Clustering & retrieval of mechanical 3D CAD models

To overcome the shortcomings of traditional attribute-based retrieval method and to realize geometrical-content-based retrieval for mechanical three-di mensional(3D) CAD models,a newapproach of clustering and re-trieval of mechanical 3D CAD models was presented.Firstly,The STandardfor the Exchange of Product model data(STEP) AP203 Part21 files of CAD model were transformedinto attributed-graph files by searching and matchingkeywords.Secondly,feature invariants were extracted and feature invariant vector of CAD model was formed bycalculating graph related attributes such as the total number of nodes and edges.Finally,a Self-Organization fea-ture Mapping(SOM) neural network model was employed to cluster and retrieve CAD models by using the extractedinvariant vector as its input to train the neural network.The proposed approach was verified to be valid and feasiblebased on 60 real industry 3D CAD models,and the experi mental results showed that it could meet general require-ments of engineering retrieval.