SHARED EXPERTISE SPACE A Learning-oriented Model for Computer Aided Engineering Design

The growing complexity of contemporary engineering designs requires the use of sophisticated computer-based design tools. Such tools increase productivity in drafting, configuration and calculations. However, the current generation of design tools plays a rather passive role in the whole design process. Recent progress in engineering design, machine learning and knowledge acquisition allows the development of knowledge-based design assistants which could behave as active partners to human designers rather than as graphical or computational aids. This paper presents the Shared Expertise Space (SES) model of cooperation between a human designer and a knowledge-based design assistant (called DISCIPLE-3) in which the design assistant behaves as an apprentice and a partner in the whole design process. The human designer and DISCIPLE-3 create designs together, with DISCIPLE-3 proposing routine and innovative designs, and the human designer correcting and finalizing these designs, as well as specifying creative designs. In this process, DISCIPLE-3 also learns from the human designer, constantly extending and improving its knowledge base, and becoming a better designer itself. This is achieved by employing apprenticeship multistrategy learning based on a Plausible Version Space approach. Within the SES framework, a human designer with limited programming skills can directly develop and maintain a personalized knowledge-based design assistant. The use of SES leads to the increased capabilities of the human-system design team. In this paper, some of the main features of the SES model are illustrated within the domain of computer systems configuration.