analiza aiqbench
This research introduces a mesh graph network architecture that solves the generalization bottleneck in machine learning surrogates for finite element analysis by encoding relative geometric features rather than absolute coordinates. By achieving high accuracy on unseen geometries and load conditions without retraining, the model offers a scalable path to accelerating structural design iterations. The approach effectively bridges computational engineering and graph neural networks, demonstrating significant performance gains over conventional methods like Random Forest and Gradient Boosting.
Mesh Graph Neural Network Framework for Accelerating Finite Element Simulation for Arbitrary Geometries
arXiv:2606.08287v1 Announce Type: new Abstract: Finite element analysis (FEA) is essential for structural design but remains computationally expensive, particularly when evaluating multiple design iterations or load scenarios. Machine learning surrogate models offer a promising alternative, yet most approaches struggle with a critical limitation: generalizing across varying geometries. This work presents a mesh graph network (MGN) for predicting von Mises stress fields in 2D structural components with arbitrary hole geometries. Unlike traditional machine learning approaches that use absolute node coordinates as features, the proposed model builds on existing MGN frameworks that encode node types (e.g., fixed boundary, free surface, hole edge), relative edge features (distance between neighbors), and global features (applied load). This architecture is inherently translation- and rotation-invariant, enabling generalization to unseen geometries without retraining. The MGN was trained on 11 plate geometries under 20 load conditions and evaluated on 7 unseen geometries and 3 unseen loads. In the most favorable case, the model achieves $R^2 \geq 0.97$ on an unseen geometry and unseen load, compared to $R^2 \approx 0.01$--$0.86$ for conventional models (Random Forest, Gradient Boosting , K-Nearest Neighbors) trained on identical data. However, even in less favorable cases, the MGN model still outperforms conventional models. This work extends the mesh-based simulation framework of Pfaff et al. (arXiv:2010.03409) to structural mechanics, demonstrating that graph neural networks can serve as efficient surrogates for finite element analysis across varying geometries.
Abstract:Finite element analysis (FEA) is essential for structural design but remains computationally expensive, particularly when evaluating multiple design iterations or load scenarios. Machine learning surrogate models offer a promising alternative, yet most approaches struggle with a critical limitation: generalizing across varying geometries. This work presents a mesh graph network (MGN) for predicting von Mises stress fields in 2D structural components with arbitrary hole geometries. Unlike traditional machine learning approaches that use absolute node coordinates as features, the proposed model builds on existing MGN frameworks that encode node types (e.g., fixed boundary, free surface, hole edge), relative edge features (distance between neighbors), and global features (applied load). This architecture is inherently translation- and rotation-invariant, enabling generalization to unseen geometries without retraining. The MGN was trained on 11 plate geometries under 20 load conditions and evaluated on 7 unseen geometries and 3 unseen loads. In the most favorable case, the model achieves $R^2 \geq 0.97$ on an unseen geometry and unseen load, compared to $R^2 \approx 0.01$--$0.86$ for conventional models (Random Forest, Gradient Boosting , K-Nearest Neighbors) trained on identical data. However, even in less favorable cases, the MGN model still outperforms conventional models. This work extends the mesh-based simulation framework of Pfaff et al. (arXiv:2010.03409) to structural mechanics, demonstrating that graph neural networks can serve as efficient surrogates for finite element analysis across varying geometries.
10 pages, 6 figures, to be published. Code available at this https URL
Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Computational Engineering, Finance, and Science (cs.CE)
arXiv:2606.08287 [cs.LG]
(or arXiv:2606.08287v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.08287 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 340 cuvinte
Subiecte conexe
IonQ and partners show practical applications and future roadmap at IEEE 2026
Quantum Zeitgeist · 14 sept. 2026
Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
arXiv · 10 iun. 2026
Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
arXiv · 14 oct. 2026
News
Quantum Computing Report · 25 iul. 2026