Connection Feature Extraction in 3D CAD Assemblies using a Knowledge Graph

Recycling is becoming increasingly important, due to growing resource shortages and the need of a reduction in CO 2 emission. Automated disassembly is essential for accelerating recycling processes and optimizing the extraction of valuable materials. To achieve an automated disassembly, it is crucial for an automated disassembly system to know the type of connections between components in an assembly. We present a method for extracting connections from 3D CAD models of assemblies. Our approach identifies connections through collision detection and populates a knowledge graph with the acquired data. This knowledge graph serves as foundation for software systems to assess product recyclability or to optimize recycling processes.