Data and knowledge integration through the feature-based approach

Abstract

One promising and convenient approach towards the integration of data and knowledge is the so called feature-based approach. Most existing definitions of the term ‘feature’ represent an attempt at generalization. However, as a rule, they depend on the application in one or another subsystem of computer integrated manufacturing systems. Probably, the reason for this is that more attention has been paid to the feature as a data-based entity. The approach, presented in this paper, can be generalized as follows: • the part (product) features are bearers of knowledge about that part (product); • there are two general kinds of knowledge: connected with data and connected with existing and/or necessary relations among these data, leading to a part (product) description; • two general types of features can be defined which correspond to those kinds of knowledge: fact-features and rule-features. Some requirements and practical recommendations for creating a feature-based application software are given. Declarative production programming languages are proposed as a most convenient tool for creating such software. In addition, those of them in which the forward chaining inference strategy is accepted are recommended. The contents of facts- and rule-bases is discussed. It is shown that the set of rules is defined as a consequence of the necessary operations, which ensure the interface with the user and external systems, parametrization of available facts and different types of their processing. As a confirmation of the ideas presented in this paper, the main components of an intelligent system for feature-based modeling in computer-aided design and computer-aided manufacturing are briefly shown.