Evolutionary form design: the application of genetic algorithmic techniques to computer-aided product design
conference contributionposted on 30.01.2014 by Ian Graham, Robert Wood, Keith Case
Any type of content contributed to an academic conference, such as papers, presentations, lectures or proceedings.
This paper introduces the current stage of research into the development of a CAD tool that uses evolutionary techniques to assist designers in creating the form of products. A Genetic Algorithm (GA) has been combined with a commercial CAD solid modelling system. This initially enables the creation of a set of apparently random objects. These objects are then subjected to a selective breeding programme, at the hands of the user and also guided by pre-set internal, or environmental, factors. The user gives each object a score, or objective function, influencing which objects are 'fittest', and more likely to become parents of the next generation. The intention is that, through the co-operation of the user and the pre-set environmental factors, the forms on the screen progressively become more than an abstract collection of geometric primitives. On a primary level, the system can provide the inspiration for aesthetic features and characteristics of products. Further work may develop the potential for a new design methodology. The challenge will be to make the concept genuinely useful, and to do this the outcome of genetic manipulation needs to be predictable, to the extent that desirable features from objects are reproduced in the next generation of objects. The key to this is the way the genetic shape defining data is stored and processed, and is the major focus of this continuing research .
- Mechanical, Electrical and Manufacturing Engineering