A new methodology for extracting manufacturing features from CAD system

In recent years, various researchers have come up with different ways and means to integrate CAD and CAM. Automatic feature recognition from CAD solid systems highly impacts the level of integration. CAD files contain detailed geometric information of a part, which are not suitable for using in the downstream applications such as process planning. Different CAD or geometric modeling packages store the information related to the design in their own databases. Structures of these databases are different from each other. As a result no common or standard structure has been developed so far, that can be used by all CAD packages. For that reason this paper proposes an intelligent feature recognition methodology (IFRM) to develop a feature recognition system which has the ability to communicate with various CAD/ CAM systems. The proposed methodology is developed for 3D prismatic parts that are created by using solid modeling package by using CSG technique as a drawing tool. The system takes a neutral file in Initial Graphics Exchange Specification (IGES) format as input and translates the information in the file to manufacturing information. The boundary (B-rep) geometrical information of the part design is then analyzed by a feature recognition program that is created specifically to extract the features from the geometrical information based on a geometric reasoning approach by using object oriented design software which is included in C++ language. A feature recognition algorithm is used to recognize different features of the part such as step, holes, etc. Finally, a sample application description for a workpiece is presented for demonstration purposes. 2006 Elsevier Ltd. All rights reserved.