Special Panel Session for Feature Recognition

Feature recognition is a discipline focusing on the design and implementation of algorithms for detecting manufacturing information such as holes, slots, etc. in a solid model. Automated feature recognition has been an active research area in solid modeling for many years, and is considered to be a critical component for CAD/CAM integration. This paper gives foundations for understanding the state of the art in feature recognition research. It also establishes the context for a special panel session at the 17th ASME International Computers in Engineering Conference. Four papers from different research groups participated in a benchmarking exercise on feature recognition; each wrote a paper on the results of executing their feature recognition systems on a collected set of parts. This panel session should serve as a catalyst for the feature recognition community to collaborate in establishing standard test parts and performance measures and in identifying and resolving research issues. Introduction: Why Features? In the early 1960s Ivan Sutherland developed the SKETCHPAD system The evolution of computer graphics has since resulted in the development of Computer Aided Design (CAD). The early CAD systems were essentially for two-dimensional drawing and drafting. In the early 1970s, solid modeling techniques emerged in earnest to describe three-dimensional products unambiguously (6) (10) (11), and we have seen a prolif1A portion of this work was sponsored by the National Institute of Standards and Technology’s Manufacturing Systems Integration Division. eration of solid modelers and three-dimensional CAD systems. On the other hand, Numerical Control (NC) machines were first introduced in the early 1950s and sparked the research and development of Computer Aided Manufacturing (CAM). In industry, CAD and CAM are extensively used to assist in design and manufacture of products, respectively. However, effective CAD/CAM integration has been elusive, and extensive human intervention is still necessary to move ideas and designs between CAD and CAM in most manufacturing domains (1). Computer Aided Process Planning (CAPP) is seen as a communication agent between CAD and CAM. Given CAD data of a part (a component of a product to be manufactured), the goal of CAPP is to generate a sequenced set of instructions used to manufacture the specified part. In order to do that, CAPP has to interpret the part in terms of features. Informally, features are generic shapes or other characteristics of a part with which engineers can associate knowledge useful for reasoning about the part (15). Figure 1-(a) shows feature examples in the machining domain where a product is made by material removal: the part is interpreted in terms of a hole, a slot and a pocket. CAPP will use these features to generate manufacturing instructions to produce the part. For example, CAPP typically generates a drilling operation for the hole. Features play a key role in CAD/CAM integration. There have been two decades of research on recognition of features from solid models since the seminal work of Kyprianou in 1980 (7). Although significant progresses have been made on many research fronts, at present there seem to be no fully automated feature recognition or process planning systems for other (a) part and features (c) (volumetric) machining features hole slot pocket (b) surface features hole slot pocket hole slot