Automatic design synthesis with artificial intelligence techniques

Design synthesis represents a highly complex task in the field of industria l design. The main difficulty in automating it is the definition of the des ign and performance spaces, in a way that a computer can generate optimum s olutions. Following a different line from the machine learning, and knowled ge-based methods that have been proposed, our approach considers design syn thesis as an optimization problem. From this outlook, neural networks and g enetic algorithms can be used to implement the fitness function and the sea rch method needed to achieve optimum design. The proposed method has been t ested in designing a telephone handset. Although the objective of this appl ication is based on esthetic and ergonomic cues (subjective information), t he algorithm successfully converges to good solutions. (C) 1999 Elsevier Sc ience Ltd. All rights reserved.