Evaluation of existing and new feature recognition algorithms: Part 1: Theory and implementation

Abstract

This is the first of two papers evaluating the performance of general-purpose feature detection techniques for geometric models. In this paper, six different methods are described to identify sets of faces that bound depression and protrusion faces. Each algorithm has been implemented and tested on eight components from the National Design Repository. The algorithms studied include previously published general-purpose feature detection algorithms such as the single-face inner-loop and concavity techniques. Others are improvements to existing algorithms such as extensions of the two-dimensional convex hull method to handle curved faces as well as protrusions. Lastly, new algorithms based on the three-dimensional convex hull, minimum concave, visible and multiple-face inner-loop face sets are described. These algorithms provide a basis for the comparative analysis that is the subject of the second paper.

Systematic development and evaluation of composite methods for recognition of three-dimensional subtractive features

“…There are six resulting methods, which are: (a) the visible face set method, (b) the minimum and (c) the maximum concavity methods, (d) the singleface (sfil) and (e) the multiple-face inner loop (mfil) methods, and (f) the cavity method. A detailed description of these methods has been given in a previous paper [18], but for the sake of completeness, a brief description of each of them is given below.…”

“…It has been possible to determine the enveloping faces with a tenfold efficiency over the methods suggested in earlier research [14], which involves Boolean operation of the half-space of each face with the rest of the component. The efficient method, detailed elsewhere [18], uses a simpler face visibility algorithm to determine an enveloping face as one that is not visible to any face on the component.…”

“…This paper proposes and implements such a methodology for establishing and evaluating combinations of feature detection methods for face sets bounding depression features. The paper takes the earlier contributions [18,19] of the authors as a starting point. In the earlier works, types of face sets from the simplest to the most complex were systematically identified and algorithms for detecting them were developed and evaluated.…”

Fixture knowledge model development and implementation based on a functional design approach

“…Such analysis has to provide enough information to define properly the location of the different fixture elements. Design features recognition is a research discipline in itself and different algorithms have been proposed based on different approaches: visibility map and convex hull, graph-based B-rep model, volume decomposition, feature templates and discretization techniques [21,22]. The part geometry knowledge unit describes a detailed view of the geometric and topological entities that could be used to define the geometric model, both the part to be machined and of the fixture solution.…”

Algorithms for Recognition of Geometric and Parametric Features in prismatic parts using IGES

“…Feature is a portion of a solid model that finds interest in any phase of the product life cycle namely: conception, design, manufacture, service, and repair. From a production engineer's point of view features can be seen as specific geometric shapes on a part that can be associated with certain manufacturing processes [2,3]. The features which are highlighted during the modeling phase of the product's design process and the subsequent production planning phases would help the engineers to take the advantage of this information in accessing data regarding the production of these features.…”