Utilizing multilevel models and reasoning for diagnosis of a complex electro-mechanical system

ABSTRACT

A multi-level system which utilizes both an evidential and a qualitative model for diagnosing fault symptoms in complex electro-mechanical systems is presented. The operation of both models, enhancement by a historical database, and the global control strategy are all discussed. In addition, the constraining of qualitative reasoning with information from the evidential session and the enhancement of the evidential model with information from the qualitative model is demonstrated.

REFERENCES

• 1: Ray Bareiss, "Proms: A Unified Approach to Concept Representation, Classification, and Learning", Technical Report CS-88-10, Department of Computer Science, Vanderbilt University, 1989.
• 2: Gautam Biswas , Kenneth A. Debelak , Kazuhiko Kawamura, Applications of qualitative modeling to knowledge-based risk assessment studies, Proceedings of the 2nd international conference on Industrial and engineering applications of artificial intelligence and expert systems, p.92-101, June 1989, Tullahoma, Tennessee, United States [doi>10.1145/66617.66630]
• 3: Gautam Biswas, William J. Hagins, and Kenneth A. Debelek, "Qualitative Modeling in Engineering Applications", Department of Computer Science, Vanderbilt University, 1989.
• 4: D G Bobrow, Qualitative reasoning about physical systems, Massachusetts Institute of Technology, Cambridge, MA, 1985
• 5: Richard R. Cantone, Frank J. Pipitone, W. Brent Lander, and Michael P. Marrone, "Model-based Probabilistic Reasoning for Electronics Troubleshooting", in Proceedings of the Eighth International Joint Conference on Artificial Intelligence, pp. 207-211, 1983.
• 6: B. Chandrasekaran and Sanjay Mittal, "Deep versus compiled knowledge approaches to diagnostic problemsolving", International Journal of Man-Machine Studies, vol. 19, no. 5, pp. 425-436, 1983.
• 7: William J. Clancey, "The Epistemology of a Rule-Based Expert System-a Framework for Explanation", Artificial Intelligence, vol. 20, pp. 215-251 , 1983.
• 8: William J Clancey, From Guidon to Neomycin and Heracles in twenty short lessons, AI Magazine, v.7 n.3, p.40-60, August 1986
• 9: Vasant Dhar , Harry E. Pople, Rule-based versus structure-based models for explaining and generating expert behavior, Communications of the ACM, v.30 n.6, p.542-555, June 1987 [doi>10.1145/214762.214773]
• 10: Randall Davis, "Reasoning from first principles in electronic troubleshooting", International Journal of Man-Machine Studies, vol. 19, no. 5, pp. 403-423, 1983.
• 11: 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]
• 12: Johan De Kleer , John Seely Brown, A qualitative physics based on confluences, Artificial Intelligence, v.24 n.1-3, p.7-83, Dec. 1984 [doi>10.1016/0004-3702(84)90037-7]
• 13: Johan de Kleer , John Seely Brown, Theories of causal ordering, Artificial Intelligence, v.29 n.1, p.33-61, July 1986 [doi>10.1016/0004-3702(86)90090-1]
• 14: Pamela K. Fink and John C. Lusth, "Expert Systems and Diagnostic Expertise in the Mechanical and Electrical Domains", IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-17, no. 3, pp. 340-349, 1987.
• 15: Kenneth D. Forbus, Qualitative process theory, Artificial Intelligence, v.24 n.1-3, p.85-168, Dec. 1984 [doi>10.1016/0004-3702(84)90038-9]
• 16: Kenneth D. Forbus, "Interpreting Observations of Physical Systems", IEEE Transactions on Systems, Man and Cybernetics, vol. 17, no. 3, pp. 350-359, 1987.
• 17: Ken Forbus, Intelligent computer-aided engineering, AI Magazine, v.9 n.3, p.23-36, September 1988
• 18: 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]
• 19: M.R. Herbert and G. H.Williams, "An initial evaluation of the detection and diagnosis of power plant faults using a deep knowledge representation of physical behavior", Expert Systems, vol. 4, no. 2, pp. 90-99, 1987.
• 20: Yumi Iwasaki , Herbert A. Simon, Causality in device behavior, Artificial Intelligence, v.29 n.1, p.3-32, July 1986 [doi>10.1016/0004-3702(86)90089-5]
• 21: Phyllis Koton, "Using a Case Memory to Integrate Case-Based and Causal Reasoning", in Proceedings of the Case-Based Reasoning Workshop-AAAI-88, Minneapolis-St. Paul, August, 1988.
• 22: Benjamin Kuipers, Commonsense reasoning about causality: deriving behavior from structure, Artificial Intelligence, v.24 n.1-3, p.169-203, Dec. 1984 [doi>10.1016/0004-3702(84)90039-0]
• 23: B J Kuipers, Qualitative simulation, Artificial Intelligence, v.29 n.3, p.289-338, Sept. 1986 [doi>10.1016/0004-3702(86)90073-1]
• 24: Robert Milne, "Strategies for Diagnosis", IEEE Transactions on Systems, Man, and Cybernectics, vol. SMC-17, no. 3, pp. 333-339 , 1987.
• 25: Michael J. Pazzani, "Failure-Driven Learning of Fault Diagnosis Heuristics", }EEE Transactions on Systems, Man, and Cybernetics, vol. SMC-17, no. 3, pp. 380- 394, 1987.
• 26: Frank Pipitone, The FIS electronics troubleshooting system, Computer, v.19 n.7, p.68-76, July 1986 [doi>10.1109/MC.1986.1663281]
• 27: Ethan A. Scarl, John R. Jamieson, and Carl i. Delaune, "Diagnosis and Sensor Validation through Knowledge of Structure and Function", IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-17, no. 3, pp. 360-368, 1987.
• 28: Jeff Shrager , Daniel S. Jordan , Thomas P. Moran , Gregor Kiczales , Daniel M. Russell, Issues in the pragmatics of qualitative modeling: lessons learned from a xerographics project, Communications of the ACM, v.30 n.12, p.1036-1047, Dec. 1987 [doi>10.1145/33447.33449]
• 29: John Smith and Gautam Biswas, "Multi-level representation and reasoning in diagnosis of complex, electro-mechanical domains", Technical Report CS-89- 01, Department of Computer Science, Vanderbilt University, 1989.
• 30: John Smith and Gautam Biswas, "Multilevel Models for Diagnosis of Complex Electro-Mechanical Systems", to appear, Proceedings of Applications of Artificial intelligence VII, Orlando, FL, March 1989.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.4 PERFORMANCE OF SYSTEMS
      Subjects: Modeling techniques

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

  J. Computer Applications
  J.7 COMPUTERS IN OTHER SYSTEMS
      Subjects: Industrial control

General Terms:
Design, Performance, Reliability