An improved structured mesh generation method based on physics-informed neural networks

Le résumé fourni par la source

Purpose Mesh generation remains a key technology in many areas where numerical simulations are required. As numerical algorithms become more efficient and computers become more powerful, the percentage of time devoted to mesh generation becomes higher. This article is to improve the usefulness of the neural network-based structured mesh generation method and accelerate the meshing process. Design/methodology/approach The article formulates the meshing problem as a global optimization problem related to a physics-informed neural network. The mesh is obtained by intelligently solving the physical boundary-constrained partial differential equations. To improve the prediction accuracy of the neural network, this article introduces a novel auxiliary line strategy and an efficient network model during meshing. The strategy first employs a priori auxiliary lines to provide ground truth data and then uses these data to construct a loss term to better constrain the convergence of the subsequent training. Findings The experimental results indicate that the proposed method is effective and robust. It can accurately approximate the mapping (transformation) from the computational domain to the physical domain and enable fast, high-quality, structured mesh generation. Research limitations/implications While the auxiliary line strategy offers an efficient way to mitigate the misprediction or distortion in complex regions, this strategy is inherently empirical and might introduce extra human intervention. Originality/value The article develops an improved structured mesh generation method based on physics-informed neural networks.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.