Search NASA⌕ Search

SEARCH · Search NASA

Results for “transient faults”

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 37 records · Page 2

A verified design of a fault-tolerant clock synchronization circuit: Preliminary investigations

Schneider demonstrates that many fault tolerant clock synchronization algorithms can be represented as refinements of a single proven correct paradigm. Shankar provides mechanical proof that Schneider's schema achieves Byzantine fault tolerant clock synchronization provided that 11 constraints are satisfied. Some of the constraints are assumptions about physical properties of the system and cannot be established formally. Proofs are given that the fault tolerant midpoint convergence function satisfies three of the constraints. A hardware design is presented, implementing the fault tolerant midpoint function, which is shown to satisfy the remaining constraints. The synchronization circuit will recover completely from transient faults provided the maximum fault assumption is not violated. The initialization protocol for the circuit also provides a recovery mechanism from total system failure caused by correlated transient faults.

Miner, Paul S.↗

LADR: low-cost application-level detector for reducing silent output corruptions

Applications running on future high performance computing (HPC) systems are more likely to experience transient faults due to technology scaling trends with respect to higher circuit density, smaller transistor size and near-threshold voltage (NTV) operations. A transient fault could corrupt application state without warning, possibly leading to incorrect application output. Such errors are called silent data corruptions (SDCs). In this paper, we present LADR, a low-cost application-level SDC detector for scientific applications. LADR protects scientific applications from SDCs by watching for data anomalies in their state variables (those of scientific interest). It employs compile-time data-flow analysis to minimize the number of monitored variables, thereby reducing runtime and memory overheads while maintaining a high level of fault coverage with low false positive rates. We evaluated LADR with 4 scientific workloads and results show that LADR achieved < 80% fault coverage with only ∼ 3% runtime overheads and ∼ 1% memory overheads. As compared to prior state-of-the-art anomaly-based detection methods, SDC achieved comparable or improved fault coverage, but reduced runtime overheads by 21% ∼ 75%, and memory overheads by 35% ∼ 55% for the evaluated workloads. We believe that such an approach with low memory and runtime overheads coupled with attractive detection precision makes LADR a viable approach for assuring the correct output from large-scale high performance simulations.

Chen, Chao↗

Flight experience with a fail-operational digital fly-by-wire control system

The NASA Dryden Flight Research Center is flight testing a triply redundant digital fly-by-wire (DFBW) control system installed in an F-8 aircraft. The full-time, full-authority system performs three-axis flight control computations, including stability and command augmentation, autopilot functions, failure detection and isolation, and self-test functions. Advanced control law experiments include an active flap mode for ride smoothing and maneuver drag reduction. This paper discusses research being conducted on computer synchronization, fault detection, fault isolation, and recovery from transient faults. The F-8 DFBW system has demonstrated immunity from nuisance fault declarations while quickly identifying truly faulty components.

Brown, S. R.↗

Comparative analysis of techniques for evaluating the effectiveness of aircraft computing systems

Performability analysis is a technique developed for evaluating the effectiveness of fault-tolerant computing systems in multiphase missions. Performability was evaluated for its accuracy, practical usefulness, and relative cost. The evaluation was performed by applying performability and the fault tree method to a set of sample problems ranging from simple to moderately complex. The problems involved as many as five outcomes, two to five mission phases, permanent faults, and some functional dependencies. Transient faults and software errors were not considered. A different analyst was responsible for each technique. Significantly more time and effort were required to learn performability analysis than the fault tree method. Performability is inherently as accurate as fault tree analysis. For the sample problems, fault trees were more practical and less time consuming to apply, while performability required less ingenuity and was more checkable. Performability offers some advantages for evaluating very complex problems.

Hitt, E. F.↗

The containment set approach to upsets in digital systems

An approach to the fault analysis of digital systems is proposed which combines faults, hardware, and software into one overall model. The model is useful for the consideration of intermittent/transient faults, and supports a new method, based on the concept of a containment set, for realizing transient fault tolerance without massive redundancy. The model also serves as the basis for a new approach to system fault tolerance evaluation and validation using a transition matrix defined in terms of the containment set. The application of upset theory to the design of transient fault-tolerant microprocessor controllers is discussed.

Glaser, R. E.↗

A Self-Stabilizing Byzantine-Fault-Tolerant Clock Synchronization Protocol

This report presents a rapid Byzantine-fault-tolerant self-stabilizing clock synchronization protocol that is independent of application-specific requirements. It is focused on clock synchronization of a system in the presence of Byzantine faults after the cause of any transient faults has dissipated. A model of this protocol is mechanically verified using the Symbolic Model Verifier (SMV) [SMV] where the entire state space is examined and proven to self-stabilize in the presence of one arbitrary faulty node. Instances of the protocol are proven to tolerate bursts of transient failures and deterministically converge with a linear convergence time with respect to the synchronization period. This protocol does not rely on assumptions about the initial state of the system other than the presence of sufficient number of good nodes. All timing measures of variables are based on the node s local clock, and no central clock or externally generated pulse is used. The Byzantine faulty behavior modeled here is a node with arbitrarily malicious behavior that is allowed to influence other nodes at every clock tick. The only constraint is that the interactions are restricted to defined interfaces.

Malekpour, Mahyar R.↗

Measurement and analysis of workload effects on fault latency in real-time systems

The authors demonstrate the need to address fault latency in highly reliable real-time control computer systems. It is noted that the effectiveness of all known recovery mechanisms is greatly reduced in the presence of multiple latent faults. The presence of multiple latent faults increases the possibility of multiple errors, which could result in coverage failure. The authors present experimental evidence indicating that the duration of fault latency is dependent on workload. A synthetic workload generator is used to vary the workload, and a hardware fault injector is applied to inject transient faults of varying durations. This method makes it possible to derive the distribution of fault latency duration. Experimental results obtained from the fault-tolerant multiprocessor at the NASA Airlab are presented and discussed.

Woodbury, Michael H.↗

Parameter Transient Behavior Analysis on Fault Tolerant Control System

In a fault tolerant control (FTC) system, a parameter varying FTC law is reconfigured based on fault parameters estimated by fault detection and isolation (FDI) modules. FDI modules require some time to detect fault occurrences in aero-vehicle dynamics. This paper illustrates analysis of a FTC system based on estimated fault parameter transient behavior which may include false fault detections during a short time interval. Using Lyapunov function analysis, the upper bound of an induced-L2 norm of the FTC system performance is calculated as a function of a fault detection time and the exponential decay rate of the Lyapunov function.

Belcastro, Christine↗

Redundant system reliability analysis

Computer Aided Redundant System Reliability Analysis (CARSARA) program facilitates reliability assessment of fault-tolerance reconfigurable systems. CARSRA accounts for influences from transient faults and is used to model wide range of redundancy management strategies.

Masreliez, C. J.↗

Formal design and verification of a reliable computing platform for real-time control. Phase 2: Results

The design and formal verification of the Reliable Computing Platform (RCP), a fault tolerant computing system for digital flight control applications is presented. The RCP uses N-Multiply Redundant (NMR) style redundancy to mask faults and internal majority voting to flush the effects of transient faults. The system is formally specified and verified using the Ehdm verification system. A major goal of this work is to provide the system with significant capability to withstand the effects of High Intensity Radiated Fields (HIRF).

Butler, Ricky W.↗

Formal design and verification of a reliable computing platform for real-time control (phase 3 results)

In this paper the design and formal verification of the lower levels of the Reliable Computing Platform (RCP), a fault-tolerant computing system for digital flight control applications, are presented. The RCP uses NMR-style redundancy to mask faults and internal majority voting to flush the effects of transient faults. Two new layers of the RCP hierarchy are introduced: the Minimal Voting refinement (DA_minv) of the Distributed Asynchronous (DA) model and the Local Executive (LE) Model. Both the DA_minv model and the LE model are specified formally and have been verified using the Ehdm verification system. All specifications and proofs are available electronically via the Internet using anonymous FTP or World Wide Web (WWW) access.

Butler, Ricky W.↗

Formal Techniques for Synchronized Fault-Tolerant Systems

We present the formal verification of synchronizing aspects of the Reliable Computing Platform (RCP), a fault-tolerant computing system for digital flight control applications. The RCP uses NMR-style redundancy to mask faults and internal majority voting to purge the effects of transient faults. The system design has been formally specified and verified using the EHDM verification system. Our formalization is based on an extended state machine model incorporating snapshots of local processors clocks.

DiVito, Ben L.↗

Modular DC circuit breaker with integrated energy storage for future DC networks

A T-breaker is an all-in-one solution for dc microgrid fault protection, power flow control, and power quality improvement. A T-breaker features a modular multilevel “T” structure with integrated energy storage devices. The two horizontal arms of the T-breaker realize fault current breaking, load voltage compensation, and power flow control; and the vertical arm of the T-breaker realizes shunt compensation. The configuration provides excellent voltage scalability and relaxes the requirements on the switching signal synchronization during fault transients. The local energy storage in sub-modules eases the fault energy dissipation requirement placed on the traditionally-adopted surge arrestors. The modular multilevel structure also offers immense control flexibility for all types of targeted functions of the provided T-breaker.

Wang, Jin↗

Determining diagnostic coverage for memory using redundant execution

Memory, used by a computer to store data, is generally prone to faults, including permanent faults (i.e. relating to a lifetime of the memory hardware), and also transient faults (i.e. relating to some external cause) which are otherwise known as soft errors. Since soft errors can change the state of the data in the memory and thus cause errors in applications reading and processing the data, there is a desire to characterize the degree of vulnerability of the memory to soft errors. In particular, once the vulnerability for a particular memory to soft errors has been characterized, cost/reliability trade-offs can be determined, or soft error detection mechanisms (e.g. parity) may be selectively employed for the memory. In some cases, memory faults can be diagnosed by redundant execution and a diagnostic coverage may be determined.

Bramley, Richard Gavin↗

Liveness as a factor to evaluate memory vulnerability to soft errors

Memory, used by a computer to store data, is generally prone to faults, including permanent faults (i.e. relating to a lifetime of the memory hardware), and also transient faults (i.e. relating to some external cause) which are otherwise known as soft errors. Since soft errors can change the state of the data in the memory and thus cause errors in applications reading and processing the data, there is a desire to characterize the degree of vulnerability of the memory to soft errors. In particular, once the vulnerability for a particular memory to soft errors has been characterized, cost/reliability trade-offs can be determined, or soft error detection mechanisms (e.g. parity) may be selectively employed for the memory. In some cases, memory faults can be diagnosed by redundant execution and a diagnostic coverage may be determined.

Bramley, Richard Gavin↗

FOCUS - An experimental environment for fault sensitivity analysis

FOCUS, a simulation environment for conducting fault-sensitivity analysis of chip-level designs, is described. The environment can be used to evaluate alternative design tactics at an early design stage. A range of user specified faults is automatically injected at runtime, and their propagation to the chip I/O pins is measured through the gate and higher levels. A number of techniques for fault-sensitivity analysis are proposed and implemented in the FOCUS environment. These include transient impact assessment on latch, pin and functional errors, external pin error distribution due to in-chip transients, charge-level sensitivity analysis, and error propagation models to depict the dynamic behavior of latch errors. A case study of the impact of transient faults on a microprocessor-based jet-engine controller is used to identify the critical fault propagation paths, the module most sensitive to fault propagation, and the module with the highest potential for causing external errors.

Choi, Gwan S.↗

Real-time fault detection and transient identification using extended Kalman filters - 254

In this paper, real-time fault detection and transient identification are studied with adaptive estimation methods, in particular parallel processing methods by implementing a bank of extended Kalman filters. Adaptive estimation is combined with probabilistic risk assessment to allow for real-time continuous monitoring of initiating events. The approach provides a probability of an initiating event happening. Real-time monitoring of initiating events can reduce labor demand. Each extended Kalman filter is configured to operate at a single configuration, either at normal operation or a faulted state. Fault detection is based on calculating a likelihood function for each extended Kalman filter to determine the posteriori conditional probability that the system configuration is the true configuration. The transient identification is determined by performing a multivariate statistical analysis on each extended Kalman filter to provide a posterior probability assessment that the reactor states and its dynamics are within the allowable limits. The probability distribution being outside the allowable limits indicate a transient has occurred. The combination of parallel processing methods with the multivariate statistical analysis for transient identification allows for the operator to perform transient identification with having a high level of certainty of the current system configuration. We demonstrate the real-time fault detection and transient identification on a simple reactor example to determine the reactor power, reactor temperature, and coolant temperature in the presence of various faults. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗