Manufacturing feature recognition from solid models: a status report

Abstract

The field of solid modeling has developed a variety of techniques for unambiguous representations of three-dimensional objects. Feature recognition is a sub-discipline of solid modeling that focuses on the design and implementation of algorithms for detecting manufacturing information from solid models produced by computer-aided design (CAD) systems. Examples of this manufacturing information include features such as holes, slots, pockets and other shapes that can be created on modern computer numerically controlled machining systems. Automated feature recognition has been an active research area in solid modeling for many years and is considered to be a critical component for integration of CAD and computer-aided manufacturing. This paper gives an overview of the state-of-the-art in feature recognition research. Rather than giving an exhaustive survey, we focus on the three of the major algorithmic approaches for feature recognition: graph-based algorithms, volumetric decomposition techniques, and hint-based geometric reasoning. For each approach, we present a detailed description of the algorithms being employed along with some assessments of the technology. We conclude by outlining important open research and development issues.

Automated process planning for hybrid manufacturing

“…Automatic feature recognition comprises a large body of literature for traditional SM (reviewed in [16][17][18][19]). Notable techniques include volumetric decomposition [20,21], graph-based B-rep analysis [22,23], and rule-based pattern recognition [24,25] among others.…”

“…By substituting the conjunctive expression in (15) for the subcollection of nonempty atoms A J M in the disjunctive expression in (16), we obtain a disjunctive normal form (DNF) for the manufactured outcome. For example, the 3 nonempty atoms in (17) through (19) collectively represent a decomposition of a potentially manufacturable solid shown in Fig. 8 (d) (top-left) decomposed as:…”

“…Substituting (17) through (19) in (20) yields a DNF denoted hereafter by E † [P]. It has no physical meaning by itself in terms of sequence of AM/SM actions.…”

A Novel Approach for Automatic Machining Feature Recognition with Edge Blend Feature

“…Most of researchers prefer taking the topological relationship of adjacent entities in feature recognition. A thorough review on feature recognition methodologies has been done by several researchers [1][2][3][4]. Ansaldi et al [5] proposed a face adjacency graph structure with a rule-based algorithm for generating graphs of the topological relationship of adjacent faces for several types of features.…”

Sharp feature detection in point clouds

“…Feature design consists of introducing functional or manufacturing features directly into the CAD model in order to make the design process more efficient. Feature recognition tries to extract manufacturing or form features from a solid model [JPR00]. In modeling and computer graphics the term feature is used for free form features of 3D shapes.…”