Multi-objective design of multi-material truss lattices utilizing graph neural networks
Abstract The rapid advancements in additive manufacturing (AM) across different scales and material classes have enabled the creation of architected materials with highly tailored properties. Beyond geometric flexibility, multi-material AM further expands design possibilities by combining materials...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-86812-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585759438143488 |
|---|---|
| author | Ramón Frey Michael R. Tucker Mohamadreza Afrasiabi Markus Bambach |
| author_facet | Ramón Frey Michael R. Tucker Mohamadreza Afrasiabi Markus Bambach |
| author_sort | Ramón Frey |
| collection | DOAJ |
| description | Abstract The rapid advancements in additive manufacturing (AM) across different scales and material classes have enabled the creation of architected materials with highly tailored properties. Beyond geometric flexibility, multi-material AM further expands design possibilities by combining materials with distinct characteristics. While machine learning has recently shown great potential for the fast inverse design of lattice structures, its application has largely been limited to single-material systems. In this work, we propose a novel approach that incorporates material properties as edge features within the graph representation of multi-material truss lattices, utilizing graph neural networks (GNNs) to develop a fast and efficient inverse design framework. We validate this framework by designing lattices with tunable thermal expansion and stiffness properties, showcasing its ability to explore a broad and flexible design space. We showcase the framework’s inverse design capabilities for both single and multi-objective optimization tasks and assess its limitations. Additionally, we demonstrate the superior capacity of GNNs in capturing structure-property relationships for multi-material systems. We anticipate that the continued advancement of GNN-assisted inverse design will play a key role in unlocking the full potential of multi-material truss lattices. |
| format | Article |
| id | doaj-art-213478e090a240a297ff0e4310f9d9df |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-213478e090a240a297ff0e4310f9d9df2025-01-26T12:30:54ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-025-86812-3Multi-objective design of multi-material truss lattices utilizing graph neural networksRamón Frey0Michael R. Tucker1Mohamadreza Afrasiabi2Markus Bambach3Advanced Manufacturing Lab, ETH ZürichAdvanced Manufacturing Lab, ETH ZürichAdvanced Manufacturing Lab, ETH ZürichAdvanced Manufacturing Lab, ETH ZürichAbstract The rapid advancements in additive manufacturing (AM) across different scales and material classes have enabled the creation of architected materials with highly tailored properties. Beyond geometric flexibility, multi-material AM further expands design possibilities by combining materials with distinct characteristics. While machine learning has recently shown great potential for the fast inverse design of lattice structures, its application has largely been limited to single-material systems. In this work, we propose a novel approach that incorporates material properties as edge features within the graph representation of multi-material truss lattices, utilizing graph neural networks (GNNs) to develop a fast and efficient inverse design framework. We validate this framework by designing lattices with tunable thermal expansion and stiffness properties, showcasing its ability to explore a broad and flexible design space. We showcase the framework’s inverse design capabilities for both single and multi-objective optimization tasks and assess its limitations. Additionally, we demonstrate the superior capacity of GNNs in capturing structure-property relationships for multi-material systems. We anticipate that the continued advancement of GNN-assisted inverse design will play a key role in unlocking the full potential of multi-material truss lattices.https://doi.org/10.1038/s41598-025-86812-3 |
| spellingShingle | Ramón Frey Michael R. Tucker Mohamadreza Afrasiabi Markus Bambach Multi-objective design of multi-material truss lattices utilizing graph neural networks Scientific Reports |
| title | Multi-objective design of multi-material truss lattices utilizing graph neural networks |
| title_full | Multi-objective design of multi-material truss lattices utilizing graph neural networks |
| title_fullStr | Multi-objective design of multi-material truss lattices utilizing graph neural networks |
| title_full_unstemmed | Multi-objective design of multi-material truss lattices utilizing graph neural networks |
| title_short | Multi-objective design of multi-material truss lattices utilizing graph neural networks |
| title_sort | multi objective design of multi material truss lattices utilizing graph neural networks |
| url | https://doi.org/10.1038/s41598-025-86812-3 |
| work_keys_str_mv | AT ramonfrey multiobjectivedesignofmultimaterialtrusslatticesutilizinggraphneuralnetworks AT michaelrtucker multiobjectivedesignofmultimaterialtrusslatticesutilizinggraphneuralnetworks AT mohamadrezaafrasiabi multiobjectivedesignofmultimaterialtrusslatticesutilizinggraphneuralnetworks AT markusbambach multiobjectivedesignofmultimaterialtrusslatticesutilizinggraphneuralnetworks |