Efficiency assessment of an evolutive design system of car contours

François Cluzel (1) , Bernard Yannou (1)

1 LGI - Laboratoire Génie Industriel - EA 2606

So as to create innovative car silhouettes, we propose in this paper a model based on an Interactive Genetic Algorithm using an encoding of a design solution by a Fourier analysis approach. This model permits the designer to browse through generations of car profiles from an initial population of existing silhouettes. By qualitatively assessing each individual, the user converge towards solutions complying with his/her requirements and so potentially create novelty. We describe here tests for assessing the efficiency of this innovative design platform. These tests are based on a similarity matrix, a similarity measure being the perceived distance between two cars silhouettes. The results show a really satisfactory behavior of the model and open perspectives thanks to its flexible and extensible aspects.

Mots clés: Interactive Genetic Algorithm; Evolutionary Design; user tests; similarity index; subjective evaluation

Domaines: Mécanique [physics.med-ph]; Intelligence artificielle [cs.AI]

François Cluzel, Bernard Yannou. Efficiency assessment of an evolutive design system of car contours. 17th International Conference on Engineering Design - ICED 09, Aug 2009, Palo Alto, CA, United States. pp.189-200. ⟨hal-00796940⟩