Development of design system for crack patterns on cup surface based on KANSEI
Abstract With the development of manufacturing technology in recent years, as well as with the industrial product development, differentiation in the design aspect is becoming effective, not in terms of performance or quality. In addition, as consumers seek products that match their own sensibilities (KANSEI), designers are required to propose designs that highly conform to concept presented by client, while understanding the KANSEI of diversified consumers; therefore, their burden is increasing. To address these issues, the support of the development of computer-aided design has advanced; however, it is difficult to reflect human KANSEI or to generate a design that induces a natural impression through computers. The purpose of this research is to develop a system that incorporates the KANSEI of users, and emits a pattern design that induces a natural impression using a computer. This work is focused on crack patterns that can be observed on pottery surfaces, and a method for generating crack patterns on a cup surface is suggested. In this study, a Bézier curved surface and fluctuation were employed in order to induce a natural impression. In addition, by using the neural network, the crack patterns were associated with user KANSEI. The neural network was composed of three layers, namely the input layer, the hidden layer, and the output layer; it adopted the sigmoid function as the transition function and the back propagation as the learning method. As a result, a system was constructed, in which a crack pattern that satisfied the input produces an output according to the desired impression of the user. Finally, an evaluation questionnaire was distributed, and the usefulness of the system was confirmed. Highlights A method for creating crack patterns using a computer is proposed. The relationship between KANSEI and crack patterns is modeled by neural network. A system is developed that outputs crack patterns that satisfy the inputted KANSEI.