A hybrid method for feature recognition in computer-aided design models

Abstract

Automatic feature recognition (AFR) techniques applied to three-dimensional (3D) solid models are an important tool for achieving a true integration of computer-aided design (CAD) and computer-aided manufacturing (CAM) processes. In particular, AFR systems allow the identification in CAD models of high-level geometrical entities: features that are semantically significant for manufacturing operations. However, the recognition performances of most of the existing AFR systems are limited to the requirements of specific manufacturing applications. This paper presents a new hybrid method that facilitates the deployment of AFR systems in different application domains. In particular, the method includes two main processing stages: learning and feature recognition. During the learning stage, knowledge acquisition techniques are applied for generating feature-recognition rules and feature hints automatically from training data. Then, these hints and rule bases are utilized in the feature-recognition stage to analyse boundary representation (B-Rep) part models and identify their feature-based internal structure. The proposed AFR method is implemented within a prototype feature-recognition system and its capabilities are verified on two benchmarking parts.