CHAPTER 5 - Geometric computation for the recognition of spatially interacting machining features

Abstract Machining process planners, both humans and automata, reason in terms of features such as holes, slots and pockets. Some of today's CAD systems provide capabilities for defining objects through features. But these are essentially shape macros. They are not guaranteed to be machinable, and often do not correspond directly to machining features. To establish a bridge between CAD and CAM systems, machining features must be automatically recognized. Spatially interacting features are a major source of difficulties in feature recognition. Feature interferences alter the face and edge patterns associated with the features. This complicates both the identification of the features in a part, and the derivation of all the data about the features required for automated manufacturing planning. This paper discusses the geometrical aspects of an automatic feature recognizer recently developed at the University of Southern California for the domain of parts that can be machined on 3-axis machining centers. The recognizer is implemented in an environment consisting of the KnowledgeCraft TM AI shell coupled with either the Parasolid TM or the PADL-2 solid modelers, and running on Sun workstations. It automatically produces feature removal volumes and representations for feature interactions. The recognizer's ability to deal with interacting features is due mainly to an operation called feature completion, described in this paper. Completion is a surface-to-solid transformation. It produces the largest volumetric feature that is machinable and compatible with its traces present in the object's boundary.