1、Machine Interpretation of CAD Data for ManufacturingApplicationsMachine interpretation of the shape of a component from CAD databases is an important problem in CAD/CAM, computer vision, and intelligent manufacturing. It can be used in CAD/CAM for evaluation of designs, in computer vision for machin
2、e recognition and machine inspection of objects, and in intelligent manufacturing for automating and integrating the link between design and manufacturing. This topic has been an active area of research since the late 70s, and a significant number of computational methods have been proposed to ident
3、ify portions of the geometry of a part having engineering significance (here called “features”). However, each proposed mechanism has been able to solve the problem only for components within a restricted geometric domain (such as polyhedral components), or only for components whose features interac
4、t with each other in a restricted manner. The purposes of this article are to review and summarize the development of research on machine recognition of features from CAD data, to discuss the advantages and potential problems of each approach, and to point out some of the promising directions future
5、 investigations may take. Since most work in this field has focused on machining features, the article primarily covers those features associated with the manufacturing domain. In order to better understand the state of the art, methods of automated feature recognition are divided into the following
6、 categories of methods based on their approach: graph-based, syntactic pattern recognition, rule-based, and volumetric. Within each category we have studied issues such as the definition of features, mechanisms developed for recognition of features, the application scope, and the assumptions made. I
7、n addition, the problem is addressed from the perspective of information input requirements and the advantages and disadvantages of boundary representation, constructive solid geometry (CSG), and 2D drawings with respect to machine recognition of features are examined. Emphasis is placed on the mech
8、anisms for attacking problems associated with interacting features.1. INTRODUCTIONDesign is a set of important processes that occur at different life-cycle stages of a product. Computer-aided design (CAD), in general, refers to using computers to assist with the various functions in the design proce
9、ss. Engineers consider CAD data to be the data that represent a product or component: in the domain of mechanical components these are often represented as a set of engineering drawings or a solid model of a component.Although CAD has been used to assist with various design tasks, CAPP (computer-aid
10、ed process planning) has usually referred to the collection of activities that convert a part design into manufacturing instructions that de-scribe how to produce the part or how to build an assembly to satisfy the design specifications. In the domain of machined components, process planning involve
11、s finding the sequence of processes with which parts are to be machined (such as milling, grinding, drilling, etc.), the fixturing configuration to set up the part for each process to be carried out, and the tools to be used to carry out each operation in the sequence. In order to achieve this task
12、for a component, process planners interpret the design data (the shape, surface finish, tolerances, etc.) based on process and tool capabilities.Computer-integrated manufacturing (CIM) systems attempt to integrate design, process planning, and other functions (material handling, factory management,
13、etc.) in a production environment. However, developing truly integrated manufacturing systems has proved not to be a trivial undertaking. One important reason has been that CAD data consisting of annotated engineering drawings or the solid model of a component are not manufacturing-specific and gene
14、rally represent geometry by a low-level description of edges, vertices, and faces of a component, whereas process planners work with primitives such as slots and holes (and properties of the primitives such as dimensions and surface finish) that are shapes produced by processes and tools. In order t
15、o overcome the integration barrier between design and process planning, a task which previously relied upon a manual interpretation process by an engineer, several conscious efforts have been made, all using the concept of features. As explained later, the strategy has been either to incorporate fea
16、tures in the CAD data during the design process or to extract the features from CAD data, or a combination of both. In the next section, we first consider features and what they refer to in the remainder of this article.1.1 FeaturesThere is no universally accepted definition of features. In fact, this has been one of the difficulties researchers have faced in this area. However, two recent books Shah and Mantyla 1995; Shah et al. 1994 have described features as grouping
