Building and Maintaining a Large Knowledge-Based System from a ‘Knowledge Level’ Perspective: the DIVA Experiment

  • Jean-Marc David
  • Jean-Paul Krivine
  • Benoit Ricard

Abstract

Designing knowledge-based systems from a knowledge level perspective is becoming an increasingly widespread practice. Expected benefits from using this approach have been extensively described in literature. The purpose of this paper is to throw light on actual benefits based on a project aiming to design a diagnostic system for rotating machinery: DIVA.

DIVA is a large and complex application. The project started several years ago and is now in an advanced state of industrialisation. Moreover, it has addressed most of the issues related to second generation expert systems: knowledge acquisition, explanation of reasoning and maintainability.

For each of these issues, we will discuss and demonstrate practical benefits of the chosen approach.

Keywords

Steam Brittleness Coherence Neomycin Bonnet 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Aikins J.: “Prototypical Knowledge for Expert Systems”; Artificial Intelligence 20 (2); 1983.Google Scholar
  2. [2]
    Bannister R., Moore M.: “General Rotating Machinery Expert System”; Expert Systems 86; Brighton, UK; December 1986.Google Scholar
  3. [3]
    Chandrasekaran B., Johnson T.: “Generic Tasks and Task Structures: history, critique and new directions”; in Second Generation Expert Systems; JM. David, JP. Krivine & R. Simmons (Eds); Springer-Verlag, 1993.Google Scholar
  4. [4]
    Chandrasekaran B.: “Towards a Functional Architecture for Intelligence based on Generic Information Processing Tasks”; 10th IJCAI; Milano, Italy; 1987.Google Scholar
  5. [5]
    Chandrasekaran B.: “Towards a Taxonomy of Problem-Solving Types”; AI Magazine 1983.Google Scholar
  6. [6]
    Chandrasekaran B.: “Decomposition of domain knowledge into knowledge sources: the MDX approach”; Fourth CSCSI conference, Canada, May 1982.Google Scholar
  7. [7]
    Chevalier R., Ricard B., Morel J.: “Validation of Diva, a turbine-generator diagnosis expert system”, International Joint Power Generation Conference, San Diego (USA), 1991.Google Scholar
  8. [8]
    Clancey W.: “From GUIDON to NEOMYCIN and HERACLES in Twenty Short Lessons”; AI Magazine, Summer 1986.Google Scholar
  9. [9]
    Clancey W., Letsinger R.: “NEOMYCIN: Reconfiguring a rule-based expert system for application to teaching”; 7th IJCAI; Vancouver, Canada; 1981.Google Scholar
  10. [10]
    Clapis A., Gallanti M., Stefanini A.: “Sistemi Esperti nella diagnostica di impianto: un’applicazione sperimentale” (in Italian); Automazione E Strumentazione; March 1984.Google Scholar
  11. [11]
    David J-M., Krivine J-P., Simmons R.: “Second Generation Experts Systems; a step forward in knowledge engineering”; in Second Generation Expert Systems; JM. David, JP. Krivine & R. Simmons (Eds); Springer-Verlag, 1993.Google Scholar
  12. [12]
    David J-M., Krivine J-P.: “Explaining Reasoning from Knowledge level Models”; European Conference on Artificial Intelligence (ECAI-90), 1990.Google Scholar
  13. [13]
    David J-M., Krivine J-P.: “Augmenting Experience-Based Diagnosis with Causal Reasoning”; Applied AI Journal, Special Issue on Causal Modelling (Hemisphere Publ.); 1989. also in: “Causal AI Models: steps towards applications” (Hemisphere Publ.).Google Scholar
  14. [14]
    David J-M., Krivine J-P.: “Designing KBS within Functional Architectures: the DIVA experiment”; 5th IEEE Conf. on AI Applications; Miami, FL; 1989.Google Scholar
  15. [15]
    David J-M.: “Functional Architectures and the Generic Task Approach”; the Knowledge Engineering Review, vol. 3 (3); 1988.Google Scholar
  16. [16]
    David J-M., Krivine J-P.: “Acquisition of Expert Knowledge from Prototypical Situations” (in French); 8th International Workshop on Expert Systems and their Applications; Avignon, France; May 1988.Google Scholar
  17. [17]
    David J-M., Krivine J-P.: “Using Prototypes in a Diagnosis Expert System: the DIVA Project” (in French); 7th International Workshop on Expert Systems and their Applications; Avignon, France; May 1987.Google Scholar
  18. [18]
    David J-M., Krivine J-P.: “What Happened? Causal Reasoning in DIVA”; First European Workshop on Fault Diagnostics; Rhodes, Greece; August 1986.Google Scholar
  19. [19]
    Davis R.: “Expert Systems; where are we and where do we go from here”; AI Magazine, 1982.Google Scholar
  20. [20]
    Finn G., Hall J.: “An Expert System for Rotating Equipment Vibration Diagnosis”; EPRI Seminar; Boston, MA; May 1987.Google Scholar
  21. [21]
    Hasling D., Clancey W., Renneis G.: “Strategic explanations for a diagnostic consultation system”; International Man-Machine Studies 20; 1984.Google Scholar
  22. [22]
    Korteniemi A.: “An expert system for fault diagnostics of rotating machines”, 2nd symposium on Expert Systems Applications to Power Systems, Seattle, Wash., USA, July 17–20, 1989.Google Scholar
  23. [23]
    Mazalerat J-M., Morel J., Puyal C., Monnier B., Zwingelstein G., Legaud P.: “PSAD, An integrated tool for global vibratory and acoustic surveillance of EDF nuclear plants in the near future”. SMORN 6 (Specialist Meeting On Reactor Noise), Gatlinburg, USA, May 19–24, 1991.Google Scholar
  24. [24]
    Musen M.: “An overview of knowledge acquisition”; in Second Generation Expert Systems, JM. David, JP. Krivine and R. Simmons (Eds); Springer Verlag; 1993.Google Scholar
  25. [25]
    Musen M. et al.: “Use of a domain model to drive an interactive knowledge eliciting tool”; International Journal of Man-Machine Studies (26); 1987.Google Scholar
  26. [26]
    Milne R.: “Artificial Intelligence for Rotating Machinery Monitoring”; 12th IMACS World Congress; Paris; July 1988.Google Scholar
  27. [27]
    Newell A.: “The Knowledge Level”; Artificial Intelligence, 1982.Google Scholar
  28. [28]
    Osborne R.: “Online Artificial Intelligence-Based Turbine Generator Diagnostics”; AI Magazine; fall 1986.Google Scholar
  29. [29]
    Rademakers P., Vanwelkenhuysen J.: “Generic Models and their Support in Modeling Problem Solving Behavior”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar
  30. [30]
    Reinders M., Vinkhuyzen E., Voss A., Akkermans H., Balder J., Bartsch-Spörl B., Bredeweg B., Drouven U., van Harmelen F., Karbach W., Karssen Z., Schreiber G. and Wielinga B.; “A conceptual Modelling framework for Knowledge level Reflection”; AI-Communications, Vol 4, n°2/3, 1991.Google Scholar
  31. [31]
    Ricard B., Chevalier R., Bonnet J-C., Tiarri J-P.: “Test and validation of DIVA, a turbine-generator diagnosis expert system”; Advanced Information Processing in Automatic Control (AJPAC 89), IFAC/IMACS/IFORS, Nancy (France), 1989.Google Scholar
  32. [32]
    Ricard B., Monnier B., Morel J., David J-M., Krivine J-P., Tiarri J-P.: “Overview of DIVA: an expert system for turbine-generator diagnosis”; American Nuclear Society Conference on Artificial Intelligence and Other Innovative Computer Applications in the Nuclear Industry; Snowbird, Utah; 1987.Google Scholar
  33. [33]
    Skatteboe R., Lihvod E., Hystad R.: “DIAMON: a Knowledge-Based System for Fault Diagnosis and Maintenance Planning for Rotating Machinery”; 6th International Conference on Expert Systems and their Applications; Avignon, France; May 1986.Google Scholar
  34. [34]
    Soloway E., Bachant J., Jensen K.: “Assessing the Maintainability of XCON-in-RIME: Coping with the Problems of a VERY Large Rule-Base”; Proc. of the National Conference on AI, Seattle, Washington; July 13–17, 1987.Google Scholar
  35. [35]
    Steels L.: “The Componential Framework and its Role in Reusability”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar
  36. [36]
    Steels L.: “Second Generation Expert Systems”; Future Generation in Computer Systems, (1) 4; 1985.Google Scholar
  37. [37]
    Sticklen J., Wallingford E.: “On The Relationship between Knowledge-Based Systems Theory and Application Programs: Leveraging Task Specific Approaches”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar
  38. [38]
    Stuart J., Winson J.: “Turbomac: an expert system to aid in the diagnosis of cause of vibration-producing problems in large turbomachinery”; Radian Technical Report; August 1985.Google Scholar
  39. [39]
    Swartout B., Moore J.: “Explanation in Second Generation Expert Systems: Depth and Dialogue”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar
  40. [40]
    Terpstra P., van Heijst G., Shadbolt N., Wielinga B.:“Knowledge Acquisition Process Support Through Generalised Directive Models”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar
  41. [41]
    van de Velde W.: “Issues in Knowledge Level Modelling”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar
  42. [42]
    Wick M.: “Second Generation Expert System Explanation”; in Second Generation Expert Systems, David J-M., Krivine J-P. and Simmons R. (Eds); Springer Verlag; 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Jean-Marc David
    • 1
  • Jean-Paul Krivine
    • 2
  • Benoit Ricard
    • 3
  1. 1.Service Systèmes ExpertsRENAULTBoulogne BillancourtFrance
  2. 2.EDFDirection des Etudes et RecherchesClamart CedexFrance
  3. 3.EDFDirection des Etudes et RecherchesChatou CedexFrance

Personalised recommendations