WIT Press

LEGO-type Design By Using Neural Networks

Price

Free (open access)

Volume

31

Pages

8

Published

1997

Size

637 kb

Paper DOI

10.2495/OP970241

Copyright

WIT Press

Author(s)

M. Kishi & T. Ochi

Abstract

LEGO is a toy block of North Europe origin. We classify LEGO-type structural designs into three modes: system design, connection design, and elements design. Considered in this paper is the connection design. A multi-objective optimization problem is defined for LEGO-type truss structure design. LEGO-type blocks of the same kind are used, and the loading conditions are assumed to be given. The combinatorial/discrete optimization problem can be programmed and solved on artificial neural networks. The Boltzmann machine is introduced as a probabilistic neural network. Numerical examples are provided to verify the applicability of the design method. 1 Introduction Practical structure designs have some analogy with LEGO blocks play. Such structures are composed of eleme

Keywords