Recognition of cylindrical and conical features using edge boundary classification

The work presented in this paper proposes a new technique called Edge Boundary Classification (EBC) for feature recognition from B-rep models. The technique uses the spatial addressability information of solid models that identifies the solid and void 'sides' of a boundary entity. Features can be interpreted from B-rep models based on the spatial properties of boundary entities. The purpose of feature recognition is to convert the geometric CAD data of a modeled part into a set of features suitable to support manufacturing activities such as in process planning system and inspection system. The application of the technique for cylindrical-based and conical-based features is presented. A case study is discussed and demonstrated to validate the proposed algorithms.