A Metamodel-driven Interactive Framework for a Designer Assistance System

The design of innovative products in the automotive industry is influenced by multiple criteria dominated by both human creativity and technical requirements. Thus the generation of a prototype is an adaptive process which iteratively integrates the needs of various disciplines, working on different timescales. This paper proposes and evaluates a styling design framework which introduces the application of neural networks for fast estimation of technical performance. Accurate model feedback enables the designer to include predicted responses in the styling process, especially in local areas.