Diagnosing Multiple Faults in SSM/PMAD

Abstract

This paper discusses multiple fault diagnosis for SSM/FMAD using the Knowledge Management Design System as applied to the SSM/PMAD domain (KNOMAD-SSM/PMAD). KNOMAD-SSM/PMAD provides a powerful facility for knowledge representation and reasoning which has been used to build the second generation of FRAMES (Fault Recovery and Management Expert System). FRAMES now handles the diagnosis of multiple faults as well as providing support for a more powerful interface for user interaction during autonomous operation. There are two types of multiple fault diagnosis handled in FRAMES. The first type diagnoses hard faults, soft faults, and incipient faults simultaneously. The second diagnoses multiple hard faults which happen in close proximity in time to one another. Multiple fault diagnosis in FRAMES is performed using a rule-based approach. This rule-based approach, enabled by the KNOMAD-SSM/PMAD System, has proven to be very powerful. The particular rule-based algorithms will be discussed in some detail. The paper will review the problems of multiple fault diagnosis and focus on the multiple fault diagnosis problem particular to of SSM/PMAD. The rule-based solution to this problem in FRAMES will be described as well as the enabling framework of KNOMAD-SSM/PMAD. Finally, levels of autonomy will be discussed, focusing on the approach taken in FRAMES for providing at least three levels of autonomy: Complete autonomy, partial autonomy, and complete manual mode.