Loop2Net: Data-Driven Generation and Optimization of Airfoil CFD Meshes from Sparse Boundary Coordinates

2025/06/28 by Lushun Fan, Fan, Lushun, Xia, Yuqin +4
Computer Science · Engineering · #Advanced Multi-Objective Optimization Algorithms #Topology Optimization in Engineering #Computational Fluid Dynamics and Aerodynamics

paper · pdf · doi:10.48550/arxiv.2507.01057

Abstract

In this study, an innovative intelligent optimization system for mesh quality is proposed, which is based on a deep convolutional neural network architecture, to achieve mesh generation and optimization. The core of the study is the Loop2Net generator and loss function, it predicts the mesh based on the given wing coordinates. And the model's performance is continuously optimised by two key loss functions during the training. Then discipline by adding penalties, the goal of mesh generation was finally reached.

Citations

• Swarm Reinforcement Learning For Adaptive Mesh Refinement
• MeshDQN: A Deep Reinforcement Learning Framework for Improving Meshes in Computational Fluid Dynamics
• An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks
• Reinforcement Learning for Adaptive Mesh Refinement
• Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
• Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows
• AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation
• Network In Network

Related

• AirCANS: CFD 2D Mesh Optimisation-based Airfoil Classification and Assessment using Neural Networks
• MeshDQN: A Deep Reinforcement Learning Framework for Improving Meshes in Computational Fluid Dynamics
• Machine Learning-Based Optimal Mesh Generation in Computational Fluid Dynamics
• Airfoil Shape Optimization using Deep Q-Network
• Accelerated Airfoil Design Using Neural Network Approaches