Intelligent troubleshooting of complex machinery

ABSTRACT

Proper maintenance and troubleshooting of complex mechanical equipment is a difficult task. A large amount of information, such as sensor data and previous repair actions, is available but infrequently used for interpretation by technical staff which is continually losing expertise due to turnover. Well structured knowledge-based systems can provide effective techniques for assisting in this task. A set of functional requirements for a troubleshooting advisory system is presented. Domain knowledge should be structured to make the system's operation more explicit to the knowledge engineer or end user. Reasoning must be carried out by navigating through a diagnostic network constructed from maintenance procedures and heuristics. The generic and modular approach used has the distinct advantage of making the task of creating diagnostic knowledge-bases easier. In addition, the large amount of information which is normally disseminated through many maintenance manuals can be easily accessible in a single computer environment, which in itself represents considerable savings in time for a mechanic. A generic system, called JETA (Jet Engine Troubleshooting Assistant) has been developed within this framework. In particular, JETA has been applied to troubleshoot the General Electric J85-CAN-15 jet engine that powers the CF-5 trainer fighters used by the Canadian Air Force.

REFERENCES

• 1: K.H. Abbott, Robust Operative Diagnosis as Problem Solving in a Hypothesis Space, Proceedings of the AAAI Conference, pp. 369-374, 1988.
• 2: Suhayya Abu-Hakima , Philippe Davidson , Mike Halasz , Sieu Phan, Jet engine technical advisor (JETA), Proceedings of the 2nd international conference on Industrial and engineering applications of artificial intelligence and expert systems, p.154-160, June 1989, Tullahoma, Tennessee, United States [doi>10.1145/66617.66637]
• 3: Suhayya Abu-Hakima , Franz Oppacher, RATIONALE: Reasoning by Explaining, Proceedings of the Fourth International Conference on Data Engineering, p.258-265, February 01-05, 1988
• 4: D.R. Antonelli, A Maintenance and Diagnostic Information System, Proceedings of the Air Force Workshop on AI Applications for Integrated Diagnostics, Boulder, Co., pp. 268- 275, 1986.
• 5: J. Arellano and M. Schwarzblat, A New Approach for the Development of Diagnostic Expert Systems, Transactions of the American Nuclear Society Sixth Pacific Basin Nuclear Conference, pp. 816-822, 1987.
• 6: P.P. Bonissone and H.E. Johnson, Jr. DELTA: An Expert System for Diesel Electric Locomotive Repair, Proceedings of the Joint Services Workshop, AI in Maintenance, Boulder, Co., October 4-6, pp. 391-405, 1983.
• 7: B. Chandrasekaran, Generic Tasks as Building Blocks for Knowledge-Based Systems: the Diagnosis and Routine Design Examples, The Knowledge Engineering Review, Vol. 3, no. 3, pp. 183-210, September 1988.
• 8: B. Chandrasekaran and S. Mittal, Deep versus Compiled Knowledge Approaches to Diagnostic Problem-Solving, Proceedings of the National Conference on Artificial Intelligence, 1982, pp. 349-354.
• 9: M.B. Cooper and A. L. Kidd, A Man-Machine Interface for an Expert System, British Teleeom Technology Journal, vol. 3, no. 1, pp. 112-115, January 1985.
• 10: Wei-Han Chu, Generic expert system shell for diagnostic reasoning, Proceedings of the 1st international conference on Industrial and engineering applications of artificial intelligence and expert systems, p.7-12, June 1988, Tullahoma, Tennessee, United States [doi>10.1145/51909.51910]
• 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: A. Dionisi Vici, F. Giovannini, F. Malabocchia and L. Sisto, Deep and Shallow Knowledge in an Expert System Architecture, CSELT Technical reports, Vol. XIV, no. 1, pp. 15-20, February 1986.
• 13: Richard Fikes , Tom Kehler, The role of frame-based representation in reasoning, Communications of the ACM, v.28 n.9, p.904-920, Sept. 1985 [doi>10.1145/4284.4285]
• 14: P. K. Fink and J. C. Lusth, Expert Systems and Diagnostic Expertise in the Mechanical Domains, IEEE Transactions on Systems, Man and Cybernetics, Vol. SMC-17, no. 3, pp. 340- 349, May/June 1987.
• 15: T.P. Gall, C.R. Marling, D.A. Moyer, C.K. Wu and K.J. Daniel, HypertextiExpert System for Machine Diagnostics and Mechanic Training," Proceedings of the 1988 AS ME International Computers in Engineering Conference and Exhibit, pp. 325-330, 1988.
• 16: H. Geffner and J. Pearl, Distributed Diagnosis of Systems with Multiple Faults, Proceedings of the 3rd IEEE Conference on AI Applications, pp. 156-162, 1987.
• 17: M.R. Genesereth, Diagnosis Using Hierarchical Design Models, Proceedings of the AAAI Conference, 1982, pp. 278-283.
• 18: T.J. Grant, Maintenance Engineering Management Applications of Artificial Intelligence, Proceedings of the 1st International Conference on Applications of AI in Engineering Problems, pp. 1097-1121, 1986.
• 19: P.J. Hayes, Some Problems and Non-Problems in Representation Theory, Reading in Knowledge Representation, edited by R.J. Brachrnan and H.J. Levesque, Morgan Kaufmann Publishers, Inc., Los Altos, Ca., pp. 3-22.
• 20: M. Hofman, J. Caviedes, J. Bourne, G. Beale and A. Brodersen, Building Expert Systems for Repair Domains, Expert Systems, vol.3, no.l, pp.4-12, Jan. 1986.
• 21: $.R. Hogley and A.R. Korncoff, AI in Engineering: A Revolutionary Change, Proceedings of the 1st Int'l Conference on Applications of AI in Engineering Problems, pp. 1155- 1160, 1986.
• 22: C.I. Kalme, A Rule Based Architecture for Diagnosis, Proceedings of the 3rd Annual AI and Advanced Computer Technology Conference, pp. 524-535, 1987.
• 23: S.D.S.R. Kararnchetty. HARVEST- An Expert System, Proceedings of the ASME International Computers in Engineering Conf. and Exhibit, 1985, pp. 243-248.
• 24: G. Karel and M. Kenner. KLUE: A Diagnostic Expert System Tool for Manufacturing, Proceedings of the 1988 ASME International Computers in Engineering Conference and Exhibition, pp. 331-336, 1988.
• 25: C.B. Meher-Homji, A Feasibility Study of the Application of Artificial Intelligence Techniques for Turbomachinery Diagnostics, Proceedings of the Gas Turbine Conference and Exhibit. pp. 1-8, 1985.
• 26: B.P. Millett and R.K. Maby, A Hybrid Knowledge-Based Approach to AH-64A Fault Isolation, presented at the American Helicopter Society National Specialists' Meeting on Automation Applications for Rotorcraft, Atlanta, Georgia, April 1988.
• 27: D. W. Papenhausen and B. L. Hadley, An Artificial intelligence Approach to Avionics Maintenance, Proceedings of the Air Force Workshop on AI Applications for Integrated Diagnostics, Boulder, Co., pp. 208-217, 1986.
• 28: C.K. Picketing, K.T. Wescourt and C.A. Powell, A Generic Architecture for Knowledge-Based Equipment Fault Diagnosis, Proceedings of the Air Force Workshop on AI Applications for Integrated Diagnostics, pp. 425-439, 1986.
• 29: D.W. Simmons, T.P. Hamilton and R.G. Carlson, Helix: A Causal Model-Based Diagnostic Expert System, $oumal of the American Helicopter Society, vol. 32, no. 1, pp. 19-25, January 1987.
• 30: S.J. Stolfo, Knowledge Engineering: Theory and Practice, Proceedings of the IEEE Computer Society Conference on Trends and Applications., pp. 97-104, 1983.
• 31: J.D. Smart and J.W. Vinson, TURBOMAC: An Expert System to Aid in the Diagnosis of Causes of Vibration-Producing Problems in Large Turbomachinery, Proceedings of the ASME Int'l Computers in Engineering Conference and Exhibition, Boston, Mass., pp. 319-325, 1985.
• 32: D.W. Towne, A Generic Expert Diagnostician, Proceedings of the Air Force Workshop on AI Applications for Integrated Diagnostics, pp. 218-237, 1986.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Industrial automation

Additional Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.4 Knowledge Representation Formalisms and Methods
          Subjects: Representations (procedural and rule-based)
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

General Terms:
Design, Human Factors