Combined model expert system for electronics fault diagnosis

ABSTRACT

Two main approaches are used for building diagnostic expert systems. These approaches are the shallow knowledge approach or the “fault model” and the deep knowledge approach or the “structural & functional model”. Fault model systems capture heuristics and expertise, whereas functional model system lacks such heuristics. Therefore, systems based on the first model perform diagnostic task faster and with much less user actions. On the other hand, systems based on the second model can handle hard problems and new situations whereas fault model systems deal only with the most common problem cases. This paper introduces an expert system for electronic devices diagnosis based on combining techniques from both the fault model and the functional model. It captures the advantages and overcomes the difficulties associated with each of these models when used separately.

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.2 PHYSICAL SCIENCES AND ENGINEERING
      Subjects: Electronics

Additional Classification:
  B. Hardware
  B.7 INTEGRATED CIRCUITS

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

General Terms:
Design, Reliability