SEARCH · Search NASA
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.
Design and reliability of digital systems for hard cores of fault tolerant computers /hybrid- redundant systems/, discussing advantages over multiplexed systems
A corona vacuum test facility for nondestructive testing of power system components was built in the Reliability and Quality Engineering Test Laboratories at the NASA Lewis Research Center. The facility was developed to simulate operating temperature and vacuum while monitoring corona discharges with residual gases. The facility is being used to test various high-voltage power system components.
The reliability of 45 state-of-the-art strain gage systems under full scale engine testing was investigated. The flame spray process was used to install 23 systems on the first fan rotor of a YF-100 engine; the others were epoxy cemented. A total of 56 percent of the systems failed in 11 hours of engine operation. Flame spray system failures were primarily due to high gage resistance, probably caused by high stress levels. Epoxy system failures were principally erosion failures, but only on the concave side of the blade. Lead-wire failures between the blade-to-disk jump and the control room could not be analyzed.
The objective was to search for and demonstrate approaches and concepts for fast wafer probe tests of mechanisms affecting the reliability of MOS technology and, based on these, develop and optimize test chips and test procedures. Progress is reported on four important wafer-level reliability problems: gate-oxide radiation hardness; hot-electron effects; time-dependence dielectric breakdown; and electromigration.
By viewing a composite lamina as a homogeneous solid whose directional strengths are random variables, lamina reliability under multiaxial stresses may be determined using either an interactive or a noninteractive criterion. From the reliability values for the individual laminae comprising a given laminate, Thomas and Wetherhold (1991) have proposed a method for determining bounds for the overall laminate reliability. In this paper, simple physically plausible phenomenological rules are proposed for redistribution of load after a lamina has failed within the confines of a laminate. These rules are illustrated by application to (0/ +/-15)s and (90/ +/-45/0)s graphite/epoxy laminates, and the results are compared to the previously proposed bounds.
A methodology is developed and applied for quantitatively analyzing the reliability of a dual, fail-operational redundant strapdown inertial measurement unit (RSDIMU). A Markov evaluation model is defined in terms of the operational states of the RSDIMU to predict system reliability. A 27 state model is defined based upon a candidate redundancy management system which can detect and isolate a spectrum of failure magnitudes. The results of parametric studies are presented which show the effect on reliability of the gyro failure rate, both the gyro and accelerometer failure rates together, false alarms, probability of failure detection, probability of failure isolation, and probability of damage effects and mission time. A technique is developed and evaluated for generating dynamic thresholds for detecting and isolating failures of the dual, separated IMU. Special emphasis is given to the detection of multiple, nonconcurrent failures. Digital simulation time histories are presented which show the thresholds obtained and their effectiveness in detecting and isolating sensor failures.
RAM program determines probability of success for one or more given objectives in any complex system. Program includes failure mode and effects, criticality and reliability analyses, and some aspects of operations, safety, flight technology, systems design engineering, and configuration analyses.
A composite lamina may be viewed as a homogeneous solid whose directional strengths are random variables. Calculation of the lamina reliability under a multi-axial stress state can be approached by either assuming that the strengths act separately (modal or independent action), or that they interact through a quadratic interaction criterion. The independent action reliability may be calculated in closed form, while interactive criteria require simulations; there is currently insufficient data to make a final determination of preference between them. Using independent action for illustration purposes, the lamina reliability may be plotted in either stress space or in a non-dimensional representation. For the typical laminated plate structure, the individual lamina reliabilities may be combined in order to produce formal upper and lower bounds of reliability for the laminate, similar in nature to the bounds on properties produced from variational elastic methods. These bounds are illustrated for a (0/plus or minus 15)sub s Graphite/Epoxy (GR/EP) laminate. And addition, simple physically plausible phenomenological rules are proposed for redistribution of load after a lamina has failed. These rules are illustrated by application to (0/plus or minus 15)sub s and (90/plus or minus 45/0)sub s GR/EP laminates and results are compared with respect to the proposed bounds.
HRA is a method used to describe, qualitatively and quantitatively, the occurrence of human failures in the operation of complex systems that affect availability and reliability. Modeling human actions with their corresponding failure in a PRA (Probabilistic Risk Assessment) provides a more complete picture of the risk and risk contributions. A high quality HRA can provide valuable information on potential areas for improvement, including training, procedural, equipment design and need for automation.
Companies at risk of accidents caused by human error that result in catastrophic consequences include: airline industry mishaps, medical malpractice, medication mistakes, aerospace failures, major oil spills, transportation mishaps, power production failures and manufacturing facility incidents. Human Reliability Assessment (HRA) is used to analyze the inherent risk of human behavior or actions introducing errors into the operation of a system or process. These assessments can be used to identify where errors are most likely to arise and the potential risks involved if they do occur. Using the basic concepts of HRA, an evolving group of methodologies are used to meet various industry needs. Determining which methodology or combination of techniques will provide a quality human reliability assessment is a key element to developing effective strategies for understanding and dealing with risks caused by human errors. There are a number of concerns and difficulties in "tailoring" a Human Reliability Assessment (HRA) for different industries. Although a variety of HRA methodologies are available to analyze human error events, determining the most appropriate tools to provide the most useful results can depend on industry specific cultures and requirements. Methodology selection may be based on a variety of factors that include: 1) how people act and react in different industries, 2) expectations based on industry standards, 3) factors that influence how the human errors could occur such as tasks, tools, environment, workplace, support, training and procedure, 4) type and availability of data, 5) how the industry views risk & reliability, and 6) types of emergencies, contingencies and routine tasks. Other considerations for methodology selection should be based on what information is needed from the assessment. If the principal concern is determination of the primary risk factors contributing to the potential human error, a more detailed analysis method may be employed versus a requirement to provide a numerical value as part of a probabilistic risk assessment. Industries involved with humans operating large equipment or transport systems (ex. railroads or airlines) would have more need to address the man machine interface than medical workers administering medications. Human error occurs in every industry; in most cases the consequences are relatively benign and occasionally beneficial. In cases where the results can have disastrous consequences, the use of Human Reliability techniques to identify and classify the risk of human errors allows a company more opportunities to mitigate or eliminate these types of risks and prevent costly tragedies.
The TIGER algorithm, the inputs to the program and the output are described. TIGER is a computer program designed to simulate a system over a period of time to evaluate system reliability and availability. Results can be used in the Deep Space Network for initial spares provisioning and system evaluation.
Deployable subsystems are essential to mission success of most spacecraft. These subsystems enable critical functions including power, communications and thermal control. The loss of any of these functions will generally result in loss of the mission. These subsystems and their components often consist of unique designs and applications for which various standardized data sources are not applicable for estimating reliability and for assessing risks. In this study, a two stage sequential Bayesian framework for reliability estimation of spacecraft deployment was developed for this purpose. This process was then applied to the James Webb Space Telescope (JWST) Sunshield subsystem, a unique design intended for thermal control of the Optical Telescope Element. Initially, detailed studies of NASA deployment history, "heritage information", were conducted, extending over 45 years of spacecraft launches. This information was then coupled to a non-informative prior and a binomial likelihood function to create a posterior distribution for deployments of various subsystems uSing Monte Carlo Markov Chain sampling. Select distributions were then coupled to a subsequent analysis, using test data and anomaly occurrences on successive ground test deployments of scale model test articles of JWST hardware, to update the NASA heritage data. This allowed for a realistic prediction for the reliability of the complex Sunshield deployment, with credibility limits, within this two stage Bayesian framework.
At a macroscopic level, a composite lamina may be considered as a homogeneous orthotropic solid whose directional strengths are random variables. Incorporation of these random variable strengths into failure models, either interactive or non-interactive, allows for the evaluation of the lamina reliability under a given stress state. Using a non-interactive criterion for demonstration purposes, laminate reliabilities are calculated assuming previously established load sharing rules for the redistribution of load as the failure of laminae occur. The matrix cracking predicted by ACK theory is modeled to allow a loss of stiffness in the fiber direction. The subsequent failure in the fiber direction is controlled by a modified bundle theory. Results using this modified bundle model are compared with previous models which did not permit separate consideration of matrix cracking, as well as to results obtained from experimental data.
The fast fracture strength distribution of uniaxially ground, alpha silicon carbide was investigated as a function of grinding angle relative to the principal stress direction in flexure. Both as-ground and ground/annealed surfaces were investigated. The resulting flexural strength distributions were used to verify reliability models and predict the strength distribution of larger plate specimens tested in biaxial flexure. Complete fractography was done on the specimens. Failures occurred from agglomerates, machining cracks, or hybrid flaws that consisted of a machining crack located at a processing agglomerate. Annealing eliminated failures due to machining damage. Reliability analyses were performed using two and three parameter Weibull and Batdorf methodologies. The Weibull size effect was demonstrated for machining flaws. Mixed mode reliability models reasonably predicted the strength distributions of uniaxial flexure and biaxial plate specimens.
The present study is restricted to External Tank Attachment Rings (ETA), but the concepts discussed are general in nature and can be applied to any structural component. The objective of this research work is to use some of the existing probabilistic methods to calculate the reliability of ETA Rings at various critical sections for the limit state of stress. This is done both in terms of the traditional probability of failure and reliability levels as well as the well known safety indices (beta) which have become a commonly accepted measure of safety.
The F-8 Digital Fly-by-Wire (DFBW) flight test program intended to provide the technology for advanced control systems, giving aircraft enhanced performance and operational capability is addressed. A detailed analysis of the experimental system was performed to estimated the probabilities of two significant safety critical events: (1) loss of primary flight control function, causing reversion to the analog bypass system; and (2) loss of the aircraft due to failure of the electronic flight control system. The analysis covers appraisal of risks due to random equipment failure, generic faults in design of the system or its software, and induced failure due to external events. A unique diagrammatic technique was developed which details the combinatorial reliability equations for the entire system, promotes understanding of system failure characteristics, and identifies the most likely failure modes. The technique provides a systematic method of applying basic probability equations and is augmented by a computer program written in a modular fashion that duplicates the structure of these equations.
center dot In order to reduce commanding errors that are caused by humans, we create an approach and corresponding artifacts for standardizing the command generation process and conducting risk management during the design and assurance of such processes. center dot The literature review conducted during the standardization process revealed that very few atomic level human activities are associated with even a broad set of missions. center dot Applicable human reliability metrics for performing these atomic level tasks are available. center dot The process for building a "Periodic Table" of Command and Control Functions as well as Probabilistic Risk Assessment (PRA) models is demonstrated. center dot The PRA models are executed using data from human reliability data banks. center dot The Periodic Table is related to the PRA models via Fault Links.
NASA's future human space exploration strategy includes single and multi-launch missions to various destinations including cis-lunar space, near Earth objects such as asteroids, and ultimately Mars. Each campaign is being defined by Design Reference Missions (DRMs). Many of these missions are complex, requiring multiple launches and assembly of vehicles in orbit. Certain missions also have constrained departure windows to the destination. These factors raise concerns regarding the reliability of launching and assembling all required elements in time to support planned departure. This paper describes an integrated methodology for analyzing launch and assembly reliability in any single DRM or set of DRMs starting with flight hardware manufacturing and ending with final departure to the destination. A discrete event simulation is built for each DRM that includes the pertinent risk factors including, but not limited to: manufacturing completion; ground transportation; ground processing; launch countdown; ascent; rendezvous and docking, assembly, and orbital operations leading up to trans-destination-injection. Each reliability factor can be selectively activated or deactivated so that the most critical risk factors can be identified. This enables NASA to prioritize mitigation actions so as to improve mission success.