Ran Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ran Xu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Hongqiang Lyu
College of Aerospace Engineering
3 shared publications - Xuejun Liu
Nanjing University of Aeronautics and Astronautics
3 shared publications - Chenyu Bao1 shared publication
- Hongfei Wang1 shared publication
Huanan Ai
1 shared publicationJan Yu
1 shared publication
Latest Publications
- 1 October 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (10)
Geometry-aware generative hybrid meshing with anisotropic and isotropic elements
The generation of hybrid anisotropic-isotropic meshes is a crucial step in computational simulations, as it allows for the accurate representation of both isotropic and anisotropic physical properties. However, existing methods used for mesh generation typically rely on user-defined mesh size distributions (MSDs), which can be labor-intensive and may not adapt well to complex geometries. Moreover, due to the highly nonlinear relationship, it is challenging to directly generate the corresponding hybrid anisotropic-isotropic mesh from the geometric shape. In this paper, we propose GAIMesh, a data-driven end-to-end geometry-aware anisotropic-isotropic hybrid mesh generation framework based on artificial intelligence, to conditionally map the geometric shapes to hybrid meshes. The whole framework consists of three parts: geometric feature network (GFN), mesh diffusion network (MDN), and mesh mapping network (MMN). The GFN extracts the geometric features from the rasterized representation of the geometry, which enhances the representational ability of the extracted geometric features and mesh resolution independence. The MDN utilizes diffusion models to progressively refine the MSD conditioned on geometric features, gradually optimizing it from an initial random distribution to the final optimal conditional distribution. The MMN maps the high-dimensional MSD to a distribution of mesh node positions in space, which effectively transforms it into mesh node layouts, completing the spatial mapping from geometry to hybrid meshes. The proposed GAIMesh framework is evaluated on various complex geometries, including general shapes, airfoils, and missiles, demonstrating its ability to directly generate geometrically aligned hybrid meshes from the input geometries. The results exhibit the potential of GAIMesh to be a flexible and reliable tool for automatic hybrid anisotropic−isotropic mesh generation in scientific and industrial fields.
- 1 October 2025
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (10)
Geometry-aware generative hybrid meshing with anisotropic and isotropic elements
The generation of hybrid anisotropic-isotropic meshes is a crucial step in computational simulations, as it allows for the accurate representation of both isotropic and anisotropic physical properties. However, existing methods used for mesh generation typically rely on user-defined mesh size distributions (MSDs), which can be labor-intensive and may not adapt well to complex geometries. Moreover, due to the highly nonlinear relationship, it is challenging to directly generate the corresponding hybrid anisotropic-isotropic mesh from the geometric shape. In this paper, we propose GAIMesh, a data-driven end-to-end geometry-aware anisotropic-isotropic hybrid mesh generation framework based on artificial intelligence, to conditionally map the geometric shapes to hybrid meshes. The whole framework consists of three parts: geometric feature network (GFN), mesh diffusion network (MDN), and mesh mapping network (MMN). The GFN extracts the geometric features from the rasterized representation of the geometry, which enhances the representational ability of the extracted geometric features and mesh resolution independence. The MDN utilizes diffusion models to progressively refine the MSD conditioned on geometric features, gradually optimizing it from an initial random distribution to the final optimal conditional distribution. The MMN maps the high-dimensional MSD to a distribution of mesh node positions in space, which effectively transforms it into mesh node layouts, completing the spatial mapping from geometry to hybrid meshes. The proposed GAIMesh framework is evaluated on various complex geometries, including general shapes, airfoils, and missiles, demonstrating its ability to directly generate geometrically aligned hybrid meshes from the input geometries. The results exhibit the potential of GAIMesh to be a flexible and reliable tool for automatic hybrid anisotropic−isotropic mesh generation in scientific and industrial fields.
- 1 September 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (9)
An attention-neural-processes approach to reconstructing unsteady water load for seaplanes
The distribution of holographic unsteady water load offers important information for evaluating the hydrodynamic performance of seaplanes. However, traditional tank test is limited by the number of sensors that can be deployed on the bottom of hull, thus only providing sparse data for estimating load distribution and leading to inaccurate evaluation of seaplane performance. To achieve accurate and rapid reconstruction of holographic load distribution, a machine learning load-reconstruction model based on Attention Neural Processes is proposed. This model performs spatiotemporal modeling of seaplane water load utilizing sparse sensor data. It directly learns the load patterns across multiple time steps and employs Attention modules to capture the spatial distribution of load. Comparisons with alternative methods demonstrate the model's superior ability to simultaneously capture spatial and temporal dependencies of the unsteady load data. In addition, the model's robust generalization capability is also validated by reducing the number of sensors in the training data. The results indicate that the proposed model exhibits high prediction efficiency, accuracy, and generalization for the reconstruction of unsteady water load distribution, which is of great significance for comprehensively evaluating the hydrodynamic performance of seaplanes.
- 1 September 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (9)
An attention-neural-processes approach to reconstructing unsteady water load for seaplanes
The distribution of holographic unsteady water load offers important information for evaluating the hydrodynamic performance of seaplanes. However, traditional tank test is limited by the number of sensors that can be deployed on the bottom of hull, thus only providing sparse data for estimating load distribution and leading to inaccurate evaluation of seaplane performance. To achieve accurate and rapid reconstruction of holographic load distribution, a machine learning load-reconstruction model based on Attention Neural Processes is proposed. This model performs spatiotemporal modeling of seaplane water load utilizing sparse sensor data. It directly learns the load patterns across multiple time steps and employs Attention modules to capture the spatial distribution of load. Comparisons with alternative methods demonstrate the model's superior ability to simultaneously capture spatial and temporal dependencies of the unsteady load data. In addition, the model's robust generalization capability is also validated by reducing the number of sensors in the training data. The results indicate that the proposed model exhibits high prediction efficiency, accuracy, and generalization for the reconstruction of unsteady water load distribution, which is of great significance for comprehensively evaluating the hydrodynamic performance of seaplanes.
- 1 March 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (3)
Flow2Mesh: A flow-guided data-driven mesh adaptation framework
Mesh adaptation is crucial in numerical simulation, providing optimal resource allocation for accurately capturing physical phenomena. However, when applied to Computational Fluid Dynamics (CFD) problems with complex multi-scale properties, existing adaptation methods face huge challenges due to the high computational cost of solving auxiliary partial differential equations (PDEs) and the difficulty in aligning the flow features with mesh geometric features. In this work, an end-to-end data-driven mesh adaptation framework, Flow2Mesh, is proposed to address these challenges by adopting a hybrid modeling strategy to construct the mapping from pixelated flow-fields to graph-based meshes. It achieves a rapid and accurate one-step mesh adaptation via a perceptual feature network (PFN) and a mesh movement network (MMN). PFN extracts the global perceptual features from flow-fields to enhance flow feature representation and mesh resolution independence. In MMN, these features are utilized to deform the initial mesh to a topology-invariant adaptive mesh by a proposed physically driven mesh convolutional network. It considers the inherent mesh geometric information for efficient node feature aggregation and alignment of mesh density with a flow-field structure. To generate high-quality adaptive meshes, various mesh-related losses are designed to regularize the mesh movement and alleviate the mesh tangling. Experiments in CFD scenarios demonstrate the generalization of our model to different design parameters and mesh configurations. It takes three orders of magnitude less time to generate similar meshes than the PDE-based method. The results exhibit the potential of Flow2Mesh to be a flexible and reliable tool for rapid mesh adaptation in scientific and industrial fields.
- 1 March 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (3)
Flow2Mesh: A flow-guided data-driven mesh adaptation framework
Mesh adaptation is crucial in numerical simulation, providing optimal resource allocation for accurately capturing physical phenomena. However, when applied to Computational Fluid Dynamics (CFD) problems with complex multi-scale properties, existing adaptation methods face huge challenges due to the high computational cost of solving auxiliary partial differential equations (PDEs) and the difficulty in aligning the flow features with mesh geometric features. In this work, an end-to-end data-driven mesh adaptation framework, Flow2Mesh, is proposed to address these challenges by adopting a hybrid modeling strategy to construct the mapping from pixelated flow-fields to graph-based meshes. It achieves a rapid and accurate one-step mesh adaptation via a perceptual feature network (PFN) and a mesh movement network (MMN). PFN extracts the global perceptual features from flow-fields to enhance flow feature representation and mesh resolution independence. In MMN, these features are utilized to deform the initial mesh to a topology-invariant adaptive mesh by a proposed physically driven mesh convolutional network. It considers the inherent mesh geometric information for efficient node feature aggregation and alignment of mesh density with a flow-field structure. To generate high-quality adaptive meshes, various mesh-related losses are designed to regularize the mesh movement and alleviate the mesh tangling. Experiments in CFD scenarios demonstrate the generalization of our model to different design parameters and mesh configurations. It takes three orders of magnitude less time to generate similar meshes than the PDE-based method. The results exhibit the potential of Flow2Mesh to be a flexible and reliable tool for rapid mesh adaptation in scientific and industrial fields.