ML based Automatic Feature Recognition (Supervised/Unsupervised)
Unsupervised machining feature recognition extracts the machining features and groups them directly from CAD models of mechanical parts. The framework handles the size variation, and learns the distribution of complex manufacturing feature shapes across a large 3D model dataset and discovers distinguishing features that help in grouping similar features. The framework can recognize manufacturing features from the low-level geometric data such as voxels / point cloud with a very high accuracy.
Recognizing planar intersecting features in the 3D CAD models. Data-driven framework that includes continuous learning to ensure that it can be easily extended to identify a large variety of machining features leading to a sound foundation for real-time computer aided process planning (CAPP) systems.