What type of study is this?

This is a Quantitative Study study.

October 13, 2025Open Access

PINN-MG: A physics-informed neural network for mesh generation

View Full Paper

Ask AI

Bookmark

Authors

Proposed method generates high-quality structured quad meshes in computational domains, suggesting efficiency and accuracy improvements.

PINN-MG optimizes mesh generation by using a physics-informed neural network, improving efficiency and quality.
The method incorporates the Navier-Lamé equation in its loss function, ensuring compliance with elastic body deformation laws.
Training of the PINN-MG is fully unsupervised, eliminating the need for prior datasets or extensive manual work.
Experimental results indicate that PINN-MG outperforms traditional algebraic and differential mesh generation methods.

Wang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark