DESIGN-MODEL GENERATION FOR REVERSE ENGINEERING USING MULTI-SENSORS

Reverse engineering is the process of creating a design model and a ma nufacturing database for an existing part or prototype. The applicatio ns of reverse engineering are in redesigning of existing parts/tools o r prototype parts where the CAD model of the part is not available. Re verse engineering, for the most part, is performed as an interactive p rocess where the designer identifies the surface features from digitiz ed data and then models the surfaces accordingly. This paper presents the algorithms and implementation results for a reverse engineering sy stem which is intended to automatically create CAD representations of part prototypes. An integrated sensory system combining contact and no n-contact sensors has been developed to digitize parts surfaces. The s ensory system fuses data from machine vision and a coordinate measurin g machine (CMM) in order to automatically digitize the part surface. M achine vision is used to capture the orthographic views of the part. T he images of these orthographic views are processed and vectorized to create five views of the part in the form of an engineering drawing. T he system utilizes the generated orthographic projections to automatic ally drive the CMM to capture a grid of point coordinates from the par t surface. The CMM digitization process is guided by the segmentation provided from the orthographic views. The segmented data from the part surface is input to the surface modeling module of the system where p arametric surfaces are fitted through the digitized points. The surfac es are then extended and intersected using the Hermite approximation m ethod to develop the 3-D CAD model of the part. Accuracy and automatio n is achieved by combining global shape information obtained from part images with the accurate point data acquired by a CMM. Algorithms for surface segmentation, part digitization, surface extension, and surfa ce intersection modeling are described in this paper.