Full-field prediction for engineering-scale three-dimensional aircraft with multigrid-hierarchical learning

2026-05-26

AI Summary

This study addresses the high computational cost of high-fidelity CFD simulations for full-scale three-dimensional aircraft and the inability of existing deep learning approaches to effectively model the multiscale, highly heterogeneous flow fields. To overcome these challenges, this work proposes MHLF, a multigrid hierarchical learning framework that, for the first time, enables efficient and accurate prediction of full-field aerodynamic flows across subsonic, transonic, and supersonic regimes for large 3D aircraft configurations. By integrating topology-consistent geometric multigrid representations with hierarchical deep learning strategies and embedding them into the CFD solver for joint optimization, the method achieves 3–8× faster convergence while preserving high-fidelity accuracy across three real-world aircraft cases, thereby surpassing prior approaches limited to two-dimensional, surface-only, or simplified three-dimensional scenarios.

Abstract

High-fidelity computational fluid dynamics is essential for aerospace design, but engineering-scale simulations of practical three-dimensional aircraft remain computationally expensive. Learning-based flow-field initialization can improve efficiency by reducing the numerical distance between the initial and converged solutions, yet existing deep learning approaches remain difficult to scale to large three-dimensional aircraft flows with multiscale regional heterogeneity. Most prior studies therefore focus on two-dimensional problems, surface quantities, integral aerodynamic coefficients, or simplified three-dimensional cases with limited grid resolution.Here we propose MHLF, a multigrid-hierarchical learning framework for accelerating engineering-scale aircraft flow simulations while preserving high-fidelity numerical accuracy. MHLF combines a topologically consistent geometric multigrid representation with a hierarchical strategy that captures regional flow heterogeneity during both prediction and subsequent CFD correction. Across three engineering-scale aircraft cases spanning Mach 0.15 to 6.0 and covering subsonic, transonic and supersonic regimes, MHLF accelerates convergence without sacrificing flow-field accuracy, achieving a 3 to 8 times efficiency improvement over conventional initialization. These results demonstrate practical full-flow-field prediction for large three-dimensional aircraft within the CFD domain and provide a foundation for data-driven acceleration of high-fidelity aircraft flow simulation.

Problem

• computational fluid dynamics
• full-field prediction
• engineering-scale aircraft
• three-dimensional flow
• flow-field initialization

Innovation

• multigrid-hierarchical learning
• full-field prediction
• computational fluid dynamics
• engineering-scale aircraft
• flow-field acceleration