Graph-Based Feature Recognition Techniques for Prismatic Parts - A Critical Review

摘要

Feature Recognition (FR) plays a major role in the engineering significance of a part model and serves as an important support tool for integrated manufacturing. Feature-based design systems typically act as interlink between the CAD and CAM activities. These systems can be broadly classified into human-assisted feature definition systems, automatic feature recognition systems and design by features systems. The researchers have realized that the best system architecture for a feature-based system would be a blend of the above mentioned approaches. This paper critically reviews the research developments in graph-based feature recognition techniques with respect to algorithms, which can recognize feature types like orthogonal, intersecting, curved, and algorithms with heuristics for recognizing additional features in the past two decades. In this review more emphasis was given on STandard for the Exchange of Product Model Data (STEP) neutral format file data exchange systems. The conclusion of the reviewed literature and possible future directions in graph-based feature recognition are also presented.