Injection Molding Simulation based on Graph Neural Networks (GNNs): Unterschied zwischen den Versionen
Keine Bearbeitungszusammenfassung |
Keine Bearbeitungszusammenfassung |
||
Zeile 6: | Zeile 6: | ||
|termin=Institutsseminar/2022-06-24 Zusatztermin | |termin=Institutsseminar/2022-06-24 Zusatztermin | ||
|vortragsmodus=in Präsenz | |vortragsmodus=in Präsenz | ||
|kurzfassung=Numerical filling simulations are an important tool for the development of injection | |kurzfassung=Numerical filling simulations are an important tool for the development of injection molding parts. Existing simulations rely on numerical solvers based on the finite element method. These solvers are reliable and precise, but very computationally expensive even | ||
molding parts. Existing simulations rely on numerical solvers based on the finite element | on simple part geometries. In this thesis, we aim to develop a faster injection molding simulation based on Graph Neural Networks (GNNs) as a surrogate model. Our approach learns a simulation as a composition of three functions: an encoder, a processor and a | ||
method. These solvers are reliable and precise, but very computationally expensive even | decoder. The encoder takes in a graph representation of a 3D geometry of an injection molding part and returns a numeric embedding of each node in the graph. The processor | ||
on simple part geometries. In this thesis, we aim to develop a faster injection molding | updates the embeddings of each node multiple times based on its neighbors. The decoder then decodes the final embeddings of each node into physically meaningful variables, say, the fill state of the node. Our model can predict the progression of the flow front during a | ||
simulation based on Graph Neural Networks (GNNs) as a surrogate model. Our approach | time step with a fixed size. To simulate a full mold filling process, our model is applied sequentially until the entire mold is filled. Our architecture is applicable to any kind of material, geometry and injection process parameters. We evaluate our architecture by | ||
learns a simulation as a composition of three functions: an encoder, a processor and a | its accuracy and runtime when predicting node properties. We also evaluate our model's transfer learning ability on a real world injection molding part. | ||
decoder. The encoder takes in a graph representation of a 3D geometry of an injection | |||
molding part and returns a numeric embedding of each node in the graph. The processor | |||
updates the embeddings of each node multiple times based on its neighbors. The decoder | |||
then decodes the final embeddings of each node into physically meaningful variables, say, | |||
the fill state of the node. Our model can predict the progression of the flow front during a | |||
time step with a fixed size. To simulate a full mold filling process, our model is applied | |||
sequentially until the entire mold is filled. Our architecture is applicable to any kind of | |||
material, geometry and injection process parameters. We evaluate our architecture by | |||
its accuracy and runtime when predicting node properties. We also evaluate our | |||
transfer learning ability on a real world injection molding part. | |||
}} | }} |
Version vom 10. Juni 2022, 09:25 Uhr
Vortragende(r) | Jonas Zoll | |
---|---|---|
Vortragstyp | Bachelorarbeit | |
Betreuer(in) | Daniel Ebi | |
Termin | Fr 24. Juni 2022 | |
Vortragssprache | ||
Vortragsmodus | in Präsenz | |
Kurzfassung | Numerical filling simulations are an important tool for the development of injection molding parts. Existing simulations rely on numerical solvers based on the finite element method. These solvers are reliable and precise, but very computationally expensive even
on simple part geometries. In this thesis, we aim to develop a faster injection molding simulation based on Graph Neural Networks (GNNs) as a surrogate model. Our approach learns a simulation as a composition of three functions: an encoder, a processor and a decoder. The encoder takes in a graph representation of a 3D geometry of an injection molding part and returns a numeric embedding of each node in the graph. The processor updates the embeddings of each node multiple times based on its neighbors. The decoder then decodes the final embeddings of each node into physically meaningful variables, say, the fill state of the node. Our model can predict the progression of the flow front during a time step with a fixed size. To simulate a full mold filling process, our model is applied sequentially until the entire mold is filled. Our architecture is applicable to any kind of material, geometry and injection process parameters. We evaluate our architecture by its accuracy and runtime when predicting node properties. We also evaluate our model's transfer learning ability on a real world injection molding part. |