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.
In developing a software system, we would like to estimate the total number of faults inserted into a software system, the residual fault content of that system at any given time, and the efficacy of the testing activity in executing the code containing the newly inserted faults.
We present a dynamic fault tree model of the benchmark propulsion system, and solve it using Galileo. Dynamic fault trees (DFT) extend traditional static fault trees with special gates to model spares and other sequence dependencies. Galileo solves DFT models using a judicious combination of automatically generated Markov and Binary Decision Diagram models. Galileo easily handles the complexities exhibited by the benchmark problem. In particular, Galileo is designed to model phased mission systems.
While every JPL spacecraft requires some unique mission specific fault protection, there are many requirements which are common to all spacecraft configurations. These consist of protecting command and data processing & attitude control computers, protection against communication loss with the spacecraft, ensuring that safe external and internal temperature levels are maintained, and recovery from power overloads. Additionally, most JPL spacecraft are equipped with a general-purpose 'Safe Mode' response algorithm which configures the spacecraft to a lower power state which is safe and predictable so that diagnosis of more complex faults can be addressed by the Operations Team. This paper details the generic application of fault protection techniques which are implemented into most JPL spacecraft designs.
GeoFEST (the Geophysical Finite Element Simulation Tool) simulates stress evolution, fault slip and plastic/elastic processes in realistic materials, and so is suitable for earthquake cycle studies in regions such as Southern California. Many new capabilities and means of access for GeoFEST are now supported. New abilities include MPI-based cluster parallel computing using automatic PYRAMID/Parmetis-based mesh partitioning, automatic mesh generation for layered media with rectangular faults, and results visualization that is integrated with remote sensing data. The parallel GeoFEST application has been successfully run on over a half-dozen computers, including Intel Xeon clusters, Itanium II and Altix machines, and the Apple G5 cluster. It is not separately optimized for different machines, but relies on good domain partitioning for load-balance and low communication, and careful writing of the parallel diagonally preconditioned conjugate gradient solver to keep communication overhead low. Demonstrated thousand-step solutions for over a million finite elements on 64 processors require under three hours, and scaling tests show high efficiency when using more than (order of) 4000 elements per processor. The source code and documentation for GeoFEST is available at no cost from Open Channel Foundation. In addition GeoFEST may be used through a browser-based portal environment available to approved users. That environment includes semi-automated geometry creation and mesh generation tools, GeoFEST, and RIVA-based visualization tools that include the ability to generate a flyover animation showing deformations and topography. Work is in progress to support simulation of a region with several faults using 16 million elements, using a strain energy metric to adapt the mesh to faithfully represent the solution in a region of widely varying strain.
NASA's exploration program envisions the utilization of a Deep Space Habitat (DSH) for human exploration of the space environment in the vicinity of Mars and/or asteroids. Communication latencies with ground control of as long as 20+ minutes make it imperative that DSH operations be highly autonomous, as any telemetry-based detection of a systems problem on Earth could well occur too late to assist the crew with the problem. A DSH-based development program has been initiated to develop and test the automation technologies necessary to support highly autonomous DSH operations. One such technology is a fault management tool to support performance monitoring of vehicle systems operations and to assist with real-time decision making in connection with operational anomalies and failures. Toward that end, we are developing Advanced Caution and Warning System (ACAWS), a tool that combines dynamic and interactive graphical representations of spacecraft systems, systems modeling, automated diagnostic analysis and root cause identification, system and mission impact assessment, and mitigation procedure identification to help spacecraft operators (both flight controllers and crew) understand and respond to anomalies more effectively. In this paper, we describe four major architecture elements of ACAWS: Anomaly Detection, Fault Isolation, System Effects Analysis, and Graphic User Interface (GUI), and how these elements work in concert with each other and with other tools to provide fault management support to both the controllers and crew. We then describe recent evaluations and tests of ACAWS on the DSH testbed. The results of these tests support the feasibility and strength of our approach to failure management automation and enhanced operational autonomy.
This paper describes the results of a special breakout session of the NASA Independent Verification and Validation (IV&V) Workshop held in the fall of 2012 entitled "V&V of Fault Management: Challenges and Successes." The NASA IV&V Program is in a unique position to interact with projects across all of the NASA development domains. Using this unique opportunity, the IV&V program convened a breakout session to enable IV&V teams to share their challenges and successes with respect to the V&V of Fault Management (FM) architectures and software. The presentations and discussions provided practical examples of pitfalls encountered while performing V&V of FM including the lack of consistent designs for implementing faults monitors and the fact that FM information is not centralized but scattered among many diverse project artifacts. The discussions also solidified the need for an early commitment to developing FM in parallel with the spacecraft systems as well as clearly defining FM terminology within a project.
Due to increasingly high DC link voltages and further advancements in the current density of silicon carbide (SiC) MOSFETs, it has become evident that conventional IGBT protection methods are not sufficient to prevent exceeding the current rating of these devices during low-inductance fault events. This paper explores the use of an air core Rogowski coil topology to mitigate these hard fault events. The design of this circuit resulted in safe shutdown of a low impedance phase-to-phase fault in under one microsecond, tested up to DC link voltages of 1 kV. This paper details the theory, design, simulation, and successful test results of this method.
Due to increasingly high DC link voltages and further advancements in the current density of silicon carbide (SiC) MOSFETs, it has become evident that conventional IGBT protection methods are not sufficient to protect these devices from overcurrent during low-inductance fault events. The use of an air core Rogowski coil topology was explored to see if it could mitigate these hard fault events. The design of this circuit resulted in safe shutdown of a low impedance phase-tophase fault, tested up to DC link voltages of 1 kV.
A method is presented for calculating event probabilities from an arbitrary fault tree. The method includes an analytical derivation of the system equation and is not a simulation program. The method can handle systems that incorporate standby redundancy and it uses conditional probabilities for computing fault trees where the same basic failure appears in more than one fault path.
Published report discusses fault location properties of arithmetic codes. Criterion for effectiveness of given code is detection probability of local fault by application of checking algorithm to results of entire set of algorithms of processor. Report also presents analysis of arithmetic codes with low-cost check algorithm which possesses partial fault-location properties.
The author has identified the following significant results. Analysis of ERTS-1 MSS and other imagery for a 125 x 25 mile area in the southern part of the Basin-Range Province of southeastern California, southern Nevada, and northwestern Arizona indicates the presence of numerous color and contrast anomalies in alluvium. Field work guided by high altitude U-2 and side-looking aerial radar imagery confirmed that these anomalies are fault zones, many of which are believed to be of recent age. Few faults in alluvium have been reported from previous ground based geologic studies in the area. ERTS-1 imagery provides a synoptic perspective previously unavailable for regional geologic studies. The ability to conduct rapid and inexpensive reconnaissance of recent faulting has important applications to land use planning, ground water exploration, geologic hazards, and the siting and design of engineering projects.
The San Andreas Fault Experiment, which employs two laser tracking systems for measuring the relative motion of two points on opposite sides of the fault, was simulated for an eight year observation period. The two tracking stations are located near San Diego on the western side of the fault and near Quincy on the eastern side; they are roughly 900 kilometers apart. Both will simultaneously track laser reflector equipped satellites as they pass near the stations. Tracking of the Beacon Explorer C Spacecraft was simulated for these two stations during August and September for eight consecutive years. An error analysis of the recovery of the relative location of Quincy from the data was made, allowing for model errors in the mass of the earth, the gravity field, solar radiation pressure, atmospheric drag, errors in the position of the San Diego site, and laser systems range biases and noise. The results of this simulation indicate that the distance of Quincy from San Diego will be determined each year with a precision of about 10 centimeters. This figure is based on the accuracy of earth models and other parameters available in 1972.
The concept of a 'system with faults' is introduced as a suggested point of departure for the theoretical study of fault tolerance and diagnosis in systems. The model is defined relative to a general representation scheme for systems and, depending on the choice of representation, can be used to investigate either hardware or software faults that occur during either the design or use of a system.
A total of 48 operational flight instrumentation measurements were identified for use in performance monitoring and fault detection. The Operational Flight Instrumentation List contains all measurements identified for fault detection and annunciation. Some 16 controller data words were identified for use in fault detection and annunciation.
A plan was developed during 1971 to determine gross tectonic plate motions along the San Andreas Fault System in California. Knowledge of the gross motion along the total fault system is an essential component in the construction of realistic deformation models of fault regions. Such mathematical models will be used in the future for studies which will eventually lead to prediction of major earthquakes. The main purpose of the experiment described is the determination of the relative velocity of the North American and the Pacific Plates. This motion being so extremely small, cannot be measured directly but can be deduced from distance measurements between points on opposite sites of the plate boundary taken over a number of years.
The San Andreas fault experiment (Safe), which employs two laser tracking systems for measuring the relative motion of two points on opposite sides of the fault, has been simulated for an 8-yr observation period. The two tracking stations are located near San Diego on the western side of the fault and near Quincy on the eastern side; they are roughly 900 km apart. Both will simultaneously track laser reflector equipped satellites as they pass near the stations. Tracking of the Beacon Explorer C spacecraft has been simulated for these two stations during August and September for 8 consecutive years. An error analysis of the recovery of the relative location of Quincy from the data has been made, allowing for model errors in the mass of the earth, the gravity field, solar radiation pressure, atmospheric drag, errors in the position of the San Diego site, and biases and noise in the laser systems. The results of this simulation indicate that the distance of Quincy from San Diego will be determined each year with a precision of about 10 cm. Projected improvements in these model parameters and in the laser systems over the next few years will bring the precision to about 1-2 cm by 1980.
This paper presents a description of redundancy techniques employed in the design of fault-tolerant computers, and a discussion of the effects of functional requirements, technology constraints, and cost considerations which enter into the choice of these techniques. The STAR computer, developed at the Jet Propulsion Laboratory for long-duration planetary spacecraft missions, is discussed along with several later fault-tolerant computer designs. The class of computers described in this paper employs dynamic redundancy, i.e., the machine is divided into a set of submodules, each with standby spares; a special hard core monitor unit detects and diagnoses faults, and effects automated recovery by replacing failed parts.
Attention is given to the formal development of the notion of a discrete-time system and the associated concepts of fault, result of a fault, and error. The considered concept of on-line diagnosis is formalized and a diagnosis using inverse machines is discussed. The case of an inverse which is lossless is investigated. It is found that in such a case the class of unrestricted faults can be diagnosed with a delay equal to the delay of losslessness of the inverse system.