Shape and Context-Based Recognition of Standard Mechanical Parts in CAD Models

The work here presented is part of a wider research project aimed at extracting and using in industrialapplications high level semantic information from 3D product models that are described by means oftheir boundary representation (B-rep). The specific focus of the paper is the recognition among thecomponents of the CAD model of an assembly of those belonging to some categories of standard partslargely employed in mechanical industry. The knowledge of these components is crucial to understandthe structure of mechanical products as they have specific meaning and function. Standard parts followinternational standard in shape and dimensions, and also typical mounting schemes exist concerningtheir use in the product assembly. These distinctive features have been exploited as a starting point todevelop a multi-step recognition algorithm. It includes a shape-based and a context-based analysis bothrelying on the geometric and topological analysis of a CAD model. As already anticipated by Voelckerin his visionary ability to anticipate open challenges, the shape of an object alone is not enough tounderstand its function. Therefore, context assessment becomes crucial to validate the recognitiongiven by the shape-based step. It allows to uniquely recognize components in mechanical CAD models,by confirming correct results, refusing the false positives, as well as choosing the correct one whenthe assignment is multiple.