Qualitative reasoning in electronic fault diagnosis

  • Authors:
  • Padraig Cunningham;Michael Brady

  • Affiliations:
  • Dept. of Computer Science, Trinity College Dublin;Dept. of Computer Science, Trinity College Dublin

  • Venue:
  • IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 1
  • Year:
  • 1987

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes some work in progress aimed at developing an expert system for fault diagnosis on switching mode power supplies. The system being developed is designed to interface with some existing automatic test equipment. Results of tests from this test equipment are the main input to the expert system. Another input is information about signals at various points in the circuit under test. This information is supplied by the user. Both deep and shallow knowledge are used in the diagnostic process. The system is developed in KEE from Intellicorp so the main knowledge representations are rules and frames. The deep knowledge in the system is represented loosely as qualitative reasoning as this is considered to be the way that technicians reason about the causal interactions in a circuit.