A hybrid approach for identification of 3D features from CAD database for manufacturing support

摘要

A number of approaches for identification of 3D features are available today including syntactic recognition methods, graph based methods, expert systems and knowledge based approach. Work done on all such approaches shows lack of generalization, difficulty in implementation or little demonstrated computational viability. In this paper, a hybrid approach for non-interacting 3D-feature identification from CAD database has been proposed, which is partly mathematically iterative and partly based on heuristic rules. Initially a void non-polyhedral pocket feature has been undertaken to establish the procedures and later this is extended for all features in general. A couple of test results are presented with CPU times and inherent heuristics. The process is applicable for process planners and manufacturers in industries.