LGFNet: Local-Global Fusion Network with Fidelity Gap Delta Learning for Multi-Source Aerodynamics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Qinye, Xiang, Yu, Zhang, Jun, Wang, Wenyong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911556593254400
author Zhu, Qinye
Xiang, Yu
Zhang, Jun
Wang, Wenyong
author_facet Zhu, Qinye
Xiang, Yu
Zhang, Jun
Wang, Wenyong
contents The precise fusion of computational fluid dynamic (CFD) data, wind tunnel tests data, and flight tests data in aerodynamic area is essential for obtaining comprehensive knowledge of both localized flow structures and global aerodynamic trends across the entire flight envelope. However, existing methodologies often struggle to balance high-resolution local fidelity with wide-range global dependency, leading to either a loss of sharp discontinuities or an inability to capture long-range topological correlations. We propose Local-Global Fusion Network (LGFNet) for multi-scale feature decomposition to extract this dual-natured aerodynamic knowledge. To this end, LGFNet combines a spatial perception layer that integrates a sliding window mechanism with a relational reasoning layer based on self-attention, simultaneously reinforcing the continuity of fine-grained local features (e.g., shock waves) and capturing long-range flow information. Furthermore, the fidelity gap delta learning (FGDL) strategy is proposed to treat CFD data as a "low-frequency carrier" to explicitly approximate nonlinear discrepancies. This approach prevents unphysical smoothing while inheriting the foundational physical trends from the simulation baseline. Experiments demonstrate that LGFNet achieves state-of-the-art (SOTA) performance in both accuracy and uncertainty reduction across diverse aerodynamic scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29303
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LGFNet: Local-Global Fusion Network with Fidelity Gap Delta Learning for Multi-Source Aerodynamics
Zhu, Qinye
Xiang, Yu
Zhang, Jun
Wang, Wenyong
Machine Learning
Fluid Dynamics
The precise fusion of computational fluid dynamic (CFD) data, wind tunnel tests data, and flight tests data in aerodynamic area is essential for obtaining comprehensive knowledge of both localized flow structures and global aerodynamic trends across the entire flight envelope. However, existing methodologies often struggle to balance high-resolution local fidelity with wide-range global dependency, leading to either a loss of sharp discontinuities or an inability to capture long-range topological correlations. We propose Local-Global Fusion Network (LGFNet) for multi-scale feature decomposition to extract this dual-natured aerodynamic knowledge. To this end, LGFNet combines a spatial perception layer that integrates a sliding window mechanism with a relational reasoning layer based on self-attention, simultaneously reinforcing the continuity of fine-grained local features (e.g., shock waves) and capturing long-range flow information. Furthermore, the fidelity gap delta learning (FGDL) strategy is proposed to treat CFD data as a "low-frequency carrier" to explicitly approximate nonlinear discrepancies. This approach prevents unphysical smoothing while inheriting the foundational physical trends from the simulation baseline. Experiments demonstrate that LGFNet achieves state-of-the-art (SOTA) performance in both accuracy and uncertainty reduction across diverse aerodynamic scenarios.
title LGFNet: Local-Global Fusion Network with Fidelity Gap Delta Learning for Multi-Source Aerodynamics
topic Machine Learning
Fluid Dynamics
url https://arxiv.org/abs/2603.29303