The Fault Tolerant Computer System of The Brazilian Scientific Application Microsatellites

نویسنده

  • Alderico Rodrigues
چکیده

A fault tolerant computer system has been conceived to become the standard framework that will be utilized by the future family of Brazilian small satellites for scientific applications. Based on the proposed standard, a computer system with three processing modules was developed for the First Brazilian Scientific Application Microsatellite (SACI-1 Satélite Científico). Each processing module is based on a 32bit Transputer that is connected to the two other processing modules, as well as, to the satellite subsystems through a 10 Mbit serial bus. A set of fault handling mechanisms is implemented in the computer system which enable it to tolerate a single fault and most of the double faults. Four switches controlled by a watch-dog-timer are used in each processing module to allow the serial links to bypass the processor when a catastrophic fault is detected in that module. This technique allows the computer system to degrade gracefully to two processing modules, or even to one processing module. The computer system is designed to execute all on board tasks with three or two processing modules and the essential tasks with one processing module. A large mass memory that uses memory chips not qualified for space was implemented in each processing module. Since these memory chips are susceptible to cosmic radiation, a special circuit was used to detect latchups and to power off the memory chip for 10 msec when a latchup is detected. Additionally, these memory chips present a high single event upset (SEU) rate, when in orbit, producing single, double and, less frequently, triples errors in a memory word. To overcome this problem, the scientific experiment data frames are coded before being stored in the mass memory using an error correction code. The on board software was organized around a set of processes that communicate among themselves through a routing process. The essential software was formally specified and its correctness certified using the CSP-Z formalism. ------------------(1) PhD in Computer Science UCLA 1982 Professor and Researcher in Computer Science at Universidade do Vale do Paraíba E-mail: [email protected] (2) PhD in Computer Engineering University of Michigan 1974 Professor and Researcher in Computer Science at Universidade do Vale do Paraíba E-Mail: [email protected]

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Voting Algorithm Based on Adaptive Neuro Fuzzy Inference System for Fault Tolerant Systems

some applications are critical and must designed Fault Tolerant System. Usually Voting Algorithm is one of the principle elements of a Fault Tolerant System. Two kinds of voting algorithm are used in most applications, they are majority voting algorithm and weighted average algorithm these algorithms have some problems. Majority confronts with the problem of threshold limits and voter of weight...

متن کامل

Voting Algorithm Based on Adaptive Neuro Fuzzy Inference System for Fault Tolerant Systems

some applications are critical and must designed Fault Tolerant System. Usually Voting Algorithm is one of the principle elements of a Fault Tolerant System. Two kinds of voting algorithm are used in most applications, they are majority voting algorithm and weighted average algorithm these algorithms have some problems. Majority confronts with the problem of threshold limits and voter of weight...

متن کامل

A Microprocessor-Based Hybrid Duplex Fault-Tolerant System

Reliability is one of the fundamental considerations in the design of industrial control equipment. The microprocessor-based Hybrid Duplex fault-tolerant System (HDS) proposed in this paper has high reliability to meet this demand although its hardware structure is simple. The hardware configuration of HDS and the fault tolerance of this system are described. The switching control strategies in...

متن کامل

Fault Tolerant DNA Computing Based on ‎Digital Microfluidic Biochips

   Historically, DNA molecules have been known as the building blocks of life, later on in 1994, Leonard Adelman introduced a technique to utilize DNA molecules for a new kind of computation. According to the massive parallelism, huge storage capacity and the ability of using the DNA molecules inside the living tissue, this type of computation is applied in many application areas such as me...

متن کامل

On Feasibility of Adaptive Level Hardware Evolution for Emergent Fault Tolerant Communication

A permanent physical fault in communication lines usually leads to a failure. The feasibility of evolution of a self organized communication is studied in this paper to defeat this problem. In this case a communication protocol may emerge between blocks and also can adapt itself to environmental changes like physical faults and defects. In spite of faults, blocks may continue to function since ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002