An artificial intelligence approach to efficient fusion first wall design

  • Shinobu Yoshimura
  • Genki Yagawa
  • Yoshihkio Mochizuki
Design Methods
Part of the Lecture Notes in Computer Science book series (LNCS, volume 492)


This paper describes the application of artificial intelligence techniques to the design automation of the fusion first wall, which will be operated under complex conditions including huge electromagnetic and thermal loading as well as heavy neutron irradiation.

As a basic strategy of the design, the generate and test strategy is adopted because of its simplicity and broad applicability. To automate the design procedure with maintaining flexibility, extensibility and efficiency, some artificial intelligence techniques are utilized as follows:

An object-oriented knowledge representation technique is adopted to store knowledge modules, that is, objects, related to the first wall design. A data-flow processing technique is utilized as an inference mechanism among the knowledge modules. These techniques realize the flexibility and extensibility of the system. In addition, as an efficient design modification mechanism, we introduce an empirical approach based on both experts' knowledge and a fuzzy control technique.

The developed system is applied to a simple example of the design of a two-dimensional model of the first wall with a cooling channel, and its fundamental performance is demonstrated.

Key Words

Fusion First Wall Artificial Intelligence Object-Oriented Knowledge Representation Data Flow Processing Design Modification Fuzzy Control 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    G. Gasini, Fusion Engrg. & Design., 6, 95, 1982.Google Scholar
  2. [2]
    S. Mittal, C. Dym, M. Marjaria, IEEE-Computer, 119, 102, 1986.Google Scholar
  3. [3]
    J. A. Bennet, M. A. Botkin, The Optimum Shape, Plenum Press, 1986.Google Scholar
  4. [4]
    S. Nakagiri and K. Suzuki, Seisan-Kenkyu, J. of Institute of Industrial Science, Univ. of Tokyo, 39, 460, 1987.Google Scholar
  5. [5]
    R. G. Smith, Proc. of the 8th Int. Joint Conf. on Artificial Intelligence, 855, 1983Google Scholar
  6. [6]
    J. B. Dennis, Lecture Notes in Computer Science, 19, 362, 1974Google Scholar
  7. [7]
    L. A. Zadeh, Information and Control, 12, 94, 1968.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Shinobu Yoshimura
    • 1
  • Genki Yagawa
    • 1
  • Yoshihkio Mochizuki
    • 1
  1. 1.Department of Nuclear EngineeringUniversity of TokyoJapan

Personalised recommendations