DAKA: design activity knowledge acquisition through data-mining

Engineering knowledge is an important asset of industrial companies. The present research focuses on design activity knowledge and it attempts to develop effective ways to capture this operational knowledge from the design events monitored during the design process. A design activity is defined as a sequence of meaningful design operations carried out by designers to advance the design from its current state to the new state. The paper proposes a design activity knowledge acquisition (DAKA) framework that extracts designers’ design activity knowledge from the computer-aided design (CAD) operation event data obtained through commercial CAD systems. DAKA is composed of a product model roadmap for capturing the trajectory of designers’ design moves and a function-based design operation-mining algorithm for extracting meaningful design operations from CAD event databases. DAKA has been evaluated through case studies using real CAD operation event data as well as computer-generated synthetic data. In this paper, the details of the DAKA framework are described and a case example involving automotive door design is presented to demonstrate the effectiveness of the proposed approach.