Meta-neural Topology Optimization: Knowledge Infusion with Meta-learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917911111663616 |
|---|---|
| author | Kuszczak, Igor Kus, Gawel Bosi, Federico Bessa, Miguel A. |
| author_facet | Kuszczak, Igor Kus, Gawel Bosi, Federico Bessa, Miguel A. |
| contents | Engineers learn from every design they create, building intuition that helps them quickly identify promising solutions for new problems. Topology optimization (TO) - a well-established computational method for designing structures with optimized performance - lacks this ability to learn from experience. Existing approaches treat design tasks in isolation, starting from a "blank canvas" design for each new problem, often requiring many computationally expensive steps to converge. We propose a meta-learning strategy, termed meta-neural TO, that finds effective initial designs through a systematic transfer of knowledge between related tasks, building on the mesh-agnostic representation provided by neural reparameterization. We compare our approach against established TO methods, demonstrating efficient optimization across diverse test cases without compromising design quality. Further, we demonstrate powerful cross-resolution transfer capabilities, where initializations learned on lower-resolution discretizations lead to superior convergence in 74.1% of tasks on a higher-resolution test set, reducing the average number of iterations by 33.6% compared to standard neural TO. Remarkably, we discover that meta-learning naturally gravitates toward the strain energy patterns found in uniform density designs as effective starting points, aligning with engineering intuition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01830 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Meta-neural Topology Optimization: Knowledge Infusion with Meta-learning Kuszczak, Igor Kus, Gawel Bosi, Federico Bessa, Miguel A. Computational Engineering, Finance, and Science Computational Physics Engineers learn from every design they create, building intuition that helps them quickly identify promising solutions for new problems. Topology optimization (TO) - a well-established computational method for designing structures with optimized performance - lacks this ability to learn from experience. Existing approaches treat design tasks in isolation, starting from a "blank canvas" design for each new problem, often requiring many computationally expensive steps to converge. We propose a meta-learning strategy, termed meta-neural TO, that finds effective initial designs through a systematic transfer of knowledge between related tasks, building on the mesh-agnostic representation provided by neural reparameterization. We compare our approach against established TO methods, demonstrating efficient optimization across diverse test cases without compromising design quality. Further, we demonstrate powerful cross-resolution transfer capabilities, where initializations learned on lower-resolution discretizations lead to superior convergence in 74.1% of tasks on a higher-resolution test set, reducing the average number of iterations by 33.6% compared to standard neural TO. Remarkably, we discover that meta-learning naturally gravitates toward the strain energy patterns found in uniform density designs as effective starting points, aligning with engineering intuition. |
| title | Meta-neural Topology Optimization: Knowledge Infusion with Meta-learning |
| topic | Computational Engineering, Finance, and Science Computational Physics |
| url | https://arxiv.org/abs/2502.01830 |