Model-based fault diagnosis: knowledge acquisition and system design

ABSTRACT

Within this paper a model-based approach for knowledge-based diagnosis-systems is discussed. The model is derived from the fault recognition and fault searching techniques used by maintenance experts in general. The presented model has implications on the knowledge acquisition method in a way that only such data that are usually known to the maintenance expert have to be gathered and interlinked. This means that knowledge acquisition has only to deal with a knowledge source that can be prestructured. The model for knowledge-based diagnosis-systems and the knowledge acquisition method has been successfully used to develop diagnosis systems for a SMD-insertion machine and an extrusion machine. Time needed for knowledge acquistion has been reduced.

REFERENCES

• BEN 88: M. Ben-Bassat, D. Ben-Arie, I. Beniaminy, J. Cheifetz, M. Klinger: AITF_3T: A Real Life Expert System for Electronic Troubleshooring. Proc. 4th Conference on Artificial Intelligence Applications, San Diego 1988.
• BUB 88: S.C. Bublin, R.L. Kashyap: CONSOLIDATE: Merging Heuristic Classification with Causal Reasoning in Maschine Fault Diagnosis. Proc. 4th Conference on Artificial Intelligen ce Applications, San Diego 1988.
• BUC 84: B.G. Buchanan, E.H. Shortliffe: Rule-Based Expert Systems. Addison-Wesley Publishing Company, 1984
• DAV 84: Randall Davis, Diagnostic reasoning based on structure and behavior, Artificial Intelligence, v.24 n.1-3, p.347-410, Dec. 1984 [doi>10.1016/0004-3702(84)90042-0]
• GES 84: Michael R. Genesereth, The use of design descriptions in automated diagnosis, Artificial Intelligence, v.24 n.1-3, p.411-436, Dec. 1984 [doi>10.1016/0004-3702(84)90043-2]
• KAH 87: G.S. Kahn, A. Kepner, J. Pepper: TEST: A Model-Driven Application Shell. Proc, AAAI-87, pp 814-818.
• KER 86: E. T. Keravnou , L. Johnson, Competent expert systems: a case study in fault diagnosis, McGraw-Hill, Inc., New York, NY, 1986
• MAT 87: R. Mathonet, H. van Cotthem, L. Vanryckeg hem: DANTES: An Expert System for Real- Time Network Troubleshooting. 7th Int. Workshop Expert Systems & Their Applications, Avignon 1987, pp 468-488.
• NGU 87: Tin A Nguyen , Walton Perkin , Thomas J Laffey , Deanne Pecora, Knowledge base verification, AI Magazine, v.8 n.2, p.69-75, Summer 1987
• NOL 87: S. Nold, R. Isermann, B. Freyermuth: A Multilevel Knowledge-Based Concept for the Supervision of Technical Processes. 5th International Symposium on Technical Diagnostics, Paderborn 1987, pp. 145-152.
• PIP 86: Frank Pipitone, The FIS electronics troubleshooting system, Computer, v.19 n.7, p.68-76, July 1986 [doi>10.1109/MC.1986.1663281]
• SHA 86: S.C. Shapiro, S.N. Srihari, M. Taie, J.Geller: VMES: A Network Based Versatile Mainte nance Expert System. 1s Int. Conference Applications of Artificial Intelligence in Engineering Problems, 1986.
• SCH 85: M. Schwarzblat, J. Arellano: An Expert Diagnostic and Prediction System Based on Minimal Cut Set Techniques. Proc. 2nd Conference on Artificial Intelligen ce Applications, Miami 1985.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Induction

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Knowledge acquisition

General Terms:
Design, Theory