—Automatic recognition of machining features is essential for the integration of CAD and CAM. Graph-based recognition is the most researched feature recognition method as the B-Rep CAD modelers’ database uses graph to store the model data. A graph-based feature recognition system uses attributed graphs to store CAD models as well as machining feature templates. The graph isomorphism is used to extract features in the model graph and template graphs. There are two main research issues in this system- (1) Efficiently recognize the features as the graph isomorphism is computationally very expensive and (2) incrementally expanding the feature template database to include new features, without any structural change in the recognizer. In this paper, the application of feature vectors (a heuristic developed by the authors that converts a feature graph into a unique vector of integers, irrespective of the node-labeling scheme used by B-Rep modelers), to automatically expand the recognizer’s feature template database, is presented. It facilitates automatic inclusion of new features in a feature database, without requiring any additional programming effort from the user or any changes in the structure of the recognizer. The proposed system has been implemented in Visual C++ and ACIS solid modeling toolkit. Further, the proposed system is intelligent as it has the capabilities to learn from the examples to incrementally build the feature database.
—Machining feature, feature recognition, graph matching, solid model.
Rachna Verma is with the Department of Computer Science and Engineering, J.N.V. University, Jodhpur, India (e-mail: firstname.lastname@example.org).
A. K. Verma is with the Department of Production and Industrial Engineering, J.N.V. University, Jodhpur, India (e-mail: email@example.com).
Cite:Rachna Verma and A. K. Verma, "Development of an Intelligent Database System to Automate the Recognition of Machining Features from a Solid Model Using Graph Theory," International Journal of Computer Theory and Engineering vol. 9, no. 1, pp. 58-61, 2017.