Toward automated topology optimization : identification of non-design features of CAD models using graph neural networks

Jasinski, MichaelMichaelJasinskiSchöfer, FabianFabianSchöferSeibel, ArthurArthurSeibel2024-09-092024-09-092023-09-12Proceedings of the International Conference on Additive Manufacturing in Products and Applications (AMPA 2023)978-3-031-42982-8978-3-031-42983-5https://hdl.handle.net/11420/48990This paper presents an automated identification of non-design features of CAD models for topology optimization using learning-based segmentation. The CAD files are taken from a large database of industry-relevant components. Based on the geometry and topology of the components, a graph structure is created and processed by a deep neural network. The results show good match with real cases and can be continuously improved by training with additional data.enDesign AutomationGraph Neural NetworksTopology OptimizationTechnology::620: EngineeringComputer Science, Information and General Works::005: Computer Programming, Programs, Data and SecurityToward automated topology optimization : identification of non-design features of CAD models using graph neural networksBook part10.1007/978-3-031-42983-5_19Other