A Model of the Operator’s Task in Diagnostic Problem Solving

  • Vijay Vasandani
  • T. Govindaraj


In supervisory control of complex dynamic systems a major part of the problem solving activity is concerned with fault diagnosis. Therefore, operator training for diagnostic problem solving is essential to ensure competent performance. Intelligent computer aids and operator associates can be very effective for training operators in a variety of domains. Development of such computer aids depends on the availability of suitable models of the operator’s task. The task model must incorporate the structure, functions, and behavior of the system in an appropriate form. This paper proposes a methodology for building a normative model of the operator’s task. The proposed model supports qualitative reasoning for schema instantiation based on qualitative values of the system state. The choice of qualitative reasoning makes the model consistent with how human operators function while diagnosing faults. The model uses level of abstraction inherent in the dynamic systems to decompose the operator’s fault diagnosis task into a hierarchy of functions. An application of the model to an existing marine power plant simulator is also presented.


Solution Space Fault Diagnosis Micro Model Declarative Knowledge Complex Dynamic System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Clancey, W. J., Shorliffe, E. H., and Buchanan, B. G., 1979, Intelligent Computer-Aided Instruction for Medical Diagnosis, Proceedings of the Third Annual Symposium on Computer Applications in Medical Computing, Silver Springs, MD, pp. 175–183.Google Scholar
  2. de Kleer, J., and Brown, J. S., 1981, Mental Models of Physical Systems and Their Acquisition, Cognitive Skills and Their Acquisition, Anderson, John R., ed., Lawrence Erlbaum Associates, pp. 285–309.Google Scholar
  3. de Kleer, J., and Brown, J. W., 1984, A Qualitative Physics Based on Confluences, Artificial Intelligence, Vol. 24, No. 1–3, pp. 7–83.CrossRefGoogle Scholar
  4. Forbus, K. D., 1984, Qualitative Process Theory, Artificial Intelligence, Vol. 24, No. 1–3, pp. 85–168.CrossRefGoogle Scholar
  5. Govindaraj, T., Su Yuan-Liang, D., 1988, A Model of Fault Diagnosis Performance on Expert Marine Engineers, International Journal of Man-Machine Studies, to appear.Google Scholar
  6. Govindaraj, T., 1987, Qualitative Approximation Methodology for Modeling and Simulation of Large Dynamic Systems: Applications to a Marine Steam Powerplant, IEEE Transactions on Systems, Man, and Cybernetics, Vol. SMC-17, pp. 937–955.Google Scholar
  7. Kolodner, J. L., 1983, Maintaining Organization in a Dynamic Long Term Memory, Cognitive Science, Vol. 7, No. 4, pp. 243–280.CrossRefGoogle Scholar
  8. Kolodner, J. L., 1983, Reconstructive Memory, Cognitive Science, Vol. 7, No. 4, pp. 281–328.CrossRefGoogle Scholar
  9. Kolodner, J. L., and Kolodner, R. M., 1984, An Algorithm for Diagnosis Based on Analysis of Previous Cases, Experience in Problem Solving: A Trilogy of Papers, GIT-ICS, 84/16, School of Information and Computer Science, Georgia Institute of Technology.Google Scholar
  10. Kuipers, B., 1984, Commonsense Reasoning about Causality: Deriving Behavior from Structure, Artificial Intelligence, Vol. 24, No. 1–3, pp. 169–203.CrossRefGoogle Scholar
  11. Kuipers, B., 1986, Qualitative Simulation, Artificial Intelligence, Vol. 29, No. 1–3, pp. 289–338.MathSciNetMATHCrossRefGoogle Scholar
  12. Kuipers, B., and Kassirer, J. P., 1984, Causal Reasoning in Medicine: Analysis of a Protocol, Cognitive Science, Vol. 8, No. 4, pp. 363–385.CrossRefGoogle Scholar
  13. Rasmussen, J., 1981, Models of Mental Strategies in Process Plant Diagnosis, Human Detection and Diagnosis of System Failures, Rasmussen, J., and Rouse, W. B., ed., Plenum Press, New York.Google Scholar
  14. Rasmussen, J., 1985, The Role of Hierarchical Knowledge Representation in Decision Making and System Management, IEEE Transactions on Systems, Man, and Cybernetics, Vol. SMC-15, No. 2, pp. 234–243.Google Scholar
  15. Rasmussen, J., 1986, Information Processing and Human Machine Interaction: An Approach to Cognitive Engineering, North-Holland, New York.Google Scholar
  16. Rieger, C., 1975, The Commonsense Algorithm as a Basis for Computer Models of Human Memory, Inference, Belief, and Contextual Language Comprehension, Proceedings of the Conference on Theoretical Issues in Natural Language Processing, Cambridge, MA, pp. 180–195.Google Scholar
  17. Rieger, C., and Grinberg, M., 1977, The Declarative Representation and Procedural Simulation of Causality in Physical Mechanisms, Proceedings of the Fifth International Joint Conference in Artificial Intelligence, Cambridge, Mass.Google Scholar
  18. Rouse, W. G., and Hunt, R. M., 1984, Human Problem Solving in Fault Diagnosis Tasks, Advances in Man-Machine Systems Research, Rouse, W. B., ed., JAI Press, Vol. 1, pp. 195–222.Google Scholar
  19. Rubin, K. S., Mitchell, C. M., and Jones, P. M., 1988, Using a Blackboard Architecture for Dynamic Intent Inferencing, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 3, pp. 1150–1153.Google Scholar
  20. Steven, A., 1982, Quantitative and Qualitative Simulation in Portable Training Devices,Bolt Beranek and Newman Inc., for National Academy of Sciences.Google Scholar
  21. Towne, D. M., and Munro, A., 1988, Intelligent Maintenance Training System, Intelligent Tutoring Systems: Lessons Learned, Psotka, Joseph, Massey, L. Dan, and Mutter, Sharon A., eds., Lawrence Erlbaum Associates Publishers, Hillsdale, NY.Google Scholar

Copyright information

© Plenum Press, New York 1990

Authors and Affiliations

  • Vijay Vasandani
    • 1
  • T. Govindaraj
    • 1
  1. 1.Center for Human-Machine Systems Research School of Industrial and Systems EngineeringGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations