Knowledge Acquisition Based on Representation (KAR) for Design Model Development

Abstract

In recent years, knowledge-based systems have become one of the most popular approaches for solving engineering problems. Along with the rising complexity of the problem, knowledge management, acquisition, representation, inferencing, and refinement become increasingly difficult. Conventionally, tasks of knowledge acquisition and representation are accomplished separately and sequentially. Knowledge engineers are responsible for preparing question patterns and setting up personnel interviews with domain experts for knowledge acquisition. All acquired knowledge is then manually interpreted, verified, and transformed into a predefined representation scheme. In this chapter, a new methodology for knowledge acquisition, termed Knowledge Acquisition based on Representation (KAR) is presented. Instead of treating acquisition and representation separately and sequentially, KAR deals with acquisition and representation in an integrated manner. All knowledge acquired with KAR is verified and transformed into a representation scheme which is ready for inferencing. The major objectives of KAR are to facilitate the knowledge acquisition process, to increase its reliability, and to reduce the development cost of the model bases.