Model Construction for Knowledge-Intensive Engineering Tasks

  • Benno Stein
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 116)

Summary

The construction of adequate models to solve engineering tasks is a field of paramount interest. The starting point for an engineering task is a single system, S, or a set of systems, S, along with a. shortcoming of information, often formulated as a question:

  • Which component is broken in S? (diagnosis ∼ analysis)

  • How does S react on the input u? (simulation ∼ analysis)

  • Does a system with the desired functionality exist in S? (design ∼ synthesis)

If such an analysis or synthesis question shall be answered automatically, both adequate algorithmic models along with the problem solving expertise of a human problem solver must be operationalized on a computer. Often, the construction of an adequate model turns out to be the key challenge when tackling the engineering task. Model construction – also known as model creation, model formation, model finding, or model building – is an artistic discipline that highly depends on the reasoning job in question.

Model construction can be supported by means of a computer, and in this chapter we present a comprehensive view on model construction, characterize both existing and new paradigms, and give examples for the state of the art of the realization technology. Our contributions are as follows:

  • In Sect. 2 we classify existing model construction approaches with respect to their position in the model hierarchy. Nearly all of the existing methods support a top-down procedure of the human modeler; they can be characterized as being either structure-defining (top), structure-filling (middle), or structure propagating (down).

  • Domain experts and knowledge engineers rarely start from scratch when constructing a new model; instead, they develop an appropriate model by modifying an existing one. Following this observation we analyzed various projects and classified the found model construction principles as model simplification, model compilation, and model reformulation. In Sect. 3 we introduce these principles as horizontal modeling construction and provide a generic characterization of each.

  • Section 4 presents real-world case studies to show horizontal model construction principles at work. The underlying technology includes, among others, hybrid knowledge representations, case-based as well as rule-based reasoning, and machine learning.

Keywords

Source Model Behavior Model Model Construction Algorithmic Model Graph Grammar 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. Abderrahim and A. Whittaker. Mechatronics ’98. In J. Adolfsson and J. Karlsen, editors, Interfacing Autolev to Matlab and Simulink, pages 897–901. Pergamon, September 1998.Google Scholar
  2. 2.
    Sanjaya Addanki, Roberto Cremonini, and J. Scott Penberthy. Reasoning about assumptions in graphs of models. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence (IJCAI 89), pages 1324–1330, Detroit, MI, August 1989.Google Scholar
  3. 3.
    Martin Anantharaman, Bodo Fink, Martin Hiller, and Stefan Vogel. Integrated development environment for mechatronic systems. In Proceedings of the Third Conference on Mechatronics and Robotics, Paderborn, Germany, 1995.Google Scholar
  4. 4.
    D. Angluin and C. H. Smith. Inductive inference: theory and methods. Computational Surveys, 15(3):237–269, 1983.CrossRefMathSciNetGoogle Scholar
  5. 5.
    Elisabeth Bradley and Reinhard Stolle. Automatic construction of accurate models of physical systems. Annals of Mathematics and Artificial Intelligence, 17(1–2):1–28, 1996.MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    David C. Brown and B. Chandrasekaran. Design Problem Solving. Morgan Kaufmann, San Mateo, 1989.Google Scholar
  7. 7.
    François E. Cellier. Continuous System Simulation. Springer, Berlin Heidelberg New York, 1991.Google Scholar
  8. 8.
    Daniel J. Clancy and Benjamin Kuipers. Model decomposition and simulation. In Toyoaki Nishida, editor, Proceedings of the Eighth International Workshop on Qualitative Reasoning about Physical Systems (QR 94), pages 45–54, Nara, Japan, June 1994.Google Scholar
  9. 9.
    Rina Dechter and Judea Pearl. The cycle-cutset method for improving search performance in AI applications. In Proceedings of the Third Conference on Artificial Intelligence Applications, Orlando, Florida, 1987.Google Scholar
  10. 10.
    Hilding Elmquist. Object-oriented modeling and automated formula manipulation in Dymola. In SIMS’93, Kongsberg, Norway, June 1993. Scandinavian Simulation Society.Google Scholar
  11. 11.
    Alfred Fettweis. Wave digital filters: theory and practice. Proceedings of the IEEE, 74(2):270–327, February 1986.CrossRefGoogle Scholar
  12. 12.
    Paul A. Fishwick. The role of process abstraction in simulation. IEEE Transactions on Systems, Man, and Cybernetics, 18:18–39, 1988.CrossRefGoogle Scholar
  13. 13.
    Charles L. Forgy. Rete: a fast algorithm for the many pattern/many object pattern match problem. Artificial Intelligence, 19:17–37, 1982.CrossRefGoogle Scholar
  14. 14.
    Frederick K. Frantz. A taxonomy of model abstraction techniques. In Proceedings of the 1995 Winter Simulation Conference (WSC 95), Proceedings in Artificial Intelligence, pages 1413–1420, Arlington, VA, December 1995.Google Scholar
  15. 15.
    John S. Gero. Design prototypes: a knowledge representation scheme for design. AI Magazine, 11:26–36, 1990.Google Scholar
  16. 16.
    Stefan Goldschmidt. Modellbildung am Beispiel von Starrkörpersystemen. Systematische Darstellung und Untersuchung von Software-Unterstützung. Study work, University of Paderborn, November 1996.Google Scholar
  17. 17.
    R. C. Hibbeler. Engineering Mechanics: Statics and Dynamics, 6th edition. MacMillan, New York, 1992.Google Scholar
  18. 18.
    Yumi Iwasaki and Alon Y. Levy. Automated model selection for simulation. Knowledge Systems Laboratory (KSL), QS93, 1993.Google Scholar
  19. 19.
    Johan de Kleer. Problem solving with the ATMS. Artificial Intelligence, 28:197–224, 1986.CrossRefGoogle Scholar
  20. 20.
    G. J. Klir. Architecture of Systems Complexity. Sauders, New York, 1985.Google Scholar
  21. 21.
    Granino A. Korn and John V. Wait. Digital Continuous-System Simulation. Prentice-Hall, Englewood Cliffs, NJ, 1978.Google Scholar
  22. 22.
    Klaus Ulrich Leweling and Benno Stein. Hybrid constraints in automated model synthesis and model processing. In Susanne Heipcke and Mark Wallace, editors, 5th International Conference on Principles and Practice of Constraint Programming (CP 99), Workshop on Large Scale Combinatorial Optimisation and Constraints, pages 45–56, Leamington Spa England, October 1999. Dash Associates.Google Scholar
  23. 23.
    R. S. H. Mah. Chemical Process Structures and Information Flows. Butterworths, Boston, 1990.Google Scholar
  24. 24.
    Mary Lou Maher and Pearl Pu, editors. Issues and Applications of Case-Based Reasoning in Design. Lawrence Erlbaum Associates, Mahwah, NJ, 1997.Google Scholar
  25. 25.
    Sandra Marcus. Salt: a knowledge acquisition language for propose-and-revise systems. In Sandra Marcus, editor, Automating Knowledge Acquisition for Expert Systems, pages 81–123. Kluwer Academic, Norwell, MA, 1988.Google Scholar
  26. 26.
    B. T. Messmer and H. Bunke. Subgraph isomorphism in polynomial time. Technical Report AM-95-003, Research Group of Computer Vision and Artificial Intelligence, University of Bern, 1995.Google Scholar
  27. 27.
    Marvin Minsky. Models, minds, machines. In Proceedings of the IFIP Congress, pages 45–49, 1965.Google Scholar
  28. 28.
    P. Pandurang Nayak. Causal approximations. Artificial Intelligence, 70:277–334, 1994.MATHCrossRefMathSciNetGoogle Scholar
  29. 29.
    P. Pandurang Nayak. Automated Modelling of Physical Systems. Springer, Berlin Heidelberg New York, 1995.MATHGoogle Scholar
  30. 30.
    P. C. Piela, T. G. Epperly, K. M. Westerberg, and A. W. Westerberg. Ascend: an object-oriented computer environment for modeling and analysis: the modeling language. Computers Chemical Engineering, 15(1):53–72, 1991.CrossRefGoogle Scholar
  31. 31.
    Frank Puppe. Systematic Introduction to Expert Systems, Knowledge Representations and Problem-Solving Methods. Springer, Berlin Heidelberg New York, 1993.MATHGoogle Scholar
  32. 32.
    Lisa Purvis and Pearl Pu. An approach to case combination. In Proceedings of the Workshop on Adaptation in Case Based Reasoning, European Conference on Artificial Intelligence (ECAI 96), Budapest, Hungary, 1996.Google Scholar
  33. 33.
    Olivier Raiman. Order of magnitude reasoning. Artificial Intelligence, 51:11–38, 1991.CrossRefGoogle Scholar
  34. 34.
    B. Raphael and B. Kumar. Indexing and retrieval of cases in a case-based design system. Artificial Intelligence for Engineering Design, Analysis, and Manufacturing, 10:47–63, 1996.CrossRefGoogle Scholar
  35. 35.
    Jeff Rickel and Bruce Porter. Automated modeling for answering prediction questions: selecting the time scale and system boundary. In Proceedings of the Twelfth National Conference on Artificial Intelligence (AAAI 93), pages 1191–1198, Cambridge, MA, 1994. AAAI Press.Google Scholar
  36. 36.
    Elisha Sacks. Piecewise linear reasoning. In Proceedings of the Sixth National Conference on Artificial Intelligence (AAAI 87), pages 655–659, Seattle, WA, July 1987. AAAI Press.Google Scholar
  37. 37.
    Munehiko Sasajima, Yoshinobu Kitamura, Mitsuru Ikeda, and Shinji Yoshikawa. An investigation on domain ontology to represent functional models. In Toyoaki Nishida, editor, Proceedings of Eighth International Workshop on Qualitative Reasoning about Physical Systems (QR 94), pages 224–233, Nara, Japan, June 1994.Google Scholar
  38. 38.
    D. B. Schaechter, D. A. Levinson, and T. R. Kane. Autolev User’s Manual, 1991.Google Scholar
  39. 39.
    L. C. Schmidt and J. Cagan. Configuration design: an integrated approach using grammars. ASME Journal of Mechanical Design, 120(1):2–9, 1998.CrossRefGoogle Scholar
  40. 40.
    Bart Selman and Henry Kautz. Knowledge compilation using Horn approximations. In Proceedings of the Ninth National Conference on Artificial Intelligence (AAAI 91), pages 904–909, Anaheim, CA, 1991. AAAI Press.Google Scholar
  41. 41.
    Benno Stein. Functional Models in Configuration Systems. Dissertation, University of Paderborn, Institute of Computer Science, 1995.Google Scholar
  42. 42.
    Benno Stein. Model Construction in Analysis and Synthesis Tasks. Habilitation, Department of Computer Science, University of Paderborn, Germany, June 2001. URL http://ubdata.uni-paderborn.de/ediss/17/2001/stein/.
  43. 43.
    Benno Stein, Daniel Curatolo, and Hans Kleine Büning. Speeding up the simulation of fluidic systems by a knowledge-based selection of numerical methods. In Euromech Colloquium 370 Synthesis of Mechatronic Systems. University of Duisburg, September 1997.Google Scholar
  44. 44.
    Benno Stein, Daniel Curatolo, and Marcus Hoffmann. Simulation in Fluidsim. In Helena Szczerbicka, editor, Workshop on Simulation in Knowledge-Based Systems (SIWIS 98), number 61 in ASIM Notes, Bremen, Germany, April 1998. Technical committee 4.5 ASIM of the GI.Google Scholar
  45. 45.
    Peter Struss. Multiple models for diagnosis. SPQR-Workshop on Multiple Models, FRG Karlsruhe, March 1991.Google Scholar
  46. 46.
    Michael Suermann. Wissensbasierte Modellbildung und Simulation von hydraulischen Schaltkreisen. Diploma thesis, University of Paderborn, 1994.Google Scholar
  47. 47.
    J. Wallaschek. Modellierung und Simulation als Beitrag zur Verkürzung der Entwicklungszeiten mechatronischer Produkte. VDI Berichte, Nr. 1215, pages 35–50, 1995.Google Scholar
  48. 48.
    Daniel S. Weld. The use of aggregation in causal simulation. Artificial Intelligence, 30:1–34, 1986.CrossRefGoogle Scholar
  49. 49.
    A. Wayne Wymore. Systems Engineering for Interdisciplinary Teams. Wiley, New York, 1976.Google Scholar
  50. 50.
    Kenneth Man-kam Yip. Model simplification by asymptotic order of magnitude reasoning. Artificial Intelligence, 80:309–348, 1996.CrossRefMathSciNetGoogle Scholar
  51. 51.
    Bernard P. Zeigler, Herbert Praehofer, and Tag Gon Kim. Theory of Modeling and Simulation. Academic, New York, 2000.Google Scholar
  52. 52.
    Blaz̆ Zupan. Optimization of rule-based systems using state space graphs. IEEE Transactions on Knowledge and Data Engineering, 10(2):238–253, March 1998.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Benno Stein
    • 1
  1. 1.Faculty of Media, Media SystemsBauhaus University WeimarWeimarGermany

Personalised recommendations