A computational approach to innovative conceptual design

Conceptual design is a vital part of the design process during which designers first envision new ideas and then synthesize them into physical configurations that meet certain design specifications. In this research, a computational approach is developed to assist the designers perform this non-trivial task of navigating the design space for creating conceptual design configurations. The methodology is based on combining empirical reverse engineering techniques with a graph-grammar approach. Accordingly, design knowledge is systematically extracted from past designs, formulated as procedural grammar rules, and employed in building new design concepts. The implemented system provides a theoretical framework for automatically searching conceptual design spaces and produces novel alternative configurations to real design problems. The application of the approach to the design of various electromechanical devices shows the method's range of capabilities, and how it serves as a comparison to human conceptual design generation and as a tool to complement the skills of a designer.