Skip to main content
SpringerLink
Log in

Building case-based preliminary design systems: A Hopfield network approach

  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This paper addresses the issue of building a case-based preliminary design system by using Hopfield networks. One limitation of Hopfield networks is that it cannot be trained, i.e. the weights between two neurons must be set in advance. A pattern stored in Hopfield networks cannot be recalled if the pattern is not a local minimum. Two concepts are proposed to deal with this problem. They are the multiple training encoding method and the puppet encoding method. The multiple training encoding method, which guarantees to recall a single stored pattern under appropriate initial conditions of data, is theoretically analyzed, and the minimal number of times for using a pattern for training to guarantee recalling of the pattern among a set of patterns is derived. The puppet encoding method is proved to be able to guarantee recalling of all stored patterns if attaching puppet data to the stored patterns is available.

An integrated software PDS (Preliminary Design System), which is developed from two aspects, is described. One is from a case-based expert system—CPDS (Case-based Preliminary Design System), which is based on the algorithm of the Hopfield and developed for uncertain problems in PDS; the other is RPDS (Rule-based Preliminary Design System), which attacks logic or deduced problems in PDS. Based on the results of CPDS, RPDS can search for feasible solution in design model. CPDS is demonstrated to be useful in the domains of preliminary designs of cable-stayed bridges in this paper.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Chen Qin. Knowledge-based engineering design.Artificial Intelligence, 1992, 903–924.

  2. Clifford G Y Lau, Bernard Widrow. Neural Networks in IEEE Proceedings.IEEE Trans. on Neural Networks, 1990, 1: 276–279.

    Google Scholar 

  3. Tank D W, Hopfield J J. Collective computation in neuronlike circuits.Scientific American, 1987, 257: 104–114.

    Article  Google Scholar 

  4. Elaine Rich. Expert systems and neural networks can work together.IEEE EXPERT, 1990, 5–7.

  5. Nagy G. Neural networks — then and now.IEEE Trans. on Neural Networks, 1991, 2: 316–318.

    Article  Google Scholar 

  6. Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci., U.S.A., 1982, 79, 6871–6874.

    Article  MathSciNet  Google Scholar 

  7. Hopfield J J, Tank D W. “Neural” computation of decisions in optimization problems.Biological Cybernetics, 1985, 52: 141–152.

    MATH  MathSciNet  Google Scholar 

  8. Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. U.S.A., 81, 3088–3092.

  9. Takeda M, Goodman J W. Neural networks for computation, number representations and programming complexity.Applied Optics, 1986, 25: 3033–3046.

    Article  Google Scholar 

  10. Liman Richard P. An introduction to computing with neural nets.IEEE ASSP Magazine, 1987, 4–22.

  11. Narasimhan R. Human intelligence and AI: How close are we to bridging the gap?IEEE EXPERT, April, 1990, 77–83.

  12. Robert Hecht-Nielsen. Neurocomputing: Picking the human brain.IEEE SPECTRUM, Mar., 1988, 36–41.

  13. Pressman Roger S. Software engineering — A practitioner's approach. 1988. McGraw-Hill Book Company, New York, U.S.A.

    Google Scholar 

  14. Grossberg Stephen. Burning the candle from both ends.IEEE EXPERT, 1991, 3–6.

  15. Schwartz Tom J. NIPS'90: The IEEE Conference on Neural Information Processing Systems.IEEE EXPERT, Feb., 1991, 60–61.

  16. Schwartz Tom J. Winter in Washington: IJCNN-90 — A Great Success.IEEE EXPERT, April, 1990, 83–84.

  17. Wolfe W J, Mathis D, Anderson Cet al. K-winner networks.IEEE Trans. on Neural Networks, 1991, 2: 310–315.

    Article  Google Scholar 

  18. Wu Wei, Chen Qin. A neural network for the pattern choice of cable-stayed bridge. International Conference on EPMESC'92,, 1, 376–382.

  19. Wang Yeou-Fang, Cruz JR Jose B, Mulligan JR James H. On multiple training for bidirectional associative memory.IEEE Trans. on Neural Networks, Sept. 1990, 1: 275–276.

    Article  Google Scholar 

  20. Podolny Walter, Scalzi John B. Construction and design of cable-stayed bridges. 1976, John Wiley & Sons, Inc., U.S.A.

    Google Scholar 

  21. Troitsky M S. Cable-stayed bridges: Theory and design. 1977, Crosby Lockwood Staples, London.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Research Institute of Engineering Mechanics, Dalian University of Technology, 116024, Dalian

    Wu Wei & Zhong Wanxie

  2. China National Computer Software & Technology Service Corporation, 100080, Beijing

    Sheng Zhijin

Authors
  1. Wu Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhong Wanxie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sheng Zhijin
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wu, W., Zhong, W. & Sheng, Z. Building case-based preliminary design systems: A Hopfield network approach. J. of Comput. Sci. & Technol. 9, 329–341 (1994). https://doi.org/10.1007/BF02943580

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02943580

Keywords

Search

Navigation