Learning yacht hull adjectives and their relationship with hull surface geometry using GMDH-type neural networks for human oriented smart design

Abstract

Abstract Several efforts have been made to describe cars by adjectives, however there is no particular work exploring adjectives describing yacht hulls which motivates this study. First, a novel design schema is developed for representing yacht hulls in 3D, which is parametric based and includes several geometric parameters quantifying the hull models. Three surveys are then conducted to learn the relationship between hulls and hull adjectives. In the first survey, yacht models with different geometries are shown to participants to form the hull adjective dictionary. Next, geometric parameters having no impact on the hull adjectives are eliminated via the second survey. Hull adjectives are then matched with yacht hull models via the third survey. The models shown in the third survey are obtained by performing sampling using the Taguchi experimental method. Finally, GMDH-type neural network (GMDH) is applied to the data sets obtained from the third survey to determine the relationships between the hull adjectives and the geometric parameters. GMDH provides mathematical models for each adjective consisting of geometric parameters with coefficients. With the outcomes of this work, we expect that communication between designers and customers can be easier, and adjective based design variations of yacht hulls can be achieved in a shorter amount of time.