The authors have been involved in the use of generative techniques for building envelope design since 1968 and the use of genetic algorithms since 1990. Recent work has focused on incorporating optimization functions into form generating processes in order for new forms responding to varied design environments to be created and determined. This paper will summarise the authors’ previous work in this field and explain the theory behind this approach, and illustrate recent developments. While the initial implementation of a new building envelope design system is reported in more details in a related paper at this conference, this paper outlines its main features and points out the direction at which it is to be fully developed and further improved.

This paper presents a new design optimization technique by artificial neural networks. Based on the theory of partial ordering and cones in Banach spaces, a new kind of neural networks with functional links is proposed. Learning algorithm lies heavily on the ordering structure of the sample space with an alternative feed-forward and backpropagation technique. Experiments are described with comparison with traditional functional link networks and wavelet networks.

This paper desla with a class of nonlinear boundary value problems which appears in the study of models of flows through porous media. Existence results of asymptotic bifureation and continua are reported both for operator equations and for boundary value problems

The purpose of this paper is to investigate generative and evolutionary design models by the new idea of co-evolution. Multi-objective optimization is our main concern. A dynamic co-evolution model is presented with detailed description of its application in eco-conscious housing design. Area and solar constraints of housing design problems are considered with maximum architectural area and solar illumination been optimized. We use dynamic niche models based on a fitness-sharing scheme to define energy and fitness functions for the co-evolution system. Early experimental data are presented and analyzed to show the effectiveness of this approach to evolutionary design optimization and its computational implementation of the algorithms.