A hybrid 3D feature recognition method based on rule and graph


The implementation of automatic feature recognition (AFR) techniques is considered an indispensable concept in transferring product data between computer-aided design (CAD) and computer-aided process planning (CAPP). Different AFR techniques and systems have been developed to serve this aim; however, each of them have limitations. The main research gap is that each system is restricted to a specific set of predefined manufacturing features, which makes the universality of these methods difficult to extended. To solve this problem, a new hybrid 3D feature recognition method (graph and rule based) is proposed for recognizing machining features, and shaft parts are taken as an example in this paper. First, the reverse modeling method is used to classify the machining features in the part design process. Second, the 3D model is represented by B-Rep, and the weighted attribute adjacency matrix (WAAM) is proposed to represent the data structure of the B-Rep model. Third, the recognition and suppression rules are defined. Finally, three typical shaft parts are used as the test cases in MATLAB. The test results show hybrid feature recognition method can recognize all features. The comparative test shows that the practicability and efficiency of the method are satisfactory. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

International Journal of Computer Integrated Manufacturing
Yuqian Lu
Yuqian Lu
Principle Investigator / Senior Lecturer

My research interests include smart manufacturing systems, industrial AI and robotics.