Accelerated intelligent generation of high-fidelity universal O-grids for airfoil aerodynamics
- 1 August 2025
- journal article
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (8)
Abstract
The pursuit of high-fidelity aerodynamic optimization has long been hindered by three interdependent bottlenecks: (1) exponential computational costs in parametric mesh generation, (2) geometric fidelity loss during automated shape discretization, and (3) inflexible batch processing in commercial computational fluid dynamics suites. Here, a topology-aware deep learning framework that synergizes physics-guided O-grid generation with sparse autoencoder-based parameter optimization was presented. The methodology integrates topology-specific strategies for closed/open trailing edges based on aerodynamic characteristics, with generalizability validated through wind tunnel domain and surface mesh generation tests. Optimal grid parameters (surface cell size yb = 3, radial node count jx = 120, wind tunnel diameter d = 6 × 340C (C: chord length) are determined via sparse autoencoder deep neural networks. Comparative validation against experimental datasets confirms the method's efficacy, demonstrating seamless integration with novel airfoil generation algorithms. This paradigm shift enables real-time batch optimization previously deemed computationally intractable, as evidenced by second-level grid generation (1.74 s vs 20 min manually), and with the optimal grid parameters determined based on computational parameters that yield lift-to-drag ratio curves closest to experimental data, thereby significantly enhancing computational throughput in aerodynamic optimization workflows.Keywords
Funding Information
- the national defence science and technology project (KYGYJKZBXM24002)
- the national defence science and technology project (KYGYZXJK150025)
- The Doctoral Fund of Southwest University of Science and Technology (22zx7161)
This publication has 31 references indexed in Scilit:
- NeuFENet: neural finite element solutions with theoretical bounds for parametric PDEsEngineering with Computers, 2024
- Medial hex-meshing: high-quality all-hexahedral mesh generation based on medial meshEngineering with Computers, 2024
- A comprehensive survey on design and application of autoencoder in deep learningApplied Soft Computing, 2023
- A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility predictionLandslides, 2019
- Mesh Partitioning and Efficient Equation Solving Techniques by Distributed Finite Element Methods: A SurveyArchives of Computational Methods in Engineering, 2017
- An airfoil optimization technique for wind turbinesApplied Mathematical Modelling, 2012
- Patient-specific computational fluid dynamics: structured mesh generation from coronary angiographyMedical & Biological Engineering & Computing, 2010
- Approximate Shape Quality Mesh GenerationEngineering with Computers, 2001
- Efficient three‐dimensional Delaunay triangulation with automatic point creation and imposed boundary constraintsInternational Journal for Numerical Methods in Engineering, 1994
- Automatic three‐dimensional mesh generation by the modified‐octree techniqueInternational Journal for Numerical Methods in Engineering, 1984