• Journal of Internet Computing and Services
• /
• v.9 no.5
• /
• pp.185-193
• /
• 2008

An MTBF(mean time between failures) of large scale parallel systems is known to be only an order of several hours, and large computations sometimes result in a waste of huge amount of CPU time, However. the MPI(Message Passing Interface), a de facto standard for message passing parallel programming, suggests no possibility to handle such a problem. In this paper, we propose an application-level fault tolerant computation system, purely on the basis of the current MPI standard without using any non-standard fault tolerant MPI library, that can be used for general scientific synchronous parallel computation.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.2
• /
• pp.204-210
• /
• 1988

The residue number system offers the possibility of high-speed operation and error detection/correction because of the separability of arithmetic operations on each digit. A compact residue arithmetic module named the self-checking pulse-train residue arithmetic circuit is effectively employed as the basic module, and an efficient error detection/correction algorithm in which error detection is performed in each basic module and error correction is performed based on the parallelism of residue arithmetic is also employed. In this case, the error correcting circuit is imposed in series to non-redundant system. This design method has an advantage of compact hardware. Following the proposed method, a 2nd-order recursive fault-tolerant digital filter is practically implemented, and its fault-tolerant ability is proved by noise injection testing.

• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3283-3292
• /
• 2022

Based on the Deep Q-Network(DQN) algorithm of reinforcement learning, an active fault-tolerance method with incremental action is proposed for the control system with sensor faults of the once-through steam generator(OTSG). In this paper, we first establish the OTSG model as the interaction environment for the agent of reinforcement learning. The reinforcement learning agent chooses an action according to the system state obtained by the pressure sensor, the incremental action can gradually approach the optimal strategy for the current fault, and then the agent updates the network by different rewards obtained in the interaction process. In this way, we can transform the active fault tolerant control process of the OTSG to the reinforcement learning agent's decision-making process. The comparison experiments compared with the traditional reinforcement learning algorithm(RL) with fixed strategies show that the active fault-tolerant controller designed in this paper can accurately and rapidly control under sensor faults so that the pressure of the OTSG can be stabilized near the set-point value, and the OTSG can run normally and stably.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.6
• /
• pp.1538-1545
• /
• 1998

System reliability has been a major concern since the beginning age of the electronic digital computers. One of the modest ways of increasing reliability is to design fault-tolerant system. This paper propose a construction mechanism of fault-tolerant system for the general graph topology. This system has several spare nodes. Up to date, fault-tolerant system design is applied only to loop and tree networks. But they are very limited cases. New algorithm of this paper tried to have a capability which can be applied to any kinds of topologies without such a many restriction. the algorithm consist of several steps : minimal diameter spaning tree extraction step, optimal node decision step, original connectivity restoration step and finally redundancy graph construction step.

• The Journal of Information Technology
• /
• v.9 no.4
• /
• pp.25-34
• /
• 2006

As most application programs are more sophisticated and are adopted the distributed object technology, the object based distributed design became widespread since it supports portability and reusability. The approaches for fault-tolerant distributed computing are categorized into the active replica mechanism for mission-critical application programs and the passive replica mechanism for non mission-critical ones, when fault-tolerant facilities are added on. Our paper introduces the pros and drawbacks of several approaches for the add-on low-overhead fault-tolerant services by the surveys and shows the results of experiments for bench-mark models in order to demonstrate their performance.

• Proceedings of the KSR Conference
• /
• 2002.05a
• /
• pp.530-534
• /
• 2002

This paper show serial communication method in order to design how to interface between fault tolerant systems with redundancy. Problem has been in the method that fault tolerant system had switched of serial data with common switching device. This problem degrade reliability in itself and total system which is interfaced with that serial communication system. So Arbitration module of serial communication which is suggested in this paper can improve the reliability using voter algorithm which fault is detected passively.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.4
• /
• pp.235-245
• /
• 2004

In this paper, fault tolerant mechanisms are presented for a servo manipulator system designed to operate in a hot cell. A hot cell is a sealed and shielded room to handle radioactive materials, and it is dangerous for people to work in the hot cell. So, remote operations are necessary to handle the radioactive materials in the hot cell. KAERI has developed a servo manipulator system to perform such remote operations. However, since electric components such as servo motors may fail by radiation, fault tolerant mechanisms have to be considered. For fault tolerance of the servo manipulator system, duplication mechanism increasing the reliability of the transport's driving motors and reconfiguration algorithm accommodating the slave's motor failure have been presented. The reconfiguration algorithm recovering the end effector's motion in spite of one motor's failure is based on control allocation redistributing redundant axes. The constrained optimization method and pseudo inverse method have been adopted for control allocation. Simulation examples and real test results have been presented to verify the Proposed methods.

• Journal of Power Electronics
• /
• v.6 no.1
• /
• pp.8-17
• /
• 2006

In this paper, we propose a fault-tolerant control system for the position control and vibration suppression of a flexible arm robot. The proposed control system has a strain gauge sensor signal observer based on a reaction force observer and detects a fault by monitoring an estimated error. In order to improve the estimation accuracy, the plant parameters included in the sensor signal observer are updated by using the strain gauge sensor signal in normal time through the adaptive law. After fault detection, the proposed control system exchanges the faulty sensor signal for the estimated one and switches to a fault mode controller so as to maintain the stability and the control performance. We confirmed the effectiveness of the proposed control system through several experiments.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.14 no.6
• /
• pp.34-42
• /
• 2006

As many systems depend on electronics, concern for fault tolerance is growing rapidly. For example, a car with its steering controlled by electronics and no mechanical linkage from steering wheel to front tires(steer-by-wire) should be fault tolerant because a failure can come without any warning and its effect is devastating. In order to make system fault tolerant, there has been a body of research mainly from aerospace field. This paper presents the structure of predictive smoothing voter that can filter out most erroneous values and noise. In addition, several numerical simulation results are given where the predictive smoothing voter outperforms well-known average and median voters.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.1
• /
• pp.126-134
• /
• 2008

As many systems depend on electronics, concern for fault tolerance is growing rapidly. For example, a car with its steering controlled by electronics and no mechanical linkage from steering wheel to front tires (steer-by-wire) should be fault tolerant because a failure can come without any warning and its effect is devastating. In order to make system fault tolerant, there has been a body of research mainly from aerospace field. This paper presents the structure of predictive hybrid redundancy that can remove most erroneous values. In addition, several numerical simulation results are given where the predictive hybrid redundancy outperforms wellknown average and median voters.