Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “high throughput computing”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

SPIKE-Dx : A Low-Power High-Throughput Fault Diagnostics Tool using Spiking Neural Networks for Constrained Systems

Diagnostic systems are important for many aerospace systems, which are severely limited in available power, like cubesats or UAVs. Therefore, traditional diagnostics systems cannot be used due to their substantial footprint and constraints. In this paper, we present our very low power diagnostic tool SPIKE-DX to monitor critical systems with constrained computational and energy resources. This is made possible through spiking neural networks (SNNs), which are executable within optimized simulation environments and further implemented on on cutting-edge neuromorphic hardware. Based upon FMEA (Failure Mode and Effect Analysis) framework, Diagnostic Bayesian Networks (DBNs) can be constructed that provide powerful means for diagnostic reasoning. In this paper, we describe such DBNs and a method to automatically translate the DBN into highly structured networks of spiking neurons for execution in SPIKE-DX.

Spiking Neural Networks↗
NASA NTRS2019

Challenges Using Linux as a Real-Time Operating System

Human-in-the-loop (HITL) simulation groups at NASA and the Air Force Research Lab have been using Linux as a real-time operating system (RTOS) for over a decade. More recently, SpaceX has revealed that it is using Linux as an RTOS for its Falcon launch vehicles and Dragon capsules. As Linux makes its way from ground facilities to flight critical systems, it is necessary to recognize that the real-time capabilities in Linux are cobbled onto a kernel architecture designed for general purpose computing. The Linux kernel contain numerous design decisions that favor throughput over determinism and latency. These decisions often require workarounds in the application or customization of the kernel to restore a high probability that Linux will achieve deadlines.

Madden, Michael M.↗
NASA NTRS1979

Recycling isoelectric focusing with computer controlled data acquisition system

Isoelectric focusing is a high-resolution technique for separating and purifying large peptides, proteins, and other biomolecules. The apparatus described in the present paper constitutes a new approach to fluid stabilization and increased throughput. Stabilization is achieved by flowing the process fluid uniformly through an array of closely spaced filter elements oriented parallel both to the electrodes and the direction of the flow. This seems to overcome the major difficulties of parabolic flow and electroosmosis at the walls, while limiting the convection to chamber compartments defined by adjacent spacers. Increased throughput is achieved by recirculating the process fluid through external heat exchange reservoirs, where the Joule heat is dissipated.

Egen, N. B.↗
NASA NTRS1975

LSI computer for 1980's space mission

The low power, high reliability, SUMC-III-C computer is one member of the Space Ultrareliable Modular Computer (SUMC) family designed by NASA/MSFC to meet a wide range of missions through modularity in word size, throughput, and reliability. The SUMC-III-C, directed at such missions as the Large Space Telescope and Space Tug, uses custom designed CMOS/SOS LSI arrays with critical computer paths packaged on thick-film hybrids. This technology provides 300 to 600 logic gates per array with a typical stage delay of 3 to 5 nsec. SUMC-III-C is fully S/360 compatible at the user level, and includes virtual memory for the first time in an aerospace computer.

Clapp, W. A.↗
NASA NTRS1994

VLSI neuroprocessors

Electronic and optoelectronic hardware implementations of highly parallel computing architectures address several ill-defined and/or computation-intensive problems not easily solved by conventional computing techniques. The concurrent processing architectures developed are derived from a variety of advanced computing paradigms including neural network models, fuzzy logic, and cellular automata. Hardware implementation technologies range from state-of-the-art digital/analog custom-VLSI to advanced optoelectronic devices such as computer-generated holograms and e-beam fabricated Dammann gratings. JPL's concurrent processing devices group has developed a broad technology base in hardware implementable parallel algorithms, low-power and high-speed VLSI designs and building block VLSI chips, leading to application-specific high-performance embeddable processors. Application areas include high throughput map-data classification using feedforward neural networks, terrain based tactical movement planner using cellular automata, resource optimization (weapon-target assignment) using a multidimensional feedback network with lateral inhibition, and classification of rocks using an inner-product scheme on thematic mapper data. In addition to addressing specific functional needs of DOD and NASA, the JPL-developed concurrent processing device technology is also being customized for a variety of commercial applications (in collaboration with industrial partners), and is being transferred to U.S. industries. This viewgraph p resentation focuses on two application-specific processors which solve the computation intensive tasks of resource allocation (weapon-target assignment) and terrain based tactical movement planning using two extremely different topologies. Resource allocation is implemented as an asynchronous analog competitive assignment architecture inspired by the Hopfield network. Hardware realization leads to a two to four order of magnitude speed-up over conventional techniques and enables multiple assignments, (many to many), not achievable with standard statistical approaches. Tactical movement planning (finding the best path from A to B) is accomplished with a digital two-dimensional concurrent processor array. By exploiting the natural parallel decomposition of the problem in silicon, a four order of magnitude speed-up over optimized software approaches has been demonstrated.

Kemeny, Sabrina E.↗
NASA NTRS1986

Advanced dendritic web growth development and development of single-crystal silicon dendritic ribbon and high-efficiency solar cell program

Efforts to demonstrate that the dendritic web technology is ready for commercial use by the end of 1986 continues. A commercial readiness goal involves improvements to crystal growth furnace throughput to demonstrate an area growth rate of greater than 15 sq cm/min while simultaneously growing 10 meters or more of ribbon under conditions of continuous melt replenishment. Continuous means that the silicon melt is being replenished at the same rate that it is being consumed by ribbon growth so that the melt level remains constant. Efforts continue on computer thermal modeling required to define high speed, low stress, continuous growth configurations; the study of convective effects in the molten silicon and growth furnace cover gas; on furnace component modifications; on web quality assessments; and on experimental growth activities.

Duncan, C. S.↗
NASA NTRS2011

Kalman Orbit Optimized Loop Tracking

Under certain conditions of low signal power and/or high noise, there is insufficient signal to noise ratio (SNR) to close tracking loops with individual signals on orbiting Global Navigation Satellite System (GNSS) receivers. In addition, the processing power available from flight computers is not great enough to implement a conventional ultra-tight coupling tracking loop. This work provides a method to track GNSS signals at very low SNR without the penalty of requiring very high processor throughput to calculate the loop parameters. The Kalman Orbit-Optimized Loop (KOOL) tracking approach constitutes a filter with a dynamic model and using the aggregate of information from all tracked GNSS signals to close the tracking loop for each signal. For applications where there is not a good dynamic model, such as very low orbits where atmospheric drag models may not be adequate to achieve the required accuracy, aiding from an IMU (inertial measurement unit) or other sensor will be added. The KOOL approach is based on research JPL has done to allow signal recovery from weak and scintillating signals observed during the use of GPS signals for limb sounding of the Earth s atmosphere. That approach uses the onboard PVT (position, velocity, time) solution to generate predictions for the range, range rate, and acceleration of the low-SNR signal. The low- SNR signal data are captured by a directed open loop. KOOL builds on the previous open loop tracking by including feedback and observable generation from the weak-signal channels so that the MSR receiver will continue to track and provide PVT, range, and Doppler data, even when all channels have low SNR.

Young, Lawrence E.↗
NASA NTRS1985

Evaluation of an experimental system for spaceborne processing of multispectral image data

An experimental data processing system has been developed to demonstrate the feasibility of processing high speed, multispectral image data on board the spacecraft. The design incorporates real-time processing with adaptable operation in an expandable architecture. The experimental hardware is coupled to test support and computing equipment to provide a laboratory tool for evaluating and demonstrating each of the processing functions as well as the overall system operation. An evaluation of the high speed processor was conducted to ensure that the desired system throughput was achieved without sacrificing processing accuracy. A description of the system is presented along with the results of the test and evaluation activity.

Meredith, B. D.↗
NASA NTRS1988

Systolic architectures for vector quantization

A family of architectural techniques are proposed which offer efficient computation of weighted Euclidean distance measures for nearest-neighbor codebook searching. The general approach uses a single metric comparator chip in conjunction with a linear array of inner product processor chips. Very high vector-quantization (VQ) throughput can be achieved for many speech and image-processing applications. Several alternative configurations allow reasonable tradeoffs between speed and VLSI chip area required.

Davidson, Grant A.↗
NASA NTRSDate not supplied

Screening of Li-Based Solid Electrolytes Using Bond-Valence Methods and Graph Neural Networks

Li-based solid-state electrolyte (Li-SSE) materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. We present a high-throughput screening approach for Li-SSE materials using a combination of bond-valence methods and graph neural networks. We demonstrate the screening approach with a dataset containing tens of thousands of Li-containing compounds. Furthermore, we combine the machine-learning screening procedure with an isovalent substitution scheme to generate and screen additional Li SSE candidates beyond existing databases. Finally, we discuss relative importances of geometric and bond-valence quantities in the training of graph neural networks, providing insight for future modeling of ionic conductivity in Li-SSE materials.

Materials discovery↗
NASA NTRS1984

A fast, programmable hardware architecture for the processing of spaceborne SAR data

The development of high-throughput SAR processors (HTSPs) for the spaceborne SARs being planned by NASA, ESA, DFVLR, NASDA, and the Canadian Radarsat Project is discussed. The basic parameters and data-processing requirements of the SARs are listed in tables, and the principal problems are identified as real-operations rates in excess of 2 x 10 to the 9th/sec, I/O rates in excess of 8 x 10 to the 6th samples/sec, and control computation loads (as for range cell migration correction) as high as 1.4 x 10 to the 6th instructions/sec. A number of possible HTSP architectures are reviewed; host/array-processor (H/AP) and distributed-control/data-path (DCDP) architectures are examined in detail and illustrated with block diagrams; and a cost/speed comparison of these two architectures is presented. The H/AP approach is found to be adequate and economical for speeds below 1/200 of real time, while DCDP is more cost-effective above 1/50 of real time.

Bennett, J. R.↗
NASA NTRS1991

An ultrareliable integrated digital computer for helicopters

The US Army Fault-Tolerant Architecture (AFTA) has been defined to meet real-time fault-tolerant processing requirements of future Army applications. AFTA is the enabling technology that will allow the Army to configure existing processors and other hardware to provide high throughput and ultrahigh reliability necessary for terrain-following/terrain-avoidance (TF/TA) and nap-of-the-earth (NOE) flight control and other advanced Army applications. A brief description of AFTA's relevant attributes and theory of operation is given. The systems engineering models which permit the configuration on an AFTA to meet mission requirements as they evolve are presented, along with an example of their use to engineer an AFTA configuration. The resulting AFTA configuration, its predicted throughput, reliability, availability, weight, power, volume, and life-cycle cost impact, and the effects of possible engineering tradeoffs are presented.

Harper, Richard E.↗
NASA NTRSDate not supplied

Hierarchical screening for Li-based solid electrolytes using fast, interpretable machine-learned potentials

Li-based solid-state electrolyte materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. The prohibitive cost of high-throughput screening with DFT has lead to the development of surrogate models using geometric analysis, empirical potentials, and descriptors for ionic transport. Here, I will discuss a hierarchical screening approach for identifying promising materials using a combination of density functional theory, bond-valence methods, and machine learning potentials generated with the Ultra-Fast Force Fields (UF3) framework. We show how the inexpensive bond-valence method can be used to guide the generation of training samples for machine learning, in addition to filtering candidates. Finally, we apply the hierarchical workflow to screen for ionic conductivity across a database of Li-containing compounds.

Materials discovery↗
NASA NTRSDate not supplied

Hierarchical Screening for Li-Based Solid Electrolytes Using Fast, Interpretable Machine-Learned Potentials

Li-based solid-state electrolyte materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. The prohibitive cost of high-throughput screening with DFT has lead to the development of surrogate models using geometric analysis, empirical potentials, and descriptors for ionic transport. Here, I will discuss a hierarchical screening approach for identifying promising materials using a combination of density functional theory, bond-valence methods, and machine learning potentials generated with the Ultra-Fast Force Fields (UF3) framework. We show how the inexpensive bond-valence method can be used to guide the generation of training samples for machine learning, in addition to filtering candidates.

Materials discovery↗
NASA NTRS1987

Fault-free performance validation of fault-tolerant multiprocessors

A validation methodology for testing the performance of fault-tolerant computer systems was developed and applied to the Fault-Tolerant Multiprocessor (FTMP) at NASA-Langley's AIRLAB facility. This methodology was claimed to be general enough to apply to any ultrareliable computer system. The goal of this research was to extend the validation methodology and to demonstrate the robustness of the validation methodology by its more extensive application to NASA's Fault-Tolerant Multiprocessor System (FTMP) and to the Software Implemented Fault-Tolerance (SIFT) Computer System. Furthermore, the performance of these two multiprocessors was compared by conducting similar experiments. An analysis of the results shows high level language instruction execution times for both SIFT and FTMP were consistent and predictable, with SIFT having greater throughput. At the operating system level, FTMP consumes 60% of the throughput for its real-time dispatcher and 5% on fault-handling tasks. In contrast, SIFT consumes 16% of its throughput for the dispatcher, but consumes 66% in fault-handling software overhead.

Czeck, Edward W.↗
NASA NTRS1986

Application of laser-velocimetry to the study of the flow around a two-dimensional airfoil

The experimental techniques employed by NASA researchers to obtain a high volume throughput of data in a study of high-lift multielement airfoils using a laser velocimeter (LV) are detailed. The two-dimensional LV system recorded mean velocity, turbulence intensities, Re shear stresses, skewness and kurtosis of the flow. A computer-controlled positioning mount for the LV allowed automated surveys of the flows with a 0.001 in. positioning accuracy. The flow was seeded with oil droplets and additional refinement of the wind tunnel controls permitted rapid speedup at selected areas of the flowfield over specific regions of the airfoil. Surface pressure taps furnished data for selecting regions for more detailed investigation. The data processing capabilities processed 30-40 samples every 10 min in an automated mode. Profiles of the data were computed automatically to furnish graphical displays on demand. Numerous samples of the data displays generated are provided.

Braden, J. A.↗
NASA NTRS2006

Non Radiation Hardened Microprocessors in Spaced Based Remote Sensing Systems

The CALIPSO (Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations) mission is a comprehensive suite of active and passive sensors including a 20Hz 230mj Nd:YAG lidar, a visible wavelength Earth-looking camera and an imaging infrared radiometer. CALIPSO flies in formation with the Earth Observing System Post-Meridian (EOS PM) train, provides continuous, near-simultaneous measurements and is a planned 3 year mission. CALIPSO was launched into a 98 degree sun synchronous Earth orbit in April of 2006 to study clouds and aerosols and acquires over 5 gigabytes of data every 24 hours. The ground track of one CALIPSO orbit as well as high and low intensity South Atlantic Anomaly outlines is shown. CALIPSO passes through the SAA several times each day. Spaced based remote sensing systems that include multiple instruments and/or instruments such as lidar generate large volumes of data and require robust real-time hardware and software mechanisms and high throughput processors. Due to onboard storage restrictions and telemetry downlink limitations these systems must pre-process and reduce the data before sending it to the ground. This onboard processing and realtime requirement load may mean that newer more powerful processors are needed even though acceptable radiation-hardened versions have not yet been released. CALIPSO's single board computer payload controller processor is actually a set of four (4) voting non-radiation hardened COTS Power PC 603r's built on a single width VME card by General Dynamics Advanced Information Systems (GDAIS). Significant radiation concerns for CALIPSO and other Low Earth Orbit (LEO) satellites include the South Atlantic Anomaly (SAA), the north and south poles and strong solar events. Over much of South America and extending into the South Atlantic Ocean the Van Allen radiation belts dip to just 200-800km and spacecraft entering this area are subjected to high energy protons and experience higher than normal Single Event Upset (SEU) and Single Event Latch-up (SEL) rates. Although less significant, spacecraft flying in the area around the poles experience similar upsets. Finally, powerful solar proton events in the range of 10MeV/10pfu to 100MeV/1pfu as are forecasted and tracked by NOAA's Space Environment Center in Colorado can result in Single Event Upset (SEU), Single Event Latch-up (SEL) and permanent failures such as Single Event Gate Rupture (SEGR) in some technologies. (Galactic Cosmic Rays (GCRs) are another source, especially for gate rupture) CALIPSO mitigates common radiation concerns in its data handling through the use of redundant processors, radiation-hardened Application Specific Integrated Circuits (ASIC), hardware-based Error Detection and Correction (EDAC), processor and memory scrubbing, redundant boot code and mirrored files. After presenting a system overview this paper will expand on each of these strategies. Where applicable, related on-orbit data collected since the CALIPSO initial boot on May 4, 2006 will be noted.

Decoursey, Robert J.↗
NASA NTRS2013

Effects of Airport Tower Controller Decision Support Tool on Controllers Head-Up Time

Despite that aircraft positions and movements can be easily monitored on the radar displays at major airports nowadays, it is still important for the air traffic control tower (ATCT) controllers to look outside the window as much as possible to assure safe operations of traffic management. The present paper investigates whether an introduction of the NASA's proposed Spot and Runway Departure Advisor (SARDA), a decision support tool for the ATCT controller, would increase or decrease the controllers' head-up time. SARDA provides the controller departure-release schedule advisories, i.e., when to release each departure aircraft in order to minimize individual aircraft's fuel consumption on taxiways and simultaneously maximize the overall runway throughput. The SARDA advisories were presented on electronic flight strips (EFS). To investigate effects on the head-up time, a human-in-the-loop simulation experiment with two retired ATCT controller participants was conducted in a high-fidelity ATCT cab simulator with 360-degree computer-generated out-the-window view. Each controller participant wore a wearable video camera on a side of their head with the camera facing forward. The video data were later used to calculate their line of sight at each moment and eventually identify their head-up times. Four sessions were run with the SARDA advisories, and four sessions were run without (baseline). Traffic-load levels were varied in each session. The same set of user interface - EFS and the radar displays - were used in both the advisory and baseline sessions to make them directly comparable. The paper reports the findings and discusses their implications.

airport surface operations↗