Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913819029143552 |
|---|---|
| author | Chen, Yu-hsuan Bi, Jing Ngoc, Cyril Ngo Oancea, Victor Cagan, Jonathan Kara, Levent Burak |
| author_facet | Chen, Yu-hsuan Bi, Jing Ngoc, Cyril Ngo Oancea, Victor Cagan, Jonathan Kara, Levent Burak |
| contents | AI-driven surrogate modeling has become an increasingly effective alternative to physics-based simulations for 3D design, analysis, and manufacturing. These models leverage data-driven methods to predict physical quantities traditionally requiring computationally expensive simulations. However, the scarcity of labeled CAD-to-simulation datasets has driven recent advancements in self-supervised and foundation models, where geometric representation learning is performed offline and later fine-tuned for specific downstream tasks. While these approaches have shown promise, their effectiveness is limited in applications requiring fine-scale geometric detail preservation. This work introduces a self-supervised geometric representation learning method designed to capture fine-scale geometric features from non-parametric 3D models. Unlike traditional end-to-end surrogate models, this approach decouples geometric feature extraction from downstream physics tasks, learning a latent space embedding guided by geometric reconstruction losses. Key elements include the essential use of near-zero level sampling and the innovative batch-adaptive attention-weighted loss function, which enhance the encoding of intricate design features. The proposed method is validated through case studies in structural mechanics, demonstrating strong performance in capturing design features and enabling accurate few-shot physics predictions. Comparisons with traditional parametric surrogate modeling highlight its potential to bridge the gap between geometric and physics-based representations, providing an effective solution for surrogate modeling in data-scarce scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20110 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling Chen, Yu-hsuan Bi, Jing Ngoc, Cyril Ngo Oancea, Victor Cagan, Jonathan Kara, Levent Burak Machine Learning AI-driven surrogate modeling has become an increasingly effective alternative to physics-based simulations for 3D design, analysis, and manufacturing. These models leverage data-driven methods to predict physical quantities traditionally requiring computationally expensive simulations. However, the scarcity of labeled CAD-to-simulation datasets has driven recent advancements in self-supervised and foundation models, where geometric representation learning is performed offline and later fine-tuned for specific downstream tasks. While these approaches have shown promise, their effectiveness is limited in applications requiring fine-scale geometric detail preservation. This work introduces a self-supervised geometric representation learning method designed to capture fine-scale geometric features from non-parametric 3D models. Unlike traditional end-to-end surrogate models, this approach decouples geometric feature extraction from downstream physics tasks, learning a latent space embedding guided by geometric reconstruction losses. Key elements include the essential use of near-zero level sampling and the innovative batch-adaptive attention-weighted loss function, which enhance the encoding of intricate design features. The proposed method is validated through case studies in structural mechanics, demonstrating strong performance in capturing design features and enabling accurate few-shot physics predictions. Comparisons with traditional parametric surrogate modeling highlight its potential to bridge the gap between geometric and physics-based representations, providing an effective solution for surrogate modeling in data-scarce scenarios. |
| title | Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.20110 |