A semantic transformation method for product form design is proposed. In this model, an image database for the relationships between the product shapes and image words is built using the membership functions of a fuzzy set, and a multidimensional perceptual space for the relationships between the abstract image words and the embodiment shape regulating rules is also constructed using the multidimensional scaling (MDS) method. A computer program is constructed by integrating the technique of constructing B-splines, the image database and fuzzy query operations to provide a CAD environment in which 3D basic models of a product can be constructed by starting with inputting an image word(s) for describing the image of the required product. After a basic product model has been constructed, new product forms can further be generated by regulating the shape of the basic model using the suggested embodiment shape regulation rule which is obtained by inputting a required image to analyze the direction cosines of the embodiment shape regulation rules with respect to the required image in the multidimensional semantic recognition space. Though automotive form design is taken as an example in this study, this method can also be used to develop other products.
All Science Journal Classification (ASJC) codes
- Arts and Humanities (miscellaneous)
- Social Sciences(all)
- Computer Science Applications
- Artificial Intelligence