During the last two decades, 3D scanning technology has further advanced and successfully facilitated the reconstruction of complex engineering parts. In Reverse Engineering, surface reconstruction is performed by recognizing every face of features on a machining part that is derived from a set of points cloud. Boundary representation (B-rep) is one of the existing CAD modeling methods that works well out for recognition of features.
A feature, in computer-aided design (CAD), represents a region of a part with some significant geometric and topological patterns. The most common type of feature is the “form feature” (e.g., round holes, slots, bosses, pockets, etc.) which contains both shape information and parametric information.
Feature recognition applies a set of logic and rules used to identify faces of an object. The classical Kyprianou's feature recognition method (1980) was aimed to encode parts for group technology (GT). The purpose of GT is to systematically classify objects based on their manufacturing method. Kyprianou's work involved classifying faces into primary and secondary groups and, then, identifying features according to patterns of these primary or secondary faces. A primary face is one with multiple boundaries, also called "hole-loops", or mixed concave and convex boundaries. A concave boundary is a set of concave edges, where the solid angle over the edge is more than 180. Meanwhile, secondary faces refer to all the other faces.
By using features to build up shape models, the design process becomes more efficient, because the shape of features can be pre-defined. Features can be directly associated to manufacturing information so that these information can be retrieved in downstream applications. Furthermore, knowledge of features can be stored and reusable for use either in its original or modified designs for developing a new model.
Therefore, a research is attempted to obtain a better understanding on the properties and characteristics of 2D (i.e., points, lines, planes, circles, ellipses, triangles, polygons, spline curves) and 3D (i.e., cube, spehere, cylinder, cone, pyramid, prism, torus) geometric primitives and the rules to be set-up for recognizing them as features in a CAD model.
Fig.-1. Vector graphics consists of geometrical primitives (Wikipedia, 2011)
1. Understanding the state-of-the-art of CAD feature recognition.
2. Identifying the properties and characteristics of 2D and 3D geometric primitives.
3. Developing an algorithm on C++ programming language for recognition of features on machining parts.