Structural approach to a system-level fault model
Thesis/Dissertation
·
OSTI ID:7245039
The widespread use of computers, both large and small, has led to an increase in the fault problem. This problem is most acute while the system is operating, because testing and fault diagnosis may not be possible during operation. One method of addressing this problem is to use the processing power of the system itself to enhance its ability to diagnose faults. System-level fault models provide a framework for addressing this problem. These models represent a system in terms of its constituent processing elements, its faults, the tests to identify the faults, and the relationship between the fault and the test outcomes. This work considers the system level faults model of Preparata, Metze, and Chien which envisions a multiple-computer system as a collection of processing elements and test links. The focus of the work is the relationship between the test-link structure and the system-diagnosis properties. Results include a test-link based method for partitioning the processing elements that provide both a new measure for comparing systems and an indication of the complexity of identifying the maximum diagnosability number of a system.
- Research Organization:
- Johns Hopkins Univ., Baltimore, MD (USA)
- OSTI ID:
- 7245039
- Country of Publication:
- United States
- Language:
- English
Similar Records
Complexity of system-level fault diagnosis and diagnosability
Diagnosability issues in multiprocessor systems
Fault diagnosis in computing networks
Thesis/Dissertation
·
Tue Dec 31 23:00:00 EST 1985
·
OSTI ID:6987373
Diagnosability issues in multiprocessor systems
Thesis/Dissertation
·
Sat Dec 31 23:00:00 EST 1988
·
OSTI ID:6046358
Fault diagnosis in computing networks
Thesis/Dissertation
·
Tue Dec 31 23:00:00 EST 1985
·
OSTI ID:6935908