A Fuzzy Genetic Algorithm for Creative Shape Design

Design is a multi-criteria decision-making process under multiple constraints. In the conceptual design stage, design is intrinsically imprecise because of designers’ vague thinking and incomplete initial information. When exploring possible design candidates, designers are generally more interested in sets of the most promising solutions rather than the best single solution. Therefore, in contrast to conventional optimisation approaches that aim to find exact optimal points, we aim to find optimal set of alternatives with variable satisfaction degrees. A fuzzy-set-based approach for representation and optimisation of design objects is particularly suitable for solving this problem. The concept of a fuzzy shape is defined as a family of shapes with similar properties where a fuzzy solid shape is represented by a set of parameters that have fuzzy set values. Evolutionary computation is used to obtain fuzzy solutions to the fuzzy shape optimisation problem since it is the most powerful tool for supporting creative design through multiple objectives, multi-dimensional searching. The representation of fuzzy sets, its initialisation, crossover, mutation, and validation, the ranking approach for fuzzy shapes, and the propagation method of fuzzy information are discussed. A case study for illustrating this fuzzy design approach is provided.