AN INTEGRATION OF CASE-BASED AND MODEL-BASED REASONING AND ITS APPLICATION TO PHYSICAL SYSTEM FAULTS

Current Case-Based Reasoning (CBR) systems have been used in planning, engineering design, and memory organization. There has been only a limited amount of work, however, in the area of reasoning about physical systems. This type of reasoning is a difficult task, and every attempt to automate the process must overcome the problems of modeling normal behavior, diagnosing faults, and predicting future behavior. We maintain that the ability of a CBR program to reason about physical systems can be significantly enhanced by the addition to the CBR program of a model of the physical system to describe the system's structural, functional, and causal behavior. We are in the process of designing and implementing a prototypical CBR/MBR system for dealing with the faults of physical systems. The system is being tested in the domain of in-flight fault diagnosis and prognosis of aviation subsystems, particularly jet engines.