Development of a neural network to recognize standards and features from 3D CAD models
This work addresses the need for automated part recognition in CAD systems, which is incremental as it applies existing neural network methods to a specific domain.
The researchers tackled the problem of automatically recognizing standards and features from 3D CAD models by training a neural network to identify nine classes of machine elements, such as hexagon head screws, and using an API to access and supplement geometric information.
Focus of this work is to recognize standards and further features directly from 3D CAD models. For this reason, a neural network was trained to recognize nine classes of machine elements. After the system identified a part as a standard, like a hexagon head screw after the DIN EN ISO 8676, it accesses the geometrical information of the CAD system via the Application Programming Interface (API). In the API, the system searches for necessary information to describe the part appropriately. Based on this information standardized parts can be recognized in detail and supplemented with further information.