes. This state-of-the-art cloud-radiation product will be used to substantially improve our understanding of the complex relationship between clouds and the radiation budget of the Earth-atmosphere system.

Source record↗
DOE OSTI2020

Hierarchical, rotation‐equivariant neural networks to select structural models of protein complexes

Abstract Predicting the structure of multi‐protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational structure prediction methods generally leverage predefined structural features to distinguish accurate structural models from less accurate ones. This raises the question of whether it is possible to learn characteristics of accurate models directly from atomic coordinates of protein complexes, with no prior assumptions. Here we introduce a machine learning method that learns directly from the 3D positions of all atoms to identify accurate models of protein complexes, without using any precomputed physics‐inspired or statistical terms. Our neural network architecture combines multiple ingredients that together enable end‐to‐end learning from molecular structures containing tens of thousands of atoms: a point‐based representation of atoms, equivariance with respect to rotation and translation, local convolutions, and hierarchical subsampling operations. When used in combination with previously developed scoring functions, our network substantially improves the identification of accurate structural models among a large set of possible models. Our network can also be used to predict the accuracy of a given structural model in absolute terms. The architecture we present is readily applicable to other tasks involving learning on 3D structures of large atomic systems.

Eismann, Stephan↗
DOE OSTI2021

Identification of localized radiation damage in power MOSFETs using EBIC imaging

The rapidly increasing use of electronics in high-radiation environments and the continued evolution in transistor architectures and materials demand improved methods to characterize the potential damaging effects of radiation on device performance. Here, electron-beam-induced current is used to map hot-carrier transport in model metal-oxide semiconductor field-effect transistors irradiated with a 300 KeV focused He + beam as a localized line spanning across the gate and bulk Si. By correlating the damage to the electronic properties and combining these results with simulations, the contribution of spatially localized radiation damage on the device characteristics is obtained. Furthermore, this identified damage, caused by the He + beam, is attributed to localized interfacial P b centers and delocalized positive fixed-charges, as surmised from simulations. Comprehension of the long-term interaction and mobility of radiation-induced damage are key for future design of rad-hard devices.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Acoustic-based monitoring and machine learning of component status for microreactor applications

This report provides a description and assessment of recent efforts to couple acoustic-based experimental measurements and characterization with machine learning models in order to enhance structural health monitoring capabilities for nuclear microreactors. With resilient embedded sensors in development by others supported by programs funded by the US Department of Energy’s Office of Nuclear Energy, the work described herein builds upon ongoing efforts to improve non-destructive testing technology that relates measured acoustic signatures to component stresses and/or structural defects, using a combination of new experimental measurements and machine learning architectures. The experimental procedure remained similar to that developed for the previous year’s demonstration of damage detection by the authors, with the same damaged sample tested under similar applied stress conditions. Notably, a new mounting fixture was designed and implemented to improve measurement consistency and a more sophisticated laser Doppler vibrometer was employed to make high-fidelity vibration measurements. Two nominally identical sets of training data were collected for each experimental setup to better understand the repeatability of the experiment and to better test the generality of trained neural network models. Additionally, we obtained new high-quality 3D mode shapes of the damaged test article at various stress and excitation levels, providing greater insights into the physical response of the sample during testing. Previously, we demonstrated that a machine learning model based on a convolutional neural network can predict structural details of an artificially introduced interface (intact, rough cut, smooth cut), and the applied torque level. In this study, we have transitioned to graph-based neural network architectures to better develop and test a flexible framework that is more suitable to being transferred away from controlled benchtop experiments and into more applied settings where less-structured data inputs may be expected. In general, performance testing of a graph neural network on frequency-domain representations of the data indicates strong and consistent identification of test conditions for datasets recorded on damaged components. With goals of predicting damage location and other changing experimental conditions using limited datasets, predictive models using a graph neural network architecture correctly predicted the applied torque level with an accuracy of 85% using only a single measurement point and predicted within one torque level in 95% of test windows. Predictions of damage location had limited success due to the symmetry and minimal number of the damage scenarios presented during model training. Results were ambiguous as to whether the model could detect the location of the artificial damage, or if it was instead learning the location of a given measurement point on the part and subsequently detecting which points were closest to the location of the damage. This finding will be factored into upcoming planned work on damaged graphite components, where new experimental tests with a larger number and variety of damage scenarios are expected to provide improved validation of recent developments in monitoring methodology.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

The genetic architecture of biomechanical traits in sorghum

Sorghum bicolor (L.) Moench is the fifth most commonly grown cereal crop worldwide with unrivaled drought tolerance compared with other cereal crops. Drought and heat tolerance and high biomass yield potential make sorghum a promising bioenergy crop. However, stem lodging is a significant problem that results in substantial yield losses. Stem biomechanical traits influence the mechanical stability of crops and breeding for desirable biomechanical traits may result in improved lodging resistance. In this study, we report the identification of quantitative trait loci (QTL) for stem mechanical and morphological traits in three recombinant inbred line (RIL; populations from Tx623/Rio, Tx623/Della, and Tx631/Della) crosses between elite grain and sweet sorghum parents. The genetic architecture of stem biomechanical traits in the three RIL populations is multigenic and pleiotropic. Additionally, eight QTL affecting mechanical and morphological traits were detected; two main effects of these QTL were consistently found in all populations and colocated with previously identified dwarfing genes Dw1 and Dw3. These results indicate that dwarfing genes affect the mechanical properties of sorghum stems and their lodging resistance, while also having demonstrable effects on stem morphology. The identification of these QTL provides new opportunities for improving stem lodging resistance via genomics-assisted breeding.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data

Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗